H. Verma
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
10 records found
1
Exploring Cognitive Load in Simulation-Based Training
A Case Study of a Medical Training Platform
This Master's Thesis examines cognitive load and usability heuristics in simulation-based training, specifically through a case study of a medical training platform developed by Laerdal Global Health, known as LIFT Scenarios. The study aims to determine the extent to which usability heuristics help reduce the cognitive load experienced by observers while using LIFT Scenarios during medical simulation training.
Following the Improving Improvement model, the research systematically addresses the behavioural and user interface factors that influence cognitive load throughout the application. Each design phase employs various methods, including user tests, interviews, heuristic evaluations, and prototyping. A total of 20 participants were involved in the research activities, excluding observations. The application of usability heuristics positively impacted the ranking of the prototypes. However, a significant portion of the cognitive load associated with LIFT Scenarios is intrinsic, stemming from task difficulty or the skills of the facilitator. This research utilizes quick testing and evaluation methods that are both feasible and adaptable. ...
Following the Improving Improvement model, the research systematically addresses the behavioural and user interface factors that influence cognitive load throughout the application. Each design phase employs various methods, including user tests, interviews, heuristic evaluations, and prototyping. A total of 20 participants were involved in the research activities, excluding observations. The application of usability heuristics positively impacted the ranking of the prototypes. However, a significant portion of the cognitive load associated with LIFT Scenarios is intrinsic, stemming from task difficulty or the skills of the facilitator. This research utilizes quick testing and evaluation methods that are both feasible and adaptable. ...
This Master's Thesis examines cognitive load and usability heuristics in simulation-based training, specifically through a case study of a medical training platform developed by Laerdal Global Health, known as LIFT Scenarios. The study aims to determine the extent to which usability heuristics help reduce the cognitive load experienced by observers while using LIFT Scenarios during medical simulation training.
Following the Improving Improvement model, the research systematically addresses the behavioural and user interface factors that influence cognitive load throughout the application. Each design phase employs various methods, including user tests, interviews, heuristic evaluations, and prototyping. A total of 20 participants were involved in the research activities, excluding observations. The application of usability heuristics positively impacted the ranking of the prototypes. However, a significant portion of the cognitive load associated with LIFT Scenarios is intrinsic, stemming from task difficulty or the skills of the facilitator. This research utilizes quick testing and evaluation methods that are both feasible and adaptable.
Following the Improving Improvement model, the research systematically addresses the behavioural and user interface factors that influence cognitive load throughout the application. Each design phase employs various methods, including user tests, interviews, heuristic evaluations, and prototyping. A total of 20 participants were involved in the research activities, excluding observations. The application of usability heuristics positively impacted the ranking of the prototypes. However, a significant portion of the cognitive load associated with LIFT Scenarios is intrinsic, stemming from task difficulty or the skills of the facilitator. This research utilizes quick testing and evaluation methods that are both feasible and adaptable.
The Design of a User Interface for Intraoperative Decision Support
The application of Hyperspectral Imaging for Tumor Margin Assessment during a Vulvectomy
Master thesis
(2025)
-
I.A.W. Rijpkema, J. Dankelman, N.J. van de Berg, L.S. van der Weerd, H. Verma
Background
Vulvar squamous cell carcinoma accounts for 90% of vulvar cancers and is primarily treated by surgical excision. To reduce the risk of recurrence, surgeons aim to remove tumor-free margins of 2–3 mm, which can lead to extensive tissue loss, among others. Accurate intraoperative margin assessment is critical, but it currently relies on the surgeon’s experience and judgment, as well as time-consuming frozen section analysis, both of which are limited in precision.
Hyperspectral imaging offers a promising solution. This technique captures both spatial and spectral tissue information. It is a non-contact, non-invasive technique that is based on the interaction of light with the target object. However, implementation remains limited, as the current systems are restricted to image capture only.
This study aims to bridge the gap between hyperspectral imaging data and its practical use in surgery. The primary goal is to design and evaluate an interface that supports intraoperative decision-making for gynecological oncologists, ensuring the medical specialist remains in control. Since interpretability is essential, the second goal is to enhance the transparency of the HSI classification model by applying an explainable AI method.
Design Process
Research was conducted concerning the user, the context in which the user operates, existing medical interfaces, and optimal visualization of clinical data. A user survey and usability test were conducted to evaluate the prototype, which was developed through an iterative design process. The research produced a user persona, a context and task analysis, insights into medical interface layouts, and guidelines for visualizing clinical data. These aspects formed the basis for the requirements and wishes for the interface, in conjunction with the principles of the design frameworks applied. The user survey (n = 40, with a medical background) provided design direction and recommendations. The usability test was designed to evaluate the overall workload of the designed interface and its intuitiveness. The test was performed on nine participants.
The mean accuracy of all the tasks performed was 88%, indicating that the interface is straightforward to use. NASA-TLX scores ranged from 6.7 to 24 across six parameters, suggesting low to moderate cognitive load. Semantic differential results showed high ratings for user-friendliness (7.8), logical structure (8.2), and color aesthetics (7.9). However, improvements are still needed in visualizing classification outcomes and tissue parameters, which were partially addressed in the redesign.
Data Analysis
As a first step in distinguishing healthy from tumor tissue, hyperspectral data was collected intraoperatively before tumor excision. The data was then preprocessed by data calibration, glare removal, and data extraction. The preprocessed data was classified with a Support Vector Machine. This classification model was first optimized by tuning the kernel type and then validated through different evaluation metrics. To interpret the model’s decision-making, SHapley Additive exPlanations was applied to identify which features contributed most to the classification. Three types of input features were assessed: wavelengths (500–1000 nm), visual fractions, and tissue parameters.
The tuning of the kernel type yielded the Radial Basis Function kernel as the optimized model, with an average area under the curve of 1 and an accuracy of 99%. The SHapley Additive exPlanations analysis of the spectral dataset showed that all wavelengths consistently support the prediction for healthy tissue and oppose in predicting tumor. Suggesting that the model is biased toward classifying samples as healthy, and tumor is identified primarily by the absence of features associated with healthy tissue. Notably, the 500–595 nm range and the near-infrared region were most influential in supporting prediction for healthy tissue and opposing tumor.
Using spectral fractions and tissue parameters as input features did not yield accurate enough results(macro AUC = 0.65 and accuracy is 10%) to apply SHAP. This suggests that these features alone do not provide sufficient discriminatory information. This displays the need for additional spectral data to improve model performance for these input features.
Conclusion
The results of this study indicate that the initial probabilistic interface design is relatively intuitive, requiring only low to medium cognitive effort and workload. The application of explainable AI revealed that the 500–595 nm range and the near-infrared region are most influential in predicting healthy tissue versus tumor. This improves the transparency and interpretability of the classification model for gynecological oncologists. Together, the intuitive probabilistic interface and explainable AI support the integration of hyperspectral imaging into surgical practice. ...
