Dataset Information

Artificial intelligence in medical referrals triage based on Clinical Prioritization Criteria.

ABSTRACT: The clinical prioritisation criteria (CPC) are a clinical decision support tool that ensures patients referred for public specialist outpatient services to Queensland Health are assessed according to their clinical urgency. Medical referrals are manually triaged and prioritised into three categories by the associated health service before appointments are booked. We have developed a method using artificial intelligence to automate the process of categorizing medical referrals based on clinical prioritization criteria (CPC) guidelines. Using machine learning techniques, we have created a tool that can assist clinicians in sorting through the substantial number of referrals they receive each year, leading to more efficient use of clinical specialists' time and improved access to healthcare for patients. Our research included analyzing 17,378 ENT referrals from two hospitals in Queensland between 2019 and 2022. Our results show a level of agreement between referral categories and generated predictions of 53.8%.

SUBMITTER: Abdel-Hafez A

PROVIDER: S-EPMC10642163 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Artificial intelligence in medical referrals triage based on Clinical Prioritization Criteria.

Abdel-Hafez Ahmad A Jones Melanie M Ebrahimabadi Maziiar M Ryan Cathi C Graham Steve S Slee Nicola N Whitfield Bernard B

Frontiers in digital health 20231027

The clinical prioritisation criteria (CPC) are a clinical decision support tool that ensures patients referred for public specialist outpatient services to Queensland Health are assessed according to their clinical urgency. Medical referrals are manually triaged and prioritised into three categories by the associated health service before appointments are booked. We have developed a method using artificial intelligence to automate the process of categorizing medical referrals based on clinical p ...[more]

PMID: 37964894

Similar Datasets

Project description:ObjectiveTo determine the rigor, generalizability, and reproducibility of published classification and detection artificial intelligence (AI) models for prostate cancer (PCa) on MRI using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) guidelines, a 42-item checklist that is considered a measure of best practice for presenting and reviewing medical imaging AI research.Materials and methodsThis review searched English literature for studies proposing PCa AI detection and classification models on MRI. Each study was evaluated with the CLAIM checklist. The additional outcomes for which data were sought included measures of AI model performance (eg, area under the curve [AUC], sensitivity, specificity, free-response operating characteristic curves), training and validation and testing group sample size, AI approach, detection versus classification AI, public data set utilization, MRI sequences used, and definition of gold standard for ground truth. The percentage of CLAIM checklist fulfillment was used to stratify studies into quartiles. Wilcoxon's rank-sum test was used for pair-wise comparisons.ResultsIn all, 75 studies were identified, and 53 studies qualified for analysis. The original CLAIM items that most studies did not fulfill includes item 12 (77% no): de-identification methods; item 13 (68% no): handling missing data; item 15 (47% no): rationale for choosing ground truth reference standard; item 18 (55% no): measurements of inter- and intrareader variability; item 31 (60% no): inclusion of validated interpretability maps; item 37 (92% no): inclusion of failure analysis to elucidate AI model weaknesses. An AUC score versus percentage CLAIM fulfillment quartile revealed a significant difference of the mean AUC scores between quartile 1 versus quartile 2 (0.78 versus 0.86, P = .034) and quartile 1 versus quartile 4 (0.78 versus 0.89, P = .003) scores. Based on additional information and outcome metrics gathered in this study, additional measures of best practice are defined. These new items include disclosure of public dataset usage, ground truth definition in comparison to other referenced works in the defined task, and sample size power calculation.ConclusionA large proportion of AI studies do not fulfill key items in CLAIM guidelines within their methods and results sections. The percentage of CLAIM checklist fulfillment is weakly associated with improved AI model performance. Additions or supplementations to CLAIM are recommended to improve publishing standards and aid reviewers in determining study rigor.

Project description:BACKGROUND:Before patients are admitted into the emergency department, it is important to undertake a pre-hospital process, both in terms of treatment performance and a request for resources from an emergency unit. The existing system to triage patients in Thailand is not functioning to its full capacity in either the primary medical system or pre-hospital treatment with shortcomings in the areas of speed, features, and appropriate systems. There is a high possibility of issuing a false Initial Dispatch Code (IDC), which will cause the over or underutilisation of emergency resources, such as rescue teams, community hospitals and emergency medical volunteers. METHODS:A usability system design, together with a reliability test, was applied to develop an application to optimise the pre-hospital process, specifically to sort patients, using an IDC to improve the request for emergency resources. The triage mobile application was developed on both iOS and Android operating systems to support patient triage based on Criteria Based Dispatch (CBD). The 25 main symptom categories covered by CBD were used to design and develop the application, and 12 emergency medical staff, including doctors and nurses, were asked to test the system in the aspects of triage protocol correction, triage reliability, usability and user satisfaction. RESULTS:The results of testing the proposed triage application were compared with the time used to triage by experienced staff and it was found that, in non-trauma cases, it was faster and more effective to use the application for emergency operations and to correct the IDC code representation. CONCLUSIONS:The triage application will be utilised to support the pre-hospital process and to classify patients' conditions before they are admitted to the Emergency Department (ED). The application is suitable for users who are not medical emergency staff. Patients with non-trauma symptoms may be a suitable group to use the application in terms of time used to identify IDC for their own symptoms. The use of the application can be beneficial for those who wish to self-identify their symptoms before requesting medical services.

