IS in Healthcare
Loading...
Paper Type
Complete
Paper Number
2493
Description
Cardiovascular Diseases (CVDs) are the number one cause of deaths worldwide and management of these highly chronic diseases is a major concern to healthcare providers. Progression of CVDs often involves several comorbidities, multi-morbidities, and multiple episodic occurrences, involving recur-ring hospitalization over a period of time. Using longitudinal data of 4839 CVD episodes of 1274 real patients and continuous-time Markov model as the kernel theory, this research finds the CVD progression paths and transition probabilities. The resultant probability data and the transition paths open the door for building simulation models and tools which can help the hospital administrators to improve resource and capacity planning. Practitioners can compare a patient’s disease progression trend against the pattern revealed by the model. Results are actionable and can influence treatment and intervention strategies in overall CVD progression management by clinicians and providers. The framework developed is repeatable, reusable, and extensible to other diseases and populations.
Recommended Citation
Brahma, Arin; Chatterjee, Samir; Fitzpatrick, Ben G.; and Seal, Kala Chand, "Understanding Cardiovascular Disease Progression Behavior from Patient Cohort Data using Markov Chain Model" (2020). ICIS 2020 Proceedings. 19.
https://aisel.aisnet.org/icis2020/is_health/is_health/19
Understanding Cardiovascular Disease Progression Behavior from Patient Cohort Data using Markov Chain Model
Cardiovascular Diseases (CVDs) are the number one cause of deaths worldwide and management of these highly chronic diseases is a major concern to healthcare providers. Progression of CVDs often involves several comorbidities, multi-morbidities, and multiple episodic occurrences, involving recur-ring hospitalization over a period of time. Using longitudinal data of 4839 CVD episodes of 1274 real patients and continuous-time Markov model as the kernel theory, this research finds the CVD progression paths and transition probabilities. The resultant probability data and the transition paths open the door for building simulation models and tools which can help the hospital administrators to improve resource and capacity planning. Practitioners can compare a patient’s disease progression trend against the pattern revealed by the model. Results are actionable and can influence treatment and intervention strategies in overall CVD progression management by clinicians and providers. The framework developed is repeatable, reusable, and extensible to other diseases and populations.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
5-Health