Home // eTELEMED 2023, The Fifteenth International Conference on eHealth, Telemedicine, and Social Medicine // View article
Authors:
Junpei Zhong
Nanxi Dong
Luhua Chen
Kevin K.F. Yuen
Arnold Y.L. Wong
Sam C.C. Chan
Keywords: dementia; comorbidities; clinical data; machine learning
Abstract:
Dementia is a condition characterized by a group of symptoms that affect memory, learning, and cognitive function. It negatively impacts patients' daily functional skills and independence, particularly in the later stages of the disease when comorbidities are often present. With the global aging problem leading to an increasing number of dementia cases, there is a significant burden on healthcare systems worldwide. Despite growing research on risk mitigation, early diagnosis, and intervention of dementia, few studies have focused on the developmental trajectory of the disease. In this study, we utilized the Hospital Authority (HA) Electronic Clinical Record to analyze structured clinical data of dementia patients in Hong Kong. Using mixed methods, we created a population-based case-control cohort to determine the association between dementia and other disease diagnoses based on ICD-10 codes. We identified significant associations with comorbidities in the categories of "Endocrine, nutritional and metabolic diseases" and "Mental, Behavioral and Neurodevelopmental disorders". Further, we plan to employ machine learning models to predict patient comorbidities data and understand the complex short-term and long-term dependencies in dementia progression.
Pages: 6 to 7
Copyright: Copyright (c) IARIA, 2023
Publication date: April 24, 2023
Published in: conference
ISSN: 2308-4359
ISBN: 978-1-68558-080-3
Location: Venice, Italy
Dates: from April 24, 2023 to April 28, 2023