Deep Learning for Improved Risk Prediction in Surgical Outcomes

• Published in: Scientific reports Vol. 10; no. 1; p. 9289
• Main Authors: Jalali, Ali, Lonsdale, Hannah, Do, Nhue, Peck, Jacquelin, Gupta, Monesha, Kutty, Shelby, Ghazarian, Sharon R., Jacobs, Jeffrey P., Rehman, Mohamed, Ahumada, Luis M.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 09.06.2020; Nature Publishing Group; Nature Portfolio
• Subjects: 639/705/258; 692/308/575; 692/499; Decision making; Decision Making, Organizational; Deep Learning; Heart transplantation; Heart transplants; Heart Ventricles - pathology; Heart Ventricles - surgery; Hospital Mortality; Humanities and Social Sciences; Humans; Hypoplastic Left Heart Syndrome - surgery; Infant; Infant, Newborn; Learning algorithms; Length of Stay; Machine learning; Markov Chains; Models, Statistical; Monte Carlo Method; Monte Carlo simulation; Mortality; Mortality risk; multidisciplinary; Neonates; Neural networks; Neural Networks, Computer; Norwood Procedures - methods; Norwood Procedures - mortality; Patients; Prediction models; Risk; Risk factors; Science; Science (multidisciplinary); Ventricle
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-020-62971-3

The Norwood surgical procedure restores functional systemic circulation in neonatal patients with single ventricle congenital heart defects, but this complex procedure carries a high mortality rate. In this study we address the need to provide an accurate patient specific risk prediction for one-year postoperative mortality or cardiac transplantation and prolonged length of hospital stay with the purpose of assisting clinicians and patients’ families in the preoperative decision making process. Currently available risk prediction models either do not provide patient specific risk factors or only predict in-hospital mortality rates. We apply machine learning models to predict and calculate individual patient risk for mortality and prolonged length of stay using the Pediatric Heart Network Single Ventricle Reconstruction trial dataset. We applied a Markov Chain Monte-Carlo simulation method to impute missing data and then fed the selected variables to multiple machine learning models. The individual risk of mortality or cardiac transplantation calculation produced by our deep neural network model demonstrated 89 ± 4% accuracy and 0.95 ± 0.02 area under the receiver operating characteristic curve (AUROC). The C-statistics results for prediction of prolonged length of stay were 85 ± 3% accuracy and AUROC 0.94 ± 0.04. These predictive models and calculator may help to inform clinical and organizational decision making.