Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist

By Beau Norgeot, G. Quer, Brett K. Beaulieu-Jones, Ali Torkamani, Raquel Dias, M. Gianfrancesco, Rima Arnaout, Isaac S. Kohane, Suchi Saria, Eric J. Topol and 3 more. Nature Medicine, 2020

485 citations recorded by the source corpus.

Here we present the MI-CLAIM checklist, a tool intended to improve transparent reporting of AI algorithms in medicine.

Subfields: Artificial Intelligence, Health Informatics, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/ac9bfb4ef6a1b3db3143ccf5394edc1171725234

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Health Informatics

In Molecular Biology

Citations in the corpus

Characteristics of publicly available skin cancer image datasets: a systematic review. (2021, background): “…development transparency have been proposed that highlight the importance of cohort characteristics and reproducibility to target populations, 66,67 to the best of our knowledge, no consensus standards or guidelines specifically exist for the publication of skin cancer image datasets that have…”
Artificial intelligence in histopathology: enhancing cancer research and clinical oncology (2022, background): “Rigorous standards should already be applied to preclinical and early clinical work; and indeed this is increasingly mandated by AI-specific reporting guidelines for scientific studies 147,148 .”
Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review (2022, methodology): “The literature stresses that detailed description of any preprocessing steps applied to the raw data should be provided, including software used to perform the processing steps 3,6,7,9,13 – 15, 22, 50, 61, 62, Data coding standards .”
The TRIPOD-LLM reporting guideline for studies using large language models (2025, unknown): “This is in addition to other guidelines that offer complementary guidance on AI development throughout the model life cycle 12–14 .”
CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection (2023, methodology): “Furthermore, we validate several clinically important merits of the CLIP-Driven Universal Model, including compelling efﬁciency, generalizability, transfer-ability, and expansibility, through experimental results.”
Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI (2022, background): “…AI-based diagnostic decision support systems 3 ; (2) an additional literature search about existing guidance for AI evaluation in clinical settings (search strategy available on the OSF 44 ); (3) literature recommended by Steering Group members 19,22,45–49 ; and (4) institutional documents 50–53 .”
AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem? (2020, background): “reach high accuracy, but also can generalize well on data from different sources [8], [9].”
Causal machine learning for predicting treatment outcomes (2024, unknown): “While there are checklists for traditional, predictive ML 96 and for generating real-world evidence 88,97 , future research is needed that adapts such checklists to account for the needs of causal ML in medicine.”