Mapping Medical Context: Workshop-Driven Clustering of Influencing Factors on Medical Decision-Making.

Clinical decision support systems (CDSS) can efficiently support doctors in coping with ever-increasing amounts of data by providing evidence-based recommendations for medical decisions. To integrate the systems into the medical workflow and provide patient-specific recommendations for action in the context of personalized medicine, it is essential to tailor the systems to the context of use. This study aims to present an overview of factors influencing medical decision-making that CDSS must consider. Our approach involves the systematic identification and categorization of contextual factors relevant to medical decision-making. Through extensive literature research and a structured card-sorting workshop, we systematized 774 context factors and mapped them into a model. This model includes six primary entities: the treating physician, the patient, the patient's family, disease treatment, the physician's institution, and professional colleagues, each with their relevant context categories. The developed model could serve as a foundation for communication between developers and physicians, supporting the creation of more context-sensitive CDSS in the future. Ultimately, this could enhance the utilization of CDSS and improve patient care.

Visualization Techniques for Summarizing Single Patient Health Data to Support Physicians' Clinical Decisions - A Scoping Review.

INTRODUCTION: User-centered data visualizations can reduce physician cognitive load and support clinical decision making. To facilitate the selection of appropriate visualizations for single patient health data summaries, this scoping review provides a literature overview of possible visualization techniques and the corresponding reported user-centered design phases. METHODS: The publication databases PubMed, Web of Science, IEEE Xplore and ACM Digital Library were searched for relevant articles from 2017 to 2022. RESULTS: Of the 777 articles screened, 78 articles were included in the final analysis. The most commonly used visualization techniques are table, scatterplot-line timeline, text and event timelines, with 24 other visualization techniques identified. The testing phase of the user centered design process is reported most frequently. CONCLUSION: This scoping review can support developers in the selection of suitable visualizations for single patient health data by revealing the design space of possible visualization techniques.

User-Centered Development of Explanation User Interfaces for AI-Based CDSS: Lessons Learned from Early Phases.

This paper reports lessons learned during the early phases of the user-centered design process for an explanation user interface for an AI-based clinical decision support system for the intensive care unit. This paper focuses on identifying and verifying physicians' explanation needs in a multi-center, multi-country project. The explanation needs identified through context analysis and user requirements prioritization in an initial center differed from those identified through questionnaire responses from N= 9 physicians after a multi-center project workshop. These results highlight the caution that should be taken when eliciting explanation needs during the user-centered design process.

Context-Sensitive Common Data Models for Genetic Rare Diseases - A Concept.

Current challenges of rare diseases need to involve patients, physicians, and the research community to generate new insights on comprehensive patient cohorts. Interestingly, the integration of patient context has been insufficiently considered, but might tremendously improve the accuracy of predictive models for individual patients. Here, we conceptualized an extension of the European Platform for Rare Disease Registration data model with contextual factors. This extended model can serve as an enhanced baseline and is well-suited for analyses using artificial intelligence models for improved predictions. The study is an initial result that will develop context-sensitive common data models for genetic rare diseases.

Patient Quality of Life After Subpectoral Implant-based Breast Reconstruction With Synthetic or Biological Materials.

AIM: Quality of life and patient satisfaction after subpectoral breast reconstruction with meshes or acellular dermal matrices (ADM) and implants were assessed using the BreastQ questionnaire to investigate a potential influence of the materials on these parameters. PATIENTS AND METHODS: The BreastQ questionnaire was completed by 121 patients, who had received material-assisted, heterologous, subpectoral breast reconstruction between 2010 and 2018. RESULTS: Answers were similar independent of the reconstruction materials used. After prophylactic mastectomy, the physical wellbeing (chest) improved significantly with all materials (p=0.04). Postoperative radiotherapy significantly reduced satisfaction with outcome (p=0.005). Patients under 50 years old had significantly better postoperative sexual wellbeing than older patients (p=0.03). CONCLUSION: No influence was detected of the materials on the postoperative quality of life and patient satisfaction. An overall better quality of life was reported by younger and normal-weight patients with prophylactic or nipple-sparing mastectomy without radiotherapy.

Postoperative Complications in Breast Reconstruction With Porcine Acellular Dermis and Polypropylene Meshes in Subpectoral Implant Placement.

AIM: This research compares postoperative complication rates with Strattice™, SERAGYN® BR, and TiLOOP® Bra interposition devices for subpectoral implant placement after skin or nipple sparing mastectomy. PATIENTS AND METHODS: 188 breast reconstructions in 157 patients after primary (n=96), secondary (n=71), or prophylactic (n=21) surgery were analyzed regarding major and minor complications. RESULTS: With acellular dermal matrix (ADM) Strattice™, 27.5% major and 27.5% minor complications occurred. Implant loss rates were 27.3% in primary and 30.8% in secondary reconstructions. With SERAGYN® BR, 11.1% major and 13,0% minor complications occurred. Implant losses (6.1%) occurred exclusively in primary reconstructions. With TiLOOP® Bra, 14.9% major and 9.6% minor complications occurred. Implant loss rates were 7.7% in primary and 7.1% in secondary reconstructions. CONCLUSION: ADM was associated with high complication rates in primary and secondary reconstructions. Low complication rates were seen with mesh interposition devices in primary, secondary, and prophylactic reconstructions.