A call for better validation of opioid overdose risk algorithms.

J Am Med Inform Assoc

Program Evaluation Resource Center, Office of Mental Health and Suicide Prevention, US Department of Veterans Affairs, Menlo Park, California, USA.

Published: September 2023

Clinical decision support (CDS) systems powered by predictive models have the potential to improve the accuracy and efficiency of clinical decision-making. However, without sufficient validation, these systems have the potential to mislead clinicians and harm patients. This is especially true for CDS systems used by opioid prescribers and dispensers, where a flawed prediction can directly harm patients. To prevent these harms, regulators and researchers have proposed guidance for validating predictive models and CDS systems. However, this guidance is not universally followed and is not required by law. We call on CDS developers, deployers, and users to hold these systems to higher standards of clinical and technical validation. We provide a case study on two CDS systems deployed on a national scale in the United States for predicting a patient's risk of adverse opioid-related events: the Stratification Tool for Opioid Risk Mitigation (STORM), used by the Veterans Health Administration, and NarxCare, a commercial system.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10531142PMC
http://dx.doi.org/10.1093/jamia/ocad110DOI Listing

Publication Analysis

Top Keywords

cds systems
16
predictive models
8
harm patients
8
systems
6
cds
5
call better
4
better validation
4
validation opioid
4
opioid overdose
4
overdose risk
4

Similar Publications

Intramicellar sensor assays: Improving sensing sensitivity of sensor array for thiol biomarkers.

Biosens Bioelectron

January 2025

Liaoning Province Key Laboratory for Green Synthesis and Preparative Chemistry of Advanced Materials, Liaoning University, Shenyang, 110036, PR China; School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore, 637371, PR Singapore. Electronic address:

Array-based analysis allows for precise disease diagnosis by simultaneously detecting multiple biomarkers. However, most array sensing platforms rely on non-covalent interactions between sensors and analytes, which limits their sensitivity. This study enhances the sensitivity of array analysis for thiol biomarkers by incorporating polyion complex micelles into the sensor array design.

View Article and Find Full Text PDF

Technoeconomic analysis for near-term scale-up of bioprocesses.

Curr Opin Biotechnol

January 2025

Life-cycle, Economics, and Agronomy Division, Joint BioEnergy Institute, Emeryville, CA 94608, United States; Energy & Biosciences Institute, University of California, Berkeley, CA 94720, United States; Biological Systems and Engineering Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, United States; Energy Analysis and Environmental Impacts Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, United States. Electronic address:

Growing the bioeconomy requires products and pathways that are cost-competitive. Technoeconomic analyses (TEAs) aim to predict the long-term economic viability and often use what are known as n plant cost and performance parameters. However, as TEA is more widely adopted to inform everything from early-stage research to company and investor decision-making, the n plant approach is inadequate and risks being misused to inform the early stages of scale-up.

View Article and Find Full Text PDF

In January 2021, the Gulf Health Council (GHC), established the Gulf Centre for Disease Prevention and Control (Gulf CDC) in Riyadh, marking a pivotal step in harmonizing health strategies, enhancing knowledge generation, and promoting evidence-based approaches to both communicable (CD) and non-communicable diseases (NCD). The Gulf CDC's mission includes consolidating the region's health information systems, crucial for monitoring disease burden and shaping effective public health policies. An initial assessment of public health surveillance systems across the Gulf Cooperation Council (GCC) member states was conducted by the Gulf CDC.

View Article and Find Full Text PDF

Gold nanoparticles (AuNPs) have been widely used as efficient and environmentally friendly catalysts due to their high specific surface area and abundant active sites. However, AuNP-based catalytic systems face several challenges, including the instability of AuNPs during the reaction, the difficulty in monitoring the process, which can easily result in insufficient reaction due to short reaction time or waste of resources due to long reaction time, as well as issues of catalyst recovery. This study proposes a novel catalyst integrating various functions, such as high stability, the capacity for real-time monitoring of the catalytic process, and rapid recycling.

View Article and Find Full Text PDF

Background: Integrating algorithm-based clinical decision support (CDS) systems poses significant challenges in evaluating their actual clinical value. Such CDS systems are traditionally assessed via controlled but resource-intensive clinical trials.

Objective: This paper presents a review protocol for preimplementation in silico evaluation methods to enable broadened impact analysis under simulated environments before clinical trials.

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!