Artificial intelligence in risk prediction and diagnosis of vertebral fractures
Abstract With the increasing prevalence of vertebral fractures, accurate diagnosis and prognostication are essential. This study assesses the effectiveness of AI in diagnosing and predicting vertebral fractures through a systematic review and meta-analysis. A comprehensive search across major databa...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-75628-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850133717917368320 |
|---|---|
| author | Srikar R. Namireddy Saran S. Gill Amaan Peerbhai Abith G. Kamath Daniele S. C. Ramsay Hariharan Subbiah Ponniah Ahmed Salih Dragan Jankovic Darius Kalasauskas Jonathan Neuhoff Andreas Kramer Salvatore Russo Santhosh G. Thavarajasingam |
| author_facet | Srikar R. Namireddy Saran S. Gill Amaan Peerbhai Abith G. Kamath Daniele S. C. Ramsay Hariharan Subbiah Ponniah Ahmed Salih Dragan Jankovic Darius Kalasauskas Jonathan Neuhoff Andreas Kramer Salvatore Russo Santhosh G. Thavarajasingam |
| author_sort | Srikar R. Namireddy |
| collection | DOAJ |
| description | Abstract With the increasing prevalence of vertebral fractures, accurate diagnosis and prognostication are essential. This study assesses the effectiveness of AI in diagnosing and predicting vertebral fractures through a systematic review and meta-analysis. A comprehensive search across major databases selected studies utilizing AI for vertebral fracture diagnosis or prognosis. Out of 14,161 studies initially identified, 79 were included, with 40 undergoing meta-analysis. Diagnostic models were stratified by pathology: non-pathological vertebral fractures, osteoporotic vertebral fractures, and vertebral compression fractures. The primary outcome measure was AUROC. AI showed high accuracy in diagnosing and predicting vertebral fractures: predictive AUROC = 0.82, osteoporotic vertebral fracture diagnosis AUROC = 0.92, non-pathological vertebral fracture diagnosis AUROC = 0.85, and vertebral compression fracture diagnosis AUROC = 0.87, all significant (p < 0.001). Traditional models had the highest median AUROC (0.90) for fracture prediction, while deep learning models excelled in diagnosing all fracture types. High heterogeneity (I² > 99%, p < 0.001) indicated significant variation in model design and performance. AI technologies show considerable promise in improving the diagnosis and prognostication of vertebral fractures, with high accuracy. However, observed heterogeneity and study biases necessitate further research. Future efforts should focus on standardizing AI models and validating them across diverse datasets to ensure clinical utility. |
| format | Article |
| id | doaj-art-daed93ce69b74596821cf8baefb8f7c9 |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-daed93ce69b74596821cf8baefb8f7c92025-08-20T02:31:54ZengNature PortfolioScientific Reports2045-23222024-12-0114111610.1038/s41598-024-75628-2Artificial intelligence in risk prediction and diagnosis of vertebral fracturesSrikar R. Namireddy0Saran S. Gill1Amaan Peerbhai2Abith G. Kamath3Daniele S. C. Ramsay4Hariharan Subbiah Ponniah5Ahmed Salih6Dragan Jankovic7Darius Kalasauskas8Jonathan Neuhoff9Andreas Kramer10Salvatore Russo11Santhosh G. Thavarajasingam12Imperial Brain & Spine Initiative, Imperial College LondonImperial Brain & Spine Initiative, Imperial College LondonImperial Brain & Spine Initiative, Imperial College LondonImperial Brain & Spine Initiative, Imperial College LondonImperial Brain & Spine Initiative, Imperial College LondonImperial Brain & Spine Initiative, Imperial College LondonImperial Brain & Spine Initiative, Imperial College LondonDepartment of Neurosurgery, University Medical Center MainzDepartment of Neurosurgery, University Medical Center MainzCenter for Spinal Surgery and Neurotraumatology, Berufsgenossenschaftliche Unfallklinik Frankfurt am MainDepartment of Neurosurgery, University Medical Center MainzDepartment of Neurosurgery, Imperial College Healthcare NHS TrustImperial Brain & Spine Initiative, Imperial College LondonAbstract With the increasing prevalence of vertebral fractures, accurate diagnosis and