Background Systemic drug reaction (SDR) is a major safety concern with weekly rifapentine-based treatment (3HP) for latent tuberculosis infection (LTBI). Identifying SDR predictors and at-risk subjects before treatment can improve cost-effectiveness of the LTBI program. Methods We prospectively recruited 187 cases receiving 3HP (44 SDRs and 143 non-SDRs). A pilot cohort (8 SDRs and 12 non-SDRs) was selected for generating whole-blood transcriptomic data. Through the incorporation of the hierarchical system biology model and therapy–biomarker pathway approach, candidate genes were selected and evaluated using reverse transcription-quantitative polymerase chain reaction (RT-qPCR). Then, interpretable machine learning models presenting as SHapley Additive exPlanations (SHAP) values were applied for SDR risk prediction. Finally, an independent cohort was used to evaluate the performance of these predictive models. Results Based on the whole-blood transcriptomic profile of the pilot cohort and the RT-qPCR results of 2 SDR and 3 non-SDR samples in training cohort, six genes were selected. According to SHAP values for model construction and validation, a 3-gene model for SDR risk prediction achieved a sensitivity and specificity of 0.972 and 0.947, respectively, under a universal cutoff value for the joint of the training (28 SDRs and 104 non-SDRs) and testing (8 SDRs and 27 non-SDRs) cohorts. It also worked well across different subgroups. Conclusions The prediction model for 3HP-related SDR serves as a guide for establishing a safe and personalized regimen to foster the implementation of the LTBI program. Additionally, it provides a potential translational value for future studies on drug-related hypersensitivity.

中文翻译：

---

全血 3 基因特征作为基于利福喷汀的结核病预防治疗的辅助决策

背景 全身性药物反应 (SDR) 是针对潜伏性结核感染 (LTBI) 的每周一次基于利福喷汀的治疗 (3HP) 的主要安全问题。在治疗前识别 SDR 预测因子和高危受试者可以提高 LTBI 计划的成本效益。方法 我们前瞻性地招募了 187 例接受 3HP 的病例（44 例 SDR 和 143 例非 SDR）。选择一个试点队列（8 个 SDR 和 12 个非 SDR）来生成全血转录组数据。通过结合分级系统生物学模型和治疗-生物标志物途径方法，使用逆转录-定量聚合酶链反应 (RT-qPCR) 选择和评估候选基因。然后，将呈现为 SHapley 加法解释 (SHAP) 值的可解释机器学习模型应用于 SDR 风险预测。最后，一个独立的队列被用来评估这些预测模型的性能。结果 根据试点队列的全血转录组学概况和训练队列中 2 个 SDR 和 3 个非 SDR 样本的 RT-qPCR 结果，选择了 6 个基因。根据用于模型构建和验证的 SHAP 值，用于 SDR 风险预测的 3 基因模型在联合训练的通用截止值（28 个 SDR 和 104 个非 SDR）下分别实现了 0.972 和 0.947 的灵敏度和特异性) 和测试（8 个 SDR 和 27 个非 SDR）队列。它在不同的子组中也很有效。结论 3HP 相关 SDR 的预测模型可作为建立安全和个性化方案的指南，以促进 LTBI 计划的实施。此外，