arXiv：cs.CL· Mingchen Li, Rohan Pandey, Junhui Qian, Feiyun Ouyang, Sunjae Kwon, Hong Yu·· 4 小时前AI 评分31
OverdoseMoE：面向阿片类药物过量风险预测的多专家框架
OverdoseMoE: A Multi-Expert Framework for Opioid Overdose Risk Prediction
AI 导读
研究团队提出 OVERDOSEMOE 多专家框架，用于基于患者一年 ICD 病史预测 180 天阿片类药物过量风险，其 AUPRC 达 25.17、AUROC 达 69.49，优于最强单模型基线。该框架整合不同规模模型并采用互补专家加权策略，在预测风险排名前 5% 的患者中 PPV 达 25.38%。在独立 MIMIC-IV 队列上的评估显示其具备跨队列稳健性。
正文
Abstract: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.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2609.40108 [cs.CL] |
| (or arXiv:2609.40108v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.40108 arXiv-issued DOI via DataCite |
Submission history
From: Mingchen Li [view email]
[v1]
Wed, 30 Sep 2026 16:39:38 UTC (1,893 KB)
[v2]
Fri, 2 Oct 2026 13:51:22 UTC (1,893 KB)
来源：arXiv：cs.CL · arxiv.org