Integrating Exosomal MicroRNA and Electronic Health Data Improves Tuberculosis Diagnosis

Abstract

Background: Tuberculosis is difficult to diagnose under complex clinical conditions. Diagnostic information from electronic health records (EHRs) remains insufficient. Exosomal miRNAs have emerged as promising disease biomarkers. We aimed to investigate the potential of exosomal miRNAs and EHRs to assist with the clinical diagnosis of tuberculosis. Methods: We recruited 407 individuals through a multi-stage approach. Exosomal miRNA expression was profiled using microarray and qRT-PCR method. Differentially expressed miRNAs (DEMs) were selected in the discovery set and validated in the prospective selection and independent testing cohorts. EHRs and follow-up information were collected accordingly. The 'EHR miRNA', 'miRNA only' and 'EHR only' models were established using the Support Vector Machine algorithm. Findings: A total of 370 individuals were ultimately enrolled. Six DEMs (miR-20a, miR-20b, miR-26a, miR-106a, miR-191, and miR-486) were found to be overexpressed in pulmonary tuberculosis (PTB) and tuberculous meningitis (TBM) patients relative to their controls. The 'EHR miRNA' model showed a superior clinical diagnostic efficacy, with an increased AUC of 0.97 (95% CI 0.80-0.99) in TBM and 0.97 (0.87-0.99) in PTB, respectively. Model feature analysis determined that miR-20b, miR-191, and miR-486 were promising diagnostic biomarkers for tuberculosis. The expression of DEMs presented a decreased trend after 2-month intensive anti-tuberculosis therapy (adjusted p = 4.80 ×10-5). Interpretation: Our results concluded that the combination of exosomal miRNAs and EHRs in a machine learning algorithm potentially improved TBM and PTB clinical diagnoses. Further validation is warranted. Funding Statement: Funds for the Central Universities, the National Natural Science Foundation of China. Declaration of Interests: The authors declare that they have no competing interests. Ethics Approval Statement: The study was approved by the Clinical Trials and Biomedical Ethics Committee of West China Hospital, Sichuan University [No. 2014 (198)]. Informed consent was obtained from the participants.