Deep Medicine: Artificial Intelligence and Clinical Big Data-driven Integration to Develop Precision Medicine of Alzheimer’s Disease

Project Details

Description

Alzheimer’s disease (AD) is an irreversible and progressive degenerative brain disease and accounts for 50% to 60% of the population suffering from dementia. AD still has unmet needs from clinicians to anticipate the increased AD diagnostic and subgrouping accuracy to provide precise drug treatment and accurate prognostic prediction. Big data is an important foundation for developing precision medicine and diagnostic classification via artificial intelligence (AI) technique in AD patients. Kaohsiung Medical University Hospital Database (KMUHRD) provides high quality medical research data and integrated research resource platform based on the related hospitals, including KMU Chung-Ho memorial hospital (medical center), Kaohsiung Municipal Siaogang hospital (regional hospital), and Kaohsiung Municipal Ta-Tong hospital (regional hospital), Kaohsiung Municipal Ci-Jin hospital (domestic hospital). The KMUHRD includes hospital electronic medical record, medical imaging, electronic encephalogram, in-hospital cancer registry, human cell databank, death registry and the air-quality open big data registry, etc. KMU organizes the AD research team to develop the 5 cross-disciplinary subprojects, including: 1) Establishing an integrated platform for AD cohort to develop disease subgrouping and precision medicine. Currently, KMU AD patient’s cohort has accumulated more than 3,000 cases, with mean follow up period up to 5 years; 2) Using AI computing for genome-wide Axiom array to enhance the AD precision medicine, including to apply Taiwan Precision Medicine Initiative (TPMI) near 750,000 single nucleotide polymorphisms (SNP) and the angiotensin-converting enzyme (ACE) and apolipoprotein E-e4 (APOEe4) genotyping to apply pharmacogenomics for AD precision medicine to decrease drug adverse effect and comorbidity complications; 3) Integrating AI computing and brain imaging for AD clinical severity staging and outcome prediction; 4) Implementing Holo-Hilbert Spectral Analysis (HHSA) in electroencephalography for monitoring cerebral functional subgrouping and clinical disease progression of AD. It will establish the sensitive and specific AD encephalogram indicator and explore the AD subgrouping and prognostic prediction; 5) Integrating clinical data warehouse and AI platform to improve AD precision medicine, especially the domestic specific air-pollution environmental monitoring big data will be linked to determine such risk factors and impact on AD prognosis. The cross-disciplinary integration of these 5 subprojects to apply the large-scaled KMUHRD to establish AD big data warehouse, and to cooperate with industrial organization(s) to develop an AI precision medicine clinical decision system to improve the AD diagnostic accuracy, AD subgrouping, and precise AD drug selections, decrease drug adverse effect, improve comorbidity care, illustrate the interaction of genetic and environmental factors on AD. As well, the system is anticipated to offer the monitoring AD clinical progression and the predication for AD prognosis, and finally to improve the quality of life of AD patients.
StatusActive
Effective start/end date1/07/2130/06/22

UN Sustainable Development Goals

In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This project contributes towards the following SDG(s):

  • SDG 3 - Good Health and Well-being
  • SDG 4 - Quality Education
  • SDG 8 - Decent Work and Economic Growth

Keywords

  • Alzheimer’s disease; Clinical big data; AD cohort; Artificial intelligence; Precision medicine; Axiom genome-wide array analysis; Genetic polymorphism; Brain imaging; Holo-Hilbert spectral analysis (HHSA) of electroencephalography; Pharmacogenomics; Environmental monitoring; Clinical decision support system

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.