Kathryn Rendell1, Irena Koprinska2, Andre Kyme1, Anja A Ebker-White3,4, Michael M Dinh3,5. 1. School of Aerospace, Mechanical and Mechatronic Engineering, Faculty of Engineering and Information Technologies, The University of Sydney, Sydney, New South Wales, Australia. 2. School of Information Technologies, Faculty of Engineering and Information Technologies, The University of Sydney, Sydney, New South Wales, Australia. 3. Emergency Department, Royal Prince Alfred Hospital, Sydney, New South Wales, Australia. 4. School of Nursing, Faculty of Medicine and Health, The University of Sydney, Sydney, New South Wales, Australia. 5. Discipline of Emergency Medicine, School of Medicine, Faculty of Medicine and Health, The University of Sydney, Sydney, New South Wales, Australia.
Abstract
OBJECTIVE: To further develop and refine an Emergency Department (ED) in-patient admission prediction model using machine learning techniques. METHODS: This was a retrospective analysis of state-wide ED data from New South Wales, Australia. Six classification algorithms (Bayesian networks, decision trees, logistic regression, naïve Bayes, neural networks and nearest neighbour) and five feature selection techniques (none, manual, correlation-based, information gain and wrapper) were examined. Presenting problem was categorised using broad (n = 20) and specific (n = 100) representations. Models were evaluated based on Area Under the Curve (AUC) and accuracy. The results were compared with the Sydney Triage to Admission Risk Tool (START), which uses logistic regression and six manually selected features. RESULTS: Sixty admission prediction models were trained and validated using data from 1 721 294 patients. Under the broad representation of presenting problem, the nearest neighbour algorithm with manual feature selection had the best AUC of 0.8206 (95% CI ±0.0006), while the decision tree with no feature selection had the best accuracy of 74.83% (95% CI ±0.065). Under the specific representation, almost all models improved; the nearest neighbour with information gain feature selection had the best AUC of 0.8267 (95% CI ±0.0006), while the decision tree with wrapper or no feature selection had the best accuracy of 75.24% (95% CI ±0.064). Eleven of the machine learning models had slightly better AUC than the START model. CONCLUSION: Machine learning methods demonstrate similar performance to logistic regression for ED disposition prediction models using basic triage information. This should be investigated further, especially for larger data sets with more complex clinical information.
OBJECTIVE: To further develop and refine an Emergency Department (ED) in-patient admission prediction model using machine learning techniques. METHODS: This was a retrospective analysis of state-wide ED data from New South Wales, Australia. Six classification algorithms (Bayesian networks, decision trees, logistic regression, naïve Bayes, neural networks and nearest neighbour) and five feature selection techniques (none, manual, correlation-based, information gain and wrapper) were examined. Presenting problem was categorised using broad (n = 20) and specific (n = 100) representations. Models were evaluated based on Area Under the Curve (AUC) and accuracy. The results were compared with the Sydney Triage to Admission Risk Tool (START), which uses logistic regression and six manually selected features. RESULTS: Sixty admission prediction models were trained and validated using data from 1 721 294 patients. Under the broad representation of presenting problem, the nearest neighbour algorithm with manual feature selection had the best AUC of 0.8206 (95% CI ±0.0006), while the decision tree with no feature selection had the best accuracy of 74.83% (95% CI ±0.065). Under the specific representation, almost all models improved; the nearest neighbour with information gain feature selection had the best AUC of 0.8267 (95% CI ±0.0006), while the decision tree with wrapper or no feature selection had the best accuracy of 75.24% (95% CI ±0.064). Eleven of the machine learning models had slightly better AUC than the START model. CONCLUSION: Machine learning methods demonstrate similar performance to logistic regression for ED disposition prediction models using basic triage information. This should be investigated further, especially for larger data sets with more complex clinical information.
Authors: Daniel Trotzky; Noaa Shopen; Jonathan Mosery; Neta Negri Galam; Yizhaq Mimran; Daniel Edward Fordham; Shiran Avisar; Aya Cohen; Malka Katz Shalhav; Gal Pachys Journal: BMJ Open Date: 2021-12-09 Impact factor: 2.692
Authors: Adrian Xi Lin; Andrew Fu Wah Ho; Kang Hao Cheong; Zengxiang Li; Wentong Cai; Marcel Lucas Chee; Yih Yng Ng; Xiaokui Xiao; Marcus Eng Hock Ong Journal: Int J Environ Res Public Health Date: 2020-06-11 Impact factor: 3.390