Application of Machine Learning in Measurement of Ageing and Geriatric Diseases: A Systematic Review (76813)

Session Information: Interdisciplinary, Multidisciplinary Research
Session Chair: James W. McNally

Wednesday, 27 March 2024 11:10
Session: Session 2
Room: Room 603
Presentation Type: Oral Presentation

All presentation times are UTC + 9 (Asia/Tokyo)

The prevalence of geriatric diseases is increasing due to an aging population, prompting healthcare providers to explore novel ways of improving elderly individuals' quality of life. Over the last decade, machine learning (ML) has gained prominence in geriatric disease research, offering promise for diagnosis, treatment, and management. Our study seeks to assess the current state of geriatric research and the application of ML. We conducted a systematic review following PRISMA guidelines, focusing on healthy aging in individuals aged 45 and above, emphasizing commonly occurring diseases. We searched PubMed for peer-reviewed articles with a focus on ML methods and older populations. Out of 81 identified papers, we selected 59 after title and abstract screening, along with reference searches. Limited research exists on predicting biological or brain age using deep learning and supervised ML methods. Neurodegenerative disorders, particularly Alzheimer's disease, were extensively studied. Non-communicable diseases such as diabetes, hypertension, cancer, kidney diseases, and cardiovascular diseases were also explored. Some papers investigated rare diseases like oral health-related and bone diseases. Regarding ML applications, risk prediction was prevalent. More than half of the studies utilized supervised ML algorithms, with logistic regression, random forest, and XG Boost being commonly employed. Diverse datasets, including population-based data, hospital records, and social media, were used. A wide range of ML studies analyzing various diseases and datasets in geriatric care are well-explored, still, opportunities for future development remain; these include validating models across diverse populations and leveraging personalized digital datasets for customized, patient-centric care among older populations.

Authors:
Ayushi Das, International Institute for Population Sciences, India
Preeti Dhillon, International Institute for Population Sciences, India


About the Presenter(s)
Ms. Ayushi Das is currently enrolled in a Ph.D. (senior research fellow) at the International Institute for Population Sciences, Mumbai, India.

See this presentation on the full scheduleWednesday Schedule



Conference Comments & Feedback

Place a comment using your LinkedIn profile

Comments

Share on activity feed

Powered by WP LinkPress

Share this Presentation

Posted by Clive Staples Lewis

Last updated: 2023-02-23 23:45:00