发表机构
Soroti University（索罗蒂大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对撒哈拉以南非洲低资源医疗环境，提出基于Qwen2.5 - 3B - Instruct并经QLoRA微调的Aletheia临床决策支持系统，评估显示其在诊断准确率等指标上表现良好，证明在无云设施的资源受限环境初级保健层部署大语言模型临床推理的可行性。
AI 中文摘要
在撒哈拉以南非洲，获得专业临床专业知识的机会仍然极为有限，农村地区医患比例可能低于1:25000。现有的人工智能辅助诊断工具主要需要可靠的互联网连接和高规格硬件，对地区医院和健康中心的一线医护人员不实用。本文提出了Aletheia，一个专为撒哈拉以南非洲低资源医疗环境设计的离线优先临床决策支持系统。Aletheia基于Qwen2.5 - 3B - Instruct构建，使用量化低秩适应（QLoRA）在一个包含27000个临床推理样本的精选数据集上进行微调，该数据集涵盖东非50种高流行疾病状况。评估显示在十个代表性临床病例类别中，Top - 1诊断准确率为80.0%，Top - 3准确率为100.0%，BERTScore - F1为0.909，METEOR为0.467。系统的预期校准误差（ECE）为0.275，通过了2026年非洲深度科技挑战赛（ADTC 2026）7168MB的内存预算限制，在标准化基准笔记本电脑上实现了约3630MB的峰值推理RAM。这些结果证明了在没有云基础设施的资源受限环境中，在初级保健层面部署基于大语言模型的临床推理的可行性。
英文摘要
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% (8 of 10 cases; 95% CI: 49.0-94.3%), Top-3 accuracy of 100% (10 of 10 cases; 95% CI: 72.2-100%), BERTScore-F1 of 0.909, and METEOR of 0.467. These diagnostic figures are computed over a deliberately small set of ten representative clinical case categories, one case each, and are therefore indicative rather than statistically robust; the wide confidence intervals should be read alongside them. 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 7168 MB, achieving a peak inference RAM of approximately 3630 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.
Comments9 pages, 7 figures, 4 tables
