Ignite Creation Date:
2025-12-24 @ 11:45 PM
Ignite Modification Date:
2025-12-25 @ 9:37 PM
Study NCT ID:
NCT06740851
Status:
ACTIVE_NOT_RECRUITING
Last Update Posted:
2024-12-20
First Post:
2024-12-13
Is NOT Gene Therapy:
False
Has Adverse Events:
False
Brief Title:
Predictive Model for 1-Year Pain and Function Outcomes After Thumb Joint Surgery in Osteoarthritic Patients
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}, 'conditionBrowseModule': {'meshes': [{'id': 'D010003', 'term': 'Osteoarthritis'}, {'id': 'D010146', 'term': 'Pain'}], 'ancestors': [{'id': 'D001168', 'term': 'Arthritis'}, {'id': 'D007592', 'term': 'Joint Diseases'}, {'id': 'D009140', 'term': 'Musculoskeletal Diseases'}, {'id': 'D012216', 'term': 'Rheumatic Diseases'}, {'id': 'D009461', 'term': 'Neurologic Manifestations'}, {'id': 'D012816', 'term': 'Signs and Symptoms'}, {'id': 'D013568', 'term': 'Pathological Conditions, Signs and Symptoms'}]}, 'interventionBrowseModule': {'meshes': [{'id': 'D014110', 'term': 'Touch'}], 'ancestors': [{'id': 'D012677', 'term': 'Sensation'}, {'id': 'D009424', 'term': 'Nervous System Physiological Phenomena'}, {'id': 'D055687', 'term': 'Musculoskeletal and Neural Physiological Phenomena'}]}}, 'protocolSection': {'designModule': {'studyType': 'OBSERVATIONAL', 'designInfo': {'timePerspective': 'PROSPECTIVE', 'observationalModel': 'COHORT'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 330}, 'targetDuration': '1 Year', 'patientRegistry': True}, 'statusModule': {'overallStatus': 'ACTIVE_NOT_RECRUITING', 'startDateStruct': {'date': '2022-02-08', 'type': 'ACTUAL'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2024-12', 'completionDateStruct': {'date': '2025-02-28', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2024-12-18', 'studyFirstSubmitDate': '2024-12-13', 'studyFirstSubmitQcDate': '2024-12-13', 'lastUpdatePostDateStruct': {'date': '2024-12-20', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2024-12-18', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2025-02-28', 'type': 'ESTIMATED'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'Pain During Activities at 1-Year Post-Surgery', 'timeFrame': '1 year after surgery', 'description': 'Pain during activities will be measured using a Numeric Rating Scale (NRS) ranging from 0 (no pain) to 10 (maximum pain). Participants rate the level of pain experienced during typical daily activities.'}, {'measure': 'Hand Function at 1-Year Post-Surgery', 'timeFrame': '1 year after surgery', 'description': 'Hand function will be assessed using the brief Michigan Hand Outcomes Questionnaire (bMHQ), which evaluates hand performance in various activities. Scores range from 0 to 100, with higher scores indicating better function.'}]}, 'oversightModule': {'isUsExport': False, 'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['prediction', 'xgboost', 'thumb arthroplasty', 'osteoarthritis', 'pain', 'function'], 'conditions': ['Osteoarthritis', 'Thumb Arthritis', 'Arthroplasty of the MCP Joint']}, 'referencesModule': {'references': [{'pmid': '35415551', 'type': 'BACKGROUND', 'citation': 'Hamasaki T, Harris PG, Bureau NJ, Gaudreault N, Ziegler D, Choiniere M. Efficacy of Surgical Interventions for Trapeziometacarpal (Thumb Base) Osteoarthritis: A Systematic Review. J Hand Surg Glob Online. 2021 Mar 23;3(3):139-148. doi: 10.1016/j.jhsg.2021.02.003. eCollection 2021 May.'}, {'pmid': '21193136', 'type': 'BACKGROUND', 'citation': 'Vermeulen GM, Slijper H, Feitz R, Hovius SE, Moojen TM, Selles RW. Surgical management of primary thumb carpometacarpal osteoarthritis: a systematic review. J Hand Surg Am. 2011 Jan;36(1):157-69. doi: 10.1016/j.jhsa.2010.10.028.'}, {'pmid': '36855785', 'type': 'BACKGROUND', 'citation': 'Falkner F, Tumkaya AM, Thomas B, Panzram B, Bickert B, Harhaus L. Dual mobility prosthesis for trapeziometacarpal osteoarthritis: results from a prospective study of 55 prostheses. J Hand Surg Eur Vol. 2023 Jun;48(6):566-574. doi: 10.1177/17531934231156280. Epub 2023 Feb 28.'}, {'pmid': '37310049', 'type': 'BACKGROUND', 'citation': 'Herren DB, Marks M, Neumeister S, Schindele S. Low complication rate and high implant survival at 2 years after Touch(R) trapeziometacarpal joint arthroplasty. J Hand Surg Eur Vol. 2023 Oct;48(9):877-883. doi: 10.1177/17531934231179581. Epub 2023 Jun 13.'