Development and reporting of artificial intelligence in osteoporosis management
Authors' conclusion
The current work highlights disparities in study quality and a lack of standardized reporting practices.
Study context
- Population
- Artificial intelligence (AI) articles relating to osteoporosis, PubMed, December 17, 2020 to February 1, 2023
- Participants
- 97 articles
- Comparison
- Bone properties assessment vs Osteoporosis classification vs Fracture detection/classification vs Risk prediction vs Bone segmentation
- Bone properties assessmentn = 11
- Osteoporosis classificationn = 26
- Fracture detection/classificationn = 25
- Risk predictionn = 24
- Bone segmentationn = 11
- Outcome
- Quality score based on 12 quality items from the minimum information about clinical AI modeling checklist
Methodological detailssystematic quality assessment, 12 quality items from the MI-CLAIM checklist
- Systematic quality assessment
- 12 quality items from the MI-CLAIM checklist
Pooled result
As reported in the abstract
Average quality score
Bone properties assessment
8.9
average · range 7–11
Osteoporosis classification
7.8
average · range 5–11
Fracture detection/classification
8.4
average · range 7–11
Risk prediction
7.6
average · range 4–11
Bone segmentation
9.0
average · range 6–11
Further pooled results
AI-driven clinical decision support
- A sixth area identified studies from the 5 areas aiming to improve clinician efficiency, diagnostic accuracy and patient outcomes via AI-driven models and opportunistic screening
Original publication
Development and reporting of artificial intelligence in osteoporosis management. J Bone Miner Res. Published 20 August 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →