Feasibility of streamlining an interactive Bayesian-based diagnostic support tool designed for clinical practice

Author(s):  
Po-Hao Chen ◽  
Emmanuel Botzolakis ◽  
Suyash Mohan ◽  
R. N. Bryan ◽  
Tessa Cook
2019 ◽  
Vol 26 (7) ◽  
pp. 630-636 ◽  
Author(s):  
Ellen K Kerns ◽  
Vincent S Staggs ◽  
Sarah D Fouquet ◽  
Russell J McCulloh

Abstract Objective Estimate the impact on clinical practice of using a mobile device–based electronic clinical decision support (mECDS) tool within a national standardization project. Materials and Methods An mECDS tool (app) was released as part of a change package to provide febrile infant management guidance to clinicians. App usage was analyzed using 2 measures: metric hits per case (metric-related screen view count divided by site-reported febrile infant cases in each designated market area [DMA] monthly) and cumulative prior metric hits per site (DMA metric hits summed from study month 1 until the month preceding the index, divided by sites in the DMA). For each metric, a mixed logistic regression model was fit to model site performance as a function of app usage. Results An increase of 200 cumulative prior metric hits per site was associated with increased odds of adherence to 3 metrics: appropriate admission (odds ratio [OR], 1.12; 95% confidence interval [CI], 1.06-1.18), appropriate length of stay (OR, 1.20; 95% CI, 1.12-1.28), and inappropriate chest x-ray (OR, 0.82; 95% CI, 0.75-0.91). Ten additional metric hits per case were also associated: OR were 1.18 (95% CI, 1.02-1.36), 1.36 (95% CI, 1.14-1.62), and 0.74 (95% CI, 0.62-0.89). Discussion mECDS tools are increasingly being implemented, but their impact on clinical practice is poorly described. To our knowledge, although ecologic in nature, this report is the first to link clinical practice to mECDS use on a national scale and outside of an electronic health record. Conclusions mECDS use was associated with changes in adherence to targeted metrics. Future studies should seek to link mECDS usage more directly to clinical practice and assess other site-level factors.


2021 ◽  
Author(s):  
Elena Lazarova ◽  
Sara Mora ◽  
Davide Armanino ◽  
Alessandro Poire ◽  
Fabio Furlani ◽  
...  

Psychology tests are tools used to evaluate specific aspects of individual psyche and behavior, in clinical practice and for research purposes. They are validated and standardized both in the administration procedures and interpretation of results. Nowadays, most of these tests are questionnaires administered to patients on paper support. The patient’s answers to the questionnaires constitute a basis for self-presentation and self-awareness at the beginning of the therapeutic path. The computer is a valuable aid allowing a quickly consultation of all the answers and highlighting the most salient ones. The main aim of this work was to design, develop and test a computerized support tool for the interpretation of psychological tests that allow good interaction between groups of therapists sharing the same operating modes. The developed system allows: first the storing of the numerical values corresponding to the answers to the questionnaires of the patients; then it creates a complete ’Picture’ of the patient and allows the automatic computation of the correlation between the indexes of the various scales. The graphical correlations between scales can be also a valuable aid in finding the outliers, so patients far away from the trend line.


Healthcare ◽  
2019 ◽  
Vol 7 (4) ◽  
pp. 136 ◽  
Author(s):  
Joyce Samuel ◽  
Travis Holder ◽  
Donald Molony

The n-of-1 trial can utilized in clinical practice as a decision support tool, which may improve patient outcomes by providing both the patient and the clinician with objective evidence to inform personalized treatment decisions. As its use broadens, it will be important to study whether the added time and effort of an n-of-1 trial results in measurable improvements in important patient outcomes compared to usual clinical practice. Parallel-group randomized clinical trials testing the n-of-1 approach versus usual care have been undertaken in a number of medical settings. A systematic review will be performed according to PRISMA guidelines, using MEDLINE, Embase, Cochrane, CINAHL, PsycINFO, Scopus, and Web of Science to search for randomized clinical trials in humans, without date or language restriction. Reports from the gray literature and ongoing studies in trial registries will be included. Articles will be screened by two independent reviewers with a third reviewer consulted to adjudicate disagreement. The quality of included studies will be assessed using the Cochrane Collaboration’s tool for assessing risk of bias. A narrative synthesis will explore the differing methodological approaches of the included studies. The protocol will be registered in the PROSPERO registry, and the results of the review will be published in a peer-reviewed journal. To our knowledge, this systematic review will be the first to comprehensively assess the existing research on randomized trials testing the n-of-1 trial approach in clinical practice.


2020 ◽  
Vol 50 ◽  
pp. 102224
Author(s):  
Pattanasin Areeudomwong ◽  
Kitti Jirarattanaphochai ◽  
Thapakorn Ruanjai ◽  
Vitsarut Buttagat

Author(s):  
Makenzie Pryor ◽  
Doug Ebert ◽  
Vicky Byrne ◽  
Khalaeb Richardson ◽  
Qua Jones ◽  
...  

The present study examined a diagnostic medical decision aid developed to help inexperienced operators to diagnose and treat a simulated patient. Diagnosis and treatment accuracy using the tool were assessed and compared across both physicians and non-physicians. Initial analysis revealed more accurate diagnostic and treatment choices for non-physicians, but upon further investigation, physicians were found to have recognized signs for another diagnosis and correctly diagnosed and treated based on the limited information in the patient simulation. This fit with other noted behaviors, such as non-physicians opening the diagnostic support tool within the aid more often than physicians, and frequently returning to the tool during the task. In general, non-physicians were supported in choosing the correct diagnosis and treatment by the aid, while physicians disregarded the aid’s recommendations to make decisions based on their own expertise. These results have implications for the development of future decision support aids for non-physicians performing medical procedures.


Sign in / Sign up

Export Citation Format

Share Document