Machine Learning Predictive Model for Rotator Cuff Repair Failure

Predictive Model for Minimal Important Change After Rotator Cuff Repair Using Machine Learning Methods: A Pilot Study

There is little overall evidence behind clinical practice guidelines for diagnosis and treatment of rotator cuff repair. The purpose of this study was to compare the performance of different machine learning models that use pre-operative data from an international and multicentric database to predict if a patient that underwent rotator cuff repair could achieve the minimal important change (MIC) for single assessment numeric evaluation (SANE) at one year follow-up.

Study Overview

• Status: Completed
• Conditions: Rotator Cuff Tears
• Intervention / Treatment: Procedure: Arthroscopic rotator cuff repair

• Study Type: Observational
• Enrollment (Actual): 4789

Contacts and Locations

Study Locations

• Switzerland
  • Geneva
    • Meyrin, Geneva, Switzerland, 1217
      • La Tour Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: N/A

• Sampling Method: Non-Probability Sample

Study Population

All adult patients who were primarily treated for rotator cuff tears by partial or complete surgical repair with a planned arthroscopic procedure were included in study.

Description

Inclusion Criteria:

• Primarily treated for rotator cuff tears by partial or complete surgical repair with a planned arthroscopic procedure
• Reparable tears
• No language barrier hindering questionnaire completion or legal incompetence were not included

Exclusion Criteria:

• missing pre- or post-operative single-assessment numeric evaluation (SANE)

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
MIC RCR patients; Patients who improved their SANE score beyond the minimal important change one year after arthroscopic rotator cuff repair	Procedure: Arthroscopic rotator cuff repair; Patients underwent an arthroscopic repair for rotator cuff lesions
No-MIC RCR patients; Patients who did not improve their SANE score beyond the minimal important change one year after arthroscopic rotator cuff repair	Procedure: Arthroscopic rotator cuff repair; Patients underwent an arthroscopic repair for rotator cuff lesions

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
SANE score	Single Assessment Numeric Evaluation (SANE). From 0 (worst) to 100 (best).	At 12 post-operative months

Collaborators and Investigators

• Sponsor: La Tour Hospital
• Investigators: Principal Investigator: Alexandre Lädermann, MD, La Tour hospital, Meyrin (1217) Geneva, Switzerland

Study record dates

Study Major Dates

• Study Start (Actual): September 1, 2022
• Primary Completion (Actual): September 1, 2022
• Study Completion (Actual): November 1, 2023

Study Registration Dates

• First Submitted: November 17, 2023
• First Submitted That Met QC Criteria: November 22, 2023
• First Posted (Actual): November 24, 2023

Study Record Updates

• Last Update Posted (Actual): November 29, 2023
• Last Update Submitted That Met QC Criteria: November 24, 2023
• Last Verified: November 1, 2023

More Information

Terms related to this study

• Keywords: Artificial intelligence; Machine Learning; Minimal Important Change
• Additional Relevant MeSH Terms: Wounds and Injuries; Rupture; Shoulder Injuries; Tendon Injuries; Rotator Cuff Injuries
• Other Study ID Numbers: CCER #2020-02670

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No