}, {'pmid': '25559974', 'type': 'BACKGROUND', 'citation': 'Bertozzi L, Valdes K, Vanti C, Negrini S, Pillastrini P, Villafane JH. Investigation of the effect of conservative interventions in thumb carpometacarpal osteoarthritis: systematic review and meta-analysis. Disabil Rehabil. 2015;37(22):2025-43. doi: 10.3109/09638288.2014.996299. Epub 2015 Jan 5.'}, {'pmid': '37903291', 'type': 'BACKGROUND', 'citation': 'Esteban Lopez LMJ, Hoogendam L, Vermeulen GM, Tsehaie J, Slijper HP, Selles RW, Wouters RM; The Hand-Wrist Study Group. Long-Term Outcomes of Nonsurgical Treatment of Thumb Carpometacarpal Osteoarthritis: A Cohort Study. J Bone Joint Surg Am. 2023 Dec 6;105(23):1837-1845. doi: 10.2106/JBJS.22.01116. Epub 2023 Oct 30.'}, {'pmid': '20124359', 'type': 'BACKGROUND', 'citation': 'Bijsterbosch J, Visser W, Kroon HM, Stamm T, Meulenbelt I, Huizinga TW, Kloppenburg M. Thumb base involvement in symptomatic hand osteoarthritis is associated with more pain and functional disability. Ann Rheum Dis. 2010 Mar;69(3):585-7. doi: 10.1136/ard.2009.104562. Epub 2010 Feb 2.'}, {'pmid': '20807622', 'type': 'BACKGROUND', 'citation': 'Gehrmann SV, Tang J, Li ZM, Goitz RJ, Windolf J, Kaufmann RA. Motion deficit of the thumb in CMC joint arthritis. J Hand Surg Am. 2010 Sep;35(9):1449-53. doi: 10.1016/j.jhsa.2010.05.026.'}, {'pmid': '25626796', 'type': 'BACKGROUND', 'citation': 'Bakri K, Moran SL. Thumb carpometacarpal arthritis. Plast Reconstr Surg. 2015 Feb;135(2):508-520. doi: 10.1097/PRS.0000000000000916.'}, {'pmid': '33744429', 'type': 'BACKGROUND', 'citation': 'van der Oest MJW, Duraku LS, Andrinopoulou ER, Wouters RM, Bierma-Zeinstra SMA, Selles RW, Zuidam JM. The prevalence of radiographic thumb base osteoarthritis: a meta-analysis. Osteoarthritis Cartilage. 2021 Jun;29(6):785-792. doi: 10.1016/j.joca.2021.03.004. Epub 2021 Mar 17.'}, {'pmid': '21622766', 'type': 'BACKGROUND', 'citation': 'Haugen IK, Englund M, Aliabadi P, Niu J, Clancy M, Kvien TK, Felson DT. Prevalence, incidence and progression of hand osteoarthritis in the general population: the Framingham Osteoarthritis Study. Ann Rheum Dis. 2011 Sep;70(9):1581-6. doi: 10.1136/ard.2011.150078. Epub 2011 May 27.'}, {'pmid': '30509411', 'type': 'BACKGROUND', 'citation': 'Kloppenburg M, van Beest S, Kroon FPB. Thumb base osteoarthritis: A hand osteoarthritis subset requiring a distinct approach. Best Pract Res Clin Rheumatol. 2017 Oct;31(5):649-660. doi: 10.1016/j.berh.2018.08.007. Epub 2018 Sep 26.'}]}, 'descriptionModule': {'briefSummary': 'This study aims to develop a predictive model to help doctors better understand expected outcomes one year after thumb joint surgery for osteoarthritis. By analyzing clinical and patient-reported data from individuals who underwent surgery with the Touch® implant, the study seeks to predict pain levels and hand function 1-year after surgery. This information can support shared decision-making, set realistic expectations, and improve personalized treatment planning.', 'detailedDescription': "This study aims to develop and validate predictive models for assessing pain and hand function outcomes one year after trapeziometacarpal joint (TMJ) arthroplasty using the Touch® prosthesis. The study leverages a single-center prospective registry from a specialized orthopedic hospital in Zurich, Switzerland.\n\nAnalytical methods:\n\nThe investigators will use the following modeling approach to determine the best predictive value for the 1-year outcome of pain. The model chosen is:\n\n\\- Extreme Gradient Boosting (XGBoost): A non-parametric, ensemble-based approach that combines decision trees through boosting to capture complex feature interactions and model non-linearity effectively. XGBoost also includes L1 and L2 regularization, allowing it to manage overfitting while providing strong predictive performance. XGBoost is known for its superior performance in capturing intricate relationships, providing robust predictions across various data contexts, as well as obtaining the first prize in many AI datathons.