Donghee Han1, Kranthi K Kolli2, Heidi Gransar3, Ji Hyun Lee1, Su-Yeon Choi4, Eun Ju Chun5, Hae-Won Han6, Sung Hak Park7, Jidong Sung8, Hae Ok Jung9, James K Min2, Hyuk-Jae Chang10. 1. Division of Cardiology, Severance Cardiovascular Hospital, Yonsei University Health System, Seoul, Republic of Korea. 2. Dalio Institute of Cardiovascular Imaging, New York-Presbyterian Hospital and the Weill Cornell Medical College, New York, NY, USA. 3. Department of Imaging, Cedars Sinai Medical Center, Los Angeles, CA, USA. 4. Division of Cardiology, Seoul National University Healthcare System Gangnam Center, Seoul National University College of Medicine, Seoul, Republic of Korea. 5. Department of Radiology, Seoul National University Bundang Hospital, Seoul, Republic of Korea. 6. Department of Internal Medicine, Gangnam Heartscan Clinic, Seoul, Republic of Korea. 7. Department of Radiology, Gangnam Heartscan Clinic, Seoul, Republic of Korea. 8. Division of Cardiology, Department of Medicine, Sungkyunkwan University School of Medicine, Heart Stroke & Vascular Institute, Samsung Medical Center, Seoul, Republic of Korea. 9. Division of Cardiology, Cardiovascular Center, College of Medicine, Seoul St. Mary's Hospital, The Catholic University of Korea, Seoul, Republic of Korea. 10. Division of Cardiology, Severance Cardiovascular Hospital, Yonsei University Health System, Seoul, Republic of Korea. Electronic address: hjchang@yuhs.ac.
Abstract
BACKGROUND: Machine learning (ML) is a computer algorithm used to identify patterns for prediction in various tasks, and ML methods have been beneficial for developing prediction models when applied to heterogeneous and large datasets. We aim to examine the prognostic ability of a ML-based prediction algorithm utilizing routine health checkup data to predict all-cause mortality (ACM) compared to established risk prediction approaches. METHODS: A total 86155 patients with seventy available parameters (35 clinical, 32 laboratory, and 3 coronary artery calcium score [CACS] parameters) were analyzed. ML involved feature selection, splitting data randomly into a training (70%) and test set (30%), and model building with a boosted ensemble algorithm. The developed ML model was validated in a separate cohort of 4915 patients. The performance of ML for predicting ACM was compared with the following models: (i) the Framingham risk score (FRS) + CACS, (ii) atherosclerotic cardiovascular disease (ASCVD) + CACS, with (iii) logistic regression (LR) model. RESULTS: In the derivation dataset, 690 patients died during the median 4.6-year follow-up (interquartile range, 3.0-6.6 years). The AUC value in the ML model was significantly higher than the other models in test set (ML: 0.82, FRS + CACS: 0.70, ASCVD + CACS: 0.74; LR model: 0.79, p < 0.05 for all), but not statistically significantly higher in validation set (ML: 0.78, FRS + CACS: 0.62, ASCVD + CACS: 0.72; LR model: 0.74, p: 0.572 and 0.625 for ASCVD + CACS and LR model, respectively). The ML model improved reclassification over the other models in low to intermediate risk patients (p < 0.001 for all). CONCLUSION: The prediction algorithm derived by ML methods showed a robust ability to predict ACM and improved reclassification over established conventional risk prediction approaches in asymptomatic population undergoing a health checkup.
BACKGROUND: Machine learning (ML) is a computer algorithm used to identify patterns for prediction in various tasks, and ML methods have been beneficial for developing prediction models when applied to heterogeneous and large datasets. We aim to examine the prognostic ability of a ML-based prediction algorithm utilizing routine health checkup data to predict all-cause mortality (ACM) compared to established risk prediction approaches. METHODS: A total 86155 patients with seventy available parameters (35 clinical, 32 laboratory, and 3 coronary artery calcium score [CACS] parameters) were analyzed. ML involved feature selection, splitting data randomly into a training (70%) and test set (30%), and model building with a boosted ensemble algorithm. The developed ML model was validated in a separate cohort of 4915 patients. The performance of ML for predicting ACM was compared with the following models: (i) the Framingham risk score (FRS) + CACS, (ii) atherosclerotic cardiovascular disease (ASCVD) + CACS, with (iii) logistic regression (LR) model. RESULTS: In the derivation dataset, 690 patients died during the median 4.6-year follow-up (interquartile range, 3.0-6.6 years). The AUC value in the ML model was significantly higher than the other models in test set (ML: 0.82, FRS + CACS: 0.70, ASCVD + CACS: 0.74; LR model: 0.79, p < 0.05 for all), but not statistically significantly higher in validation set (ML: 0.78, FRS + CACS: 0.62, ASCVD + CACS: 0.72; LR model: 0.74, p: 0.572 and 0.625 for ASCVD + CACS and LR model, respectively). The ML model improved reclassification over the other models in low to intermediate risk patients (p < 0.001 for all). CONCLUSION: The prediction algorithm derived by ML methods showed a robust ability to predict ACM and improved reclassification over established conventional risk prediction approaches in asymptomatic population undergoing a health checkup.
Authors: Ankush Jamthikar; Deep Gupta; Luca Saba; Narendra N Khanna; Tadashi Araki; Klaudija Viskovic; Sophie Mavrogeni; John R Laird; Gyan Pareek; Martin Miner; Petros P Sfikakis; Athanasios Protogerou; Vijay Viswanathan; Aditya Sharma; Andrew Nicolaides; George D Kitas; Jasjit S Suri Journal: Cardiovasc Diagn Ther Date: 2020-08
Authors: C R Aditya; Naveen Chakravarthy Sattaru; Kumaraguruparan Gopal; R Rahul; G Chandra Shekara; Omaima Nasif; Sulaiman Ali Alharbi; S S Raghavan; S Arockia Jayadhas Journal: Biomed Res Int Date: 2022-06-23 Impact factor: 3.246
Authors: Eduardo A Trujillo Rivera; Anita K Patel; James M Chamberlain; T Elizabeth Workman; Julia A Heneghan; Douglas Redd; Hiroki Morizono; Dongkyu Kim; James E Bost; Murray M Pollack Journal: Pediatr Crit Care Med Date: 2021-01-01 Impact factor: 3.971
Authors: Chris Boyd; Greg Brown; Timothy Kleinig; Joseph Dawson; Mark D McDonnell; Mark Jenkinson; Eva Bezak Journal: Diagnostics (Basel) Date: 2021-03-19