AI Article Synopsis
Article Abstract
Background And Objective: This study aimed to develop and evaluate an algorithm to reduce the chart review burden of improvement efforts by automatically labeling antibiotic selection as either guideline-concordant or -discordant based on electronic health record data for patients with community-acquired pneumonia (CAP).
Methods: We developed a 3-part algorithm using structured and unstructured data to assess adherence to an institutional CAP clinical practice guideline. The algorithm was applied to retrospective data for patients seen with CAP from 2017 to 2019 at a tertiary children's hospital. Performance metrics included positive predictive value (precision), sensitivity (recall), and F1 score (harmonized mean), with macro-weighted averages. Two physician reviewers independently assigned "actual" labels based on manual chart review.
Results: Of 1345 patients with CAP, 893 were included in the training cohort and 452 in the validation cohort. Overall, the model correctly labeled 435 of 452 (96%) patients. Of the 286 patients who met guideline inclusion criteria, 193 (68%) were labeled as having received guideline-concordant antibiotics, 48 (17%) were labeled as likely in a scenario in which deviation from the clinical practice guideline was appropriate, and 45 (16%) were given the final label of "possibly discordant, needs review." The sensitivity was 0.96, the positive predictive value was 0.97, and the F1 was 0.96.
Conclusions: An automated algorithm that uses structured and unstructured electronic health record data can accurately assess the guideline concordance of antibiotic selection for CAP. This tool has the potential to improve the efficiency of improvement efforts by reducing the manual chart review needed for quality measurement.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10823186 | PMC |
| http://dx.doi.org/10.1542/hpeds.2023-007418 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Physical Activity and Sedentary Behavior in Patients With Breast Cancer: Results of a Single Cohort in the Midwestern United States.
Am J Lifestyle Med
December 2024
University of Nebraska Medical Center, Omaha, NE, USA (SC, JG).
Physical activity and sedentary behavior have significant prognostic importance in survivors of breast cancer. However, not much is known about physical activity and sedentary behavior in the midwestern United States for patients who have breast cancer. This study provides patient-reported physical activity and sedentary behavior from a cohort of patients from the midwestern United States.
View Article and Find Full Text PDFDevelopment of evidence-based standards for inpatient physiotherapy services: a systematic review and content analysis of clinical practice guidelines.
BMJ Open
December 2024
Health Sciences Library, University of Otago, Dunedin, New Zealand.
Objective: Performance standards are critical to service design and quality improvement. There are no published standards defining the care inpatients should receive from physiotherapists in Aotearoa New Zealand. This study aims to explore the potential of using clinical practice guidelines (CPGs) to develop a set of evidence-based standards for physiotherapy in inpatient settings.
View Article and Find Full Text PDFThe "Mammograms Available Due to Resources and Education" (MADRE) Study: Rationale and Design.
Contemp Clin Trials
December 2024
University of Illinois at Chicago, 601 S Morgan St, Chicago, IL 60607, USA.
Background: Latinas suffer disproportionately from breast cancer, partially due to lower uptake of guideline-concordant breast cancer screening. We describe the design of a study to compare two approaches addressing this important public health problem.
Design/methods: We are conducting a 5-year randomized controlled trial.
The lifecycle and evolution of new regimens on the National Comprehensive Cancer Network Guidelines for newly diagnosed multiple myeloma.
Oncologist
December 2024
Division of Epidemiology and Biostatistics, University of California San Francisco, San Francisco, CA 94158, United States.
Introduction: Prior studies have evaluated the level of evidence behind treatment options listed in the National Comprehensive Cancer Network (NCCN) guidelines, but no study has categorized the life cycle of regimens listed in the NCCN guidelines. We longitudinally assessed the life cycle for each regimen for newly diagnosed multiple myeloma. We track the date of first clinical data, the date of regimen addition to NCCN guidelines, the date phase 3 data (if performed) were reported, and the results of phase 3 trials.
View Article and Find Full Text PDFConsideration of Cybersecurity Risks in the Benefit-Risk Analysis of Medical Devices: Scoping Review.
J Med Internet Res
December 2024
Else Kröner Fresenius Center for Digital Health, Dresden University of Technology, Dresden, Germany.
Background: The integration of connected medical devices (MDs) into health care brings benefits but also introduces new, often challenging-to-assess risks related to cybersecurity, which have the potential to harm patients. Current regulations in the European Union and the United States mandate the consideration of these risks in the benefit-risk analysis (BRA) required for MD approval. This important step in the approval process weighs all the defined benefits of a device with its anticipated risks to ensure that the product provides a positive argument for use.
View Article and Find Full Text PDFWant 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!