Machine learning models predicting risk of revision or secondary knee injury after anterior cruciate ligament reconstruction demonstrate variable discriminatory and accuracy performance: a systematic review
Abstract Background To summarize the statistical performance of machine learning in predicting revision, secondary knee injury, or reoperations following anterior cruciate ligament reconstruction (ACLR), and to provide a general overview of the statistical performance of these models. Methods Three...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Musculoskeletal Disorders |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12891-024-08228-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559908209655808 |
|---|---|
| author | Benjamin Blackman Prushoth Vivekanantha Rafay Mughal Ayoosh Pareek Anthony Bozzo Kristian Samuelsson Darren de SA |
| author_facet | Benjamin Blackman Prushoth Vivekanantha Rafay Mughal Ayoosh Pareek Anthony Bozzo Kristian Samuelsson Darren de SA |
| author_sort | Benjamin Blackman |
| collection | DOAJ |
| description | Abstract Background To summarize the statistical performance of machine learning in predicting revision, secondary knee injury, or reoperations following anterior cruciate ligament reconstruction (ACLR), and to provide a general overview of the statistical performance of these models. Methods Three online databases (PubMed, MEDLINE, EMBASE) were searched from database inception to February 6, 2024, to identify literature on the use of machine learning to predict revision, secondary knee injury (e.g. anterior cruciate ligament (ACL) or meniscus), or reoperation in ACLR. The authors adhered to the PRISMA and R-AMSTAR guidelines as well as the Cochrane Handbook for Systematic Reviews of Interventions. Demographic data and machine learning specifics were recorded. Model performance was recorded using discrimination, area under the curve (AUC), concordance, calibration, and Brier score. Factors deemed predictive for revision, secondary injury or reoperation were also extracted. The MINORS criteria were used for methodological quality assessment. Results Nine studies comprising 125,427 patients with a mean follow-up of 5.82 (0.08–12.3) years were included in this review. Two of nine (22.2%) studies served as external validation analyses. Five (55.6%) studies reported on mean AUC (strongest model range 0.77–0.997). Four (44.4%) studies reported mean concordance (strongest model range: 0.67–0.713). Two studies reported on Brier score, calibration intercept, and calibration slope, with values ranging from 0.10 to 0.18, 0.0051–0.006, and 0.96–0.97 amongst highest performing models, respectively. Four studies reported calibration error, with all four studies demonstrating significant miscalibration at either two or five-year follow-ups amongst 10 of 14 models assessed. Conclusion Machine learning models designed to predict the risk of revision or secondary knee injury demonstrate variable discriminatory performance when evaluated with AUC or concordance metrics. Furthermore, there is variable calibration, with several models demonstrating evidence of miscalibration at two or five-year marks. The lack of external validation of existing models limits the generalizability of these findings. Future research should focus on validating current models in addition to developing new multimodal neural networks to improve accuracy and reliability. |
| format | Article |
| id | doaj-art-b3f15473ac274fc7abf478d15dae5fa7 |
| institution | Kabale University |
| issn | 1471-2474 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Musculoskeletal Disorders |
| spelling | doaj-art-b3f15473ac274fc7abf478d15dae5fa72025-01-05T12:04:55ZengBMCBMC Musculoskeletal Disorders1471-24742025-01-0126111810.1186/s12891-024-08228-wMachine learning models predicting risk of revision or secondary knee injury after anterior cruciate ligament reconstruction demonstrate variable discriminatory and accuracy performance: a systematic reviewBenjamin Blackman0Prushoth Vivekanantha1Rafay Mughal2Ayoosh Pareek3Anthony Bozzo4Kristian Samuelsson5Darren de SA6School of Medicine, University of LimerickDivision of Orthopaedic Surgery, Department of Surgery, McMaster UniversityMichael DeGroote School of Medicine, McMaster UniversityHospital for Special SurgeryMcGill University Health CenterDepartment of Orthopaedics, Institute of Clinical Sciences, Sahlgrenska Academy, University of GothenburgDivision of Orthopaedic Surgery, Department of Surgery, McMaster UniversityAbstract Background To summarize the statistical performance of machine learning in predicting revision, secondary knee injury, or reoperations following anterior cruciate ligament reconstruction (ACLR), and to provide a general overview of the statistical performance of these models. Methods Three online databases (PubMed, MEDLINE, EMBASE) were searched from database inception to February 6, 2024, to identify literature on the use of machine learning to predict revision, secondary knee injury (e.g. anterior cruciate ligament (ACL) or meniscus), or reoperation in ACLR. The authors adhered to the PRISMA and R-AMSTAR guidelines as well as the