\n\nMissing data:\n\nThe investigators anticipate missing data for patient-reported, clinical, radiological and supplementary variables. To address this, the investigators will\n\n1. Assess the extent and patterns of missingness for each variable using descriptive statistics and graphical methods.\n2. Investigate reasons for missing values and potential differences between individuals with and without incomplete data.\n3. Handle missing data using XGBoost's native capability to manage missing values directly by learning optimal splits for missing data, thereby eliminating the need for external imputation approaches for this model.\n\nModel development:\n\nExtreme Gradient Boosting (XGBoost):\n\n* The data will be split into a training (70%) and testing (30%) set. The XGBoost model will be trained using hyperparameter tuning through grid search combined with repeated 5-fold cross-validation (repeated 5 times) on the training set. This repeated cross-validation serves as internal validation to ensure robust and unbiased estimation of model performance during training. The grid space search will explore a reasonable range of values for key hyperparameters, such as:\n\n * Number of boosting rounds (nrounds): (e.g., 50, 100, 200)\n * Learning rate (eta): (e.g., 0,05, 0.1, 0.3)\n * Maximum depth of trees (max\\_depth): (e.g., 2, 4, 6)\n * Minimum sum of instances in each node (min\\_child\\_weight): (e.g., 1, 2, 4)\n* The grid space will be kept moderate in size to balance comprehensiveness with computational feasibility, ensuring a thorough exploration of important hyperparameters while avoiding an overly exhaustive search.\n* In developing our model, the investigators will aim to enhance the performance and reduce overfitting by employing feature selection to address collinearity. The investigators will also investigate a minimal feature set using feature importance scores from an initial XGBoost model as well as expert knowledge to prioritize clinically relevant predictors. Lastly, the investigators will explore feature engineering (e.g., polynomial transformations) to enhance the predictive power of our model.\n\nModel evaluation:\n\n* Held-Out Test Set: After internal validation and hyperparameter tuning, the final model will be evaluated on the 30% held-out test set to assess its performance on unseen data, providing an unbiased estimate of generalizability.\n* Performance Metrics:\n\n * R² (Coefficient of Determination): To evaluate the proportion of variance explained by the model.\n * Mean Absolute Error (MAE): To quantify the average magnitude of prediction errors and assess model accuracy for continuous outcomes, offering a clinician-friendly interpretation of error.\n * Calibration and Validation Plots: To assess the agreement between observed and predicted outcomes, evaluating how well the predicted values align with the true values in the study population.\n* Learning Curve: Learning curves will be employed to evaluate the model performance across different training set sizes. By plotting training and validation errors against the number of training sample sizes (subsets of whole dataset), the investigators can assess the model fit, observe the learning behavior, and determine whether our model performance would benefit from additional training data.\n* Prediction Uncertainty: The investigators will use bootstrap aggregation (bagging), following methods from Hastie et al., to obtain prediction intervals, which quantify uncertainty in individual XGBoost predictions by analyzing the variance in prediction errors across bootstrap samples. Unlike confidence intervals, these intervals account for both model misspecification and outcome uncertainty.\n\nModel output:\n\nThe investigators will use the final model to develop a web-based outcome calculator for pain and function 1-year after surgery. This tool is intended primarily for use by the clinicians, aiming to facilitate shared decision-making with the patients. By providing clear visualizations and easy-to-understand classifications, the calculator will help clinicians explain potential outcomes to patients and support patient engagement in their treatment planning. The model output will include either the predicted pain score on a 0-10 Numeric Rating Scale (NRS) or the bMHQ hand function score, which ranges from 0-100.