Background:
The rising number of cancer survivors and the shortage of health care professionals challenge the accessibility of cancer care. Health technologies are necessary for sustaining optimal patient journeys. To understand individuals’ daily lives during their patient journey, qualitative studies are crucial. However, not all patients wish to share their stories with researchers.

Objective:
This study aims to identify and assess patient experiences on a large scale using a novel machine learning–supported approach, leveraging data from patient forums.

Methods:
Forum posts of patients with colorectal cancer (CRC) from the Cancer Survivors Network USA were used as the data source. Topic modeling, as a part of machine learning, was used to recognize the topic patterns in the posts. Researchers read the most relevant 50 posts on each topic, dividing them into “home” or “hospital” contexts. A patient community journey map, derived from patients stories, was developed to visually illustrate our findings. CRC medical doctors and a quality-of-life expert evaluated the identified topics of patient experience and the map.

Results:
Based on 212,107 posts, 37 topics and 10 upper clusters were produced. Dominant clusters included “Daily activities while living with CRC” (38,782, 18.3%) and “Understanding treatment including alternatives and adjuvant therapy” (31,577, 14.9%). Topics related to the home context had more emotional content compared with the hospital context. The patient community journey map was constructed based on these findings.

Conclusions:
Our study highlighted the diverse concerns and experiences of patients with CRC. The more emotional content in home context discussions underscores the personal impact of CRC beyond clinical settings. Based on our study, we found that a machine learning-supported approach is a promising solution to analyze patients’ experiences. The innovative application of patient community journey mapping provides a unique perspective into the challenges in patients’ daily lives, which is essential for delivering appropriate support at the right moment.

Background: Risk prediction models (RPM) can potentially improve treatment decisions by providing personalized survival estimates for different treatment options, but their effectiveness is uncertain. The VALUE-PERSARC study evaluated the impact of the PERsonalised SARcoma Care (or PERSARC) RPM on decision-making quality in patients with high-grade extremity soft tissue sarcomas (STS).

Methods: A parallel cluster randomized controlled trial was conducted in seven Dutch hospitals, assigned to usual care (control) or care with PERSARC (intervention). PERSARC supported treatment recommendations and informed patients about personalized risks and relevant treatment options. The primary outcome was decision-making quality, measured by patients’ knowledge of treatment risks and benefits and decisional conflict (Decisional Conflict Scale). Secondary outcomes included the Cancer Worry Scale (CWS), Shared Decision-Making (SDM-Q9), number of treatment options discussed and treatment choice.

Results: This study enrolled 120 patients: 53 patients in the control group and 67 patients in the intervention group. No significant differences were observed between the control and intervention groups in patients’ adequate knowledge (respectively 82% vs. 86%) and decisional conflict (respectively 23.1 [15.5] vs. 18.9 [12.8]). Scores on the CWS (11.7 [3.3] vs. 11.0 [3.5]) and SDM-Q9 (13.3 [4.0] vs. 15.6 [3.3]) were also similar. Treatment choices did not differ significantly between groups. However, clinicians in the intervention group were significantly more likely to discuss multiple treatment options (93% vs. 35%).

Conclusion: While PERSARC did not significantly improve patients’ knowledge or decisional conflict, it led to more frequent discussion of multiple treatment options by clinicians. This may be an important step towards enhancing shared decision-making in practice. Trail registration: The VALUE-PERSARC study was registered on January 8, 2021 in the Netherlands Trial Register (NL9160) and updated on January 23, 2023 in ClinicalTrials.gov (NCT05741944).

Sentinel lymph node (SLN) biopsy is an essential procedure for accurate disease staging and treatment planning in patients with melanoma and breast cancer. Conventional preoperative imaging primarily utilizes lymphoscintigraphy with technetium-99m (Tc-99m), which presents several limitations, including radiation exposure, logistical challenges, and potential delays in surgical workflow. Photoacoustic imaging (PAI) has emerged as a promising alternative, leveraging optical contrast provided by indocyanine green (ICG). A feasibility study was conducted at Erasmus MC, University Medical Center Rotterdam, to assess the potential of dual-wavelength PAI for SLN mapping. PAI was employed to perform spectroscopic measurements in healthy volunteers, supporting the development of an optimal excitation protocol. Subsequently, in the patient phase, SLN mapping was performed using PAI with ICG, and the results were compared to the standard-of-care method utilizing Tc-99m. The excitation wavelengths of 800 nm and 860 nm were selected for ratiometric imaging to effectively visualize ICG while suppressing clutter from hemoglobin and melanin. Among the eleven evaluated sentinel nodes, seven were successfully identified using PAI. The maximum SLN detection depth achieved with PAI was 22 mm. This study illustrates the feasibility of ICG-enhanced dual-wavelength PAI for preoperative SLN mapping in patients with melanoma and breast cancer, as an alternative to lymphoscintigraphy. Analysis of false-negative detections suggests improvements to PAI and optimal patient selection. The proposed ratiometric PAI methodology, compared to multiwavelength spectroscopic imaging, enables faster imaging speeds and facilitates the transition to cheaper light sources.