Anna Carobene, Janne Cadamuro, Glynis Frans, Hanoch Goldshmidt, Zeljiko Debeljak, Sander De Bruyne, William van Doorn, Johannes Elias, Habib Özdemir, Salomon Martin Perez, Helena Lame, Alexander Tolios, Federico Cabitza, Andrea Padoan
{"title":"用于评估实验室医学中人工智能/机器学习研究的EFLM核对表:加强用于实验室特定应用的一般医学人工智能框架。","authors":"Anna Carobene, Janne Cadamuro, Glynis Frans, Hanoch Goldshmidt, Zeljiko Debeljak, Sander De Bruyne, William van Doorn, Johannes Elias, Habib Özdemir, Salomon Martin Perez, Helena Lame, Alexander Tolios, Federico Cabitza, Andrea Padoan","doi":"10.1515/cclm-2025-0841","DOIUrl":null,"url":null,"abstract":"<p><p>The integration of artificial intelligence (AI) and machine learning (ML) into laboratory medicine shows promise for advancing diagnostic, prognostic, and decision-support tools; however, routine clinical implementation remains limited and heterogeneous. Laboratory data presents unique methodological and semantic complexities - method dependency, analyte-specific variation, and contextual sensitivity-not adequately addressed by general-purpose AI reporting guidelines. To bridge this gap, the EFLM Committee on Digitalisation and Artificial Intelligence (C-AI) proposes an expanded checklist to support assessment of requirements and recommendations for the development of AI/ML models based on laboratory data. Building upon the widely adopted ChAMAI checklist (Checklist for assessment of medical AI), our proposal introduces six additional items, each grounded in the CRoss Industry Standard Process for Data Mining (CRISP-DM) framework and tailored to the specificities of laboratory workflows. These extensions address: (1) explicit documentation of laboratory data characteristics; (2) consideration of biological and analytical variability; (3) the role of metadata and peridata in contextualizing results; (4) analyte harmonization and standardization practices; (5) rigorous external validation with attention to dataset similarity; and (6) the implementation of FAIR data principles for transparency and reproducibility. Together, these recommendations aim to foster robust, interpretable, and generalizable AI systems that are fit for deployment in clinical laboratory settings. By incorporating these laboratory-aware considerations into model development pipelines, researchers and practitioners can enhance both the scientific rigor and practical applicability of AI tools. We advocate for the adoption of this extended checklist by developers, reviewers, and regulators to promote trustworthy and reproducible AI in laboratory medicine.</p>","PeriodicalId":10390,"journal":{"name":"Clinical chemistry and laboratory medicine","volume":" ","pages":""},"PeriodicalIF":3.7000,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"EFLM checklist for the assessment of AI/ML studies in laboratory medicine: enhancing general medical AI frameworks for laboratory-specific applications.\",\"authors\":\"Anna Carobene, Janne Cadamuro, Glynis Frans, Hanoch Goldshmidt, Zeljiko Debeljak, Sander De Bruyne, William van Doorn, Johannes Elias, Habib Özdemir, Salomon Martin Perez, Helena Lame, Alexander Tolios, Federico Cabitza, Andrea Padoan\",\"doi\":\"10.1515/cclm-2025-0841\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>The integration of artificial intelligence (AI) and machine learning (ML) into laboratory medicine shows promise for advancing diagnostic, prognostic, and decision-support tools; however, routine clinical implementation remains limited and heterogeneous. Laboratory data presents unique methodological and semantic complexities - method dependency, analyte-specific variation, and contextual sensitivity-not adequately addressed by general-purpose AI reporting guidelines. To bridge this gap, the EFLM Committee on Digitalisation and Artificial Intelligence (C-AI) proposes an expanded checklist to support assessment of requirements and recommendations for the development of AI/ML models based on laboratory data. Building upon the widely adopted ChAMAI checklist (Checklist for assessment of medical AI), our proposal introduces six additional items, each grounded in the CRoss Industry Standard Process for Data Mining (CRISP-DM) framework and tailored to the specificities of laboratory workflows. These extensions address: (1) explicit documentation of laboratory data characteristics; (2) consideration of biological and analytical variability; (3) the role of metadata and peridata in contextualizing results; (4) analyte harmonization and standardization practices; (5) rigorous external validation with attention to dataset similarity; and (6) the implementation of FAIR data principles for transparency and reproducibility. Together, these recommendations aim to foster robust, interpretable, and generalizable AI systems that are fit for deployment in clinical laboratory settings. By incorporating these laboratory-aware considerations into model development pipelines, researchers and practitioners can enhance both the scientific rigor and practical applicability of AI tools. We advocate for the adoption of this extended checklist by developers, reviewers, and regulators to promote trustworthy and reproducible AI in laboratory medicine.</p>\",\"PeriodicalId\":10390,\"journal\":{\"name\":\"Clinical chemistry and laboratory medicine\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":3.7000,\"publicationDate\":\"2025-09-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Clinical chemistry and laboratory medicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1515/cclm-2025-0841\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MEDICAL LABORATORY TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical chemistry and laboratory medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1515/cclm-2025-0841","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MEDICAL LABORATORY TECHNOLOGY","Score":null,"Total":0}
EFLM checklist for the assessment of AI/ML studies in laboratory medicine: enhancing general medical AI frameworks for laboratory-specific applications.