Project description:BackgroundArtificial intelligence (AI) has developed rapidly, and its application extends to clinical decision support system (CDSS) for improving healthcare quality. However, the interpretability of AI-driven CDSS poses significant challenges to widespread application.ObjectiveThis study is a review of the knowledge-based and data-based CDSS literature regarding interpretability in health care. It highlights the relevance of interpretability for CDSS and the area for improvement from technological and medical perspectives.MethodsA systematic search was conducted on the interpretability-related literature published from 2011 to 2020 and indexed in the five databases: Web of Science, PubMed, ScienceDirect, Cochrane, and Scopus. Journal articles that focus on the interpretability of CDSS were included for analysis. Experienced researchers also participated in manually reviewing the selected articles for inclusion/exclusion and categorization.ResultsBased on the inclusion and exclusion criteria, 20 articles from 16 journals were finally selected for this review. Interpretability, which means a transparent structure of the model, a clear relationship between input and output, and explainability of artificial intelligence algorithms, is essential for CDSS application in the healthcare setting. Methods for improving the interpretability of CDSS include ante-hoc methods such as fuzzy logic, decision rules, logistic regression, decision trees for knowledge-based AI, and white box models, post hoc methods such as feature importance, sensitivity analysis, visualization, and activation maximization for black box models. A number of factors, such as data type, biomarkers, human-AI interaction, needs of clinicians, and patients, can affect the interpretability of CDSS.ConclusionsThe review explores the meaning of the interpretability of CDSS and summarizes the current methods for improving interpretability from technological and medical perspectives. The results contribute to the understanding of the interpretability of CDSS based on AI in health care. Future studies should focus on establishing formalism for defining interpretability, identifying the properties of interpretability, and developing an appropriate and objective metric for interpretability; in addition, the user's demand for interpretability and how to express and provide explanations are also the directions for future research.

Project description:In some jurisdictions, routine reporting of the estimated glomerular filtration rate (eGFR) has led to an increase in nephrology referrals and wait times.We describe the use of the Kidney Failure Risk Equation (KFRE) as part of a triage process for new nephrology referrals for patients with chronic kidney disease stages 3 to 5 in a Canadian province.A quasi-experimental study design was used.This study took place in Manitoba, Canada.Demographics, laboratory values, referral numbers, and wait times were compared between periods.In 2012, we adopted a risk-based cutoff of 3% over 5 years using the KFRE as a threshold for triage of new referrals. Referrals who did not meet other prespecified criteria (such as pregnancy, suspected glomerulonephritis, etc) and had a kidney failure risk of <3% over 5 years were returned to primary care with recommendations based on diabetes and hypertension guidelines. The average wait time and number of consults seen between the pretriage (January 1, 2011, to December 31, 2011) and posttriage period (January 1, 2013, to December 31, 2013) were compared using a general linear model.In the pretriage period, the median number of referrals was 68/month (range: 44-76); this increased to 94/month (range: 61-147) in the posttriage period. In the posttriage period, 35% of referrals were booked as urgent, 31% as nonurgent, and 34% of referrals were not booked. The median wait times improved from 230 days (range: 126-355) in the pretriage period to 58 days (range: 48-69) in the posttriage period.We do not have long-term follow-up on patients triaged as low risk. Our study may not be applicable to nephrology teams operating under capacity without wait lists. We did not collect detailed information on all referrals in the pretriage period, so any differences in our pretriage and posttriage patient groups may be unaccounted for.Our risk-based triage scheme is an effective health policy tool that led to improved wait times and access to care for patients at highest risk of progression to kidney failure.

Dataset Information

Artificial intelligence in medical referrals triage based on Clinical Prioritization Criteria.

Publications

Artificial intelligence in medical referrals triage based on Clinical Prioritization Criteria.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets