Development and Clinical Interpretation of an Explainable AI Model for Predicting Patient Pathways in the Emergency Department: A Retrospective Study
Background: Overcrowded emergency departments (EDs) create significant challenges for patient management and hospital efficiency. In response, Amiens Picardy University Hospital (APUH) developed the “Prediction of the Patient Pathway in the Emergency Department” (3P-U) model to enhance patient flow...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/15/8449 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849239600296361984 |
|---|---|
| author | Émilien Arnaud Pedro Antonio Moreno-Sanchez Mahmoud Elbattah Christine Ammirati Mark van Gils Gilles Dequen Daniel Aiham Ghazali |
| author_facet | Émilien Arnaud Pedro Antonio Moreno-Sanchez Mahmoud Elbattah Christine Ammirati Mark van Gils Gilles Dequen Daniel Aiham Ghazali |
| author_sort | Émilien Arnaud |
| collection | DOAJ |
| description | Background: Overcrowded emergency departments (EDs) create significant challenges for patient management and hospital efficiency. In response, Amiens Picardy University Hospital (APUH) developed the “Prediction of the Patient Pathway in the Emergency Department” (3P-U) model to enhance patient flow management. Objectives: To develop and clinically validate an explainable artificial intelligence (XAI) model for hospital admission predictions, using structured triage data, and demonstrate its real-world applicability in the ED setting. Methods: Our retrospective, single-center study involved 351,019 patients consulting in APUH’s EDs between 2015 and 2018. Various models (including a cross-validation artificial neural network (ANN), a k-nearest neighbors (KNN) model, a logistic regression (LR) model, and a random forest (RF) model) were trained and assessed for performance with regard to the area under the receiver operating characteristic curve (AUROC). The best model was validated internally with a test set, and the F1 score was used to determine the best threshold for recall, precision, and accuracy. XAI techniques, such as Shapley additive explanations (SHAP) and partial dependence plots (PDP) were employed, and the clinical explanations were evaluated by emergency physicians. Results: The ANN gave the best performance during the training stage, with an AUROC of 83.1% (SD: 0.2%) for the test set; it surpassed the RF (AUROC: 71.6%, SD: 0.1%), KNN (AUROC: 67.2%, SD: 0.2%), and LR (AUROC: 71.5%, SD: 0.2%) models. In an internal validation, the ANN’s AUROC was 83.2%. The best F1 score (0.67) determined that 0.35 was the optimal threshold; the corresponding recall, precision, and accuracy were 75.7%, 59.7%, and 75.3%, respectively. The SHAP and PDP XAI techniques (as assessed by emergency physicians) highlighted patient age, heart rate, and presentation with multiple injuries as the features that most specifically influenced the admission from the ED to a hospital ward. These insights are being used in bed allocation and patient prioritization, directly improving ED operations. Conclusions: The 3P-U model demonstrates practical utility by reducing ED crowding and enhancing decision-making processes at APUH. Its transparency and physician validation foster trust, facilitating its adoption in clinical practice and offering a replicable framework for other hospitals to optimize patient flow. |
| format | Article |
| id | doaj-art-a0f53ab0be5e4588bfff9e79c0776996 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-a0f53ab0be5e4588bfff9e79c07769962025-08-20T04:00:54ZengMDPI AGApplied Sciences2076-34172025-07-011515844910.3390/app15158449Development and Clinical Interpretation of an Explainable AI Model for Predicting Patient Pathways in the Emergency Department: A Retrospective StudyÉmilien Arnaud0Pedro Antonio Moreno-Sanchez1Mahmoud Elbattah2Christine Ammirati3Mark van Gils4Gilles Dequen5Daniel Aiham Ghazali6Department of Emergency Medicine, Amiens Picardy University Hospital, 80000 Amiens, FranceFaculty of Medicine and Health Technology, Tampere University, 60100 Seinäjoki, FinlandLaboratoire Modélisation, Information, Systèmes (MIS) UR4290, University of Picardie Jules Verne, 80000 Amiens, FranceDepartment of Emergency Medicine, Amiens Picardy University Hospital, 80000 Amiens, FranceFaculty of Medicine and Health Technology, Tampere University, 60100 Seinäjoki, FinlandLaboratoire Modélisation, Information, Systèmes (MIS) UR4290, University of Picardie Jules Verne, 80000 Amiens, FranceDepartment of Emergency Medicine, Amiens Picardy University Hospital, 80000 Amiens, FranceBackground: Overcrowded emergency departments (EDs) create significant challenges for patient management and hospital efficiency. In response, Amiens Picardy University Hospital (APUH) developed the “Prediction of the Patient Pathway in the Emergency Department” (3P-U) model to enhance patient flow