LSTM-Based Prediction Model for Tuberculosis Among HIV-Infected Patients Using Structured Electronic Medical Records: A Retrospective Machine Learning Study

Abstract

Background: Both HIV and TB are chronic infectious diseases requiring long-term treatment and follow-up, resulting in extensive electronic medical records. With the exponential growth of health and medical big data, effectively extracting and analyzing these data has become the research hotspot. As a fundamental aspect of artificial intelligence, machine learning has been extensively applied in medical research, encompassing diagnosis, treatment, patient monitoring, drug development, and epidemiological investigations. This significantly enhances medical information systems and facilitates the interoperability of medical data. Methods: In our study, we analyzed longitudinal data from the electronic health records of 4540 patients, gathered from the National Clinical Research Center for Infectious Diseases in Shenzhen, China, spanning from 2017 to 2021. Initially, we employed the fine-tuned ChatGLM to structure the electronic medical records. Subsequently, we utilized a multi-layer perceptron to classify each patient and determined the presence of tuberculosis in HIV patients. Using machine learning-based natural language processing, we structured these records to build a specialized database for HIV and TB co-infection. We studied the epidemiological characteristics, focusing on incidence patterns, patient characteristics, and influencing factors, to uncover the transmission characteristics of these diseases in Shenzhen. Additionally, we used Long Short-Term Memory to create a predictive model for TB co-infection among HIV patients, based on their medical records. This model predicted the risk of TB co-infection, providing scientific evidence for clinical decision-making and enabling early detection and precise intervention. Results: Based on the refined ChatGLM model tailored for structured electronic health records, the accuracy of symptom extraction consistently surpassed 0.95 precision. Key symptoms such as diarrhea and normal showed precision rates exceeding 0.90. High scores were also achieved in recall and F1 scores. Among 4540 HIV patients, 758 were diagnosed with concurrent tuberculosis, indicating a 16.7% co-infection rate, while syphilis co-infection affected 25.1%, underscoring the prevalence of concurrent infections among HIV patients. Utilizing electronic health records, a Multilayer Perceptron classifier was developed as a benchmark against Long Short-Term Memory to predict high-risk groups for HIV and tuberculosis co-infections. The Multilayer Perceptron classifier demonstrated predictive ability with AUROC values ranging from 0.616 to 0.682 on the test set, suggesting opportunities for further optimization and generalization despite its accuracy in identifying HIV-TB co-infections. In tuberculosis intelligent diagnosis based on laboratory results, the Long Short-Term Memory showed consistent performance across 5-fold cross-validation, with AUROC values ranging from 0.827 to 0.850, indicating reliability and consistency in tuberculosis prediction. Furthermore, by optimizing classification thresholds, the model achieved an overall accuracy of 81.18% in distinguishing HIV co-infected tuberculosis from simple HIV infection. Conclusion: Combining the Multilayer Perceptron classifier with Long Short-Term Memory represented an advanced approach for effectively extracting electronic health records and utilizing it for disease prediction. This underscored the superior performance of deep learning techniques in managing both structured and unstructured medical data. Models leveraging laboratory time-series data demonstrated notably better performance compared to those relying solely on electronic health records for predicting tuberculosis incidence. This emphasized the benefits of deep learning in handling intricate medical data and provided valuable insights for healthcare providers exploring the use of deep learning in disease prediction and management.