Machine Learning Approaches to Determine Feature Importance for Predicting Infant Autopsy Outcome
| Autor: | J. Ciaran Hutchinson, William Bryant, Neil J. Sebire, John Booth, Nigel Martin, Ben Margetts, Richard Issitt |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Decision tree
Autopsy Machine learning computer.software_genre Outcome (game theory) Unexpected death Pathology and Forensic Medicine Machine Learning 03 medical and health sciences 0302 clinical medicine Postneonatal death Clinical Decision Rules 030225 pediatrics Health care Humans Medicine Stage (cooking) Cause of death Models Statistical 030219 obstetrics & reproductive medicine business.industry Decision Trees Infant Newborn Infant General Medicine Infant mortality Feature (computer vision) Pediatrics Perinatology and Child Health Feasibility Studies Gradient boosting Artificial intelligence Presentation (obstetrics) business computer Decision tree model Sudden Infant Death |
| DOI: | 10.1101/2020.05.21.20105221 |
| Popis: | Introduction: Sudden unexpected death in infancy (SUDI) represents the commonest presentation of postneonatal death, yet despite full postmortem examination (autopsy), the cause of death is only determined in around 45% of cases, the majority remaining unexplained. In order to aid counselling and understand how to improve the investigation, we explored whether machine learning could be used to derive data driven insights for prediction of infant autopsy outcome. Methods: A paediatric autopsy database containing >7,000 cases in total with >300 variables per case, was analysed with cases categorised both by stage of examination (external, internal and internal with histology), and autopsy outcome classified as explained-(medical cause of death identified) or unexplained. For the purposes of this study only cases from infant and child deaths aged ≤ 2 years were included (N=3100). Following this, decision tree, random forest, and gradient boosting models were iteratively trained and evaluated for each stage of the post-mortem examination and compared using predictive accuracy metrics. Results: Data from 3,100 infant and young child autopsies were included. The naive decision tree model using initial external examination data had a predictive performance of 68% for determining whether a medical cause of death could be identified. Model performance increased when internal examination data was included and a core set of data items were identified using model feature importance as key variables for determining autopsy outcome. The most effective model was the XG Boost, with overall predictive performance of 80%, demonstrating age at death, and cardiovascular or respiratory histological findings as the most important variables associated with determining cause of death. Conclusion: This study demonstrates the feasibility of using machine learning models to objectively determine component importance of complex medical procedures, in this case infant autopsy, to inform clinical practice. It further highlights the value of collecting routine clinical procedural data according to defined standards. This approach can be applied to a wide range of clinical and operational healthcare scenarios providing objective, evidence-based information for uses such counselling, decision making and policy development. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|