The integration of artificial intelligence (AI) and machine learning (ML) into laboratory medicine shows promise for advancing diagnostic, prognostic, and decision-support tools; however, routine clinical implementation remains limited and heterogeneous. Laboratory data presents unique methodological and semantic complexities - method dependency, analyte-specific variation, and contextual sensitivity-not adequately addressed by general-purpose AI reporting guidelines. To bridge this gap, the EFLM Committee on Digitalisation and Artificial Intelligence (C-AI) proposes an expanded checklist to support assessment of requirements and recommendations for the development of AI/ML models based on laboratory data. Building upon the widely adopted ChAMAI checklist (Checklist for assessment of medical AI), our proposal introduces six additional items, each grounded in the CRoss Industry Standard Process for Data Mining (CRISP-DM) framework and tailored to the specificities of laboratory workflows. These extensions address: (1) explicit documentation of laboratory data characteristics; (2) consideration of biological and analytical variability; (3) the role of metadata and peridata in contextualizing results; (4) analyte harmonization and standardization practices; (5) rigorous external validation with attention to dataset similarity; and (6) the implementation of FAIR data principles for transparency and reproducibility. Together, these recommendations aim to foster robust, interpretable, and generalizable AI systems that are fit for deployment in clinical laboratory settings. By incorporating these laboratory-aware considerations into model development pipelines, researchers and practitioners can enhance both the scientific rigor and practical applicability of AI tools. We advocate for the adoption of this extended checklist by developers, reviewers, and regulators to promote trustworthy and reproducible AI in laboratory medicine.
期刊介绍:
Clinical Chemistry and Laboratory Medicine (CCLM) publishes articles on novel teaching and training methods applicable to laboratory medicine. CCLM welcomes contributions on the progress in fundamental and applied research and cutting-edge clinical laboratory medicine. It is one of the leading journals in the field, with an impact factor over 3. CCLM is issued monthly, and it is published in print and electronically.
CCLM is the official journal of the European Federation of Clinical Chemistry and Laboratory Medicine (EFLM) and publishes regularly EFLM recommendations and news. CCLM is the official journal of the National Societies from Austria (ÖGLMKC); Belgium (RBSLM); Germany (DGKL); Hungary (MLDT); Ireland (ACBI); Italy (SIBioC); Portugal (SPML); and Slovenia (SZKK); and it is affiliated to AACB (Australia) and SFBC (France).
Topics:
- clinical biochemistry
- clinical genomics and molecular biology
- clinical haematology and coagulation
- clinical immunology and autoimmunity
- clinical microbiology
- drug monitoring and analysis
- evaluation of diagnostic biomarkers
- disease-oriented topics (cardiovascular disease, cancer diagnostics, diabetes)
- new reagents, instrumentation and technologies
- new methodologies
- reference materials and methods
- reference values and decision limits
- quality and safety in laboratory medicine
- translational laboratory medicine
- clinical metrology
Follow @cclm_degruyter on Twitter!