ClinicalTrials.gg
RecruitingNCT07620834Updated Jun 2, 2026

Artificial Intelligence-Guided Diagnosis for High-Risk Osteoporosis Populations: A Pragmatic Randomized Clinical Trial

An interventional study of VeriOsteo OP in Osteoporosis, sponsored by Taichung Veterans General Hospital. Recruiting at 3 sites in Taiwan. Open to participants aged 40 Years to 80 Years, including healthy volunteers. Per ClinicalTrials.gov, last updated 2026-06-02.

Sponsored by Taichung Veterans General Hospital · Not applicable, Interventional, and Diagnostic

How we know

From the registry’s dates

  • Primary completion was expected by Jun 2026, 5 months ago, but the record still lists the study as recruiting.
  • Started Mar 2026; still recruiting 8 months later.

Help build ClinicalTrials.gg — short surveys, remote interviews or testing, in your language. Take part →

Phase
Not applicable
Study type
Interventional
Enrollment
1,180
Allocation
Randomized
Ages
40 Years to 80 Years
Sex
All
01

Where this study stands

Counted across the records on this site · 2026-11-22

Among 56 studies in Osteoporosis with a site in Taiwan — 12 open to participants now, 16 under way, none of them phase 3. Osteoporosis · Taiwan.

Planned enrollment
3rd of 33
1,180 · median 101
Started
2026
with 3 others
No phase
18 of 56
5 open now
Primary completion
2026-06
later than 7 of 15 live
Registered
55th of 56
by date
Lead sponsor
3 of 56
Taichung Veterans General Hospital

Among the 56 studies in Osteoporosis with a site in Taiwan, this one is the 3rd largest by planned enrollment of the 33 interventional ones that give a count, is one of 4 that started in 2026, is one of 18 with no phase, reaches primary completion later than 7 of the 15 other live ones, and was the 55th registered.

Osteoporosis

1,602 studies on the registry are indexed under Osteoporosis; 209 are open to participants now.

Browse Osteoporosis studies →

Open to participants now

12 of the 56 studies in Osteoporosis with a site in Taiwan are open now. Recruiting first, the newest first:

6 more — sign in →

All 12 open studies →

A study can be open while its sites in Taiwan have not opened yet or have stopped. Only those recruiting at a site in Taiwan →

Who these studies take

Of the 133 Osteoporosis studies recruiting now, 77 (58%) set no upper age limit and 20 (15%) stop at 75 or younger; 9 take children under 18; 36 take healthy volunteers.

This study: 40 Years to 80 Years · all sexes · healthy volunteers too.

The full table on the hub →

This tab as a report to print or save as PDF → With an account.

Was this useful?
Get alerts for this landscapeDownload CSVNarrow it in search →With an account: a weekly mail of what changed among 56 studies in Osteoporosis with a site in Taiwan, or all of them as a file.
02

Study 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

    This project will be led by Taichung Veterans General Hospital (TCVGH) as the principal site, with collaboration from Kaohsiung Medical University Chung-Ho Memorial Hospital and Changhua Show Chwan Memorial Hospital. This cross-institutional, cross-regional alliance ensures diverse clinical samples, enhances the representativeness of study results, and allows evaluation of AI medical devices across different healthcare systems and environments.

  2. Clinical Trial Design and Implementation for Smart Medical Devices

    The project will design and execute systematic clinical trials for smart medical devices using methodologies such as randomized controlled trials (RCTs), before-and-after studies, pragmatic RCTs (PCTs), cluster RCTs, and stepped-wedge RCTs. These rigorous designs will ensure scientific validity, reproducibility, and practical feasibility in real-world clinical settings.

  3. Health Economic Evaluation

    A key component of this project is the medical economic assessment, conducted by experienced health economists through cost-effectiveness analysis. The evaluation will focus on how smart medical devices reduce healthcare costs, improve diagnostic efficiency, and enhance treatment outcomes, quantifying their economic value within the NHI system. This evidence will guide policy makers in making data-driven reimbursement decisions.

