Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
The aim of this study is to evaluate clinical effectiveness and cost-effectiveness after implementing a medically approved and commercially available AI support system for opportunistic vertebral fracture screening in CT examinations within an adapted fracture care pathway (integrated care process) in clinical routine. Data will be compared to historical data (same period the previous year).
The main question it aims to answer is: Does opportunistic AI-supported vertebral fracture screening in CT examinations integrated to a fracture care pathway increase the numbers of diagnosed vertebral fractures compared to usual care?
CT scans in the clinical routine care will be opportunistically screened for vertebral fractures by the AI for 4 months. All positive findings will be confirmed by a radiologist and triaged by the FLS (Fracture Liaison Service).
Objective: This study aims to compare a 4-month period during which AI support was integrated into the clinical fracture pathway (AI-cohort) with a historical cohort from the same period one year earlier (control-cohort). The prevalence of vertebral fractures on CT scans is expected to remain constant during this period.
The two cohorts include:
Timeframe: Data from the AI-intervention period, spanning 4 months (20 October 2024-19 February 2025), will be analyzed. The same timeframe will be used for the historical cohort from the previous year (2023-2024).
Not provided
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Usual care | The control cohort (usual care), representing routine care, consists of historical data from the corresponding period one year prior to the implementation of AI-based screening. In standard clinical practice, radiologists are expected to report incidental findings, including vertebral fractures. It is then the responsibility of the referring physician to act upon such findings and ensure appropriate follow-up. This includes initiating further investigation and treatment for osteoporosis in accordance with established clinical guidelines. | ||
| AI screening aligned with FLS | In the AI cohort, an algorithm was integrated into the clinical workflow to automatically analyze CT scans of the thoracic and lumbar spine for vertebral fractures as part of opportunistic screening. Positive findings were automatically listed in the radiology PACS and subsequently reviewed and confirmed by dedicated radiologists. Confirmed fractures were referred to the Fracture Liaison Service (FLS), where a coordinator and osteoporosis specialist managed further care. Based on clinical assessment, a referral was issued to primary care, which remained responsible for continued investigation and treatment according to standard regional practice. |
|
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| AI vertebral fracture diagnostics (Flamingo) | Device | The AI (name: Flamingo from Image Biopsy Lab, IBL, Vienna, Austria) screens thoracic and abdominal CT scans for vertebral fractures. |
| Measure | Description | Time Frame |
|---|---|---|
| Vertebral fractures (ICD coded) | Numbers of ICD-coded vertebral fractures within 3 months from the CT scan. | Within 3 months from CT scan |
| Measure | Description | Time Frame |
|---|---|---|
| Reported vertebral fractures (radiology report) | Numbers of patients with vertebral fractures that are mentioned in the radiology report after the CT scan. | Within 2 months after the CT scan |
| DXA screened patients |
| Measure | Description | Time Frame |
|---|---|---|
| Performance of AI | Performance (true positive, false positive, true negative and false negative) of AI detection of vertebral fractures compared to radiologist (ground truth). Only in the cohort "AI screening aligned with FLS" | Baseline |
| Vertebral fractures (radiologist confirmed) |
Inclusion criteria:
Exclusion criteria:
-CT scans using spine-only protocol with exclusively skeletal queries
Not provided
Not provided
Not provided
Patients >= 50 years, undergoing a clinical thoracic or abdominal CT-scan in at Linköping University Hospital
Not provided
| Name | Affiliation | Role |
|---|---|---|
| Anna Spångeus, Ass Prof MD | Linköpings University Hospital | Principal Investigator |
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| Linköping University Hospital | Linköping | Sweden |
| PubMed Identifier | Type | Citation | Retractions |
|---|---|---|---|
| 41805842 | Derived | Woisetschlager M, Baldimtsi E, Lindblom M, Davidson T, Bjerner T, Spangeus A. Clinical implementation of AI for vertebral fracture detection in CT aligned with fracture liaison services: high prevalence of undiagnosed vertebral fractures. Osteoporos Int. 2026 Mar 10. doi: 10.1007/s00198-026-07907-9. Online ahead of print. |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| ID | Term |
|---|---|
| D016103 | Spinal Fractures |
| D010024 | Osteoporosis |
| ID | Term |
|---|---|
| D013124 | Spinal Injuries |
| D019567 | Back Injuries |
| D014947 | Wounds and Injuries |
| D050723 | Fractures, Bone |
Not provided
Not provided
Not provided
Not provided
Not provided
Numbers of patients screened with DXA (osteoporosis investigation) within 1 year after the CT scan.
| Within 12 months after the CT scan |
| Medical treatment (anti-osteoporotic) | Numbers of patients treated with antiosteoporotic drugs 1 year after CT scan. | Within 12 months after the CT scan |
| Cost-effectiveness | Incremental cost per outcome compared to no AI guidance. | Two time frames: Within 12 months after the CT scan and long-term using a decision-analytic model to assess outcome in 10 years |
Numbers of vertebral fractures that are detected by AI and confirmed by radiologist in an opportunistic clinical setting. Only in the cohort "AI screening aligned with FLS". |
| Baseline |
| New or worsened vertebral fractures | Numbers of radiologist verified vertebral fractures that were new (not previously visualised), or worsened since previous CT (minimum 3 months old). Only in the cohort "AI screening aligned with FLS" | Baseline |
| Undiagnosed vertebral fracture | Numbers of old previously visualized vertebral fractures that were previously undiagnosed (ICD-code). Only in the cohort "AI screening aligned with FLS" | Baseline |
| Untreated patients with vertebral fracture | Numbers of patients with vertebral fracture that were untreated at the time of the CT scan. Only in the cohort "AI screening aligned with FLS". | Baseline |
| Patients requiring further action according to clinical triage (FLS) | Numbers of patients with vertebral fracture that needs further action according to the FLS. Only in the cohort "AI screening aligned with FLS". | 1 month |
| D001851 |
| Bone Diseases, Metabolic |
| D001847 | Bone Diseases |
| D009140 | Musculoskeletal Diseases |
| D008659 | Metabolic Diseases |
| D009750 | Nutritional and Metabolic Diseases |