RareLens: Towards End-to-End Rare Disease Care via Aligning Divergent Large Language Model Reasoning
Organizations: Sports Medicine Center, Department of Orthopedics and Orthopedic Research Institute, West China Hospital, Sichuan University, Chengdu, China · Center for Cleft Lip and Palate Treatment, Plastic Surgery Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China · School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHKSZ), Shenzhen, China · West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, China · School of Computer Science, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA · School of Medicine, The Chinese University of Hong Kong, Shenzhen (CUHKSZ), Shenzhen, China · School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China · College of Computing and Data Science, Nanyang Technological University (NTU), Singapore 639798, Singapore · Plastic Surgery Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China · Pittsburgh Institute, Sichuan University, Chengdu, China · West China School of Medicine, Sichuan University, Chengdu, Sichuan 610041, P. R. China · The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong, China · Department of Aesthetic Plastic Surgery and Laser Medicine, Beijing Anzhen Hospital Affiliated to Capital Medical University, Beijing, China · Department of Orthopedics, Qilu Hospital of Shandong University, Jinan, Shandong, China · Shanghai Artificial Intelligence Laboratory, OpenMedLab, Shanghai, China · Med-X Center for Informatics, Sichuan University, Chengdu, Sichuan 610041, P. R. China
Abstract
Rare diseases represent one of the most challenging settings for clinical decision-making, where heterogeneous presentations, sparse evidence and limited expertise create persistent uncertainty throughout the care pathway. Although artificial intelligence could help, existing systems largely address isolated tasks, particularly diagnosis, and usually rely on downstream investigations rather than information available at initial presentation. Here we show that clinical AI performance under uncertainty can be improved not by scaling a single model, but by exploiting the diversity of multiple imperfect reasoning systems. Across heterogeneous large language models, we identify divergent reasoning trajectories with complementary error patterns and develop RareLens, which learns to reconcile these perspectives into actionable decisions across four stages of rare disease care: risk screening, diagnosis, treatment planning and prognosis prediction. Built on RarelensBench, a real-world dataset of 157,525 cases spanning all 33 Orphanet categories and more than 7,000 conditions, RareLens outperformed every frontier model tested, including GPT-5, DeepSeek-R1, Claude-3.7-Sonnet and Gemini-2.5-Pro, across all stages. It achieved an area under the curve of 0.917 for screening and top-1 accuracies of 65.5% and 89.8% for diagnosis and treatment. In an external evaluation involving 1,287 cases and 23 physicians, autonomous RareLens and physicians assisted by RareLens both outperformed unaided physicians, while demonstrating that effective human-AI collaboration requires more than simply providing model outputs. These findings establish divergent model reasoning as an exploitable source of information and suggest a general strategy for building AI systems that operate reliably under high clinical uncertainty.