Vulvar squamous cell carcinoma accounts for 90% of vulvar cancers and is primarily treated by surgical excision. To reduce the risk of recurrence, surgeons aim to remove tumor-free margins of 2–3 mm, which can lead to extensive tissue loss, among others. Accurate intraoperative margin assessment is critical, but it currently relies on the surgeon’s experience and judgment, as well as time-consuming frozen section analysis, both of which are limited in precision.
Hyperspectral imaging offers a promising solution. This technique captures both spatial and spectral tissue information. It is a non-contact, non-invasive technique that is based on the interaction of light with the target object. However, implementation remains limited, as the current systems are restricted to image capture only.
This study aims to bridge the gap between hyperspectral imaging data and its practical use in surgery. The primary goal is to design and evaluate an interface that supports intraoperative decision-making for gynecological oncologists, ensuring the medical specialist remains in control. Since interpretability is essential, the second goal is to enhance the transparency of the HSI classification model by applying an explainable AI method.
Design Process
Research was conducted concerning the user, the context in which the user operates, existing medical interfaces, and optimal visualization of clinical data. A user survey and usability test were conducted to evaluate the prototype, which was developed through an iterative design process. The research produced a user persona, a context and task analysis, insights into medical interface layouts, and guidelines for visualizing clinical data. These aspects formed the basis for the requirements and wishes for the interface, in conjunction with the principles of the design frameworks applied. The user survey (n = 40, with a medical background) provided design direction and recommendations. The usability test was designed to evaluate the overall workload of the designed interface and its intuitiveness. The test was performed on nine participants.
The mean accuracy of all the tasks performed was 88%, indicating that the interface is straightforward to use. NASA-TLX scores ranged from 6.7 to 24 across six parameters, suggesting low to moderate cognitive load. Semantic differential results showed high ratings for user-friendliness (7.8), logical structure (8.2), and color aesthetics (7.9). However, improvements are still needed in visualizing classification outcomes and tissue parameters, which were partially addressed in the redesign.
Data Analysis
As a first step in distinguishing healthy from tumor tissue, hyperspectral data was collected intraoperatively before tumor excision. The data was then preprocessed by data calibration, glare removal, and data extraction. The preprocessed data was classified with a Support Vector Machine. This classification model was first optimized by tuning the kernel type and then validated through different evaluation metrics. To interpret the model’s decision-making, SHapley Additive exPlanations was applied to identify which features contributed most to the classification. Three types of input features were assessed: wavelengths (500–1000 nm), visual fractions, and tissue parameters.
The tuning of the kernel type yielded the Radial Basis Function kernel as the optimized model, with an average area under the curve of 1 and an accuracy of 99%. The SHapley Additive exPlanations analysis of the spectral dataset showed that all wavelengths consistently support the prediction for healthy tissue and oppose in predicting tumor. Suggesting that the model is biased toward classifying samples as healthy, and tumor is identified primarily by the absence of features associated with healthy tissue. Notably, the 500–595 nm range and the near-infrared region were most influential in supporting prediction for healthy tissue and opposing tumor.
Using spectral fractions and tissue parameters as input features did not yield accurate enough results(macro AUC = 0.65 and accuracy is 10%) to apply SHAP. This suggests that these features alone do not provide sufficient discriminatory information. This displays the need for additional spectral data to improve model performance for these input features.
Conclusion
The results of this study indicate that the initial probabilistic interface design is relatively intuitive, requiring only low to medium cognitive effort and workload. The application of explainable AI revealed that the 500–595 nm range and the near-infrared region are most influential in predicting healthy tissue versus tumor. This improves the transparency and interpretability of the classification model for gynecological oncologists. Together, the intuitive probabilistic interface and explainable AI support the integration of hyperspectral imaging into surgical practice. ...
Background
Vulvar squamous cell carcinoma accounts for 90% of vulvar cancers and is primarily treated by surgical excision. To reduce the risk of recurrence, surgeons aim to remove tumor-free margins of 2–3 mm, which can lead to extensive tissue loss, among others. Accurate intraoperative margin assessment is critical, but it currently relies on the surgeon’s experience and judgment, as well as time-consuming frozen section analysis, both of which are limited in precision.
Hyperspectral imaging offers a promising solution. This technique captures both spatial and spectral tissue information. It is a non-contact, non-invasive technique that is based on the interaction of light with the target object. However, implementation remains limited, as the current systems are restricted to image capture only.
This study aims to bridge the gap between hyperspectral imaging data and its practical use in surgery. The primary goal is to design and evaluate an interface that supports intraoperative decision-making for gynecological oncologists, ensuring the medical specialist remains in control. Since interpretability is essential, the second goal is to enhance the transparency of the HSI classification model by applying an explainable AI method.
Design Process
Research was conducted concerning the user, the context in which the user operates, existing medical interfaces, and optimal visualization of clinical data. A user survey and usability test were conducted to evaluate the prototype, which was developed through an iterative design process. The research produced a user persona, a context and task analysis, insights into medical interface layouts, and guidelines for visualizing clinical data. These aspects formed the basis for the requirements and wishes for the interface, in conjunction with the principles of the design frameworks applied. The user survey (n = 40, with a medical background) provided design direction and recommendations. The usability test was designed to evaluate the overall workload of the designed interface and its intuitiveness. The test was performed on nine participants.
The mean accuracy of all the tasks performed was 88%, indicating that the interface is straightforward to use. NASA-TLX scores ranged from 6.7 to 24 across six parameters, suggesting low to moderate cognitive load. Semantic differential results showed high ratings for user-friendliness (7.8), logical structure (8.2), and color aesthetics (7.9). However, improvements are still needed in visualizing classification outcomes and tissue parameters, which were partially addressed in the redesign.
Data Analysis
As a first step in distinguishing healthy from tumor tissue, hyperspectral data was collected intraoperatively before tumor excision. The data was then preprocessed by data calibration, glare removal, and data extraction. The preprocessed data was classified with a Support Vector Machine. This classification model was first optimized by tuning the kernel type and then validated through different evaluation metrics. To interpret the model’s decision-making, SHapley Additive exPlanations was applied to identify which features contributed most to the classification. Three types of input features were assessed: wavelengths (500–1000 nm), visual fractions, and tissue parameters.
The tuning of the kernel type yielded the Radial Basis Function kernel as the optimized model, with an average area under the curve of 1 and an accuracy of 99%. The SHapley Additive exPlanations analysis of the spectral dataset showed that all wavelengths consistently support the prediction for healthy tissue and oppose in predicting tumor. Suggesting that the model is biased toward classifying samples as healthy, and tumor is identified primarily by the absence of features associated with healthy tissue. Notably, the 500–595 nm range and the near-infrared region were most influential in supporting prediction for healthy tissue and opposing tumor.
