Tags

Type your tag names separated by a space and hit enter

Predicting deterioration of ventricular function in patients with repaired tetralogy of Fallot using machine learning.
Eur Heart J Cardiovasc Imaging. 2018 07 01; 19(7):730-738.EH

Abstract

Aims

Previous studies using regression analyses have failed to identify which patients with repaired tetralogy of Fallot (rTOF) are at risk for deterioration in ventricular size and function despite using common clinical and cardiac function parameters as well as cardiac mechanics (strain and dyssynchrony). This study used a machine learning pipeline to comprehensively investigate the predictive value of the baseline variables derived from cardiac magnetic resonance (CMR) imaging and provide models for identifying patients at risk for deterioration.

Methods and results

Longitudinal deterioration for 153 patients with rTOF was categorized as 'none', 'minor', or 'major' based on changes in ventricular size and ejection fraction between two CMR scans at least 6 months apart (median 2.7 years). Baseline variables were measured at the time of the first CMR. An exhaustive variable search with a support vector machine classifier and five-fold cross-validation was used to predict deterioration and identify the most useful variables. For predicting any deterioration (minor or major) vs. no deterioration, the mean area under the curve (AUC) was 0.82 ± 0.06. For predicting major deterioration vs. minor or no deterioration, the AUC was 0.77 ± 0.07. Baseline left ventricular (LV) ejection fraction, LV circumferential strain, and pulmonary regurgitation were most useful for achieving accurate predictions.

Conclusion

For the prediction of deterioration in patients with rTOF, a machine learning pipeline uncovered the utility of baseline variables that was previously lost to regression analyses. The predictive models may be useful for planning early interventions in patients with high risk.

Authors+Show Affiliations

Department of Imaging Science and Innovation, Center for Health Research, Geisinger Clinic, 100 North Academy Avenue, Danville, 17822-4400 PA, USA.Department of Biomedical Engineering, University of Kentucky, 522 Robotics and Manufacturing Building, Lexington, 40506-0108 KY, USA.Department of Imaging Science and Innovation, Center for Health Research, Geisinger Clinic, 100 North Academy Avenue, Danville, 17822-4400 PA, USA.Department of Imaging Science and Innovation, Center for Health Research, Geisinger Clinic, 100 North Academy Avenue, Danville, 17822-4400 PA, USA.Department of Cardiology, Boston Children's Hospital, 300 Longwood Ave, Boston, 02115 MA, USA.Department of Cardiology, Boston Children's Hospital, 300 Longwood Ave, Boston, 02115 MA, USA.Department of Imaging Science and Innovation, Center for Health Research, Geisinger Clinic, 100 North Academy Avenue, Danville, 17822-4400 PA, USA.Department of Imaging Science and Innovation, Center for Health Research, Geisinger Clinic, 100 North Academy Avenue, Danville, 17822-4400 PA, USA. Department of Radiology, Geisinger, 100 North Academy Ave, Danville, 17822 PA, USA.

Pub Type(s)

Comparative Study
Journal Article

Language

eng

PubMed ID

29538684

Citation

Samad, Manar D., et al. "Predicting Deterioration of Ventricular Function in Patients With Repaired Tetralogy of Fallot Using Machine Learning." European Heart Journal Cardiovascular Imaging, vol. 19, no. 7, 2018, pp. 730-738.
Samad MD, Wehner GJ, Arbabshirani MR, et al. Predicting deterioration of ventricular function in patients with repaired tetralogy of Fallot using machine learning. Eur Heart J Cardiovasc Imaging. 2018;19(7):730-738.
Samad, M. D., Wehner, G. J., Arbabshirani, M. R., Jing, L., Powell, A. J., Geva, T., Haggerty, C. M., & Fornwalt, B. K. (2018). Predicting deterioration of ventricular function in patients with repaired tetralogy of Fallot using machine learning. European Heart Journal Cardiovascular Imaging, 19(7), 730-738. https://doi.org/10.1093/ehjci/jey003
Samad MD, et al. Predicting Deterioration of Ventricular Function in Patients With Repaired Tetralogy of Fallot Using Machine Learning. Eur Heart J Cardiovasc Imaging. 2018 07 1;19(7):730-738. PubMed PMID: 29538684.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Predicting deterioration of ventricular function in patients with repaired tetralogy of Fallot using machine learning. AU - Samad,Manar D, AU - Wehner,Gregory J, AU - Arbabshirani,Mohammad R, AU - Jing,Linyuan, AU - Powell,Andrew J, AU - Geva,Tal, AU - Haggerty,Christopher M, AU - Fornwalt,Brandon K, PY - 2017/10/25/received PY - 2018/01/05/accepted PY - 2018/3/15/pubmed PY - 2019/3/9/medline PY - 2018/3/15/entrez SP - 730 EP - 738 JF - European heart journal cardiovascular Imaging JO - Eur Heart J Cardiovasc Imaging VL - 19 IS - 7 N2 - Aims: Previous studies using regression analyses have failed to identify which patients with repaired tetralogy of Fallot (rTOF) are at risk for deterioration in ventricular size and function despite using common clinical and cardiac function parameters as well as cardiac mechanics (strain and dyssynchrony). This study used a machine learning pipeline to comprehensively investigate the predictive value of the baseline variables derived from cardiac magnetic resonance (CMR) imaging and provide models for identifying patients at risk for deterioration. Methods and results: Longitudinal deterioration for 153 patients with rTOF was categorized as 'none', 'minor', or 'major' based on changes in ventricular size and ejection fraction between two CMR scans at least 6 months apart (median 2.7 years). Baseline variables were measured at the time of the first CMR. An exhaustive variable search with a support vector machine classifier and five-fold cross-validation was used to predict deterioration and identify the most useful variables. For predicting any deterioration (minor or major) vs. no deterioration, the mean area under the curve (AUC) was 0.82 ± 0.06. For predicting major deterioration vs. minor or no deterioration, the AUC was 0.77 ± 0.07. Baseline left ventricular (LV) ejection fraction, LV circumferential strain, and pulmonary regurgitation were most useful for achieving accurate predictions. Conclusion: For the prediction of deterioration in patients with rTOF, a machine learning pipeline uncovered the utility of baseline variables that was previously lost to regression analyses. The predictive models may be useful for planning early interventions in patients with high risk. SN - 2047-2412 UR - https://www.unboundmedicine.com/medline/citation/29538684/Predicting_deterioration_of_ventricular_function_in_patients_with_repaired_tetralogy_of_Fallot_using_machine_learning_ L2 - https://academic.oup.com/ehjcimaging/article-lookup/doi/10.1093/ehjci/jey003 DB - PRIME DP - Unbound Medicine ER -