Discovering the Type 2 Diabetes in Electronic Health Records Using the Sparse Balanced Support Vector Machine

• Published in: IEEE journal of biomedical and health informatics Vol. 24; no. 1; pp. 235 - 246
• Main Authors: Bernardini, Michele, Romeo, Luca, Misericordia, Paolo, Frontoni, Emanuele
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aged; Aged, 80 and over; Computational modeling; Computer applications; Data models; Datasets; decision support system; Decision support systems; Decision Support Systems, Clinical; Diabetes; Diabetes mellitus; Diabetes mellitus (non-insulin dependent); Diabetes Mellitus, Type 2 - diagnosis; Diagnosis; electronic health record; Electronic Health Records; Electronic medical records; Feature extraction; Female; Humans; Informatics; Learning algorithms; Machine learning; Male; Middle Aged; Performance prediction; Reproducibility of Results; Support Vector Machine; Support vector machines; Type 2 diabetes
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2019.2899218

The diagnosis of type 2 diabetes (T2D) at an early stage has a key role for an adequate T2D integrated management system and patient's follow-up. Recent years have witnessed an increasing amount of available electronic health record (EHR) data and machine learning (ML) techniques have been considerably evolving. However, managing and modeling this amount of information may lead to several challenges, such as overfitting, model interpretability, and computational cost. Starting from these motivations, we introduced an ML method called sparse balanced support vector machine (SB-SVM) for discovering T2D in a novel collected EHR dataset (named Federazione Italiana Medici di Medicina Generale dataset). In particular, among all the EHR features related to exemptions, examination, and drug prescriptions, we have selected only those collected before T2D diagnosis from an uniform age group of subjects. We demonstrated the reliability of the introduced approach with respect to other ML and deep learning approaches widely employed in the state-of-the-art for solving this task. Results evidence that the SB-SVM overcomes the other state-of-the-art competitors providing the best compromise between predictive performance and computation time. Additionally, the induced sparsity allows to increase the model interpretability, while implicitly managing high-dimensional data and the usual unbalanced class distribution.