====== Clinical Diagnosis Agents: MACD ======

Multi-agent systems are entering clinical medicine, where specialized LLM agents collaborate on diagnostic tasks that traditionally require years of physician expertise. **MACD** (Multi-Agent Clinical Diagnosis, 2025) introduces a framework where agents self-learn reusable clinical knowledge from historical patient cases and apply it to achieve diagnostic accuracy that matches or exceeds human physicians.

===== Architecture: Self-Learned Knowledge =====

MACD's core innovation is **Self-Learned Knowledge** -- structured diagnostic knowledge that agents automatically extract, refine, and apply from historical case data. This mimics how physicians build expertise through clinical experience.

The knowledge is stored as structured 5-tuples capturing clinical features, conditions, relevance scores, and diagnostic implications. A greedy algorithm with **maximal marginal relevance** selects diverse concepts while removing redundancies.

**Concept-Based Causal Intervention** assesses knowledge importance by ablating each concept and measuring the change in diagnostic accuracy:

$$\Delta Acc_c = Acc_{\text{with } c} - Acc_{\text{without } c}$$

Concepts with high $\Delta Acc$ are retained as high-impact knowledge, while low-impact or redundant concepts are pruned.

===== Three Specialized Agents =====

**Knowledge Summarizer Agent:** Extracts and structures diagnostic concepts from a sampling set of historical patient cases. It then refines the knowledge base through diversity selection and causal ablation to retain only high-impact knowledge.

**Diagnostician Agent:** Applies the Self-Learned Knowledge during inference. For each new patient case (history, exams, labs, radiology), it augments its prompt with relevant knowledge and produces a primary diagnosis with explicit rationales linking evidence to knowledge.

**Evaluator Agent:** Normalizes diagnostic terminology through tolerant name-matching and computes BioBERT semantic similarity scores to assess consensus among multiple diagnostician agents using diverse LLMs.

===== MACD-Human Collaborative Workflow =====

In the extended workflow, multiple Diagnostician agents (powered by different LLMs, each with their own knowledge base) engage in iterative consultations:

  - Each agent independently diagnoses the case
  - Agents exchange anonymized opinions
  - The Evaluator checks for consensus
  - Unresolved cases escalate to human physician oversight

This simulates real-world clinical team consultations where multiple specialists review complex cases.

===== Code Example: Clinical Diagnosis Pipeline =====

<code python>
class MACDFramework:
    def __init__(self, summarizer_llm, diagnostician_llms, evaluator_llm):
        self.summarizer = KnowledgeSummarizer(summarizer_llm)
        self.diagnosticians = [
            DiagnosticianAgent(llm) for llm in diagnostician_llms
        ]
        self.evaluator = EvaluatorAgent(evaluator_llm)

    def build_knowledge_base(self, historical_cases, disease):
        raw_concepts = self.summarizer.extract_concepts(historical_cases)
        diverse_concepts = self.summarizer.select_diverse(
            raw_concepts, method="maximal_marginal_relevance"
        )
        refined_knowledge = []
        for concept in diverse_concepts:
            delta_acc = self.causal_ablation(concept, historical_cases)
            if delta_acc > self.threshold:
                refined_knowledge.append(concept)
        return refined_knowledge

    def diagnose(self, patient_case, knowledge_base):
        diagnoses = []
        for agent in self.diagnosticians:
            diagnosis = agent.diagnose(
                patient_case, knowledge=knowledge_base
            )
            diagnoses.append(diagnosis)
        consensus = self.evaluator.check_consensus(diagnoses)
        if consensus.agreement_score > 0.8:
            return consensus.primary_diagnosis
        return self.escalate_to_human(patient_case, diagnoses)

    def causal_ablation(self, concept, cases):
        acc_with = self.evaluate_accuracy(cases, include=concept)
        acc_without = self.evaluate_accuracy(cases, exclude=concept)
        return acc_with - acc_without
</code>

===== Results =====

Evaluated on 4,390 real-world cases from the **MIMIC-MACD** dataset across seven diseases:

^ Metric ^ Result ^
| Primary Diagnostic Accuracy | Up to **22.3%** over clinical guidelines (e.g., Mayo Clinic) |
| Avg improvement from Self-Learned Knowledge | **11.6%** |
| MACD vs Human Physicians | Llama-3.1 70B: 0.81 vs Human: 0.65 (p < 0.001) |
| MACD-Human Workflow vs Physicians-only | **18.6%** improvement |
| Consensus Rate (MACD-Human) | **58.6%** |
| Effective Agent Opinions | **88.5%** |

The self-learned knowledge transfers across models and provides traceable rationales for explainability.

===== Multi-Agent Diagnosis Diagram =====

<mermaid>
flowchart TD
    A[Historical Patient Cases] --> B[Knowledge Summarizer Agent]
    B --> C[Raw Diagnostic Concepts]
    C --> D[Diversity Selection + Causal Ablation]
    D --> E[Refined Self-Learned Knowledge]
    F[New Patient Case] --> G[Diagnostician Agent 1]
    F --> H[Diagnostician Agent 2]
    F --> I[Diagnostician Agent 3]
    E --> G
    E --> H
    E --> I
    G --> J[Evaluator Agent]
    H --> J
    I --> J
    J --> K{Consensus?}
    K -->|Yes| L[Primary Diagnosis + Rationale]
    K -->|No| M[Escalate to Human Physician]
</mermaid>

===== Clinical Significance =====

  * **Outperforms clinical guidelines:** Self-learned knowledge from case data is more specific and actionable than generic guidelines
  * **Exceeds human physicians:** On the MIMIC-MACD benchmark, MACD agents achieve 16% higher accuracy than physicians (p < 0.001)
  * **Explainable diagnostics:** Each diagnosis includes traceable rationales linking patient evidence to specific knowledge concepts
  * **Cross-model stability:** Self-learned knowledge transfers effectively across different LLM backbones
  * **Human-AI collaboration:** The MACD-Human workflow preserves physician oversight while leveraging agent capabilities

===== References =====

  * [[https://arxiv.org/abs/2509.20067|MACD: Multi-Agent Clinical Diagnosis with Self-Learned Knowledge for LLMs (arXiv:2509.20067)]]

===== See Also =====

  * [[causal_reasoning_agents|Causal Reasoning Agents: Causal-Copilot]]
  * [[knowledge_graph_world_models|Knowledge Graph World Models: AriGraph]]
  * [[agent_resource_management|Agent Resource Management: AgentRM]]