从手册到维护：在低资源场景中微调MedGemma以提供多模态成像系统支持
From Manuals to Maintenance: Fine-Tuning MedGemma for Multi-Modal Imaging System Support in Low-Resource Settings
浏览论文内容
中文总结 AI 辅助
针对中低收入国家医疗设备维护难题，研究人员构建INGENZI_DatasetV1数据集，用QLoRA微调MedGemma-4b-it模型，使维修问答指标大幅提升，为低资源场景AI辅助医疗维护奠定基础。
中文摘要 AI 辅助
中低收入国家（LMICs）的医疗设备停机是医疗服务提供的主要障碍，这通常是由于难以获得专业生物医学工程支持所致。我们提出了一种多模态医疗设备维护问答（QA）框架，并展示了针对专业技术故障排查任务微调医疗基础模型的过程。基于对9个中低收入国家的跨国调查，我们整理了MRI和超声系统的技术手册，生成了INGENZI_DatasetV1数据集，该数据集包含10294个高质量、经过筛选的问答-上下文对。我们使用基于QLoRA的参数高效微调方法，对MedGemma-4b-it模型进行适配，使其能够解析系统错误日志并生成分步设备维修说明。与基线模型相比，微调后的系统在各项指标上均取得了显著提升，包括F1分数从0.22提升至0.38，ROUGE-2分数从0.18提升至0.41，BERTScore F1分数从0.86提升至0.91。这些指标提升表明，该模型能够针对新的故障排查查询生成更精准、流程更准确的技术响应。本研究为资源受限场景下的AI辅助诊断和维护工具奠定了可靠基础。
英文摘要
Imaging device downtime is a major barrier to healthcare delivery in low- and middle-income countries (LMICs), often driven by limited access to specialized biomedical engineering support. We present a multi-modality medical equipment maintenance question-answering (QA) framework and demonstrate the fine-tuning of a medical foundation model for specialized technical troubleshooting tasks. Guided by a multi-country survey across nine LMICs, we curated technical manuals from MRI and ultrasound systems to generate the INGENZI_DatasetV1, containing 10,294 high-quality, filtered QA-context pairs. Using QLoRA-based parameter-efficient fine-tuning, we adapted the MedGemma-4b-it model to interpret system error logs and generate step-by-step equipment repair instructions. Compared to the baseline model, the fine-tuned system achieved substantial improvements across metrics, including F1 score (0.22 to 0.38), ROUGE-2 (0.18 to 0.41), and BERTScore F1 (0.86 to 0.91). These metric gains demonstrate that the model generates significantly more precise and procedurally accurate technical responses to new troubleshooting queries. This work establishes a reliable foundation for AI-assisted diagnostic and maintenance tools in resource-constrained settings.
发表机构
- Carnegie Mellon University Africa（非洲卡内基梅隆大学）
- IngenziAI（因根齐人工智能公司）
- Federal University of Health Sciences Azare（阿扎雷联邦健康科学大学）
- University of Maiduguri Teaching Hospital（迈杜古里大学教学医院）
- Lawson Health Research Institute（劳森健康研究所）
- University of Pennsylvania（宾夕法尼亚大学）
- McGill University（麦吉尔大学）
机构由 AI 辅助整理，请以论文原文为准。
