Adult Disease Risk Prediction Using Wearables, Hearing, and Health Data

NCT07541547 | Recruiting

• 1 other identifier: EC1140910
• Study Type: observational
• Target: 1,500
• Locations: 1 country
• Sites: 1

Brief Summary

This prospective cohort study aims to develop and validate a personalized disease risk prediction model for adults by integrating multiple sources of health data. The study will recruit community-dwelling adults aged 18 years and older in Taiwan. After providing informed consent, participants will complete a structured questionnaire, undergo pure tone hearing testing, and wear a smartwatch for 2 weeks to collect continuous physiological data, including heart rate and physical activity. With participant authorization, the study will also collect data from personal health records and national health insurance databases to allow longer-term follow-up of health outcomes. The main goals of the study are to examine the relationships among hearing, lifestyle factors, and wearable device data; to identify combinations of risk factors associated with progression from health to subclinical or chronic disease states; and to develop analytical methods for integrating heterogeneous health data from questionnaires, physiological monitoring, hearing tests, and medical databases. Machine learning methods will be used to identify important predictors and build risk prediction models. The study hypothesis is that combining hearing measures, lifestyle information, wearable physiological data, and longitudinal medical record data will improve the ability to identify individuals at higher risk of future disease compared with using a single source of information alone. The long-term objective is to support early risk identification, personalized health management, and prevention strategies in community adults.

Conditions

Chronic Disease; Risk Assessment

Keywords

Wearable Devices; Risk Assessment; Chronic Disease; Disease Prediction; Machine Learning; Cohort Studies; Physiological Monitoring; Personal Health Records; Health Insurance Claims

Outcome Measures

Primary Outcomes (1)

• Performance of Personalized Disease Risk Prediction Models

  Model performance will be evaluated for personalized disease risk prediction models developed using integrated questionnaire, hearing, wearable device, personal health record, and national health insurance data. Performance metrics will include area under the receiver operating characteristic curve (AUC-ROC), accuracy, and related validation measures in training and test datasets.

  At the completion of data collection and model validation, including baseline assessment and 2-week wearable monitoring

Study Arms (1)

Community-Dwelling Adults

Adults aged 18 years and older recruited from community settings in Taiwan. Participants will complete a structured questionnaire, undergo hearing assessment, wear a smartwatch for 2 weeks, and authorize collection of personal health records and linked national health insurance data for health outcome follow-up.

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Community-dwelling adults aged 18 years and older in Taiwan will be recruited from community settings, including community care stations, public health centers, activity centers, lifelong learning centers for older adults, and collaborating local organizations. Public recruitment may also be conducted through online platforms and social media. Recruitment will be carried out across multiple geographic regions in Taiwan to include participants from both urban and rural communities.

You may qualify if:

• Adults aged 18 years and older
• Living in the community in Taiwan
• Able to understand the study procedures and provide written informed consent
• Able and willing to complete the study questionnaire, hearing assessment, and wearable device monitoring procedures
• Has access to a smartphone and is able to install and use the study-related application, with assistance from study staff if needed

You may not qualify if:

• Diagnosis of dementia
• Too frail or has other health conditions that make participation in the study procedures not feasible
• Bilateral deafness without use of any hearing assistive device
• Does not have a smartphone or is unable to use a smartphone application required for the study procedures

Sponsors & Collaborators

• National Health Research Institutes, Taiwan: lead

Study Sites (1)

National Health Research Institutes

Zhunan, Miaoli, 350, Taiwan

RECRUITING

MeSH Terms

Conditions

Chronic Disease

Condition Hierarchy (Ancestors)

Disease Attributes; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Central Study Contacts

Ren-Hua Chung, PhD

CONTACT

886-37206166; rchung@nhri.edu.tw

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Target Duration: 2 Weeks
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: April 13, 2026
• First Posted: April 21, 2026
• Study Start: January 9, 2026
• Primary Completion (Estimated): January 1, 2029
• Study Completion (Estimated): January 1, 2029
• Last Updated: April 21, 2026

Record last verified: 2026-04

Data Sharing

• IPD Sharing: Will not share

Locations

TW (1)