Tuberculosis (TB) is a major global health challenge, and is compounded by co-morbidities such as HIV, diabetes, and anemia, which complicate treatment outcomes and contribute to heterogeneous patient responses. Traditional models of TB often overlook this heterogeneity by focusing on broad, pre-defined patient groups, thereby missing the nuanced effects of individual patient contexts. We propose moving beyond coarse subgroup analyses by using contextualized modeling, a multi-task learning approach that encodes patient context into personalized models of treatment effects, revealing patient-specific treatment benefits. Applied to the TB Portals dataset with multi-modal measurements for over 3,000 TB patients, our model reveals structured interactions between co-morbidities, treatments, and patient outcomes, identifying anemia, age of onset, and HIV as influential for treatment efficacy. By enhancing predictive accuracy in heterogeneous populations and providing patient-specific insights, contextualized models promise to enable new approaches to personalized treatment.

翻译：结核病（TB）是全球重大健康挑战，其治疗因合并症（如HIV、糖尿病和贫血）而复杂化，这些合并症影响治疗结果并导致患者反应的异质性。传统的结核病模型常通过聚焦于宽泛的预定义患者群体而忽视这种异质性，从而遗漏了个体患者背景的细微效应。我们提出超越粗糙的亚组分析，采用情境化建模——一种将患者背景编码为个性化治疗效应模型的多任务学习方法，以揭示患者特异性的治疗获益。将该模型应用于包含3,000多名结核病患者多模态测量数据的TB Portals数据集，我们的模型揭示了合并症、治疗方案与患者预后之间的结构化交互作用，识别出贫血、发病年龄和HIV是影响治疗效能的关键因素。通过提升异质人群的预测准确性并提供患者特异性洞察，情境化模型有望为个性化治疗开辟新途径。