在非洲农村用离线大模型辅助诊断，让基层医生也能高效判断常见病。
Aletheia: An Offline-First Clinical Decision Support System for Differential Diagnosis in Low-Resource Healthcare Settings
- 用量化微调技术将小模型适配临床推理，支持离线运行。
- 诊断准确率80%（Top-1），9种病类全对（Top-3达100%）。
- 适合网络差、设备旧的基层医院，特别适合非洲医疗资源匮乏地区。
撒哈拉以南非洲地区医疗资源极度匮乏，乡村医生与患者比例可低至1:25,000。现有AI诊断工具多依赖稳定网络和高性能硬件，难以在基层医疗机构部署。本文提出Aletheia，一种面向非洲低资源医疗环境的离线优先临床决策支持系统。该系统基于Qwen2.5-3B-Instruct模型，采用量化低秩适配（QLoRA）技术，在包含50种东非高发疾病、共27,000个临床推理样本的数据集上进行微调。评估显示，系统在10类代表性临床病例中实现Top-1诊断准确率80.0%，Top-3准确率100.0%，BERTScore-F1为0.909，METEOR得分为0.467。系统预期校准误差（ECE）为0.275，符合非洲深科技挑战赛2026（ADTC 2026）内存预算限制（7,168 MB），在标准笔记本上峰值推理内存约为3,630 MB。结果表明，无需云端基础设施，即可在初级医疗层面部署基于大语言模型的临床推理能力。
原文摘要 · Abstract (English)
Access to specialist clinical expertise remains severely limited across sub-Saharan Africa, where physician-to-patient ratios can fall below 1:25,000 in rural settings. Existing AI-assisted diagnostic tools predominantly require reliable internet connectivity and high-specification hardware, rendering them impractical for frontline healthcare workers in district hospitals and health centres. This paper presents Aletheia, an offline-first clinical decision support system designed for low-resource healthcare contexts across sub-Saharan Africa. Aletheia is built upon Qwen2.5-3B-Instruct, fine-tuned using Quantised Low- Rank Adaptation (QLoRA) on a curated dataset of 27,000 clinical reasoning samples spanning 50 disease conditions with elevated prevalence in East Africa. Evaluation demonstrates a Top-1 diagnostic accuracy of 80.0%, Top-3 accuracy of 100.0%, BERTScore-F1 of 0.909, and METEOR of 0.467 across ten representative clinical case categories. The system achieves an Expected Calibration Error (ECE) of 0.275 and passes the Africa Deep Tech Challenge 2026 (ADTC 2026) memory budget constraint of 7 168 MB, achieving a peak inference RAM of approximately 3 630 MB on the standardised benchmark laptop. These results demonstrate the feasibility of deploying large language model-based clinical reasoning at the primary care level in resource-constrained settings without cloud infrastructure.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。