Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 May 3;19(5):e0301472.
doi: 10.1371/journal.pone.0301472. eCollection 2024.

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

Hassan Farhat  1   2   3 , Ahmed Makhlouf  1   4 , Padarath Gangaram  5 , Kawther El Aifa  1 , Ian Howland  1 , Fatma Babay Ep Rekik  1 , Cyrine Abid  6 , Mohamed Chaker Khenissi  1 , Nicholas Castle  1 , Loua Al-Shaikh  1 , Moncef Khadhraoui  7 , Imed Gargouri  8 , James Laughton  1 , Guillaume Alinier  1   9   10   11
Affiliations

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

Hassan Farhat et al. PLoS One. .

Abstract

Background: 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.

Methods: 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.

Results: 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).

Conclusion: 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.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. Geographical distribution of transported and not transported patients across Qatar.
(This map was created by the first author using the “Leaflet” package in R. The data is available under the Open Database License).
Fig 2
Fig 2. Confusion matrix plots of the four algorithms.
Fig 3
Fig 3. Feature importance of the four machine learning models.
Fig 4
Fig 4. Statistical process control of the prediction data of the hourly patients not transported per model.
Fig 5
Fig 5. Hourly and weekly number of patients predicted to be transported to the hospital for all models.
See this image and copyright information in PMC

References

    1. Alhabdan N., Alhusain F., Alharbi A., Alsadhan M., Hakami M., and Masuadi E. , ‘Exploring emergency department visits: factors influencing individuals’ decisions, knowledge of triage systems and waiting times, and experiences during visits to a tertiary hospital in Saudi Arabia’, Int. J. Emerg. Med., vol. 12, no. 1, p. 35, Nov. 2019, doi: 10.1186/s12245-019-0254-7 - DOI - PMC - PubMed
    1. M. A. Ahmad, C. Eckert, and A. Teredesai, ‘Interpretable Machine Learning in Healthcare’, in Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, in BCB ‘18. New York, NY, USA: Association for Computing Machinery, Aug. 2018, pp. 559–560. doi: 10.1145/3233547.3233667 - DOI
    1. Olave-Rojas D. and Nickel S., ‘Modeling a pre-hospital emergency medical service using hybrid simulation and a machine learning approach’, Simul. Model. Pract. Theory, vol. 109, p. 102302, May 2021, doi: 10.1016/j.simpat.2021.102302 - DOI
    1. Al Muftah H., ‘Demographic Policies and Human Capital Challenges’, in Policy-Making in a Transformative State: The Case of Qatar, Tok M. E., Alkhater L. R. M., and Pal L. A., Eds., London: Palgrave Macmillan UK, 2016, pp. 271–294. doi: 10.1057/978-1-137-46639-6_10 - DOI
    1. Teisberg E., Wallace S., and O’Hara S., ‘Defining and Implementing Value-Based Health Care: A Strategic Framework’, Acad. Med., vol. 95, no. 5, pp. 682–685, May 2020, doi: 10.1097/ACM.0000000000003122 - DOI - PMC - PubMed

Publication types