Using spectral fractions and tissue parameters as input features did not yield accurate enough results(macro AUC = 0.65 and accuracy is 10%) to apply SHAP. This suggests that these features alone do not provide sufficient discriminatory information. This displays the need for additional spectral data to improve model performance for these input features.
Conclusion
The results of this study indicate that the initial probabilistic interface design is relatively intuitive, requiring only low to medium cognitive effort and workload. The application of explainable AI revealed that the 500–595 nm range and the near-infrared region are most influential in predicting healthy tissue versus tumor. This improves the transparency and interpretability of the classification model for gynecological oncologists. Together, the intuitive probabilistic interface and explainable AI support the integration of hyperspectral imaging into surgical practice.
Vulvar squamous cell carcinoma accounts for 90% of vulvar cancers and is primarily treated by surgical excision. To reduce the risk of recurrence, surgeons aim to remove tumor-free margins of 2–3 mm, which can lead to extensive tissue loss, among others. Accurate intraoperative margin assessment is critical, but it currently relies on the surgeon’s experience and judgment, as well as time-consuming frozen section analysis, both of which are limited in precision.
Hyperspectral imaging offers a promising solution. This technique captures both spatial and spectral tissue information. It is a non-contact, non-invasive technique that is based on the interaction of light with the target object. However, implementation remains limited, as the current systems are restricted to image capture only.
This study aims to bridge the gap between hyperspectral imaging data and its practical use in surgery. The primary goal is to design and evaluate an interface that supports intraoperative decision-making for gynecological oncologists, ensuring the medical specialist remains in control. Since interpretability is essential, the second goal is to enhance the transparency of the HSI classification model by applying an explainable AI method.
Design Process
Research was conducted concerning the user, the context in which the user operates, existing medical interfaces, and optimal visualization of clinical data. A user survey and usability test were conducted to evaluate the prototype, which was developed through an iterative design process. The research produced a user persona, a context and task analysis, insights into medical interface layouts, and guidelines for visualizing clinical data. These aspects formed the basis for the requirements and wishes for the interface, in conjunction with the principles of the design frameworks applied. The user survey (n = 40, with a medical background) provided design direction and recommendations. The usability test was designed to evaluate the overall workload of the designed interface and its intuitiveness. The test was performed on nine participants.
The mean accuracy of all the tasks performed was 88%, indicating that the interface is straightforward to use. NASA-TLX scores ranged from 6.7 to 24 across six parameters, suggesting low to moderate cognitive load. Semantic differential results showed high ratings for user-friendliness (7.8), logical structure (8.2), and color aesthetics (7.9). However, improvements are still needed in visualizing classification outcomes and tissue parameters, which were partially addressed in the redesign.
Data Analysis
As a first step in distinguishing healthy from tumor tissue, hyperspectral data was collected intraoperatively before tumor excision. The data was then preprocessed by data calibration, glare removal, and data extraction. The preprocessed data was classified with a Support Vector Machine. This classification model was first optimized by tuning the kernel type and then validated through different evaluation metrics. To interpret the model’s decision-making, SHapley Additive exPlanations was applied to identify which features contributed most to the classification. Three types of input features were assessed: wavelengths (500–1000 nm), visual fractions, and tissue parameters.
The tuning of the kernel type yielded the Radial Basis Function kernel as the optimized model, with an average area under the curve of 1 and an accuracy of 99%. The SHapley Additive exPlanations analysis of the spectral dataset showed that all wavelengths consistently support the prediction for healthy tissue and oppose in predicting tumor. Suggesting that the model is biased toward classifying samples as healthy, and tumor is identified primarily by the absence of features associated with healthy tissue. Notably, the 500–595 nm range and the near-infrared region were most influential in supporting prediction for healthy tissue and opposing tumor.
Using spectral fractions and tissue parameters as input features did not yield accurate enough results(macro AUC = 0.65 and accuracy is 10%) to apply SHAP. This suggests that these features alone do not provide sufficient discriminatory information. This displays the need for additional spectral data to improve model performance for these input features.
Conclusion
The results of this study indicate that the initial probabilistic interface design is relatively intuitive, requiring only low to medium cognitive effort and workload. The application of explainable AI revealed that the 500–595 nm range and the near-infrared region are most influential in predicting healthy tissue versus tumor. This improves the transparency and interpretability of the classification model for gynecological oncologists. Together, the intuitive probabilistic interface and explainable AI support the integration of hyperspectral imaging into surgical practice.
Stimulating fast fashion consumers in-stores to slow down consumption with AI art
Designing for socio-environmental impact
The fast fashion industry faces critical challenges by overconsumption and overproduction driven by high demand, coupled with a lack of transparency in supply chains for many brands. This gap in transparency has led to limited consumer awareness regarding the environmental and ethical consequences of their clothing purchases. This research explores the potential of generative visual art in raising consumer awareness and changing perceptions within fast fashion stores. It serves as a proof of concept to test the impact of AI-generated visual art on engaging consumers, evoking emotional responses, and shifting mindsets related to overconsumption. The project utilized theories from related works and elements from the Vision in Product (ViP) framework to develop a concept, which was tested through two experimental studies. In the pre-study, with evaluating the effectiveness of various aesthetic combinations of AI-generated images, among 111 participants, black-and-white, zoom-in compositions were found most effective in capturing attention and sparking reflection on fast fashion. The main study, comparing AI-generated images with traditional visuals, dividing participants into control and treatment groups, involved 254 participants. The results showed that AI-generated images had a statistically significant impact, with mean scores on attention, cognitive engagement, and behavioral change exceeding those of traditional images by 13.94% and 7.33%. One AI-generated image, depicting a critical fashion scenario of over disposal, stood out by driving significant cognitive engagement and behavioral change. These findings underscore the transformative potential of AI-generated visual art in enhancing consumer awareness and driving change within the fashion industry. By employing creative and impactful visual strategies, it is possible to foster greater consumer perception, disrupt the cycle of overconsumption, and promote more sustainable fashion practices.
...
