Dataset Information

Understanding machine learning applications in dementia research and clinical practice: a review for biomedical scientists and clinicians.

ABSTRACT: Several (inter)national longitudinal dementia observational datasets encompassing demographic information, neuroimaging, biomarkers, neuropsychological evaluations, and muti-omics data, have ushered in a new era of potential for integrating machine learning (ML) into dementia research and clinical practice. ML, with its proficiency in handling multi-modal and high-dimensional data, has emerged as an innovative technique to facilitate early diagnosis, differential diagnosis, and to predict onset and progression of mild cognitive impairment and dementia. In this review, we evaluate current and potential applications of ML, including its history in dementia research, how it compares to traditional statistics, the types of datasets it uses and the general workflow. Moreover, we identify the technical barriers and challenges of ML implementations in clinical practice. Overall, this review provides a comprehensive understanding of ML with non-technical explanations for broader accessibility to biomedical scientists and clinicians.

SUBMITTER: Wang Y

PROVIDER: S-EPMC11293066 | biostudies-literature | 2024 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Understanding machine learning applications in dementia research and clinical practice: a review for biomedical scientists and clinicians.

Wang Yihan Y Liu Shu S Spiteri Alanna G AG Huynh Andrew Liem Hieu ALH Chu Chenyin C Masters Colin L CL Goudey Benjamin B Pan Yijun Y Jin Liang L

Alzheimer's research & therapy 20240801 1

Several (inter)national longitudinal dementia observational datasets encompassing demographic information, neuroimaging, biomarkers, neuropsychological evaluations, and muti-omics data, have ushered in a new era of potential for integrating machine learning (ML) into dementia research and clinical practice. ML, with its proficiency in handling multi-modal and high-dimensional data, has emerged as an innovative technique to facilitate early diagnosis, differential diagnosis, and to predict onset ...[more]

PMID: 39085973

Similar Datasets

Project description:IntroductionThe Biomedical Scientist (BMS) role is established in healthcare, working in laboratory environments to provide diagnostic testing and to monitor treatment effects on a patients' health. The profession is subject to several professional standards which highlight the importance of working in the best interests of the patient and service user. However, Biomedical Scientists have little or no patient contact. This study aimed to determine how Biomedical Scientists evidence that they meet the professional standards and support the achievement of patient outcomes.Materials and methodsThis study utilised a Delphi method to explore the opinions of professional stakeholders to determine whether there was consensus for how this professional group contributes to patient outcomes and offers evidence that they are working in the best interests of the patient. The qualitative 1st round of the study consisted of focus groups and interviews with staff and students on the BSc Biomedical Science awards, Professional, Statutory and Regulatory body (PSRB) representatives and Biomedical Scientists from the National Health Service (NHS). The first-round responses were analysed using thematic analysis which then generated attitude statements which participants scored using a 5-point Likert scale in the 2nd round. Consensus or divergence of opinion was determined based upon a 70% consensus level within each participant group and overall.ResultsFollowing analysis of the 2nd round data, there was divergence of opinion across all stakeholders, with consensus rates being highest in the Biomedical Scientist group (72.7% of statements reached 70% consensus), followed by the student group (54.5% of statements reached 70% consensus) and lowest in the academic group (40.9% of statements reached 70% consensus).DiscussionThis demonstrates a theory-practice gap in both the academic and student groups, suggesting that graduates are insufficiently prepared for their post-graduate role. This gap was particularly evident when discussing topics such as how Biomedical Scientists contribute to patient care, professional registration and working as part of the multi-disciplinary team (MDT). The identification of a theory-practice gap in the education of Biomedical Scientists is a novel finding, indicating that students may graduate with insufficient understanding of the Biomedical Scientist role.

Dataset Information

Understanding machine learning applications in dementia research and clinical practice: a review for biomedical scientists and clinicians.

Publications

Understanding machine learning applications in dementia research and clinical practice: a review for biomedical scientists and clinicians.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets