A Framework for Applied AI in Healthcare

Implementation Frameworks for Artificial Intelligence Translation Into Health Care Practice: Scoping Review

Background

Significant efforts have been made to develop artificial intelligence (AI) solutions for health care improvement. Despite the enthusiasm, health care professionals still struggle to implement AI in their daily practice.

Objective

This paper aims to identify the implementation frameworks used to understand the application of AI in health care practice.

Methods

A scoping review was conducted using the Cochrane, Evidence Based Medicine Reviews, Embase, MEDLINE, and PsycINFO databases to identify publications that reported frameworks, models, and theories concerning AI implementation in health care. This review focused on studies published in English and investigating AI implementation in health care since 2000. A total of 2541 unique publications were retrieved from the databases and screened on titles and abstracts by 2 independent reviewers. Selected articles were thematically analyzed against the Nilsen taxonomy of implementation frameworks, and the Greenhalgh framework for the nonadoption, abandonment, scale-up, spread, and sustainability (NASSS) of health care technologies.

Results

In total, 7 articles met all eligibility criteria for inclusion in the review, and 2 articles included formal frameworks that directly addressed AI implementation, whereas the other articles provided limited descriptions of elements influencing implementation. Collectively, the 7 articles identified elements that aligned with all the NASSS domains, but no single article comprehensively considered the factors known to influence technology implementation. New domains were identified, including dependency on data input and existing processes, shared decision-making, the role of human oversight, and ethics of population impact and inequality, suggesting that existing frameworks do not fully consider the unique needs of AI implementation.

Conclusions

This literature review demonstrates that understanding how to implement AI in health care practice is still in its early stages of development. Our findings suggest that further research is needed to provide the knowledge necessary to develop implementation frameworks to guide the future implementation of AI in clinical practice and highlight the opportunity to draw on existing knowledge from the field of implementation science.

Metabolomic Laboratory-Developed Tests: Current Status and Perspectives

Laboratory-developed tests (LDTs) are a subset of in vitro diagnostic devices, which the US Food and Drug Administration defines as "tests that are manufactured by and used within a single laboratory". The review describes the emergence and history of LDTs. The current state and development prospects of LDTs based on metabolomics are analyzed. By comparing LDTs with the scientific metabolomics study of human bio samples, the characteristic features of metabolomic LDT are shown, revealing its essence, strengths, and limitations. The possibilities for further developments and scaling of metabolomic LDTs and their potential significance for healthcare are discussed. The legal aspects of LDT regulation in the United States, European Union, and Singapore, demonstrating different approaches to this issue, are also provided. Based on the data presented in the review, recommendations were made on the feasibility and ways of further introducing metabolomic LDTs into practice.

The Greatest Challenge to Using AI/ML for Primary Health Care: Mindset or Datasets?

The global vision for primary health care (PHC) is defined by regular access to quality care for comprehensive services throughout the course of life. However, this is not what typically happens, especially in low- and middle-income countries, where many people access the formal health system only for emergent needs. Yet, even episodic care is nearly impossible to attain due to infrastructure barriers, critical shortages of health care providers, and low-quality care. Artificial intelligence and machine learning (AI/ML) can help us revolutionize the current reality of health care into the vision of continuous health care that promotes individuals to maintain a constant healthy state. AI/ML can deliver precise recommendations to the individual, transforming patients from a passive receiver of health services into an active participant of their own care. By accounting for each individual, AI/ML can also ensure equitable coverage for entire populations with an ongoing data exchange between personal health, genomic data, public health, and environmental factors. The greatest challenge to enlisting AI/ML in the quest toward the PHC vision will be instilling a sense of responsibility with global citizens to recognize health data for the global good while prioritizing protected, individually owned data sets. Only when individuals start taking a collective approach to health data, shifting the mindset toward the goal of prevention, will the potential of AI/ML for PHC be realized. Until we overcome this challenge, the paradigm shift of the global community away from our ad hoc, reactive health system culture will not be achieved.