  4. Standardized Impact Assessment Process

    To ensure high-quality research, the project will establish a comprehensive standardized impact assessment framework covering trial design, data collection, statistical analysis, economic evaluation, and ethical review. This standardized approach not only improves the precision of the study but also accelerates the clinical translation of AI medical devices through streamlined application and review processes.

  5. Research Case Study and Clinical Application

    The featured case study in this project is "VeriOsteo OP® Smart Bone Screening System," which targets early osteoporosis screening among adults aged 40 to 80 years in high-risk groups. This study will evaluate the clinical accuracy of AI-based osteoporosis screening and assess its economic contribution to healthcare cost reduction. The findings will directly inform the Ministry of Health and Welfare's NHI Administration in formulating reimbursement standards for AI medical devices.

  6. Data Sharing and Information Security

    Throughout the project, all research data collection, exchange, and sharing will strictly adhere to cybersecurity and privacy regulations. The AI models involved will undergo validation to ensure the reliability and scientific rigor of the results. Furthermore, the project will promote collaboration between manufacturers and healthcare institutions to support the adoption of smart medical technologies.

  7. Final Outcomes and Future Development

The final deliverables will include a comprehensive evaluation report on the clinical and economic performance of the AI medical device, along with recommendations for NHI reimbursement application. The results will provide a reference model for future AI medical devices entering the reimbursement system and further advance the field of smart healthcare. In the long term, the center aims to expand its research to other disease domains while strengthening data security and ethical oversight to ensure the feasibility and credibility of AI applications in clinical practice.

III. Expected Outcomes and Future Vision

By implementing a multi-center collaborative framework, this project aims to promote clinical adoption and economic evaluation of smart medical devices, offering concrete data to support NHI policy-making. Over time, the project is expected to establish a robust evaluation system for AI medical devices, facilitate broader market adoption, and enhance patient outcomes whi

03

Conditions studied

  • Osteoporosis

Browse trials for

Keywords

  • Software as a Medical Device (SaMD)
  • Clinical Impact Analysis
  • Health Economics
  • Standardization of NHI Reimbursement
04

Who can participate

Ages eligible
40 Years to 80 Years
Sexes eligible
All
Accepts healthy volunteers
Yes

Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.

Inclusion criteria

  • Aged between 40 to 80 years old
  • Identified as high-risk by the Osteoporosis Self-Assessment Tool for Taiwan 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

Exclusion criteria

Exclusion Criteria:

  • Age \< 40 years old
  • Age >80 years old
  • \< 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
Terms in these criteria, in plain language(2)

Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.

Postmenopausal

Periods have stopped for good: usually no period for 12 months in a row without another medical reason, sometimes confirmed by a blood test (FSH).

BMI (body mass index)

Weight in kilograms divided by height in metres squared. Example: 70 kg and 1.75 m gives 70 ÷ (1.75 × 1.75) ≈ 22.9.

What counts as overweight or obesity differs between countries (some use lower cut-offs), so go by the range the study states.

05

Study design

Phase
Not applicable
Primary purpose
Diagnostic
Allocation
Randomized
Intervention model
Parallel assignment
Masking
Single (Participant)
Enrollment
1,180 participants (estimated)

Study arms

  • Experimental
    Intervention Group

    Participants will receive AI-guided diagnosis for osteoporosis risk assessment. This group follows a 2:1 randomization ratio.

    Device: VeriOsteo OP

  • No intervention
    Control Group

    Participants will receive standard-of-care (routine diagnosis) for osteoporosis assessment.

Interventions

  • DeviceVeriOsteo OP

    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.

06

What researchers measure

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.

    Time frame: Up to the end of follow-up (average 18 months)

Secondary outcomes

  1. Incidence of Bone Fractures

    he incidence of bone fractures, including hip fracture, vertebral fracture, wrist fracture, and other fractures. Bone fractures will be identified from the participant interviews and confirmed by International Classification of Diseases (ICD) codes extracted from electronic health records (EHRs) across the three study sites.