The fast fashion industry faces critical challenges by overconsumption and overproduction driven by high demand, coupled with a lack of transparency in supply chains for many brands. This gap in transparency has led to limited consumer awareness regarding the environmental and ethical consequences of their clothing purchases. This research explores the potential of generative visual art in raising consumer awareness and changing perceptions within fast fashion stores. It serves as a proof of concept to test the impact of AI-generated visual art on engaging consumers, evoking emotional responses, and shifting mindsets related to overconsumption. The project utilized theories from related works and elements from the Vision in Product (ViP) framework to develop a concept, which was tested through two experimental studies. In the pre-study, with evaluating the effectiveness of various aesthetic combinations of AI-generated images, among 111 participants, black-and-white, zoom-in compositions were found most effective in capturing attention and sparking reflection on fast fashion. The main study, comparing AI-generated images with traditional visuals, dividing participants into control and treatment groups, involved 254 participants. The results showed that AI-generated images had a statistically significant impact, with mean scores on attention, cognitive engagement, and behavioral change exceeding those of traditional images by 13.94% and 7.33%. One AI-generated image, depicting a critical fashion scenario of over disposal, stood out by driving significant cognitive engagement and behavioral change. These findings underscore the transformative potential of AI-generated visual art in enhancing consumer awareness and driving change within the fashion industry. By employing creative and impactful visual strategies, it is possible to foster greater consumer perception, disrupt the cycle of overconsumption, and promote more sustainable fashion practices.
Mobile Touch
Responsive Wireless Tactile Communication for Portable Pneumatic Wearables
Pneumatic actuation is an effective method for recreating human touch sensations because it can apply pressure to the skin and has a natural softness. However, integrating this technology into fully wearable devices has proven to be difficult due to the lack of responsiveness with smaller pneumatic components, which limits the number of effective touches that can be portrayed.
Mobile Touch is a fully wearable system designed to deliver touch sensations to the wrist through a combination of pneumatic and vibrotactile actuation. By compensating for the inflation time of the pneumatic component with vibrations, the system's responsiveness is increased, allowing for the creation of more varied touch patterns. In addition, a wireless controller was developed that allows for programming touch patterns and directly transmitting touch wirelessly to the wearable device.
In the user study, the pneumatic-vibrotactile modality generally received significantly higher ratings for its similarity to human touch and pattern recognition by leveraging the strengths of each individual modality (n=35). Specifically, for longer touches, it was more effective due to its ability to mimic the softness of human skin and the pressure of a touch. For short taps, the vibrotactile component was clearer and enhanced the perceived realism. ...
Mobile Touch is a fully wearable system designed to deliver touch sensations to the wrist through a combination of pneumatic and vibrotactile actuation. By compensating for the inflation time of the pneumatic component with vibrations, the system's responsiveness is increased, allowing for the creation of more varied touch patterns. In addition, a wireless controller was developed that allows for programming touch patterns and directly transmitting touch wirelessly to the wearable device.
In the user study, the pneumatic-vibrotactile modality generally received significantly higher ratings for its similarity to human touch and pattern recognition by leveraging the strengths of each individual modality (n=35). Specifically, for longer touches, it was more effective due to its ability to mimic the softness of human skin and the pressure of a touch. For short taps, the vibrotactile component was clearer and enhanced the perceived realism. ...
Pneumatic actuation is an effective method for recreating human touch sensations because it can apply pressure to the skin and has a natural softness. However, integrating this technology into fully wearable devices has proven to be difficult due to the lack of responsiveness with smaller pneumatic components, which limits the number of effective touches that can be portrayed.
Mobile Touch is a fully wearable system designed to deliver touch sensations to the wrist through a combination of pneumatic and vibrotactile actuation. By compensating for the inflation time of the pneumatic component with vibrations, the system's responsiveness is increased, allowing for the creation of more varied touch patterns. In addition, a wireless controller was developed that allows for programming touch patterns and directly transmitting touch wirelessly to the wearable device.
In the user study, the pneumatic-vibrotactile modality generally received significantly higher ratings for its similarity to human touch and pattern recognition by leveraging the strengths of each individual modality (n=35). Specifically, for longer touches, it was more effective due to its ability to mimic the softness of human skin and the pressure of a touch. For short taps, the vibrotactile component was clearer and enhanced the perceived realism.
Mobile Touch is a fully wearable system designed to deliver touch sensations to the wrist through a combination of pneumatic and vibrotactile actuation. By compensating for the inflation time of the pneumatic component with vibrations, the system's responsiveness is increased, allowing for the creation of more varied touch patterns. In addition, a wireless controller was developed that allows for programming touch patterns and directly transmitting touch wirelessly to the wearable device.
In the user study, the pneumatic-vibrotactile modality generally received significantly higher ratings for its similarity to human touch and pattern recognition by leveraging the strengths of each individual modality (n=35). Specifically, for longer touches, it was more effective due to its ability to mimic the softness of human skin and the pressure of a touch. For short taps, the vibrotactile component was clearer and enhanced the perceived realism.
The aim of this master’s thesis is to lay the foundations for enhancing early dementia detection strategies across the UK, by gaining a comprehensive understanding of the current diagnostic journey from the perspectives of people living with dementia (PLWDs) and their caregivers (CGs). The project consists of a literature review establishing foundational knowledge and identifying existing research gaps, followed by a three-phase mixed-method approach to analysis of online patient stories. Inspired by Online Community Journey Mapping by Jung et al., 2023, initially, a thematic analysis of a representative sample of online patient stories is conducted, followed by LDA topic modeling to validate the thematic insights across the wider dataset of the UK Alzheimer’s Society Dementia Support forum. The synthesis of these two methods results in detailed journey maps of
the PLWD and CG experiences. The findings reveal nuanced insights into the barriers and facilitators of early dementia diagnosis and caregiving, particularly from the perspective of familial CGs. These journey maps serve as essential tools for policymakers, NHS workers, designers, and academics to inform strategic improvements, ultimately aiming to enhance early diagnosis rates and provide support for PLWDs and their CGs. ...
the PLWD and CG experiences. The findings reveal nuanced insights into the barriers and facilitators of early dementia diagnosis and caregiving, particularly from the perspective of familial CGs. These journey maps serve as essential tools for policymakers, NHS workers, designers, and academics to inform strategic improvements, ultimately aiming to enhance early diagnosis rates and provide support for PLWDs and their CGs. ...
The aim of this master’s thesis is to lay the foundations for enhancing early dementia detection strategies across the UK, by gaining a comprehensive understanding of the current diagnostic journey from the perspectives of people living with dementia (PLWDs) and their caregivers (CGs). The project consists of a literature review establishing foundational knowledge and identifying existing research gaps, followed by a three-phase mixed-method approach to analysis of online patient stories. Inspired by Online Community Journey Mapping by Jung et al., 2023, initially, a thematic analysis of a representative sample of online patient stories is conducted, followed by LDA topic modeling to validate the thematic insights across the wider dataset of the UK Alzheimer’s Society Dementia Support forum. The synthesis of these two methods results in detailed journey maps of
the PLWD and CG experiences. The findings reveal nuanced insights into the barriers and facilitators of early dementia diagnosis and caregiving, particularly from the perspective of familial CGs. These journey maps serve as essential tools for policymakers, NHS workers, designers, and academics to inform strategic improvements, ultimately aiming to enhance early diagnosis rates and provide support for PLWDs and their CGs.
the PLWD and CG experiences. The findings reveal nuanced insights into the barriers and facilitators of early dementia diagnosis and caregiving, particularly from the perspective of familial CGs. These journey maps serve as essential tools for policymakers, NHS workers, designers, and academics to inform strategic improvements, ultimately aiming to enhance early diagnosis rates and provide support for PLWDs and their CGs.
