发表机构
Manning College of Information and Computer Sciences, UMass Amherst; Center for Healthcare Organization and Implementation Research, VA Bedford Health Care; Miner School of Computer and Information Sciences, UMass Lowell（马萨诸塞大学阿默斯特分校曼宁信息与计算机科学学院; VA贝德福德医疗保健中心医疗组织与实施研究中心; 马萨诸塞大学洛厄尔分校迈纳计算机与信息科学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出OverdoseMoE多专家框架，结合疾病特异性语言模型适应与互补专家加权，利用患者纵向ICD病史预测180天阿片类药物过量风险，显著提升AUPRC和AUROC，并在独立MIMIC-IV队列中验证了跨队列稳健性。
AI 中文摘要
阿片类药物过量仍然是一个重大的临床和公共卫生负担，凸显了识别高风险患者的可扩展方法的必要性。在此，我们研究了基于患者前一年的纵向ICD病史进行180天阿片类药物过量风险预测的疾病特异性适应方法。我们通过对纵向诊断序列进行持续预训练并随后进行任务特定微调，开发了OODMAMBA和OODQWEN。在更强的基于Qwen的预测器基础上，我们进一步提出了OVERDOSEMOE，这是一个多专家框架，通过互补的专家加权策略整合不同规模的模型。疾病特异性适应持续优于通用语言模型基线，其中OODQWEN实现了24.47的AUPRC和68.56的AUROC。OVERDOSEMOE进一步改善了区分度和精确度，实现了25.17的AUPRC和69.49的AUROC，同时优于最强的单模型基线。在预测风险排名前5%的患者中，OVERDOSEMOE识别出显著富集的过量风险，实现了25.38%的PPV，同时保持了有意义的召回率。在独立的MIMIC-IV队列上的评估进一步证明了跨队列的稳健性，互补加权策略在不同性能指标上显示出优势。这些发现表明，疾病特异性语言模型适应与多专家集成相结合，可以改善阿片类药物过量风险分层，并支持在异构电子健康记录人群中实现更稳健的预测。
英文摘要
Opioid overdose remains a major clinical and public health burden, highlighting the need for scalable approaches to identify patients at high risk. Here, we investigate diagnosis-specific adaptation for 180-day opioid overdose risk prediction from patients' preceding one-year longitudinal ICD histories. We develop OODMAMBA and OODQWEN through continued pretraining on longitudinal diagnostic sequences followed by task-specific fine-tuning. Building on the stronger Qwen-based predictors, we further propose OVERDOSEMOE, a multi-expert framework that integrates models of different scales using complementary expert-weighting strategies. Diagnosis-specific adaptation consistently improved predictive performance over general-purpose language-model baselines, with OODQWEN achieving an AUPRC of 24.47 and an AUROC of 68.56. OVERDOSEMOE further improved discrimination and precision, achieving an AUPRC of 25.17 and an AUROC of 69.49 while outperforming the strongest single-model baselines. Among patients ranked in the top 5% of predicted risk, OVERDOSEMOE identified substantially enriched overdose risk, achieving a PPV of 25.38% while retaining meaningful recall. Evaluation on an independent MIMIC-IV cohort further demonstrated cross-cohort robustness, with complementary weighting strategies showing advantages across different performance measures. These findings demonstrate that diagnosis-specific language-model adaptation combined with multi-expert integration can improve opioid overdose risk stratification and support more robust prediction across heterogeneous electronic health record populations.
