Comprehensive primary care across the lifespan, including preventive medicine, chronic disease management, patient-centered care, and the coordination of healthcare services
4 papersGPT-3 demonstrates impressive performance in some cognitive tasks, including decision-making and information search. However, it struggles with causal reasoning, directed exploration, and shows sensitivity to minor changes in problem presentation, highlighting potential limitations in its cognitive abilities.
Medication adherence after myocardial infarction decreases over time for ACE inhibitors, P2Y12 inhibitors, and statins. Several sociodemographic (age, employment, education, marital status, location, economic status) and clinical factors (prior CABG) influence adherence levels, with married and younger patients tending to have better adherence.
The study found that the AI-powered triage and diagnostic system performed comparably to human doctors in identifying the condition modeled by a clinical vignette. The AI system demonstrated higher triage safety than doctors on average but slightly lower appropriateness. The quality of differential diagnoses produced by the AI system was rated comparably to those produced by human doctors, albeit with considerable disagreement among expert raters.
This paper introduces a new causal machine learning approach to medical diagnosis using counterfactual inference. The resulting algorithms outperform traditional associative methods, placing in the top 25% of doctors tested and significantly improving diagnostic accuracy, especially for rare diseases.