management. Objectives: To develop and clinically validate an explainable artificial intelligence (XAI) model for hospital admission predictions, using structured triage data, and demonstrate its real-world applicability in the ED setting. Methods: Our retrospective, single-center study involved 351,019 patients consulting in APUH’s EDs between 2015 and 2018. Various models (including a cross-validation artificial neural network (ANN), a k-nearest neighbors (KNN) model, a logistic regression (LR) model, and a random forest (RF) model) were trained and assessed for performance with regard to the area under the receiver operating characteristic curve (AUROC). The best model was validated internally with a test set, and the F1 score was used to determine the best threshold for recall, precision, and accuracy. XAI techniques, such as Shapley additive explanations (SHAP) and partial dependence plots (PDP) were employed, and the clinical explanations were evaluated by emergency physicians. Results: The ANN gave the best performance during the training stage, with an AUROC of 83.1% (SD: 0.2%) for the test set; it surpassed the RF (AUROC: 71.6%, SD: 0.1%), KNN (AUROC: 67.2%, SD: 0.2%), and LR (AUROC: 71.5%, SD: 0.2%) models. In an internal validation, the ANN’s AUROC was 83.2%. The best F1 score (0.67) determined that 0.35 was the optimal threshold; the corresponding recall, precision, and accuracy were 75.7%, 59.7%, and 75.3%, respectively. The SHAP and PDP XAI techniques (as assessed by emergency physicians) highlighted patient age, heart rate, and presentation with multiple injuries as the features that most specifically influenced the admission from the ED to a hospital ward. These insights are being used in bed allocation and patient prioritization, directly improving ED operations. Conclusions: The 3P-U model demonstrates practical utility by reducing ED crowding and enhancing decision-making processes at APUH. Its transparency and physician validation foster trust, facilitating its adoption in clinical practice and offering a replicable framework for other hospitals to optimize patient flow.https://www.mdpi.com/2076-3417/15/15/8449artificial intelligenceexplainable artificial intelligenceemergency medicinepatient pathway |
| spellingShingle | Émilien Arnaud Pedro Antonio Moreno-Sanchez Mahmoud Elbattah Christine Ammirati Mark van Gils Gilles Dequen Daniel Aiham Ghazali Development and Clinical Interpretation of an Explainable AI Model for Predicting Patient Pathways in the Emergency Department: A Retrospective Study Applied Sciences artificial intelligence explainable artificial intelligence emergency medicine patient pathway |
| title | Development and Clinical Interpretation of an Explainable AI Model for Predicting Patient Pathways in the Emergency Department: A Retrospective Study |
| title_full | Development and Clinical Interpretation of an Explainable AI Model for Predicting Patient Pathways in the Emergency Department: A Retrospective Study |
| title_fullStr | Development and Clinical Interpretation of an Explainable AI Model for Predicting Patient Pathways in the Emergency Department: A Retrospective Study |
| title_full_unstemmed | Development and Clinical Interpretation of an Explainable AI Model for Predicting Patient Pathways in the Emergency Department: A Retrospective Study |
| title_short | Development and Clinical Interpretation of an Explainable AI Model for Predicting Patient Pathways in the Emergency Department: A Retrospective Study |
| title_sort | development and clinical interpretation of an explainable ai model for predicting patient pathways in the emergency department a retrospective study |
| topic | artificial intelligence explainable artificial intelligence emergency medicine patient pathway |
| url | https://www.mdpi.com/2076-3417/15/15/8449 |
| work_keys_str_mv | AT emilienarnaud developmentandclinicalinterpretationofanexplainableaimodelforpredictingpatientpathwaysintheemergencydepartmentaretrospectivestudy AT pedroantoniomorenosanchez developmentandclinicalinterpretationofanexplainableaimodelforpredictingpatientpathwaysintheemergencydepartmentaretrospectivestudy AT mahmoudelbattah developmentandclinicalinterpretationofanexplainableaimodelforpredictingpatientpathwaysintheemergencydepartmentaretrospectivestudy AT christineammirati developmentandclinicalinterpretationofanexplainableaimodelforpredictingpatientpathwaysintheemergencydepartmentaretrospectivestudy AT markvangils developmentandclinicalinterpretationofanexplainableaimodelforpredictingpatientpathwaysintheemergencydepartmentaretrospectivestudy AT gillesdequen developmentandclinicalinterpretationofanexplainableaimodelforpredictingpatientpathwaysintheemergencydepartmentaretrospectivestudy AT danielaihamghazali developmentandclinicalinterpretationofanexplainableaimodelforpredictingpatientpathwaysintheemergencydepartmentaretrospectivestudy |