来自临床叙述的可靠多语言骨科决策支持：语言感知适应与验证引导的延迟
Reliable Multilingual Orthopedic Decision Support from Clinical Narratives: Language-Aware Adaptation and Verification-Guided Deferral
AI总结：
针对低资源医疗环境中的多语言骨科决策支持，提出结合语言感知适配编码器IndicBERT-HPA和确定性选择性验证层的可靠性框架，在英语、印地语和旁遮普语临床文本分类中取得最优性能。
摘要：
多语言骨科决策支持在低资源医疗环境中仍然具有挑战性，其中临床叙述包含专业术语、混合文字、不完整证据、标签不平衡和语言依赖的文档模式。本文提出了一个面向可靠性的框架，用于对英语、印地语和旁遮普语的自由文本骨科笔记进行分类。我们比较了任务对齐的多语言Transformer编码器、任务微调的DistilBERT基线、零样本指令微调的大语言模型（LLMs）和领域自适应编码器IndicBERT-HPA。IndicBERT-HPA通过语言感知的骨科适配器头增强IndicBERT，以支持临床相关的多语言表示学习。评估从整体准确率扩展到每类性能、ROC-AUC、AUPRC、期望校准误差、跨语言稳定性以及在受控平衡和自然患病率分布下的鲁棒性。评估的零样本LLMs在封闭集分类中远不如任务自适应编码器有效，且存在语言依赖的不稳定性。在自然临床患病率下，IndicBERT-HPA实现了最强的整体性能，平均Macro-F1达到0.8792，Macro-AUROC为0.894，AUPRC为0.902。我们进一步实现了一个确定性的选择性验证层，结合了置信门控、证据一致性检查和语言风险筛查。在随机选择的5000条保留子集上，它在72.3%的覆盖率下实现了84.4%的选择性准确率和0.76的选择性Macro-F1，而全接受预测的准确率为71.5%，Macro-F1为0.65。这些结果支持了面向可靠性的多语言临床决策支持，并带有明确的延迟机制。
英文摘要：
Multilingual orthopedic decision support remains challenging in low-resource healthcare settings, where clinical narratives contain specialized terminology, mixed scripts, incomplete evidence, label imbalance and language-dependent documentation patterns. This article presents a reliability-oriented framework for classifying free-text orthopedic notes in English, Hindi and Punjabi. We compare task-aligned multilingual transformer encoders, a task-fine-tuned DistilBERT baseline, zero-shot instruction-tuned large language models (LLMs) and a domain-adaptive encoder, IndicBERT-HPA. IndicBERT-HPA augments IndicBERT with language-aware orthopedic adapter heads to support clinically relevant multilingual representation learning. Evaluation extends beyond aggregate accuracy to per-class performance, ROC-AUC, AUPRC, expected calibration error, cross-language stability and robustness under controlled balanced and natural-prevalence distributions. The evaluated zero-shot LLMs remain substantially less effective than task-adapted encoders for closed-set classification, with language-dependent instability. Under natural clinical prevalence, IndicBERT-HPA achieves the strongest overall performance, reaching an averaged Macro-F1 of 0.8792, Macro-AUROC of 0.894 and AUPRC of 0.902. We further implement a deterministic selective-verification layer combining confidence gating, evidence-consistency checking and language-risk screening. On a randomly selected held-out 5,000-record subset, it achieves 84.4% selective accuracy and 0.76 selective Macro-F1 at 72.3% coverage, compared with 71.5% accuracy and 0.65 Macro-F1 for accept-all prediction. These results support reliability-oriented multilingual clinical decision support with explicit deferral.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
