基于大规模宿主反应数据，构建可预测多种病原体的轻量化诊断模型。
Pan-infection Foundation Framework Enables Multiple Pathogen Prediction
- 用1.1万+样本建立泛感染基础模型，再通过知识蒸馏生成轻量子模型。
- 在89个数据集上实现0.97以上AUC，对葡萄球菌等感染预测达0.99。
- 适合临床快速部署，支持跨疾病诊断与病原体精准识别。
基于宿主反应的诊断可提高细菌和病毒感染的诊断准确性，从而减少抗生素滥用。然而，现有队列样本量有限且感染类型粗略，难以支持准确且可泛化的诊断模型研究。本文整合了来自13个国家、21个平台的89个血液转录组数据集，共包含11,247个样本，构建了迄今为止最大的感染宿主反应转录组数据集。基于该数据集，我们建立了一个泛感染基础诊断模型（AUC = 0.97）。随后，利用知识蒸馏技术，将该‘教师’模型的知识高效迁移至四个轻量化病原体‘学生’模型：金黄色葡萄球菌感染（AUC = 0.99）、链球菌感染（AUC = 0.94）、HIV感染（AUC = 0.93）和呼吸道合胞病毒（RSV）感染（AUC = 0.94），以及一个脓毒症‘学生’模型（AUC = 0.99）。所提出的知识蒸馏框架不仅支持基于泛感染数据的病原体诊断，还实现了从泛感染到脓毒症的跨疾病研究。此外，该框架支持高度轻量化的模型设计，有望在临床环境中灵活部署。
原文摘要 · Abstract (English)
Host-response-based diagnostics can improve the accuracy of diagnosing bacterial and viral infections, thereby reducing inappropriate antibiotic prescriptions. However, the existing cohorts with limited sample size and coarse infections types are unable to support the exploration of an accurate and generalizable diagnostic model. Here, we curate the largest infection host-response transcriptome data, including 11,247 samples across 89 blood transcriptome datasets from 13 countries and 21 platforms. We build a diagnostic model for pathogen prediction starting from a pan-infection model as foundation (AUC = 0.97) based on the pan-infection dataset. Then, we utilize knowledge distillation to efficiently transfer the insights from this "teacher" model to four lightweight pathogen "student" models, i.e., staphylococcal infection (AUC = 0.99), streptococcal infection (AUC = 0.94), HIV infection (AUC = 0.93), and RSV infection (AUC = 0.94), as well as a sepsis "student" model (AUC = 0.99). The proposed knowledge distillation framework not only facilitates the diagnosis of pathogens using pan-infection data, but also enables an across-disease study from pan-infection to sepsis. Moreover, the framework enables high-degree lightweight design of diagnostic models, which is expected to be adaptively deployed in clinical settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。