Innovating care for people with sarcoidosis using a machine learning-data driven approach

<bold>Introduction:</bold> Understanding how patients feel and function every day is essential to improve patient centered care in sarcoidosis. So far patients’ perspectives are based on surveys and qualitative research. <bold>Aim:</bold> We used a novel machine learning-driven approach (MLD) to assess patient-driven perspectives on their care trajectories[1]. <bold>Methods:</bold> Patients’ stories were extracted from a Dutch sarcoidosis patient forum (with permission). We applied machine learning topic modelling, co-occurrence analysis, and a sentiment analysis. To validate the findings, we read the top 50 most relevant posts of each topic. An in-depth patients’ disease trajectory map was made. <bold>Results:</bold> Based on 6466 forum posts, 34 topics and 9 upper themes were generated, which formed the basis for the “patient journey-map” which shows patients’ disease trajectory. Important decision moments could be identified, as well as care “tracks” at home and hospital, and topics associated with positive or negative emotions. <bold>Discussion:</bold> A major part of living with sarcoidosis takes place outside the view of the hospital, this part often remains invisible. MLD is an innovative approach, providing a comprehensive overview of patients’ perspectives on healthcare. Integrating, these findings in the design of health care delivery has the potential to improve patient empowerment and hybrid patient-centered care. <fig><object-id>erj;64/suppl_68/OA1048/F1</object-id><object-id>F1</object-id><object-id>F1</object-id><graphic></graphic></fig> <bold>Reference</bold> 1. Jung, J. et al. Int Journal of Design 2023. 17(2) 19-44