Artificial Intelligence-Guided Diagnosis for High-Risk Osteoporosis Populations: A Pragmatic Randomized Clinical Trial
1 other identifier
interventional
1,180
1 country
3
Brief Summary
Project Summary I. Project Objectives With the rapid advancement of medical technology, smart medical devices have become one of the key components of modern healthcare. However, integrating these emerging technologies into the national health insurance (NHI) reimbursement system while ensuring their clinical value and economic benefits remains a major challenge worldwide. The primary goal of this project is to assist commercialized smart medical device products-those that have passed TFDA review and seek NHI reimbursement-in conducting comprehensive evaluations of their clinical effectiveness and medical economic impact. Through scientific data and standardized impact assessment procedures, the project aims to provide localized evidence to support reimbursement policy decisions and facilitate the market adoption of smart medical technologies. Ultimately, this project seeks to balance therapeutic efficacy and cost control, offering a scientific foundation for NHI decision-making and paving the way for the sustainable development of AI-driven healthcare innovations. II. Implementation Methods
- 1.Multi-center Collaborative Network
- 2.Clinical Trial Design and Implementation for Smart Medical Devices
- 3.Health Economic Evaluation
- 4.Standardized Impact Assessment Process
- 5.Research Case Study and Clinical Application
- 6.Data Sharing and Information Security
- 7.Final Outcomes and Future Development
Trial Health
Trial Health Score
Automated assessment based on enrollment pace, timeline, and geographic reach
participants targeted
Target at P75+ for not_applicable
Started Mar 2026
Shorter than P25 for not_applicable
3 active sites
Health score is calculated from publicly available data and should be used for screening purposes only.
Trial Relationships
Click on a node to explore related trials.
Study Timeline
Key milestones and dates
Study Start
First participant enrolled
March 13, 2026
CompletedFirst Submitted
Initial submission to the registry
May 14, 2026
CompletedFirst Posted
Study publicly available on registry
June 2, 2026
CompletedPrimary Completion
Last participant's last visit for primary outcome
June 17, 2026
ExpectedStudy Completion
Last participant's last visit for all outcomes
November 12, 2026
June 2, 2026
May 1, 2026
3 months
May 14, 2026
May 27, 2026
Conditions
Keywords
Outcome Measures
Primary Outcomes (1)
The primary objective is to evaluate the clinical effectiveness in terms of the improvement of BMD, of AI-guided diagnosis (VeriOsteo OP)
The primary endpoint of this study is the change in Bone Mineral Density (BMD) expressed as a T-score, measured by Dual-energy X-ray Absorptiometry (DXA). The T-score is a standardized metric comparing bone density to a healthy young adult. While there is no theoretical absolute minimum or maximum value, typical clinical values range from -5.0 to +2.0. According to the International Osteoporosis Foundation (IOF) and Taiwan 2020 guidelines, a T-score of -1.0 or higher is normal, between -1.0 and -2.5 indicates osteopenia, and a T-score of -2.5 or lower (≤ -2.5) indicates osteoporosis. Therefore, a higher (more positive) T-score represents a better outcome (higher bone density). To avoid inflating the detection rate for osteoporosis based on the protocolized DXA at baseline in the intervention arm, a positive AI screen was required to be present to count the chest X-ray findings for the purpose of the primary end point.
Up to the end of follow-up (average 18 months)
Secondary Outcomes (2)
Incidence of Bone Fractures
Every 6 months up to 18 months
All-Cause Mortality
Every 6 months up to 18 months
Other Outcomes (2)
Osteoporosis-related healthcare resource utilization
12th month
Osteoporosis-related medical costs
12th month
Study Arms (2)
Intervention Group
EXPERIMENTALParticipants will receive AI-guided diagnosis for osteoporosis risk assessment. This group follows a 2:1 randomization ratio.
Control Group
NO INTERVENTIONParticipants will receive standard-of-care (routine diagnosis) for osteoporosis assessment.
Interventions
Participants in the intervention group undergo VeriOsteo OP AI assessment followed by DXA confirmation. The AI system generates a diagnostic report identifying individuals at high risk for osteoporosis. Results are used to guide clinical decision-making and evaluate the diagnostic consistency between the AI-guided system and the gold-standard DXA assessment.
Eligibility Criteria
You may qualify if:
- Aged between 40 to 80 years old
- Identified as high-risk by the Osteoporosis Self-Assessment Tool for Taiwan Postmenopausal Women (OSTAi) \<-1 or Male Osteoporosis Self-Assessment Tool for Taiwan (MOSTAi) ≦11 based on the individual's age and weight (kg)
- Had chest x-ray within one year
You may not qualify if:
- Age \< 40 years old
- Age \>80 years old
- BMI\< 18 kg/m2or \>30 kg/m2
- Pregnant in prior one year
- Recorded diagnosis of osteoporosis within the past two years
- History of prior DXA imaging (prior quantification of BMD) within 2 years
- History of metabolic bone disease
Contact the study team to confirm eligibility.
Sponsors & Collaborators
Study Sites (3)
Show Chwan Memorial Hospital
Changhua, Taiwan
Kaohsiung Medical University Chung-Ho Memorial Hospital
Kaohsiung City, Taiwan
Taichung Veterans General Hospital
Taichung, Taiwan
Related Links
MeSH Terms
Conditions
Condition Hierarchy (Ancestors)
Study Officials
- PRINCIPAL INVESTIGATOR
Kun Hui Chen, MD
Taichung Veterans General Hospital
Central Study Contacts
Study Design
- Study Type
- interventional
- Phase
- not applicable
- Allocation
- RANDOMIZED
- Masking
- SINGLE
- Who Masked
- PARTICIPANT
- Purpose
- DIAGNOSTIC
- Intervention Model
- PARALLEL
- Sponsor Type
- OTHER
- Responsible Party
- PRINCIPAL INVESTIGATOR
- PI Title
- Director, Department of Medical Research
Study Record Dates
First Submitted
May 14, 2026
First Posted
June 2, 2026
Study Start
March 13, 2026
Primary Completion (Estimated)
June 17, 2026
Study Completion (Estimated)
November 12, 2026
Last Updated
June 2, 2026
Record last verified: 2026-05
Data Sharing
- IPD Sharing
- Will not share
As this is a multi-center study, the sharing of individual participant data (IPD) would require joint approval from the Institutional Review Boards (IRBs) of all three participating hospitals. Given the complex regulatory procedures and strict privacy protocols involved, the data will not be made publicly available at this time.