The healthcare industry is increasingly looking to technological solutions to enhance the efficiency and accuracy of patient interaction and medical data collection. This study investigates the development of a self-anamnesis platform designed to streamline the medical history-taking process. The importance of this topic lies in its potential to alleviate the administrative burdens on healthcare providers, improve patient care by enabling more informed consultations, and enhance the overall patient experience through acknowledgement and reassurance.

Despite advancements in healthcare technology, there remains a gap in meeting patients’ desires for longer consultations, more extensive feedback, greater empathy, and the option of receiving care from home. This often results in inefficiencies and increased workloads for healthcare providers. The Erasmus Medical Center (EMC) has expressed interest in implementing an AI avatar to address these needs but is uncertain about the design and functionality it should have. The primary research question of this study is: How can an AI avatar-driven platform, designed to gather patients’ medical histories, be developed to ensure patient acceptance?

The research employs a combination of literature review and practical implementation to develop and test the self-anamnesis platform. Key methods include conducting user interviews and tests to investigate patient preferences for the appearance and functionality of AI-driven avatars, designing the platform to be desirable for patients, viable for healthcare professionals, and feasible for software experts. Additionally, the research examines ethical considerations and integrates comprehensive data security measures.

The core message of this research is that a well-designed self-anamnesis platform has the potential to significantly improve the efficiency of medical data collection. By addressing the challenges of integration, data security, and user accessibility, such a platform can reduce administrative workloads and facilitate better patient care. The study’s findings suggest that with the right technological and user-centered design considerations, the implementation of a self-anamnesis platform is both feasible and beneficial for modern healthcare systems.

Problem Background:
Cardiovascular disease (CVD) is the most common cause of death in the world (Johnston et al., 2016). One of the main causes for cardiovascular mortality is a myocardial infarction (MI) (Jneid et al., 2013; Mishra & Ramavataram, 2021; Verburg et al., 2019). A myocardial infarction is an event in which the heart muscle is damaged because of a complete or partial absence of oxygen supply (Mishra & Ramavataram, 2021)

The healthcare system is pressured by the enormous number of CVD cases (Kaushik et al., 2020). Digital care has gained recognition in the past decade because of its potential to release some pressure from the healthcare system. With the potential of digital care in mind, Leiden University Medical Center (LUMC) has developed a concept called “The MI Box” which provides patients who have had an MI with self-monitoring devices (The Box, 2021).
During the hospitalisation phase of the MI care trajectory, there is little time to involve patients in their care because healthcare professionals (HCPs) need to work as quickly as possible to avoid as much heart damage as possible. This is causing patients to have a bad discharge experience. The MI Box shows potential to involve patients more after the discharge as the concept shows the monitored values to patients. However, it can be difficult for patients to understand these values and how to use them for self-care activities, especially because of the little involvement during hospitalisation. If LUMC wants to satisfy its aim to change from monitoring to coaching, it is crucial to provide patients with enough support to work with their monitored values and perform self-care activities.

Increasing patient involvement is an essential first step before shared decision making (SDM) can be realised. SDM is a suitable approach for the change towards coaching as it invites patients to make their own care choices. In the MI care trajectory, the implementation of SDM is currently lacking. Therefore, further analysis of SDM is needed. A tool that is valuable for the analysis and increasement of SDM, and which is used in this thesis, is the Metro Mapping tool (Metro Mapping, n.d.).

Besides, because the MI Box causes care to be transferred to a patient’s home environment, it is necessary to consider the home context of a patient as care activities do not happen in a controlled hospital environment. Currently, little is known about the context in which the MI Box is used. Therefore, more knowledge about the context is necessary to consider what support means would be suitable to offer to patients to make them more empowered to perform self-care activities.

Research Question:
How to shift from monitoring to coaching with the MI Box?

Research activities:
-Literature research;
-Interviews: HCPs (n=5), MI patients (n=4), MI Box users (n=2);
-Context mapping;
-Metro Mapping.

Design Goal:
The goal is to increase patients’ confidence to perform self-care activities by increasing patients’ involvement and guidance with the use of the MI Box.

Final Concept:
“UnBoxing the MI Box”

In this study, the aim is to find out how Erasmus MC can properly prepare for the AI Act. An iterative design approach was utilized to explore what AI project members may experience during this regulatory process. Several factors have emerged during this experimental study, including the allocation of responsibility, the importance of education and the connection of the medical, technical and legal domains. The complexity of the problem necessitates multiple solutions, which resulted in two designs, the concept of a service system and a roadmap. The service system embodies the needs of the target group, while the roadmap offers a pragmatic guide for the organization to prepare for the changes following the legislation for AI.

Clinical documentation takes up 40% of clinicians’ time. To ease the administrative burden of clinicians, digital scribes offer the potential to automate clinical note taking. Digital scribes are intelligent documentation softwares that combine automated speech recognition (ASR) and natural language processing (NLP). Digital scribes transcribe clinician-patient consultations and convert the conversation into structured clinical notes. Attendi, the client is developing a digital scribe for orthopedics: the Assistant. Hip arthrosis consultations have a well-structured anamnesis, therefore a promising use case for the digital scribe.

This Master thesis investigates the clinician perspective of implementing the Assistant. Literature was reviewed to understand the problem space and the design implications of the enabling technologies. Core concepts in human-AI collaboration such as system transparency and human control were identified to design for hybrid documentation. Also, the perspectives of recording consultations were translated into values for hospitals, clinicians and patients. The findings lead to both mutual benefits and tensions for the clinician-patient relationship and obstacles for implementation.

To contribute to developing the Assistant, user research was carried out in context by shadowing orthopedic surgeons to see their day-to-day workflow and understand the current cycle of clinical documentation. Several surgeons were interviewed to gain more in-depth views about the digital scribe. As synthesis, personas and journey maps were created both for a typical consultation cycle and a daily workflow. From the research phase, a list of user requirements were gathered in order to aid the design phase and future development. Finally, the envisioned user journey is presented in a service blueprint with the developed interface of the Assistant.