RESUMEN
Explainability for artificial intelligence (AI) in medicine is a hotly debated topic. Our paper presents a review of the key arguments in favor and against explainability for AI-powered Clinical Decision Support System (CDSS) applied to a concrete use case, namely an AI-powered CDSS currently used in the emergency call setting to identify patients with life-threatening cardiac arrest. More specifically, we performed a normative analysis using socio-technical scenarios to provide a nuanced account of the role of explainability for CDSSs for the concrete use case, allowing for abstractions to a more general level. Our analysis focused on three layers: technical considerations, human factors, and the designated system role in decision-making. Our findings suggest that whether explainability can provide added value to CDSS depends on several key questions: technical feasibility, the level of validation in case of explainable algorithms, the characteristics of the context in which the system is implemented, the designated role in the decision-making process, and the key user group(s). Thus, each CDSS will require an individualized assessment of explainability needs and we provide an example of how such an assessment could look like in practice.
RESUMEN
OBJECTIVES: To examine patterns of health care utilization among youth and young adults who have cerebral palsy (CP) and to provide information to guide the development of health services for adults who have CP. DESIGN: This study analyzed health insurance data for outpatient physician visits and hospital admissions for a 4-year period. SETTING: Six children's treatment centers in Ontario, Canada. PARTICIPANTS: The sample included 587 youth and 477 adults with CP identified from health records. Youths were 13 to 17 years of age, and adults were 23 to 32 years of age at the end of the data range. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: We computed the annual rates of outpatient physician visits and hospitalizations per 1000 persons and compared these with rates for the general population. RESULTS: Annual rates of outpatient physician visits were 6052 for youth and 6404 for adults with CP, 2.2 times and 1.9 times higher, respectively, than rates for age-matched peers (P<.01). Specialists provided 28.4% of youth visits but only 18.8% of adult visits. Annual hospital admission rates were 180 for youth and 98 for adults with CP, 4.3 times and 10.6 times higher, respectively, than rates for age-matched peers (P<.01). CONCLUSIONS: It appears that youth and adults with CP continue to have complex care needs and rely heavily on the health care system. Comprehensive services are essential to support their health as they move into youth and adulthood. However, there appear to be gaps in the adult health care system, such as limited access to specialist physicians.