clinical-diagnostic-reasoning

name	clinical-diagnostic-reasoning
license	Apache-2.0
description	Identify and counteract cognitive biases in medical decision-making through systematic error analysis and contextual algorithm application. For diagnostic reasoning, treatment decisions, and clinical judgment improvement. NOT for basic medical knowledge, technical procedures, or non-clinical healthcare domains.
allowed-tools	Read
metadata	{"tags":["clinical","diagnostic","reasoning"],"pairs-with":[{"skill":"systems-thinking","reason":"Systems thinking reveals feedback loops and hidden dependencies in diagnostic reasoning chains"},{"skill":"checklist-discipline","reason":"Diagnostic checklists reduce cognitive bias errors in medical decision-making"},{"skill":"crisis-detection-intervention-ai","reason":"Crisis detection requires the same bias-aware reasoning used in clinical diagnostics"}]}
category	Cognitive Science & Decision Making
tags	["diagnostic-reasoning","clinical","medical-decision-making","pattern-recognition","methodology"]

Clinical Diagnostic Reasoning

Improve diagnostic accuracy and treatment decisions by recognizing and overcoming systematic cognitive errors in clinical thinking.

When to Use

✅ Use for:

• Diagnostic decision-making in clinical practice
• Treatment planning and therapeutic choices
• Case review and error analysis
• Medical education on clinical reasoning
• Patient communication and shared decision-making
• Quality improvement and patient safety initiatives

❌ NOT for:

• Learning basic medical facts or pathophysiology
• Technical procedures or surgical skills
• Healthcare administration or policy
• Non-physician clinical roles without diagnostic responsibility
• Population health management without individual patient focus

Core Process

Diagnostic Reasoning Flow

New patient presentation
    ↓
┌───[Gather information through language/history]
│   ↓
│   Does presentation suggest standard algorithm?
│   ├─ NO → Continue hypothesis generation
│   │         ↓
│   │         Develop differential diagnosis
│   │         ↓
│   │         [Proceed to bias check]
│   │
│   └─ YES → Does patient context match algorithm assumptions?
│             ├─ YES → Apply algorithm
│             │         ↓
│             │         Monitor outcomes
│             │         ↓
│             │         [Proceed to bias check]
│             │
│             └─ NO → What patient-specific factors differ?
│                     ↓
│                     Does evidence justify deviation?
│                     ├─ YES → Document rationale and modify
│                     └─ NO → Apply algorithm; reconsider if new data
│
└─── [BIAS CHECK - Always perform]
     ↓
     Am I anchored to initial impression?
     ├─ POSSIBLY → Reassess case without initial anchor
     │
     Have I found one explanation and stopped searching?
     ├─ YES → Continue search: "What else could this be?"
     │         "Does this explain ALL findings?"
     │
     Am I pattern-matching from recent/memorable case?
     ├─ YES → List specific differences between cases
     │
     Am I stereotyping this patient?
     ├─ POSSIBLY → Reset: Evaluate symptoms independently
     │
     Do I feel compelled to "do something"?
     ├─ YES → Is action justified by evidence or anxiety?
     │         Is watchful waiting appropriate?
     │
     Have I sought disconfirming evidence?
     └─ NO → Actively look for data that contradicts working diagnosis

Case-Based Error Analysis Flow

Clinical error occurred
    ↓
What was the error?
    ├─ Wrong diagnosis
    ├─ Inappropriate treatment
    └─ Missed diagnosis
    ↓
Was this a knowledge gap or thinking error?
    ├─ KNOWLEDGE GAP → Address through study
    │                   (Not the focus of this skill)
    │
    └─ THINKING ERROR → Which cognitive bias operated?
                        ↓
                        ┌─ Anchoring? (stuck on initial impression)
                        ├─ Satisfaction of search? (stopped too early)
                        ├─ Availability? (recent case pattern-match)
                        ├─ Attribution? (stereotyped patient)
                        └─ Commission? (unnecessary action)
                        ↓
                        Was error preventable with current knowledge?
                        ├─ YES → How could bias have been recognized?
                        │         ↓
                        │         Extract generalizable lesson
                        │         ↓
                        │         Apply to future similar situations
                        │
                        └─ NO → Document for learning, not applicable