Related Experiment Video
Updated: Jan 15, 2026
Assessing Cardiac Reprogramming using High Content Imaging Analysis
Published on: October 26, 2020
Assessing the quality of reporting in artificial intelligence/machine learning research for cardiac amyloidosis
Asiful Arefeen1,2, Simar Singh3,4, Crystal Razavi3
1School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ 85281, United States.
Objectives:
Despite the rapid development of AI in clinical medicine, reproducibility and methodological limitations hinder its clinical utility. In response, MINimum Information for Medical AI Reporting (MINIMAR) standards were introduced to enhance publication standards and reduce bias, but their application remains unexplored. In this review, we sought to assesses the quality of reporting in AI/ML studies of cardiac amyloidosis (CA) an increasingly important cause of heart failure.
Materials And Methods:
Using PRISMA-ScR guidelines, we performed a scoping review of English-language articles published through May 2023 which applied AI/ML techniques to diagnose or predict CA. Non-CA studies and those with selective feature sets were excluded. Two researchers independently screened and extracted data. In all, 20 studies met criteria and were assessed for adherence to MINIMAR standards.
Results:
The studies showed variable compliance with MINIMAR. Most reported participant age (90%) and gender (85%), but only 25% included ethnic or racial data, and none provided socioeconomic details. The majority (95%) developed diagnostic models, yet only 85% clearly described training features, and 20% addressed missing data. Model evaluation revealed gaps; 80% reported internal validation, but only 20% conducted external validation.
Discussion And Conclusion:
This study, one of the first to apply MINIMAR criteria to ML research in CA, reveals significant variability and deficiencies in reporting, particularly in patient demographics, model architecture, and evaluation. These findings underscore the need for stricter adherence to standardized reporting guidelines to enhance the reliability, generalizability, and clinical applicability of ML/AI models in CA.
Insights
Reporting quality in AI/ML studies for cardiac amyloidosis is variable. Adherence to MINimum Information for Medical AI Reporting (MINIMAR) standards is needed to improve reliability and clinical use of these AI models.
Area of Science:
- Medical Artificial Intelligence (AI)
- Machine Learning (ML)
- Cardiac Amyloidosis (CA)
Background:
- AI/ML shows promise in clinical medicine but faces reproducibility and reporting challenges.
- MINimum Information for Medical AI Reporting (MINIMAR) standards aim to improve AI reporting quality and reduce bias.
- The application of MINIMAR standards in AI/ML studies for cardiac amyloidosis remains unevaluated.
Purpose of the Study:
- To assess the reporting quality of AI/ML studies in cardiac amyloidosis (CA).
- To evaluate the adherence of CA AI/ML studies to MINIMAR reporting standards.
- To identify deficiencies in reporting that hinder the clinical utility of AI/ML models in CA.
Main Methods:
- A scoping review was conducted following PRISMA-ScR guidelines.
- English-language articles published up to May 2023, focusing on AI/ML for CA diagnosis or prediction, were included.
- Twenty studies were assessed for adherence to MINIMAR standards, with data independently screened and extracted by two researchers.
Main Results:
- Significant variability in MINIMAR compliance was observed across the 20 reviewed studies.
- While demographic data like age and gender were often reported, ethnic/racial and socioeconomic data were lacking.
- Reporting gaps were identified in model training features (85% described), missing data handling (20%), and external validation (20%).
Conclusions:
- This review highlights substantial deficiencies in reporting quality within AI/ML research for cardiac amyloidosis.
- There is a critical need for stricter adherence to standardized reporting guidelines like MINIMAR.
- Improved reporting is essential to enhance the reliability, generalizability, and clinical applicability of AI/ML models in CA.
