INCLAIR：基于Inception的带知情推理的纵向临床异常检测
INCLAIR: Inception-Based Longitudinal Clinical Anomaly Detection with Informed Reasoning
浏览论文内容
中文总结 AI 辅助
提出INCLAIR框架，基于Inception实现纵向临床异常检测，经三个临床数据集及类固醇特征案例验证，其性能优于基线，可在有限专家监督下完成临床可操作的异常检测。
中文摘要 AI 辅助
纵向临床特征的异常检测具有重要临床意义但难度较大：异常证据通常稀疏、患者病史长度不一，且专家解释成本高昂。我们提出INCLAIR框架，该框架将每个观测值与多个历史上下文进行评分，在特征层面聚合证据，并在有限专家监督下生成有依据的自然语言解释。在给定的特征内可交换性假设下，完整的平均子序列评分采用阶数为l的U统计量形式，产生方差分解和不完全子集近似，可独立于特征长度控制组合推理成本。相同分析表明，平均聚合会根据异常支持度和特征长度衰减局部异常，从而验证选择前k个池化的合理性。在三个临床数据集上，INCLAIR始终优于最先进的基线方法。我们还通过对纵向类固醇特征的案例研究验证了其实用相关性，将INCLAIR的预测和解释与DNA分析支持的领域专家评估进行比较。结果显示，INCLAIR可在有限专家监督下实现临床可操作的异常检测。
英文摘要
Detecting anomalies in longitudinal clinical profiles is clinically important but difficult: abnormal evidence is often sparse, patient histories have unequal length, and expert explanations are costly. We propose INCLAIR, a framework that scores each observation against multiple historical contexts, aggregates evidence at the profile level, and generates grounded natural-language explanations under limited expert supervision. Under stated within-profile exchangeability assumptions, the complete mean subsequence score takes an order-$l$ U-statistic form, yielding a variance decomposition and an incomplete-subset approximation that controls combinatorial inference cost independently of profile length. The same analysis shows that mean aggregation attenuates localized anomalies by a factor set by the anomaly support and profile length, motivating validation-selected top-$k$ pooling. Across three clinical datasets, INCLAIR consistently outperforms state-of-the-art baselines. We further validate practical relevance through a case study on longitudinal steroid profiles, comparing INCLAIR's predictions and explanations against domain-expert assessments supported by DNA analysis. The results show that INCLAIR enables clinically actionable anomaly detection under limited expert supervision.
