Problems in the deployment of machine-learned models in health care.

CMAJ

Mila Quebec AI Institute (Cohen, Viviano, Huang, Bengio), University of Montreal, Montréal, Que.; Vector (Cao, Ghassemi), University of Toronto; Unity Health Toronto (Mamdani); Department of Medicine (Fralick) University of Toronto, Toronto, Ont.; Alberta Machine Intelligence Institute (Greiner), University of Alberta, Edmonton, Alta.; Department of Radiology (Cohen), and Center for Artificial Intelligence in Machine & Imagery (Cohen) Stanford University, Stanford, Calif.

Published: September 2021

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8443295PMC
http://dx.doi.org/10.1503/cmaj.202066DOI Listing

Publication Analysis

Top Keywords

problems deployment
4
deployment machine-learned
4
machine-learned models
4
models health
4
health care
4
problems
1
machine-learned
1
models
1
health
1
care
1

Similar Publications

Delay-Sensitive Multi-Sensor Routing Scheduling Method for Underground IoT in Mines.

Sensors (Basel)

January 2025

School of Cyber Science and Engineering, Liaoning University, Shenyang 110036, China.

Recently, there has been a growing interest in underground construction safety, during activities such as subway construction, underground mining, and tunnel excavation. While Internet of Things (IoT) sensors help to monitor these conditions, large-scale deployment is limited by high power needs and complex tunnel layouts, making real-time response a critical challenge. A delay-sensitive multi-sensor multi-base-station routing scheduling method is proposed for the IoT in underground mining.

View Article and Find Full Text PDF

Introduction: Parenting programs are widely used to prevent and ameliorate children's emotional and behavioral problems but low levels of engagement undermine intervention effectiveness and reach within and beyond research settings. Technology can provide flexible and cost-effective alternate service-delivery formats for parenting programs, and studies are needed to assess the extent to which parents are willing to engage with digitally assisted formats.

Methods: After Deployment, Adaptive Parenting Tools (ADAPT) is an evidence-based parenting program for military families.

View Article and Find Full Text PDF

VIEWER: an extensible visual analytics framework for enhancing mental healthcare.

J Am Med Inform Assoc

January 2025

South London and Maudsley NHS Foundation Trust, London SE5 8AZ, United Kingdom.

Objective: A proof-of-concept study aimed at designing and implementing Visual & Interactive Engagement With Electronic Records (VIEWER), a versatile toolkit for visual analytics of clinical data, and systematically evaluating its effectiveness across various clinical applications while gathering feedback for iterative improvements.

Materials And Methods: VIEWER is an open-source and extensible toolkit that employs natural language processing and interactive visualization techniques to facilitate the rapid design, development, and deployment of clinical information retrieval, analysis, and visualization at the point of care. Through an iterative and collaborative participatory design approach, VIEWER was designed and implemented in one of the United Kingdom's largest National Health Services mental health Trusts, where its clinical utility and effectiveness were assessed using both quantitative and qualitative methods.

View Article and Find Full Text PDF

Under the backdrop of frequent emergencies, the rational layout of emergency service facilities (ESF) and the effective allocation of emergency supplies have emerged as crucial in determining the timeliness of post-disaster response. By adequately accounting for potential uncertainties and carrying out comprehensive pre-planning, the robustness of location-allocation decisions can be significantly improved. This paper delves into the ESF network design problem under demand uncertainty and formulates this problem as a two-stage robust optimization model.

View Article and Find Full Text PDF

With the rapid development of artificial intelligence technology, an increasing number of village-related modeling problems have been addressed. However, first, the exploration of village-related watershed fine-grained classification problems, particularly the multi-view watershed fine-grained classification problem, has been hindered by dataset collection limitations; Second, village-related modeling networks typically employ convolutional modules for attentional modeling to extract salient features, yet they lack global attentional feature modeling capabilities; Lastly, the extensive number of parameters and significant computational demands render village-related watershed fine-grained classification networks infeasible for end-device deployment. To tackle these challenges, we introduce a multi-view attention mechanism designed for precise watershed classification, leveraging knowledge distillation techniques, abbreviated as MANet-KD.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!