Currently, biodiversity is under worldwide pressure. The organization Naturalis Biodiversity Centre wants to discover ways to address the biodiversity crisis in their museum.
For the design process, the double diamond method is applied. Through desk research and interviewing experts, the concept of biodiversity is explored. To have a clear focus early in the project and make the design process more manageable, it is chosen to focus on the decrease of insects. Insects are an undervalued group despite their importance, and they require attention as humankind depends on their existence.
Biodiversity decline is a phenomenon seen throughout history, but for the first time it is mostly caused by human activity. The causes of the decline can be at individual and systemic levels. Museums are good environments to address complex problems like this, because of the large audience and the ability to share current events and context. However, visitor’s attention span and development time can be limiting factors.
The project aims to work towards transformation, making the audience aware of the problem and encouraging them to reflect on their own role. These steps are the first two stages of a simplified plan that leads to transformation. To refine the installation further, the Com-b model of behavior change is used.
While the biodiversity crisis is addressed through the website, app, and educational programs of Naturalis, it is not addressed in the museum. Together with employees from the educational and exhibit departments, a message on biodiversity crisis is thought of, which is summarized in three pillars: connectedness, taking care of nature, and motivating the visitors.
To understand how families experience Naturalis and how they want to be approached regarding the biodiversity crisis, families visiting Naturalis are interviewed and observed. This has led to insights, resulting in the development of three personas representing certain types of families.
The design goal is: To design a playful transformative experience at Naturalis where family members can develop a deeper understanding of the biodiversity crisis and discover how they can contribute to biodiversity in their surroundings.
The exhibit journey consists of three steps: approach, interact, and take-away. The installation will be located near the entrance, where families are still open to trying something new and are motivated to learning and playing.
By consulting biologists and Naturalis employees, hosting brainstorm sessions with fellow design students, visiting museums for inspiration, and testing with families, the project has come towards a final concept. The concept allows families to discover which elements contribute to a bee-friendly environment and which do not. By manipulating physical wheels representing elements such as flowers, families can observe the effects of their choices on a screen, which also provides an explanation. The concept was understood and appealing to families, particularly the interactive part with the wheels and screen. However, the effect part should be redesigned in consultation with a bee specialist and children’s illustrator. Additionally, the game element needs reworking, to focus solely on bees to keep it understandable and engaging.
...
For the design process, the double diamond method is applied. Through desk research and interviewing experts, the concept of biodiversity is explored. To have a clear focus early in the project and make the design process more manageable, it is chosen to focus on the decrease of insects. Insects are an undervalued group despite their importance, and they require attention as humankind depends on their existence.
Biodiversity decline is a phenomenon seen throughout history, but for the first time it is mostly caused by human activity. The causes of the decline can be at individual and systemic levels. Museums are good environments to address complex problems like this, because of the large audience and the ability to share current events and context. However, visitor’s attention span and development time can be limiting factors.
The project aims to work towards transformation, making the audience aware of the problem and encouraging them to reflect on their own role. These steps are the first two stages of a simplified plan that leads to transformation. To refine the installation further, the Com-b model of behavior change is used.
While the biodiversity crisis is addressed through the website, app, and educational programs of Naturalis, it is not addressed in the museum. Together with employees from the educational and exhibit departments, a message on biodiversity crisis is thought of, which is summarized in three pillars: connectedness, taking care of nature, and motivating the visitors.
To understand how families experience Naturalis and how they want to be approached regarding the biodiversity crisis, families visiting Naturalis are interviewed and observed. This has led to insights, resulting in the development of three personas representing certain types of families.
The design goal is: To design a playful transformative experience at Naturalis where family members can develop a deeper understanding of the biodiversity crisis and discover how they can contribute to biodiversity in their surroundings.
The exhibit journey consists of three steps: approach, interact, and take-away. The installation will be located near the entrance, where families are still open to trying something new and are motivated to learning and playing.
By consulting biologists and Naturalis employees, hosting brainstorm sessions with fellow design students, visiting museums for inspiration, and testing with families, the project has come towards a final concept. The concept allows families to discover which elements contribute to a bee-friendly environment and which do not. By manipulating physical wheels representing elements such as flowers, families can observe the effects of their choices on a screen, which also provides an explanation. The concept was understood and appealing to families, particularly the interactive part with the wheels and screen. However, the effect part should be redesigned in consultation with a bee specialist and children’s illustrator. Additionally, the game element needs reworking, to focus solely on bees to keep it understandable and engaging.
...
Currently, biodiversity is under worldwide pressure. The organization Naturalis Biodiversity Centre wants to discover ways to address the biodiversity crisis in their museum.
For the design process, the double diamond method is applied. Through desk research and interviewing experts, the concept of biodiversity is explored. To have a clear focus early in the project and make the design process more manageable, it is chosen to focus on the decrease of insects. Insects are an undervalued group despite their importance, and they require attention as humankind depends on their existence.
Biodiversity decline is a phenomenon seen throughout history, but for the first time it is mostly caused by human activity. The causes of the decline can be at individual and systemic levels. Museums are good environments to address complex problems like this, because of the large audience and the ability to share current events and context. However, visitor’s attention span and development time can be limiting factors.
The project aims to work towards transformation, making the audience aware of the problem and encouraging them to reflect on their own role. These steps are the first two stages of a simplified plan that leads to transformation. To refine the installation further, the Com-b model of behavior change is used.
While the biodiversity crisis is addressed through the website, app, and educational programs of Naturalis, it is not addressed in the museum. Together with employees from the educational and exhibit departments, a message on biodiversity crisis is thought of, which is summarized in three pillars: connectedness, taking care of nature, and motivating the visitors.
To understand how families experience Naturalis and how they want to be approached regarding the biodiversity crisis, families visiting Naturalis are interviewed and observed. This has led to insights, resulting in the development of three personas representing certain types of families.
The design goal is: To design a playful transformative experience at Naturalis where family members can develop a deeper understanding of the biodiversity crisis and discover how they can contribute to biodiversity in their surroundings.
The exhibit journey consists of three steps: approach, interact, and take-away. The installation will be located near the entrance, where families are still open to trying something new and are motivated to learning and playing.
