Prognostic value of B-score for predicting joint replacement in the context of osteoarthritis phenotypes: Data from the osteoarthritis initiative
Objective: Developing new therapies for knee osteoarthritis (KOA) requires improved prediction of disease progression. This study evaluated the prognostic value of clinical clusters and machine-learning derived quantitative 3D bone shape B-score for predicting total and partial knee replacement (KR)...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-06-01
|
| Series: | Osteoarthritis and Cartilage Open |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2665913124000256 |
| _version_ | 1827250272928268288 |
|---|---|
| author | F. Saxer D. Demanse A. Brett D. Laurent L. Mindeholm P.G. Conaghan M. Schieker |
| author_facet | F. Saxer D. Demanse A. Brett D. Laurent L. Mindeholm P.G. Conaghan M. Schieker |
| author_sort | F. Saxer |
| collection | DOAJ |
| description | Objective: Developing new therapies for knee osteoarthritis (KOA) requires improved prediction of disease progression. This study evaluated the prognostic value of clinical clusters and machine-learning derived quantitative 3D bone shape B-score for predicting total and partial knee replacement (KR). Design: This retrospective study used longitudinal data from the Osteoarthritis Initiative. A previous study used patients' clinical profiles to delineate phenotypic clusters. For these clusters, the distribution of B-scores was assessed (employing Tukey's method). The value of both cluster allocation and B-score for KR-prediction was then evaluated using multivariable Cox regression models and Kaplan-Meier curves for time-to-event analyses. The impact of using B-score vs. cluster was evaluated using a likelihood ratio test for the multivariable Cox model; global performances were assessed by concordance statistics (Harrell's C-index) and time dependent receiver operating characteristic (ROC) curves. Results: B-score differed significantly for the individual clinical clusters (p < 0.001). Overall, 9.4% of participants had a KR over 9 years, with a shorter time to event in clusters with high B-score at baseline. Those clusters were characterized clinically by a high rate of comorbidities and potential signs of inflammation. Both phenotype and B-score independently predicted KR, with better prediction if combined (P < 0.001). B-score added predictive value in groups with less pain and radiographic severity but limited physical activity. Conclusions: B-scores correlated with phenotypes based on clinical patient profiles. B-score and phenotype independently predicted KR surgery, with higher predictive value if combined. This can be used for patient stratification in drug development and potentially risk prediction in clinical practice. |
| first_indexed | 2024-04-25T00:15:29Z |
| format | Article |
| id | doaj.art-17994b58de7b498d90549e144b8f1039 |
| institution | Directory Open Access Journal |
| issn | 2665-9131 |
| language | English |
| last_indexed | 2025-03-22T00:00:54Z |
| publishDate | 2024-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Osteoarthritis and Cartilage Open |
| spelling | doaj.art-17994b58de7b498d90549e144b8f10392024-05-17T04:18:59ZengElsevierOsteoarthritis and Cartilage Open2665-91312024-06-0162100458Prognostic value of B-score for predicting joint replacement in the context of osteoarthritis phenotypes: Data from the osteoarthritis initiativeF. Saxer0D. Demanse1A. Brett2D. Laurent3L. Mindeholm4P.G. Conaghan5M. Schieker6Novartis Biomedical Research, Novartis Campus, 4002, Basel, Switzerland; Medical Faculty, University of Basel, 4002, Basel, SwitzerlandNovartis Pharma AG, 4002, Basel, SwitzerlandImorphics, Worthington House, Towers Business Park, Wilmslow Road, Manchester, M20 2HJ, UKNovartis Biomedical Research, Biomarker Development, 4002, Basel, SwitzerlandNovartis Biomedical Research, Novartis Campus, 4002, Basel, SwitzerlandLeeds Institute of Rheumatic & Musculoskeletal Medicine, University of Leeds and NIHR Leeds Biomedical Research Centre, UKNovartis Biomedical Research, Novartis Campus, 4002, Basel, Switzerland; Medical Faculty, Ludwig-Maximilians-University, Munich, 80336, Germany; Corresponding author. Novartis Institutes for Biomedical Research, Novartis Campus, 4002, Basel, Switzerland.Objective: Developing new therapies for knee osteoarthritis (KOA) requires