Differential Diagnosis Framework

•
50
•

Guides structured diagnostic reasoning by generating comprehensive hypotheses, applying Bayesian testing thresholds, and preventing cognitive biases.

The Differential Diagnosis Framework skill provides structured, evidence-based methodologies for medical reasoning, clinical education, and decision-support tool design. By formalizing the generation of broad hypothesis sets through categorizations like VINDICATE, prioritizing conditions via probability and urgency, and leveraging likelihood ratios for Bayesian updates, it prevents common cognitive traps like premature closure and shotgun testing. While intended strictly for educational and algorithmic tool design rather than direct medical practice, it serves as an indispensable framework for modeling rigorous diagnostic paths.

주요 기능

01Risk-weighted hypothesis prioritization balancing pre-test probability and critical can't-miss diagnoses
02Countermeasures against cognitive biases including premature closure, anchoring, and confirmation bias
0348 GitHub stars
04Bayesian probability updating using likelihood ratios and test-treatment thresholds
05Structured clinical workflow guidance covering data gathering, diagnostic timeouts, and documentation
06Comprehensive hypothesis generation using structured frameworks like VINDICATE

사용 사례

01Evaluating test selection efficiency against likelihood ratios to prevent shotgun testing
02Structuring diagnostic reasoning scenarios for medical education and trainee assessment
03Designing and auditing clinical decision-support algorithms and health tech workflows