Deep Learning for Improved Risk Prediction in Surgical Outcomes
| العنوان: | Deep Learning for Improved Risk Prediction in Surgical Outcomes |
|---|---|
| المؤلفون: | Hannah Lonsdale, Jeffrey P. Jacobs, Monesha Gupta, Ali Jalali, Sharon R. Ghazarian, Nhue Do, Mohamed Rehman, Luis M. Ahumada, Shelby Kutty, Jacquelin Peck |
| المصدر: | Scientific Reports Scientific Reports, Vol 10, Iss 1, Pp 1-13 (2020) |
| سنة النشر: | 2019 |
| مصطلحات موضوعية: | Risk, medicine.medical_specialty, Science, Heart Ventricles, Information technology, 030204 cardiovascular system & hematology, Norwood Procedures, Article, 03 medical and health sciences, 0302 clinical medicine, Text mining, Deep Learning, Hypoplastic Left Heart Syndrome, Medicine, Humans, 030212 general & internal medicine, Hospital Mortality, Decision Making, Organizational, Multidisciplinary, Models, Statistical, Receiver operating characteristic, Artificial neural network, Markov chain, business.industry, Mortality rate, Deep learning, Infant, Newborn, Infant, Length of Stay, Translational research, Missing data, Markov Chains, Transplantation, Risk factors, Emergency medicine, Artificial intelligence, Neural Networks, Computer, business, Monte Carlo Method |
| الوصف: | 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. |
| تدمد: | 2045-2322 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fe26567c297638ea3073d606d58acd96 https://pubmed.ncbi.nlm.nih.gov/32518246 |
| Rights: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....fe26567c297638ea3073d606d58acd96 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 20452322 |
|---|