    Time frame: Every 6 months up to 18 months

  2. All-Cause Mortality

    The incidence of all-cause death. Participant status will be followed by telephone and verified through electronic health records (EHRs) from the three study sites.

    Time frame: Every 6 months up to 18 months

Other outcomes

  1. Osteoporosis-related healthcare resource utilization

    To analyze the total number of healthcare resource utilizations related to osteoporosis, including the combined counts of outpatient visits, emergency department visits, and hospitalizations. Data will be collected through a structured questionnaire via telephone interview.

    Time frame: 12th month

  2. Osteoporosis-related medical costs

    To evaluate the direct medical costs associated with osteoporosis healthcare resource utilization (expressed in New Taiwan Dollars (TWD ). Data will be collected through a structured questionnaire via telephone interview.

    Time frame: 12th month

07

Study locations

3 of 3 sites recruiting
08

References and documents

Related links

Study documents

PDFs hosted by the registry, ClinicalTrials.gov.

Individual participant data

Plan to share: No — 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.

09

Timeline

Tracking since Sep 25, 2026
ElapsedEstimatedEstimated, not yet reachedSimilar studies: half by the dot; the band is the middle halfHalf of similar studies reached it by the dot; the band is the middle half, from a quarter to three quarters

Started Mar 2026 (actual). Primary completion is estimated for Jun 2026, 3 months after the start.

Of 220 non-industry interventional studies with no phase under Osteoporosis, half reached primary completion within 22 months of starting (the median), counting those still running; a quarter within 8 and three quarters within 49. This study's planned 3 months is below that.

Counting every sponsor, half of 239 studies reached it within 26 months; a quarter within 9 and three quarters within 50.

How these figures are worked out, and which studies are left out of them.

Registered
May 14, 2026
First posted
Jun 2, 2026
StartActual
Mar 13, 2026
Primary completionEst.
Jun 17, 2026
CompletionEst.
Nov 12, 2026
Last update
Jun 2, 2026
What these dates mean
Start.
When the first participant enrolled; while estimated, when the study expects to open to recruitment.
Primary completion.
When the last participant was examined or treated to collect data for the study's main question, its primary outcome. A study that stopped early gives the date its data collection stopped.
Completion.
When the last participant's last visit took place, for every outcome, secondary ones and side effects included: the end of the study. Often later than primary completion, sometimes the same day.
Actual and Est.
Actual means the registry says the date has happened. Est. (estimated) is a date the sponsor plans or expects. It can still move, and the sponsor is expected to change it to actual once it has passed.
No changes since tracking began. The registry record was last updated on Jun 2, 2026, before this site started recording changes on Sep 25, 2026. Its history is on ClinicalTrials.gov ↗
10

Registry details

Key details

Study ID
NCT07620834
Collaborators
Ministry of Health and Welfare, Taiwan
Responsible party
Kun-Hui Chen (Director, Department of Medical Research, Taichung Veterans General Hospital) — Principal investigator
First posted
Jun 2, 2026
Start date
Mar 13, 2026
Primary completion
Jun 17, 2026 (estimated)
Completion
Nov 12, 2026 (estimated)
Last update
Jun 2, 2026

Study contacts

WU WU ZHAN, M.B.A.
Contact
tcvghaicenter@vghtc.gov.tw
04-23592525#3973
Kun Hui Chen, MD
principal investigator · Taichung Veterans General Hospital

Oversight

Data monitoring committee
Yes
FDA-regulated drug
No
FDA-regulated device
No
View the source record on ClinicalTrials.gov ↗

Interested in this study?

Eligibility is decided by the study team. Share this record with your doctor or contact the team directly.

Contact study team

Follow this study

Get an email when the registry record changes — status, dates, results — or when someone posts here.

Sign in to follow

Discussion

Questions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.

Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.

Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.

Start the discussion