Process of Medical Dataset Construction for Machine Learning - Multifield Study and Guidelines

Cychnerski, Jan; Dziubich, Tomasz

doi:10.1007/978-3-030-85082-1_20

Cited by 1 publication

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on 5 projects in different medical fields, a guideline article iteratively optimized the procedures for constructing data sets, and developed a set of guidelines and good practices that should be followed when constructing new medical data sets [47]. To improve population health information, another guideline article developed a structured interdisciplinary method for the study of population health indicators using health data and machine learning technology [48].…”

Section: Classification 4: Ai Data Applicationmentioning

confidence: 99%

“…All but 8 articles [33,[43][44][45]47,49,51,54] provided extensive information about the individuals engaged in the production of the guidelines or consensus statements, including their names, field of expertise, institution, and geographic location. All but 7 articles [22,[27][28][29]31,34,53] did not include patient values and preferences in their creation.…”

Section: Stakeholder Involvementmentioning

confidence: 99%

“…In most cases, the intended users were explicitly defined, with medical specialists and different types of health care practitioners included. Regarding target users, some of the articles were ambiguous [19,47,49,51,54].…”

Section: Stakeholder Involvementmentioning

confidence: 99%

“…Six guideline articles [21,22,28,29,34,48] that provided extensive systematic search methodologies also included detailed criteria for evidence selection. Except for 20 articles [23,30,[32][33][34][35]37,38,[43][44][45][46][47][48][49][50][51][52][53][54], the strengths and limitations of evidence were acknowledged in the other included studies. All articles, except for 5 [30,35,49,51,52], fully detailed the approach for creating recommendations.…”

Section: Rigor Of Developmentmentioning

confidence: 99%

“…Twenty-seven articles [19][20][21][22][23][24][25][26][27][28][29]31,[33][34][35][36][37][38][39][40][41][42][46][47][48][50][51][52][53] took into account the potential resource consequences of implementing the recommendations. Twenty-two articles [19,22,23,[27][28][29]32,33,35,38,39,[42][43][44][45][46][47][48][49][50][51][52][53]…”

Section: Applicabilitymentioning

confidence: 99%

See 4 more Smart Citations

Guidelines, Consensus Statements, and Standards for the Use of Artificial Intelligence in Medicine: Systematic Review

Wang,

Li,

Chen

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

Background The application of artificial intelligence (AI) in the delivery of health care is a promising area, and guidelines, consensus statements, and standards on AI regarding various topics have been developed. Objective We performed this study to assess the quality of guidelines, consensus statements, and standards in the field of AI for medicine and to provide a foundation for recommendations about the future development of AI guidelines. Methods We searched 7 electronic databases from database establishment to April 6, 2022, and screened articles involving AI guidelines, consensus statements, and standards for eligibility. The AGREE II (Appraisal of Guidelines for Research & Evaluation II) and RIGHT (Reporting Items for Practice Guidelines in Healthcare) tools were used to assess the methodological and reporting quality of the included articles. Results This systematic review included 19 guideline articles, 14 consensus statement articles, and 3 standard articles published between 2019 and 2022. Their content involved disease screening, diagnosis, and treatment; AI intervention trial reporting; AI imaging development and collaboration; AI data application; and AI ethics governance and applications. Our quality assessment revealed that the average overall AGREE II score was 4.0 (range 2.2-5.5; 7-point Likert scale) and the mean overall reporting rate of the RIGHT tool was 49.4% (range 25.7%-77.1%). Conclusions The results indicated important differences in the quality of different AI guidelines, consensus statements, and standards. We made recommendations for improving their methodological and reporting quality. Trial Registration PROSPERO International Prospective Register of Systematic Reviews (CRD42022321360); https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=321360

show abstract

Section: Classification 4: Ai Data Applicationmentioning

confidence: 99%