Machine Learning Model for Predicting Mortality Risk in Complex Chronic Patients: Retrospective Analysis from the ProPCC Program in Catalonia (Preprint)
Authors:
- Guillem Hernández GuillametGGGuillem Hernández Guillamet
- Ariadna Ning Morancho PallarueloAPAriadna Ning Morancho Pallaruelo
- Laura Miró MezquitaLMLaura Miró Mezquita
- Ramón Miralles BassedaRBRamón Miralles Basseda
- Miquel Àngel Mas BergasMBMiquel Àngel Mas Bergas
- Maria José Ulldemolins PapaseitMPMaria José Ulldemolins Papaseit
- Oriol Estrada CuxartOCOriol Estrada Cuxart
- Francesc López SeguíFSFrancesc López Seguí
Preprint
- 3 July 2023
- preprint
- Published by JMIR Publications Inc. in JMIR Preprints
Abstract
BACKGROUND The healthcare system is undergoing a shift towards a more patient-centred approach for individuals with chronic and complex conditions, which presents a series of challenges, such as predicting hospital needs and optimizing resources. At the same time, the exponential increase in health data availability has made it possible to apply advanced statistics and artificial intelligence techniques to develop decision-support systems and improve resources planning’ efficiency, diagnosis and patient screening. These methods are key to automating the analysis of large volumes of medical data and reducing professional’s workload. OBJECTIVE This article aims to present a machine learning model and a case study in a cohort of highly complex patients to predict death over the following 4 years and early death over the following 6 months since the complexity diagnosing. The method uses easily accessible variables and healthcare resource utilization information. METHODS A classification algorithm is selected among six models implemented and evaluated using a stratified cross-validation strategy with k=10 and a 70/30 train-test split. The evaluation metrics used are accuracy, recall, precision, F1-score and area under the curve (AUC-ROC). RESULTS The model predicts patient death with an 87% accuracy (recall=0.87, precision=0.82, F1=0.84, AUC=0.88) using the best model, the Extreme Gradient-Boosting classifier (XG-Boost). The results are worse when predicting premature deaths (following 6 months) with an 83% accuracy (recall=0.55, precision=0.64, F1=0.57, AUC=0.88) using the Gradient Boosting Classifier (GR-Boost). CONCLUSIONS This study showcases encouraging outcomes in forecasting mortality among patients with intricate and persistent health conditions. The employed variables are conveniently accessible and the incorporation of healthcare resource utilization information of the patient, which has not been employed by current state-of-the-art approaches, display promising predictive power. The proposed prediction model is designed to efficiently identify cases that need customized care and to proactively anticipate the demand for critical resources by healthcare providers.Keywords
This publication has 29 references indexed in Scilit:
- Development and validation of cardiovascular risk scores for haemodialysis patientsInternational Journal of Cardiology, 2016
- Machine Learning and Decision Support in Critical CareProceedings of the IEEE, 2016
- Systematic Review of Programs Treating High-Need and High-Cost People With Multiple Chronic Diseases or Disabilities in the United States, 2008–2014Preventing Chronic Disease, 2015
- Development and validation of a predictive mortality risk score from a European hemodialysis cohortKidney International, 2015
- Prevalence and characteristics of patients with advanced chronic conditions in need of palliative care in the general population: A cross-sectional studyPalliative Medicine, 2014
- Predicting sudden death in patients with mild to moderate chronic heart failureHeart, 2004
- Integrated care: meaning, logic, applications, and implications – a discussion paperInternational Journal of Integrated Care, 2002
- Hypocholesterolemia is a significant predictor of death in a cohort of chronic hemodialysis patientsKidney International, 2002
- Prediction of outcome in critically ill patients using artificial neural network synthesised by genetic algorithmThe Lancet, 1996
- Serum albumin is a strong predictor of death in chronic dialysis patientsKidney International, 1993