Predictive modelling of transport decisions and resources optimisation in pre-hospital setting using machine learning techniques

• Published in: PloS one Vol. 19; no. 5; p. e0301472
• Main Authors: Farhat, Hassan, Makhlouf, Ahmed, Gangaram, Padarath, El Aifa, Kawther, Howland, Ian, Babay Ep Rekik, Fatma, Abid, Cyrine, Khenissi, Mohamed Chaker, Castle, Nicholas, Al-Shaikh, Loua, Khadhraoui, Moncef, Gargouri, Imed, Laughton, James, Alinier, Guillaume
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 03.05.2024; Public Library of Science (PLoS)
• Subjects: Accuracy; Adaptive algorithms; Adolescent; Adult; Aged; Algorithms; Ambulance service; Analysis; Artificial intelligence; Book publishing; Call centers; Care and treatment; Chronic obstructive pulmonary disease; Cost control; Datasets; Decision trees; Decision-making; Demographic variables; Emergency medical care; Emergency Medical Services; Feature selection; Female; Forecasts and trends; Health aspects; Health care; Health care industry; Health care rationing; Health facilities; Hospitals; Humans; Learning algorithms; Machine Learning; Male; Management; Medical care; Medical research; Medicine, Experimental; Methods; Middle Aged; Missing data; Optimization; Patient satisfaction; Patients; Prediction models; Predictive analytics; Programming languages; Public health; Quality control; Quality management; Resource allocation; Statistical analysis; Support Vector Machine; Support vector machines; Transportation of Patients - methods; Variables; Young Adult; Qatar; United States
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0301472

The global evolution of pre-hospital care systems faces dynamic challenges, particularly in multinational settings. Machine learning (ML) techniques enable the exploration of deeply embedded data patterns for improved patient care and resource optimisation. This study's objective was to accurately predict cases that necessitated transportation versus those that did not, using ML techniques, thereby facilitating efficient resource allocation. ML algorithms were utilised to predict patient transport decisions in a Middle Eastern national pre-hospital emergency medical care provider. A comprehensive dataset comprising 93,712 emergency calls from the 999-call centre was analysed using R programming language. Demographic and clinical variables were incorporated to enhance predictive accuracy. Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost) algorithms were trained and validated. All the trained algorithm models, particularly XGBoost (Accuracy = 83.1%), correctly predicted patients' transportation decisions. Further, they indicated statistically significant patterns that could be leveraged for targeted resource deployment. Moreover, the specificity rates were high; 97.96% in RF and 95.39% in XGBoost, minimising the incidence of incorrectly identified "Transported" cases (False Positive). The study identified the transformative potential of ML algorithms in enhancing the quality of pre-hospital care in Qatar. The high predictive accuracy of the employed models suggested actionable avenues for day and time-specific resource planning and patient triaging, thereby having potential to contribute to pre-hospital quality, safety, and value improvement. These findings pave the way for more nuanced, data-driven quality improvement interventions with significant implications for future operational strategies.