A Framework to Guide Implementation of AI in Health Care: Protocol for a Cocreation Research Project
Notice bibliographique
Résumé
BACKGROUND: Artificial intelligence (AI) has the potential in health care to transform patient care and administrative processes, yet health care has been slow to adopt AI due to many types of barriers. Implementation science has shown the importance of structured implementation processes to overcome implementation barriers. However, there is a lack of knowledge and tools to guide such processes when implementing AI-based applications in health care. OBJECTIVE: The aim of this protocol is to describe the development, testing, and evaluation of a framework, "Artificial Intelligence-Quality Implementation Framework" (AI-QIF), intended to guide decisions and activities related to the implementation of various AI-based applications in health care. METHODS: The paper outlines the development of an AI implementation framework for broad use in health care based on the Quality Implementation Framework (QIF). QIF is a process model developed in implementation science. The model guides the user to consider implementation-related issues in a step-by-step design and plan and perform activities that support implementation. This framework was chosen for its adaptability, usability, broad scope, and detailed guidance concerning important activities and considerations for successful implementation. The development will proceed in 5 phases with primarily qualitative methods being used. The process starts with phase I, in which an AI-adapted version of QIF is created (AI-QIF). Phase II will produce a digital mockup of the AI-QIF. Phase III will involve the development of a prototype of the AI-QIF with an intuitive user interface. Phase IV is dedicated to usability testing of the prototype in health care environments. Phase V will focus on evaluating the usability and effectiveness of the AI-QIF. Cocreation is a guiding principle for the project and is an important aspect in 4 of the 5 development phases. The cocreation process will enable the use of both on research-based and practice-based knowledge. RESULTS: The project is being conducted within the frame of a larger research program, with the overall objective of developing theoretically and empirically informed frameworks to support AI implementation in routine health care. The program was launched in 2021 and has carried out numerous research activities. The development of AI-QIF as a tool to guide the implementation of AI-based applications in health care will draw on knowledge and experience acquired from these activities. The framework is being developed over 2 years, from January 2023 to December 2024. It is under continuous development and refinement. CONCLUSIONS: The development of the AI implementation framework, AI-QIF, described in this study protocol aims to facilitate the implementation of AI-based applications in health care based on the premise that implementation processes benefit from being well-prepared and structured. The framework will be coproduced to enhance its relevance, validity, usefulness, and potential value for application in practice. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/50216.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,174 | 0,203 |
| Méta-épidémiologie (sens strict) | 0,004 | 0,004 |
| Méta-épidémiologie (sens large) | 0,004 | 0,007 |
| Bibliométrie | 0,007 | 0,008 |
| Études des sciences et des technologies | 0,010 | 0,008 |
| Communication savante | 0,008 | 0,007 |
| Science ouverte | 0,007 | 0,009 |
| Intégrité de la recherche | 0,012 | 0,015 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,072 | 0,019 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».