Improving the quality of hospital sterilization process using failure modes and effects analysis, fuzzy logic, and machine learning: experience in tertiary dental centre - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue International Journal for Quality in Health Care Année : 2023

Improving the quality of hospital sterilization process using failure modes and effects analysis, fuzzy logic, and machine learning: experience in tertiary dental centre

Amélioration de la qualité du processus de stérilisation hospitalière en utilisant l'AMDEC, la logique floue et l'apprentissage automatique : cas du centre dentaire tertiaire.

Amine En-Naaoui
Aicha Aguezzoul

Résumé

Abstract Activities practiced in the hospital generate several types of risks. Therefore, performing the risk assessment is one of the quality improvement keys in the healthcare sector. For this reason, healthcare managers need to design and perform efficient risk assessment processes. Failure modes and effects analysis (FMEA) is one of the most used risk assessment methods. The FMEA is a proactive technique consisting of the evaluation of failure modes associated with a studied process using three factors: occurrence, non-detection, and severity, in order to obtain the risk priority number using fuzzy logic approach and machine learning algorithms, namely the support vector machine and the k-nearest neighbours. The proposed model is applied in the case of the central sterilization unit of a tertiary national reference centre of dental treatment, where its efficiency is evaluated compared to the classical approach. These comparisons are based on expert advice and machine learning performance metrics. Our developed model proved high effectiveness throughout the results of the expert’s vote (she agrees with 96% fuzzy-FMEA results against 6% with classical FMEA results). Furthermore, the machine learning metrics show a high level of accuracy in both training data (best rate is 96%) and testing data (90%). This study represents the first study that aims to perform artificial intelligence approach to risk management in the Moroccan healthcare sector. The perspective of this study is to promote the application of the artificial intelligence in Moroccan health management, especially in the field of quality and safety management.
Fichier non déposé

Dates et versions

hal-04393242 , version 1 (14-01-2024)

Identifiants

Citer

Amine En-Naaoui, Aicha Aguezzoul, Mohammed Kaicer. Improving the quality of hospital sterilization process using failure modes and effects analysis, fuzzy logic, and machine learning: experience in tertiary dental centre. International Journal for Quality in Health Care, 2023, 35 (4), ⟨10.1093/intqhc/mzad078⟩. ⟨hal-04393242⟩

Collections

UNIV-LORRAINE
6 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More