# Second Opinion Matters: Towards Adaptive Clinical AI via the Consensus of Expert Model Ensemble

arXiv: https://arxiv.org/abs/2505.23075 · HTML: https://mlsanity.com/paper/2505.23075/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 29 May 2025.

## Builds on (most cited first, 11 of 11)

- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding](https://mlsanity.com/paper/2501.18362/) (2025)
- [Towards Accurate Differential Diagnosis with Large Language Models](https://mlsanity.com/paper/2312.00164/) (2023)
- [A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications](https://mlsanity.com/paper/2503.07137/) (2025)
- [DDXPlus: A New Dataset For Automatic Medical Diagnosis](https://mlsanity.com/paper/2205.09148/) (2022)
- [Multi-Agent Consensus Seeking via Large Language Models](https://mlsanity.com/paper/2310.20151/) (2023)
- [Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills](https://mlsanity.com/paper/2503.05641/) (2025)
- [MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration](https://mlsanity.com/paper/2410.04521/) (2024)
- [The Rise of Small Language Models in Healthcare: A Comprehensive Survey](https://mlsanity.com/paper/2504.17119/) (2025)
- [Gatekeeper: Improving Model Cascades Through Confidence Tuning](https://mlsanity.com/paper/2502.19335/) (2025)
- [Large Language Models in Healthcare](https://mlsanity.com/paper/2503.04748/) (2025)

## Built on by (most cited first, 1 of 1)

- [AI-Generated Content in Cross-Domain Applications: Research Trends, Challenges and Propositions](https://mlsanity.com/paper/2509.11151/) (2025)

## Abstract (arXiv)

Despite the growing clinical adoption of large language models (LLMs), current approaches heavily rely on single model architectures. To overcome risks of obsolescence and rigid dependence on single model systems, we present a novel framework, termed the Consensus Mechanism. Mimicking clinical triage and multidisciplinary clinical decision-making, the Consensus Mechanism implements an ensemble of specialized medical expert agents enabling improved clinical decision making while maintaining robust adaptability. This architecture enables the Consensus Mechanism to be optimized for cost, latency, or performance, purely based on its interior model configuration. To rigorously evaluate the Consensus Mechanism, we employed three medical evaluation benchmarks: MedMCQA, MedQA, and MedXpertQA Text, and the differential diagnosis dataset, DDX+. On MedXpertQA, the Consensus Mechanism achieved an accuracy of 61.0% compared to 53.5% and 45.9% for OpenAI's O3 and Google's Gemini 2.5 Pro. Improvement was consistent across benchmarks with an increase in accuracy on MedQA (DeltaAccuracy_mathrmconsensus-O3 = 3.4%) and MedMCQA (DeltaAccuracy_mathrmconsensus-O3 = 9.1%). These accuracy gains extended to differential diagnosis generation, where our system demonstrated improved recall and precision (F1consensus = 0.326 vs. F1_mathrmO3-high = 0.2886) and a higher top-1 accuracy for DDX (Top1consensus = 52.0% vs. Top1_mathrmO3-high = 45.2%).