Prediction of complications in diabetes mellitus using machine learning models with transplanted topic model features

Abstract

Purpose: This study aims to predict the progression of Diabetes Mellitus (DM) from the clinical notes through machine learning based on latent Dirichlet allocation (LDA) topic modeling. Particularly, 174,427 clinical notes of DM patients were collected from the electronic medical record (EMR) system of the Seoul National University Hospital outpatient clinic. Method: We developed a model to predict the development of DM complications. Topics developed by the topic model were exploited as the key feature of our machine-learning model. The proposed model generalized a correlation between topic structures and complications. Results: The model provided acceptable predictive performance for all four types of complications (diabetic retinopathy, diabetic nephropathy, nonalcoholic fatty liver disease, and cerebrovascular accident). Upon employing extreme gradient boosting (XGBoost), we obtained the F1 scores of the predictions for each complication type as 0.844, 0.921, 0.831, and 0.762. Conclusion: This study shows that a machine learning project based on topic modeling can effectively predict the progress of a disease. Furthermore, a unique way of topic model transplanting, which matches the dimension of the topic structures of the two data sets, is presented.

Supplementary information: The online version contains supplementary material available at 10.1007/s13534-023-00322-7.

Keywords: Diabetes Mellitus; Latent Dirichlet allocation; Machine learning; Topic modeling.

Fig. 1

Basic concept of LDA [4] α: Initial parameter to Dirichlet distribution; β: parameter signifying the relations between words and topics; θ: parameter containing the relations between documents and topics; M: number of documents in a dataset; N: number of words in a document; w: words appearing in a document; Z:topic allocations to words in a document

Fig. 2

Overall Workflow Preprocessing: correcting typos, part of speech (POS) tagging, composing stop words list, and replacing drug product names with ingredient names; Indexing: filling a matrix (M × V) with term frequency(TF) values; Topic Modeling: filling a matrix (M × K) with the document-topic weight values; Classification: predicting the label variable utilizing the machine learning model