Multi-modal deep learning based on multi-dimensional and multi-level temporal data can enhance the prognostic prediction for multi-drug resistant pulmonary tuberculosis patients.

基于多维度多层次时态数据的多模态深度学习可增强耐多药肺结核患者的预后预测。

• 发表时间: 2022 Nov
• 来源期刊: Sci One Health
• DOI: 10.1016/j.soh.2022.100004
• PMID: 39076608
• 文章类型: Journal Article
• 作者列表: Lu ZH,Yang M,Pan CH,Zheng PY,Zhang SX

关键词: Deep learning; MDR-PTB; Multi-modal; Prognosis

Abstract

Despite the advent of new diagnostics, drugs and regimens, multi-drug resistant pulmonary tuberculosis (MDR-PTB) remains a global health threat. It has a long treatment cycle, low cure rate and heavy disease burden. Factors such as demographics, disease characteristics, lung imaging, biomarkers, therapeutic schedule and adherence to medications are associated with MDR-PTB prognosis. However, thus far, the majority of existing studies have focused on predicting treatment outcomes through static single-scale or low dimensional information. Hence, multi-modal deep learning based on dynamic data for multiple dimensions can provide a deeper understanding of personalized treatment plans to aid in the clinical management of patients.

摘要

尽管出现了新的诊断方法,药物和治疗方案，耐多药肺结核（MDR-PTB）仍然是全球健康威胁。治疗周期长,治愈率低,疾病负担重。人口统计等因素，疾病特征，肺成像,生物标志物，治疗方案和药物依从性与MDR-PTB预后相关.然而,到目前为止，现有的大部分研究集中在通过静态单尺度或低维信息预测治疗结果.因此，基于多维度动态数据的多模态深度学习可以提供对个性化治疗计划的更深入理解，以帮助患者的临床管理。