By consulting biologists and Naturalis employees, hosting brainstorm sessions with fellow design students, visiting museums for inspiration, and testing with families, the project has come towards a final concept. The concept allows families to discover which elements contribute to a bee-friendly environment and which do not. By manipulating physical wheels representing elements such as flowers, families can observe the effects of their choices on a screen, which also provides an explanation. The concept was understood and appealing to families, particularly the interactive part with the wheels and screen. However, the effect part should be redesigned in consultation with a bee specialist and children’s illustrator. Additionally, the game element needs reworking, to focus solely on bees to keep it understandable and engaging.
For the design process, the double diamond method is applied. Through desk research and interviewing experts, the concept of biodiversity is explored. To have a clear focus early in the project and make the design process more manageable, it is chosen to focus on the decrease of insects. Insects are an undervalued group despite their importance, and they require attention as humankind depends on their existence.
Biodiversity decline is a phenomenon seen throughout history, but for the first time it is mostly caused by human activity. The causes of the decline can be at individual and systemic levels. Museums are good environments to address complex problems like this, because of the large audience and the ability to share current events and context. However, visitor’s attention span and development time can be limiting factors.
The project aims to work towards transformation, making the audience aware of the problem and encouraging them to reflect on their own role. These steps are the first two stages of a simplified plan that leads to transformation. To refine the installation further, the Com-b model of behavior change is used.
While the biodiversity crisis is addressed through the website, app, and educational programs of Naturalis, it is not addressed in the museum. Together with employees from the educational and exhibit departments, a message on biodiversity crisis is thought of, which is summarized in three pillars: connectedness, taking care of nature, and motivating the visitors.
To understand how families experience Naturalis and how they want to be approached regarding the biodiversity crisis, families visiting Naturalis are interviewed and observed. This has led to insights, resulting in the development of three personas representing certain types of families.
The design goal is: To design a playful transformative experience at Naturalis where family members can develop a deeper understanding of the biodiversity crisis and discover how they can contribute to biodiversity in their surroundings.
The exhibit journey consists of three steps: approach, interact, and take-away. The installation will be located near the entrance, where families are still open to trying something new and are motivated to learning and playing.
By consulting biologists and Naturalis employees, hosting brainstorm sessions with fellow design students, visiting museums for inspiration, and testing with families, the project has come towards a final concept. The concept allows families to discover which elements contribute to a bee-friendly environment and which do not. By manipulating physical wheels representing elements such as flowers, families can observe the effects of their choices on a screen, which also provides an explanation. The concept was understood and appealing to families, particularly the interactive part with the wheels and screen. However, the effect part should be redesigned in consultation with a bee specialist and children’s illustrator. Additionally, the game element needs reworking, to focus solely on bees to keep it understandable and engaging.
Peer Mentor Support in Virtual Reality
Enable young adults with mental health experiences to engage with peer mentors in virtual reality
Young adults with Concerns about their mental health issues (YAMHI) seeking support in the Dutch mental health system struggle with long waiting times.
Enliven aims to develop a virtual peer mentor support platform for YAMHIE to bridge these waiting times. This thesis explores the design process and development of a concept with the following design goal:
To Enable young adults with concerns about their mental health issues to engage with a peer mentor through interaction in a virtual reality environment while waiting on the professional health care, with the aim to support them in addressing their problems.
The design process involved participatory design methods like contextmapping, co-design sessions and prototyping. The tools used for prototyping consisted of Minecraft to design the virtual environments, Figma and paper prototypes.
The outcome of this project is:
A design concept:
1) consisting of ten virtual environments that can be used to design a virtual peer mentor support platform.
2) An experiential prototype to demonstrate the intended interactions between YAMHI and peer mentors of some of those environments (6 of the 10)
As an addition on the side:
3) Because the platform does not exist yet, a manual to support the design team to further integrate these environments in their platform has been created.
...
Enliven aims to develop a virtual peer mentor support platform for YAMHIE to bridge these waiting times. This thesis explores the design process and development of a concept with the following design goal:
To Enable young adults with concerns about their mental health issues to engage with a peer mentor through interaction in a virtual reality environment while waiting on the professional health care, with the aim to support them in addressing their problems.
The design process involved participatory design methods like contextmapping, co-design sessions and prototyping. The tools used for prototyping consisted of Minecraft to design the virtual environments, Figma and paper prototypes.
The outcome of this project is:
A design concept:
1) consisting of ten virtual environments that can be used to design a virtual peer mentor support platform.
2) An experiential prototype to demonstrate the intended interactions between YAMHI and peer mentors of some of those environments (6 of the 10)
As an addition on the side:
3) Because the platform does not exist yet, a manual to support the design team to further integrate these environments in their platform has been created.
...
Young adults with Concerns about their mental health issues (YAMHI) seeking support in the Dutch mental health system struggle with long waiting times.
Enliven aims to develop a virtual peer mentor support platform for YAMHIE to bridge these waiting times. This thesis explores the design process and development of a concept with the following design goal:
To Enable young adults with concerns about their mental health issues to engage with a peer mentor through interaction in a virtual reality environment while waiting on the professional health care, with the aim to support them in addressing their problems.
The design process involved participatory design methods like contextmapping, co-design sessions and prototyping. The tools used for prototyping consisted of Minecraft to design the virtual environments, Figma and paper prototypes.
The outcome of this project is:
A design concept:
1) consisting of ten virtual environments that can be used to design a virtual peer mentor support platform.
2) An experiential prototype to demonstrate the intended interactions between YAMHI and peer mentors of some of those environments (6 of the 10)
As an addition on the side:
3) Because the platform does not exist yet, a manual to support the design team to further integrate these environments in their platform has been created.
Enliven aims to develop a virtual peer mentor support platform for YAMHIE to bridge these waiting times. This thesis explores the design process and development of a concept with the following design goal:
To Enable young adults with concerns about their mental health issues to engage with a peer mentor through interaction in a virtual reality environment while waiting on the professional health care, with the aim to support them in addressing their problems.
The design process involved participatory design methods like contextmapping, co-design sessions and prototyping. The tools used for prototyping consisted of Minecraft to design the virtual environments, Figma and paper prototypes.
The outcome of this project is:
A design concept:
1) consisting of ten virtual environments that can be used to design a virtual peer mentor support platform.
2) An experiential prototype to demonstrate the intended interactions between YAMHI and peer mentors of some of those environments (6 of the 10)
As an addition on the side:
3) Because the platform does not exist yet, a manual to support the design team to further integrate these environments in their platform has been created.
This thesis demonstrates that there is a need for improving the working conditions of gig workers. It establishes a need for an increase in empathy from consumers towards delivery riders. Delivery riders often make use of E-bikes which provide an excellent foundation for data collection. The main research question is stated as follows:
How can empathy towards delivery riders be increased through communicating behavioural data to the consumer?