improved prediction of disease progression. This study evaluated the prognostic value of clinical clusters and machine-learning derived quantitative 3D bone shape B-score for predicting total and partial knee replacement (KR). Design: This retrospective study used longitudinal data from the Osteoarthritis Initiative. A previous study used patients' clinical profiles to delineate phenotypic clusters. For these clusters, the distribution of B-scores was assessed (employing Tukey's method). The value of both cluster allocation and B-score for KR-prediction was then evaluated using multivariable Cox regression models and Kaplan-Meier curves for time-to-event analyses. The impact of using B-score vs. cluster was evaluated using a likelihood ratio test for the multivariable Cox model; global performances were assessed by concordance statistics (Harrell's C-index) and time dependent receiver operating characteristic (ROC) curves. Results: B-score differed significantly for the individual clinical clusters (p < 0.001). Overall, 9.4% of participants had a KR over 9 years, with a shorter time to event in clusters with high B-score at baseline. Those clusters were characterized clinically by a high rate of comorbidities and potential signs of inflammation. Both phenotype and B-score independently predicted KR, with better prediction if combined (P < 0.001). B-score added predictive value in groups with less pain and radiographic severity but limited physical activity. Conclusions: B-scores correlated with phenotypes based on clinical patient profiles. B-score and phenotype independently predicted KR surgery, with higher predictive value if combined. This can be used for patient stratification in drug development and potentially risk prediction in clinical practice.http://www.sciencedirect.com/science/article/pii/S2665913124000256Bone shapeCluster analysisOA imagingPatient stratification |
| spellingShingle | F. Saxer D. Demanse A. Brett D. Laurent L. Mindeholm P.G. Conaghan M. Schieker Prognostic value of B-score for predicting joint replacement in the context of osteoarthritis phenotypes: Data from the osteoarthritis initiative Osteoarthritis and Cartilage Open Bone shape Cluster analysis OA imaging Patient stratification |
| title | Prognostic value of B-score for predicting joint replacement in the context of osteoarthritis phenotypes: Data from the osteoarthritis initiative |
| title_full | Prognostic value of B-score for predicting joint replacement in the context of osteoarthritis phenotypes: Data from the osteoarthritis initiative |
| title_fullStr | Prognostic value of B-score for predicting joint replacement in the context of osteoarthritis phenotypes: Data from the osteoarthritis initiative |
| title_full_unstemmed | Prognostic value of B-score for predicting joint replacement in the context of osteoarthritis phenotypes: Data from the osteoarthritis initiative |
| title_short | Prognostic value of B-score for predicting joint replacement in the context of osteoarthritis phenotypes: Data from the osteoarthritis initiative |
| title_sort | prognostic value of b score for predicting joint replacement in the context of osteoarthritis phenotypes data from the osteoarthritis initiative |
| topic | Bone shape Cluster analysis OA imaging Patient stratification |
| url | http://www.sciencedirect.com/science/article/pii/S2665913124000256 |
| work_keys_str_mv | AT fsaxer prognosticvalueofbscoreforpredictingjointreplacementinthecontextofosteoarthritisphenotypesdatafromtheosteoarthritisinitiative AT ddemanse prognosticvalueofbscoreforpredictingjointreplacementinthecontextofosteoarthritisphenotypesdatafromtheosteoarthritisinitiative AT abrett prognosticvalueofbscoreforpredictingjointreplacementinthecontextofosteoarthritisphenotypesdatafromtheosteoarthritisinitiative AT dlaurent prognosticvalueofbscoreforpredictingjointreplacementinthecontextofosteoarthritisphenotypesdatafromtheosteoarthritisinitiative AT lmindeholm prognosticvalueofbscoreforpredictingjointreplacementinthecontextofosteoarthritisphenotypesdatafromtheosteoarthritisinitiative AT pgconaghan prognosticvalueofbscoreforpredictingjointreplacementinthecontextofosteoarthritisphenotypesdatafromtheosteoarthritisinitiative AT mschieker prognosticvalueofbscoreforpredictingjointreplacementinthecontextofosteoarthritisphenotypesdatafromtheosteoarthritisinitiative |