\n\nBased on the outcome, the exact predicted values will be visually highlighted followingly:\n\n* Green: NRS 0-3, bMHQ 67-100 (indicative of positive outcomes)\n* Orange: NRS 4-7, bMHQ 34-66 (indicative of moderate outcomes)\n* Red: NRS 8-10, bMHQ 0-33 (indicative of poor outcomes) This classification aims to provide a quick, visual representation of the predicted outcomes, making it easier for clinicians and patients to interpret the results and understand the level of risk or expected recovery potential. The classification thresholds may be subject to change based on further validation to ensure accuracy and clinical relevance."}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['CHILD', 'ADULT', 'OLDER_ADULT'], 'samplingMethod': 'NON_PROBABILITY_SAMPLE', 'studyPopulation': 'Study participants will be selected from a single-center prospective registry of patients treated at a specialized orthopedic hospital in Zurich, Switzerland. The population consists of individuals diagnosed with primary trapeziometacarpal joint (TMJ) osteoarthritis who underwent primary TMJ arthroplasty using the Touch® prosthesis. This population represents a mix of patients with varying severities of TMJ osteoarthritis who had failed conservative treatments such as splints, hand therapy, or corticosteroid injections before undergoing surgery.', 'healthyVolunteers': False, 'eligibilityCriteria': 'Inclusion Criteria:\n\n* Patients who were treated with a primary TMJ arthroplasty using the Touch® prosthesis for TMJ OA in our single-center prospective registry.\n* Patients who had completed their 1-year follow-up questionnaire\n\nExclusion Criteria:\n\n* Revision surgery,\n* Not treated for primary osteoarthritis (i.e., secondary osteoarthritis or rheumatoid arthritis or other),\n* Did not sign the consent form'}, 'identificationModule': {'nctId': 'NCT06740851', 'briefTitle': 'Predictive Model for 1-Year Pain and Function Outcomes After Thumb Joint Surgery in Osteoarthritic Patients', 'organization': {'class': 'OTHER', 'fullName': 'Schulthess Klinik'}, 'officialTitle': 'A Study Protocol for the Development of a Predictive Model for 1-Year Pain and Function Outcomes After Touch® Trapeziometacarpal Joint Arthroplasty', 'orgStudyIdInfo': {'id': '2019-02096'}}, 'armsInterventionsModule': {'armGroups': [{'label': 'Touch® patients', 'description': 'Patients who were treated with a primary trapeziometacarpal joint (TMJ) arthroplasty using the Touch® prosthesis for TMJ OA in our single-center prospective registry.\n\nPatients had usually received treatments with splints, hand therapy and 1-3 steroid injections before undergoing surgery. Specific indications for primary TMJ implant arthroplasty included good trapezial bone stock without cysts, a trapezial height of at least 8 mm, no clinically relevant scaphotrapezoidal OA and no severe instability of the metacarpophalangeal joint.', 'interventionNames': ['Procedure: Touch® Trapeziometacarpal Joint Arthroplasty']}], 'interventions': [{'name': 'Touch® Trapeziometacarpal Joint Arthroplasty', 'type': 'PROCEDURE', 'otherNames': ['Primary Trapeziometacarpal Joint Replacement', 'Thumb Joint Replacement with Touch® Implant'], 'description': 'The intervention involves primary trapeziometacarpal joint (TMJ) arthroplasty using the Touch® prosthesis, a dual-mobility implant designed for the treatment of osteoarthritis in the thumb.', 'armGroupLabels': ['Touch® patients']}]}, 'contactsLocationsModule': {'locations': [{'zip': '8008', 'city': 'Zurich', 'state': 'Canton of Zurich', 'country': 'Switzerland', 'facility': 'Schulthess Klinik', 'geoPoint': {'lat': 47.36667, 'lon': 8.55}}]}, 'ipdSharingStatementModule': {'ipdSharing': 'NO', 'description': 'We do not plan on sharing the raw data. The full analysis code will be shared.'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Michael Oyewale', 'class': 'OTHER'}, 'collaborators': [{'name': 'Erasmus Medical Center', 'class': 'OTHER'}, {'name': 'University of Rotterdam, The Netherlands', 'class': 'OTHER'}], 'responsibleParty': {'type': 'SPONSOR_INVESTIGATOR', 'investigatorTitle': 'Principal Investigator', 'investigatorFullName': 'Michael Oyewale', 'investigatorAffiliation': 'Schulthess Klinik'}}}}