prognostication are essential. This study assesses the effectiveness of AI in diagnosing and predicting vertebral fractures through a systematic review and meta-analysis. A comprehensive search across major databases selected studies utilizing AI for vertebral fracture diagnosis or prognosis. Out of 14,161 studies initially identified, 79 were included, with 40 undergoing meta-analysis. Diagnostic models were stratified by pathology: non-pathological vertebral fractures, osteoporotic vertebral fractures, and vertebral compression fractures. The primary outcome measure was AUROC. AI showed high accuracy in diagnosing and predicting vertebral fractures: predictive AUROC = 0.82, osteoporotic vertebral fracture diagnosis AUROC = 0.92, non-pathological vertebral fracture diagnosis AUROC = 0.85, and vertebral compression fracture diagnosis AUROC = 0.87, all significant (p < 0.001). Traditional models had the highest median AUROC (0.90) for fracture prediction, while deep learning models excelled in diagnosing all fracture types. High heterogeneity (I² > 99%, p < 0.001) indicated significant variation in model design and performance. AI technologies show considerable promise in improving the diagnosis and prognostication of vertebral fractures, with high accuracy. However, observed heterogeneity and study biases necessitate further research. Future efforts should focus on standardizing AI models and validating them across diverse datasets to ensure clinical utility.https://doi.org/10.1038/s41598-024-75628-2Artificial intelligenceMachine learningOsteoporotic vertebral fracturesNon-pathological vertebral fracturesVertebral compression fracturesML |
| spellingShingle | Srikar R. Namireddy Saran S. Gill Amaan Peerbhai Abith G. Kamath Daniele S. C. Ramsay Hariharan Subbiah Ponniah Ahmed Salih Dragan Jankovic Darius Kalasauskas Jonathan Neuhoff Andreas Kramer Salvatore Russo Santhosh G. Thavarajasingam Artificial intelligence in risk prediction and diagnosis of vertebral fractures Scientific Reports Artificial intelligence Machine learning Osteoporotic vertebral fractures Non-pathological vertebral fractures Vertebral compression fractures ML |
| title | Artificial intelligence in risk prediction and diagnosis of vertebral fractures |
| title_full | Artificial intelligence in risk prediction and diagnosis of vertebral fractures |
| title_fullStr | Artificial intelligence in risk prediction and diagnosis of vertebral fractures |
| title_full_unstemmed | Artificial intelligence in risk prediction and diagnosis of vertebral fractures |
| title_short | Artificial intelligence in risk prediction and diagnosis of vertebral fractures |
| title_sort | artificial intelligence in risk prediction and diagnosis of vertebral fractures |
| topic | Artificial intelligence Machine learning Osteoporotic vertebral fractures Non-pathological vertebral fractures Vertebral compression fractures ML |
| url | https://doi.org/10.1038/s41598-024-75628-2 |
| work_keys_str_mv | AT srikarrnamireddy artificialintelligenceinriskpredictionanddiagnosisofvertebralfractures AT saransgill artificialintelligenceinriskpredictionanddiagnosisofvertebralfractures AT amaanpeerbhai artificialintelligenceinriskpredictionanddiagnosisofvertebralfractures AT abithgkamath artificialintelligenceinriskpredictionanddiagnosisofvertebralfractures AT danielescramsay artificialintelligenceinriskpredictionanddiagnosisofvertebralfractures AT hariharansubbiahponniah artificialintelligenceinriskpredictionanddiagnosisofvertebralfractures AT ahmedsalih artificialintelligenceinriskpredictionanddiagnosisofvertebralfractures AT draganjankovic artificialintelligenceinriskpredictionanddiagnosisofvertebralfractures AT dariuskalasauskas artificialintelligenceinriskpredictionanddiagnosisofvertebralfractures AT jonathanneuhoff artificialintelligenceinriskpredictionanddiagnosisofvertebralfractures AT andreaskramer artificialintelligenceinriskpredictionanddiagnosisofvertebralfractures AT salvatorerusso artificialintelligenceinriskpredictionanddiagnosisofvertebralfractures AT santhoshgthavarajasingam artificialintelligenceinriskpredictionanddiagnosisofvertebralfractures |