Mining patterns of comorbidity evolution in patients with multiple chronic conditions using unsupervised multi-level temporal Bayesian network

• Published in: PloS one Vol. 13; no. 7; p. e0199768
• Main Authors: Faruqui, Syed Hasib Akhter, Alaeddini, Adel, Jaramillo, Carlos A., Potter, Jennifer S., Pugh, Mary Jo
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 12.07.2018; Public Library of Science (PLoS)
• Subjects: Adolescent; Alcohol; Algorithms; Ambulatory care; Analysis; Back pain; Back Pain - epidemiology; Bayes Theorem; Bayesian analysis; Biology and Life Sciences; Brain; Brain injuries; Brain Injuries, Traumatic - epidemiology; Care and treatment; Chronic conditions; Chronic illnesses; Clustering; Colorectal cancer; Comorbidity; Computer and Information Sciences; Data mining; Depression (Mood disorder); Depression - epidemiology; Drug abuse; Emergence; Family medical history; Federal agencies; Female; Greedy algorithms; Head injuries; Humans; Learning; Linear programming; Liver cancer; Lung cancer; Machine learning; Male; Markov processes; Mechanical engineering; Medical prognosis; Medicine and Health Sciences; Mental depression; Mental disorders; Mental health; Metastasis; Middle Aged; Pain; Patients; Performance prediction; Physical Sciences; Post traumatic stress disorder; Posttraumatic stress disorder; Regression; Research and Analysis Methods; Risk analysis; Risk factors; Search algorithms; Social Sciences; Stress Disorders, Post-Traumatic - epidemiology; Substance abuse; Substance use disorder; Traumatic brain injury; Unsupervised Machine Learning; Veterans - statistics & numerical data; United States; United States > US
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0199768

Over the past few decades, the rise of multiple chronic conditions has become a major concern for clinicians. However, it is still not known precisely how multiple chronic conditions emerge among patients. We propose an unsupervised multi-level temporal Bayesian network to provide a compact representation of the relationship among emergence of multiple chronic conditions and patient level risk factors over time. To improve the efficiency of the learning process, we use an extension of maximum weight spanning tree algorithm and greedy search algorithm to study the structure of the proposed network in three stages, starting with learning the inter-relationship of comorbidities within each year, followed by learning the intra-relationship of comorbidity emergence between consecutive years, and finally learning the hierarchical relationship of comorbidities and patient level risk factors. We also use a longest path algorithm to identify the most likely sequence of comorbidities emerging from and/or leading to specific chronic conditions. Using a de-identified dataset of more than 250,000 patients receiving care from the U.S. Department of Veterans Affairs for a period of five years, we compare the performance of the proposed unsupervised Bayesian network in comparison with those of Bayesian networks developed based on supervised and semi-supervised learning approaches, as well as multivariate probit regression, multinomial logistic regression, and latent regression Markov mixture clustering focusing on traumatic brain injury (TBI), post-traumatic stress disorder (PTSD), depression (Depr), substance abuse (SuAb), and back pain (BaPa). Our findings show that the unsupervised approach has noticeably accurate predictive performance that is comparable to the best performing semi-supervised and the second-best performing supervised approaches. These findings also revealed that the unsupervised approach has improved performance over multivariate probit regression, multinomial logistic regression, and latent regression Markov mixture clustering.