After establishing background and related work through desktop research, an exploration into the implementation of multiple sensors was initiated. This led to the insight that communicating heart rate data is the most promising dataflow to evoke empathy. The effect of communicating live heart rate data, next to static personalised information was empirically tested. After which all insights were synthesized into 5 design drivers which provided input for a brief design cycle. The final output is a demonstration, including a prototype, of a proof of principle that evokes empathy through communicating live heart rate data.
The most important insight substantiated in this thesis is the positive correlation that communicating live heart rate data has to the experienced empathy from end-consumers towards delivery riders. This led to the final proof of principle that revolves around a way to implement this into the delivery service context.
The conclusion of this study is that there is a strong indication that showing live heart rate data to consumers increases the experienced empathy. This could be implemented in various ways and provides a foundation for future work. More research is needed to establish the exact origin for the increase in empathy. This study is limited to exploring one way of communicating live heart rate data so more research is needed on different possibilities regarding visualization, communication and information versus the effect on experienced empathy. ...
How can empathy towards delivery riders be increased through communicating behavioural data to the consumer?
After establishing background and related work through desktop research, an exploration into the implementation of multiple sensors was initiated. This led to the insight that communicating heart rate data is the most promising dataflow to evoke empathy. The effect of communicating live heart rate data, next to static personalised information was empirically tested. After which all insights were synthesized into 5 design drivers which provided input for a brief design cycle. The final output is a demonstration, including a prototype, of a proof of principle that evokes empathy through communicating live heart rate data.
The most important insight substantiated in this thesis is the positive correlation that communicating live heart rate data has to the experienced empathy from end-consumers towards delivery riders. This led to the final proof of principle that revolves around a way to implement this into the delivery service context.
The conclusion of this study is that there is a strong indication that showing live heart rate data to consumers increases the experienced empathy. This could be implemented in various ways and provides a foundation for future work. More research is needed to establish the exact origin for the increase in empathy. This study is limited to exploring one way of communicating live heart rate data so more research is needed on different possibilities regarding visualization, communication and information versus the effect on experienced empathy. ...
This thesis demonstrates that there is a need for improving the working conditions of gig workers. It establishes a need for an increase in empathy from consumers towards delivery riders. Delivery riders often make use of E-bikes which provide an excellent foundation for data collection. The main research question is stated as follows:
How can empathy towards delivery riders be increased through communicating behavioural data to the consumer?
After establishing background and related work through desktop research, an exploration into the implementation of multiple sensors was initiated. This led to the insight that communicating heart rate data is the most promising dataflow to evoke empathy. The effect of communicating live heart rate data, next to static personalised information was empirically tested. After which all insights were synthesized into 5 design drivers which provided input for a brief design cycle. The final output is a demonstration, including a prototype, of a proof of principle that evokes empathy through communicating live heart rate data.
The most important insight substantiated in this thesis is the positive correlation that communicating live heart rate data has to the experienced empathy from end-consumers towards delivery riders. This led to the final proof of principle that revolves around a way to implement this into the delivery service context.
The conclusion of this study is that there is a strong indication that showing live heart rate data to consumers increases the experienced empathy. This could be implemented in various ways and provides a foundation for future work. More research is needed to establish the exact origin for the increase in empathy. This study is limited to exploring one way of communicating live heart rate data so more research is needed on different possibilities regarding visualization, communication and information versus the effect on experienced empathy.
How can empathy towards delivery riders be increased through communicating behavioural data to the consumer?
After establishing background and related work through desktop research, an exploration into the implementation of multiple sensors was initiated. This led to the insight that communicating heart rate data is the most promising dataflow to evoke empathy. The effect of communicating live heart rate data, next to static personalised information was empirically tested. After which all insights were synthesized into 5 design drivers which provided input for a brief design cycle. The final output is a demonstration, including a prototype, of a proof of principle that evokes empathy through communicating live heart rate data.
The most important insight substantiated in this thesis is the positive correlation that communicating live heart rate data has to the experienced empathy from end-consumers towards delivery riders. This led to the final proof of principle that revolves around a way to implement this into the delivery service context.
The conclusion of this study is that there is a strong indication that showing live heart rate data to consumers increases the experienced empathy. This could be implemented in various ways and provides a foundation for future work. More research is needed to establish the exact origin for the increase in empathy. This study is limited to exploring one way of communicating live heart rate data so more research is needed on different possibilities regarding visualization, communication and information versus the effect on experienced empathy.
In less than a decade, smart doorbells have become a household stable, introducing a new form of surveillance cameras. But while the cameras have given a new purpose to the doorbell, they also come with an array of privacy concerns. Much critique has been given to the management of data and the effect private
surveillance has on society. Smart doorbells have also entered the street of Amsterdam, prompting the municipality to look into how to deal with the arising privacy issues. In this project, we approach the smart doorbell on the interaction level, zooming in on the interaction between two people - the visitor and the owner - through the medium of a smart doorbell. We explore how this medium
facilitates the interchange and how it facilitates an emerging power difference.
To challenge the current design of smart doorbells, alternative smart doorbells were designed, taking a starting point in three different definitions of privacy. Each doorbell opens up for a new form of negotiation of the terms of the interaction between owner and visitor. The end result was an exhibition held in
Amsterdam, where three new privacy-centric designs were displayed.
At the exhibition, data was gathered about visitors’ opinions and views on the doorbells and analysed to understand better people’s values and preferences in regards to privacy in the context of smart doorbells. The result showed that speculative design exhibitions could be a valuable tool for better understanding
citizens’ values and preferences. The physical manifestations of alternative futures allowed a nuanced and concrete discussion about possible interventions. This shows how speculative design can help institutions such as Amsterdam municipality deal with emerging technologies such as the smart doorbell. ...
surveillance has on society. Smart doorbells have also entered the street of Amsterdam, prompting the municipality to look into how to deal with the arising privacy issues. In this project, we approach the smart doorbell on the interaction level, zooming in on the interaction between two people - the visitor and the owner - through the medium of a smart doorbell. We explore how this medium
facilitates the interchange and how it facilitates an emerging power difference.
To challenge the current design of smart doorbells, alternative smart doorbells were designed, taking a starting point in three different definitions of privacy. Each doorbell opens up for a new form of negotiation of the terms of the interaction between owner and visitor. The end result was an exhibition held in
Amsterdam, where three new privacy-centric designs were displayed.
At the exhibition, data was gathered about visitors’ opinions and views on the doorbells and analysed to understand better people’s values and preferences in regards to privacy in the context of smart doorbells. The result showed that speculative design exhibitions could be a valuable tool for better understanding
citizens’ values and preferences. The physical manifestations of alternative futures allowed a nuanced and concrete discussion about possible interventions. This shows how speculative design can help institutions such as Amsterdam municipality deal with emerging technologies such as the smart doorbell. ...
