Assessment of Adherence to Reporting Guidelines by Commonly Used Clinical Prediction Models From a Single Vendor

Abstract

IMPORTANCE Various model reporting guidelines have been proposed to ensure clinical prediction models are reliable and fair. However, no consensus exists about which model details are essential to report, and commonalities and differences among reporting guidelines have not been characterized. Furthermore, how well documentation of deployed models adheres to these guidelines has not been studied. OBJECTIVESTo assess information requested by model reporting guidelines and whether the documentation for commonly used machine learning models developed by a single vendor provides the information requested.EVIDENCE REVIEW MEDLINE was queried using machine learning model card and reporting machine learning from November 4 to December 6, 2020. References were reviewed to find additional publications, and publications without specific reporting recommendations were excluded. Similar elements requested for reporting were merged into representative items. Four independent reviewers and 1 adjudicator assessed how often documentation for the most commonly used models developed by a single vendor reported the items.FINDINGS From 15 model reporting guidelines, 220 unique items were identified that represented the collective reporting requirements. Although 12 items were commonly requested (requested by 10 or more guidelines), 77 items were requested by just 1 guideline. Documentation for 12 commonly used models from a single vendor reported a median of 39% (IQR, 37%-43%; range, 31%-47%) of items from the collective reporting requirements. Many of the commonly requested items had 100% reporting rates, including items concerning outcome definition, area under the receiver operating characteristics curve, internal validation, and intended clinical use. Several items reported half the time or less related to reliability, such as external validation, uncertainty measures, and strategy for handling missing data. Other frequently unreported items related to fairness (summary statistics and subgroup analyses, including for race and ethnicity or sex). CONCLUSIONS AND RELEVANCEThese findings suggest that consistent reporting recommendations for clinical predictive models are needed for model developers to share necessary information for model deployment. The many published guidelines would, collectively, require reporting more than 200 items. Model documentation from 1 vendor reported the most commonly requested items from model reporting guidelines. However, areas for improvement were identified in reporting items related to model reliability and fairness. This analysis led to feedback to the vendor, which motivated updates to the documentation for future users.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

“…Data extraction adhered to the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA guidelines. 19 , 544 We used a closed-loop cross-sequential design for quality control on data extraction and screening (5 assessors). Details on data extraction are provided in eMethods 2 and 3 in Supplement 1 .…”

“…In addition, poor reporting quality impedes the establishment of better practices in AI-based psychiatric diagnosis. Despite the developments of multifarious benchmarks for reporting clinical prediction models (eg, STARD [Standards for Reporting of Diagnostic Accuracy], DECIDE-AI [Early-Stage Clinical Evaluation of Decision Support Systems Driven by Artificial Intelligence], and TRIPOD [Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis]), 16 , 17 , 18 , 19 the reporting quality in current publications still needs to be improved, with approximately 80% of articles providing incomplete information and less than 50% of contents following the TRIPOD guideline, limiting clinical potential and contributing to research waste. 20 , 21 , 22 Even after 3 decades of neuroimaging-based AI model developments, it remains unclear whether the reports of such developments are unbiased and complete enough to warrant translation into clinical practice for psychiatric diagnosis.…”

Addressing racial disparities in surgical care with machine learning

“…While the aforementioned bias detection programs have merit, solving the problem of surgical bias will require a more comprehensive approach. That approach begins with a set of guidelines that set forth standards on how to conduct AI-related research and how to report it in the professional literature, including The Standard Protocol Items: Recommendations for Interventional Trials-Artificial Intelligence (SPIRIT-AI)extension, a set of guidelines designed to help researchers develop AI-related clinical trials 33 , and the Consolidated Standards of Reporting Trials-Artificial Intelligence (CONSORT-AI) extension 34 Unfortunately, despite the recommendations from thought leaders regarding the importance of adhering to standards that would make algorithms more equitable, Lu et al have found these guidelines are often ignored 35 .…”

Validation of a Proprietary Deterioration Index Model and Performance in Hospitalized Adults

“…Given widespread use of the DTI to assist in care delivery, it is important to measure its performance across as many health care settings as possible . Notably, the optimal DTI score at which to trigger clinical interventions remains unclear, and the vendor does not report performance across subgroups of race, ethnicity, age, or sex . This study aimed to (1) describe the overall and lead time performance of the DTI among a large cohort of patients across 8 heterogenous Midwestern US hospitals, (2) evaluate performance measures at suggested thresholds to support clinical decision-making, and (3) assess bias in predictions among demographic subgroups.…”