Multi-label classification methods for improving comorbidities identification

• Published in: Computers in biology and medicine Vol. 100; pp. 279 - 288
• Main Authors: Wosiak, A., Glinka, K., Zakrzewska, D.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.09.2018; Elsevier Limited
• Subjects: Accuracy; Artificial Intelligence; Classification; Comorbidity; Comorbidity identification; Computer applications; Datasets; Decision making; Diagnosis, Computer-Assisted; Diagnostic systems; Experiments; Humans; Identification methods; Illnesses; Improving medical diagnosis; Label dependence; Medical diagnosis; Methods; Multi-label classification; Multi-perspective recognition; Patients; Pattern Recognition, Automated; Performance evaluation; Standard deviation; Label dependence; Comorbidity identification; Multi-perspective recognition; Multi-label classification; Improving medical diagnosis
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2017.07.006

The medical diagnostic process may be supported by computational classification techniques. In many cases, patients are affected by multiple illnesses, and more than one classification label is required to improve medical decision-making. In this paper, we consider a multi-perspective classification problem for medical diagnostics, where cases are described by labels from separate sets. We attempt to improve the identification of comorbidities using multi-label classification techniques. Several investigated methods, which provide label dependencies, are analysed and evaluated. The methods' performances are verified by experiments conducted on four sets of medical data from subject patients. The results were evaluated using several metrics and were statistically verified. We compare the effects of the techniques that do and do not consider label correlations. We demonstrate that multi-label classification methods from the first group outperform the techniques from the second one. •Multi-label classification for improving comorbidity identification is discussed.•Multi-label classification methods for medical multi-perspective tasks are examined.•Exploiting label dependencies improves the accuracy of multi-label classification.•Investigation demonstrates the good performance of the proposed Labels Chain technique.