AI Article Synopsis
- This systematic review evaluated the adherence of machine learning (ML) applications in diagnosing and predicting systemic lupus erythematosus (SLE) using the TRIPOD reporting guidelines.
- Out of 45 analyzed studies, only 17% to 67% of required reporting standards were met, with notable gaps in essential areas like model performance, blinding of predictors, and handling missing data.
- The overall conclusion suggests that current reporting practices for ML-based models in SLE are inadequate, highlighting the need for improved transparency and consistency in research reporting.
Article Abstract
Objective: We carried out a systematic review (SR) of adherence in diagnostic and prognostic applications of ML in SLE using the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) Statement.
Methods: A SR employing five databases was conducted from its inception until December 2021. We identified articles that evaluated the utilization of ML for prognostic and/or diagnostic purposes. This SR was reported based on the PRISMA guidelines. The TRIPOD statement assessed adherence to reporting standards. Assessment for risk of bias was done using PROBAST tool.
Results: We included 45 studies: 29 (64.4%) diagnostic and 16 (35.5%) prognostic prediction- model studies. Overall, articles adhered by between 17% and 67% (median 43%, IQR 37-49%) to TRIPOD items. Only few articles reported the model's predictive performance (2.3%, 95% CI 0.06-12.0), testing of interaction terms (2.3%, 95% CI 0.06-12.0), flow of participants (50%, 95% CI; 34.6-65.4), blinding of predictors (2.3%, 95% CI 0.06-12.0), handling of missing data (36.4%, 95% CI 22.4-52.2), and appropriate title (20.5%, 95% CI 9.8-35.3). Some items were almost completely reported: the source of data (88.6%, 95% CI 75.4-96.2), eligibility criteria (86.4%, 95% CI 76.2-96.5), and interpretation of findings (88.6%, 95% CI 75.4-96.2). In addition, most of model studies had high risk of bias.
Conclusions: The reporting adherence of ML-based model developed for SLE, is currently inadequate. Several items deemed crucial for transparent reporting were not fully reported in studies on ML-based prediction models.
Review Registration: PROSPERO ID# CRD42021284881. (Amended to limit the scope).
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.autrev.2023.103294 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Effect of etafenone on total and regional myocardial blood flow.
Arzneimittelforschung
September 1975
The distribution of blood flow to the subendocardial, medium and subepicardial layers of the left ventricular free wall was studied in anaesthetized dogs under normoxic (A), hypoxic (B) conditions and under pharmacologically induced (etafenone) coronary vasodilation (C). Regional myocardial blood flow was determined by means of the particle distribution method. In normoxia a transmural gradient of flow was observed, with the subendocardial layers receiving a significantly higher flow rate compared with the subepicardial layers.
View Article and Find Full Text PDFArticle Synopsis
- The study measured fibrinogen fluorescence at temperatures between 20 and 80 degrees Celsius across different pH levels.
- It was found that raising the temperature from 20 to 40 degrees Celsius did not change the structure of fibrinogen in solutions with pH between 4.5 and 9.3.
- However, temperatures between 40 to 50 degrees Celsius caused some structural changes in neutral solutions, and temperatures above 50-55 degrees Celsius led to significant denaturation of the fibrinogen molecule.
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!