In less than a decade, smart doorbells have become a household stable, introducing a new form of surveillance cameras. But while the cameras have given a new purpose to the doorbell, they also come with an array of privacy concerns. Much critique has been given to the management of data and the effect private
surveillance has on society. Smart doorbells have also entered the street of Amsterdam, prompting the municipality to look into how to deal with the arising privacy issues. In this project, we approach the smart doorbell on the interaction level, zooming in on the interaction between two people - the visitor and the owner - through the medium of a smart doorbell. We explore how this medium
facilitates the interchange and how it facilitates an emerging power difference.
To challenge the current design of smart doorbells, alternative smart doorbells were designed, taking a starting point in three different definitions of privacy. Each doorbell opens up for a new form of negotiation of the terms of the interaction between owner and visitor. The end result was an exhibition held in
Amsterdam, where three new privacy-centric designs were displayed.
At the exhibition, data was gathered about visitors’ opinions and views on the doorbells and analysed to understand better people’s values and preferences in regards to privacy in the context of smart doorbells. The result showed that speculative design exhibitions could be a valuable tool for better understanding
citizens’ values and preferences. The physical manifestations of alternative futures allowed a nuanced and concrete discussion about possible interventions. This shows how speculative design can help institutions such as Amsterdam municipality deal with emerging technologies such as the smart doorbell.
surveillance has on society. Smart doorbells have also entered the street of Amsterdam, prompting the municipality to look into how to deal with the arising privacy issues. In this project, we approach the smart doorbell on the interaction level, zooming in on the interaction between two people - the visitor and the owner - through the medium of a smart doorbell. We explore how this medium
facilitates the interchange and how it facilitates an emerging power difference.
To challenge the current design of smart doorbells, alternative smart doorbells were designed, taking a starting point in three different definitions of privacy. Each doorbell opens up for a new form of negotiation of the terms of the interaction between owner and visitor. The end result was an exhibition held in
Amsterdam, where three new privacy-centric designs were displayed.
At the exhibition, data was gathered about visitors’ opinions and views on the doorbells and analysed to understand better people’s values and preferences in regards to privacy in the context of smart doorbells. The result showed that speculative design exhibitions could be a valuable tool for better understanding
citizens’ values and preferences. The physical manifestations of alternative futures allowed a nuanced and concrete discussion about possible interventions. This shows how speculative design can help institutions such as Amsterdam municipality deal with emerging technologies such as the smart doorbell.
ICU is the place with the most advanced monitoring and support machines in a hospital. But surrounded by all these machines, ICU patients are also like machines instead of humans. Scientific advances have been proved to greatly improve the cure rate. Meanwhile, patients' well-being has been gradually treated as important as curing the disease itself. With the trend of human-centred intensive care, new services are required to better satisfy patients’
needs.
Artificial intelligence can be a strong force to improve the quality of care in ICU. Apart from taking advantage of the existing monitoring data and EHR data to improve the cure rate, A.I. also has great potential to promote social support for ICU patients.
The purpose of this project is to design a roadmap for A.I. to provide social support for ICU patients, in order to improve the patient wellbeing and contribute to a humane ICU.The design solution is an application called Cricare that includes nine services: 1. Orientation; 2. Autocomplete; 3. Voice Simulator; 4. Music Creator; 5. Environment adjuster; 6. Chatbot; 7. Virtual Psychologist; 8. Peer support; 9. Goal setter.
A questionnaire evaluation with nurses was conducted to test the desirability, importance, and effect on providing social support and effect on patient wellbeing. The results show Cricare is the potential to contribute to a humane ICU. After feasibility evaluation, a primary roadmap was created to develop Cricare. ...
needs.
Artificial intelligence can be a strong force to improve the quality of care in ICU. Apart from taking advantage of the existing monitoring data and EHR data to improve the cure rate, A.I. also has great potential to promote social support for ICU patients.
The purpose of this project is to design a roadmap for A.I. to provide social support for ICU patients, in order to improve the patient wellbeing and contribute to a humane ICU.The design solution is an application called Cricare that includes nine services: 1. Orientation; 2. Autocomplete; 3. Voice Simulator; 4. Music Creator; 5. Environment adjuster; 6. Chatbot; 7. Virtual Psychologist; 8. Peer support; 9. Goal setter.
A questionnaire evaluation with nurses was conducted to test the desirability, importance, and effect on providing social support and effect on patient wellbeing. The results show Cricare is the potential to contribute to a humane ICU. After feasibility evaluation, a primary roadmap was created to develop Cricare. ...
ICU is the place with the most advanced monitoring and support machines in a hospital. But surrounded by all these machines, ICU patients are also like machines instead of humans. Scientific advances have been proved to greatly improve the cure rate. Meanwhile, patients' well-being has been gradually treated as important as curing the disease itself. With the trend of human-centred intensive care, new services are required to better satisfy patients’
needs.
Artificial intelligence can be a strong force to improve the quality of care in ICU. Apart from taking advantage of the existing monitoring data and EHR data to improve the cure rate, A.I. also has great potential to promote social support for ICU patients.
The purpose of this project is to design a roadmap for A.I. to provide social support for ICU patients, in order to improve the patient wellbeing and contribute to a humane ICU.The design solution is an application called Cricare that includes nine services: 1. Orientation; 2. Autocomplete; 3. Voice Simulator; 4. Music Creator; 5. Environment adjuster; 6. Chatbot; 7. Virtual Psychologist; 8. Peer support; 9. Goal setter.
A questionnaire evaluation with nurses was conducted to test the desirability, importance, and effect on providing social support and effect on patient wellbeing. The results show Cricare is the potential to contribute to a humane ICU. After feasibility evaluation, a primary roadmap was created to develop Cricare.
needs.
Artificial intelligence can be a strong force to improve the quality of care in ICU. Apart from taking advantage of the existing monitoring data and EHR data to improve the cure rate, A.I. also has great potential to promote social support for ICU patients.
The purpose of this project is to design a roadmap for A.I. to provide social support for ICU patients, in order to improve the patient wellbeing and contribute to a humane ICU.The design solution is an application called Cricare that includes nine services: 1. Orientation; 2. Autocomplete; 3. Voice Simulator; 4. Music Creator; 5. Environment adjuster; 6. Chatbot; 7. Virtual Psychologist; 8. Peer support; 9. Goal setter.
A questionnaire evaluation with nurses was conducted to test the desirability, importance, and effect on providing social support and effect on patient wellbeing. The results show Cricare is the potential to contribute to a humane ICU. After feasibility evaluation, a primary roadmap was created to develop Cricare.