Cochrane Handbook for Systematic Reviews of Interventions. Demographic data and machine learning specifics were recorded. Model performance was recorded using discrimination, area under the curve (AUC), concordance, calibration, and Brier score. Factors deemed predictive for revision, secondary injury or reoperation were also extracted. The MINORS criteria were used for methodological quality assessment. Results Nine studies comprising 125,427 patients with a mean follow-up of 5.82 (0.08–12.3) years were included in this review. Two of nine (22.2%) studies served as external validation analyses. Five (55.6%) studies reported on mean AUC (strongest model range 0.77–0.997). Four (44.4%) studies reported mean concordance (strongest model range: 0.67–0.713). Two studies reported on Brier score, calibration intercept, and calibration slope, with values ranging from 0.10 to 0.18, 0.0051–0.006, and 0.96–0.97 amongst highest performing models, respectively. Four studies reported calibration error, with all four studies demonstrating significant miscalibration at either two or five-year follow-ups amongst 10 of 14 models assessed. Conclusion Machine learning models designed to predict the risk of revision or secondary knee injury demonstrate variable discriminatory performance when evaluated with AUC or concordance metrics. Furthermore, there is variable calibration, with several models demonstrating evidence of miscalibration at two or five-year marks. The lack of external validation of existing models limits the generalizability of these findings. Future research should focus on validating current models in addition to developing new multimodal neural networks to improve accuracy and reliability.https://doi.org/10.1186/s12891-024-08228-wMachine learningAIAnterior cruciate ligamentRevisionReoperationModeling |
| spellingShingle | Benjamin Blackman Prushoth Vivekanantha Rafay Mughal Ayoosh Pareek Anthony Bozzo Kristian Samuelsson Darren de SA Machine learning models predicting risk of revision or secondary knee injury after anterior cruciate ligament reconstruction demonstrate variable discriminatory and accuracy performance: a systematic review BMC Musculoskeletal Disorders Machine learning AI Anterior cruciate ligament Revision Reoperation Modeling |
| title | Machine learning models predicting risk of revision or secondary knee injury after anterior cruciate ligament reconstruction demonstrate variable discriminatory and accuracy performance: a systematic review |
| title_full | Machine learning models predicting risk of revision or secondary knee injury after anterior cruciate ligament reconstruction demonstrate variable discriminatory and accuracy performance: a systematic review |
| title_fullStr | Machine learning models predicting risk of revision or secondary knee injury after anterior cruciate ligament reconstruction demonstrate variable discriminatory and accuracy performance: a systematic review |
| title_full_unstemmed | Machine learning models predicting risk of revision or secondary knee injury after anterior cruciate ligament reconstruction demonstrate variable discriminatory and accuracy performance: a systematic review |
| title_short | Machine learning models predicting risk of revision or secondary knee injury after anterior cruciate ligament reconstruction demonstrate variable discriminatory and accuracy performance: a systematic review |
| title_sort | machine learning models predicting risk of revision or secondary knee injury after anterior cruciate ligament reconstruction demonstrate variable discriminatory and accuracy performance a systematic review |
| topic | Machine learning AI Anterior cruciate ligament Revision Reoperation Modeling |
| url | https://doi.org/10.1186/s12891-024-08228-w |
| work_keys_str_mv | AT benjaminblackman machinelearningmodelspredictingriskofrevisionorsecondarykneeinjuryafteranteriorcruciateligamentreconstructiondemonstratevariablediscriminatoryandaccuracyperformanceasystematicreview AT prushothvivekanantha machinelearningmodelspredictingriskofrevisionorsecondarykneeinjuryafteranteriorcruciateligamentreconstructiondemonstratevariablediscriminatoryandaccuracyperformanceasystematicreview AT rafaymughal machinelearningmodelspredictingriskofrevisionorsecondarykneeinjuryafteranteriorcruciateligamentreconstructiondemonstratevariablediscriminatoryandaccuracyperformanceasystematicreview AT ayooshpareek machinelearningmodelspredictingriskofrevisionorsecondarykneeinjuryafteranteriorcruciateligamentreconstructiondemonstratevariablediscriminatoryandaccuracyperformanceasystematicreview AT anthonybozzo machinelearningmodelspredictingriskofrevisionorsecondarykneeinjuryafteranteriorcruciateligamentreconstructiondemonstratevariablediscriminatoryandaccuracyperformanceasystematicreview AT kristiansamuelsson machinelearningmodelspredictingriskofrevisionorsecondarykneeinjuryafteranteriorcruciateligamentreconstructiondemonstratevariablediscriminatoryandaccuracyperformanceasystematicreview AT darrendesa machinelearningmodelspredictingriskofrevisionorsecondarykneeinjuryafteranteriorcruciateligamentreconstructiondemonstratevariablediscriminatoryandaccuracyperformanceasystematicreview |