This is a retrospective cohort study utilizing radiographic and computed tomography (CT) imaging data collected during routine clinical care at Schulthess Klinik Zürich. The study focuses on developing and validating artificial intelligence (AI)-based tools for the assessment of trapeziometacarpal (TMC) joint osteoarthritis (OA) and implant monitoring.

The project is divided into four subprojects: (1) development of a new radiographic classification system for TMC OA, (2) automation of the classification using deep learning, (3) automated detection of implant migration, and (4) 3-dimensional (3D) reconstruction of the TMC joint from biplanar radiographs.

Data will be sourced from two cohorts: patients from our clinical TMC arthroplasty registry who received the Touch implant, and patients with other wrist-related conditions who underwent radiographic imaging with a visible TMC joint. Together, these cohorts provide a broad coverage across the full spectrum of OA severity.

OA-related features and implant related features will serve as the foundation for model training and validation. Also, they will be validated with CT images regarding reliability and accuracy. The resulting prototypes for automated OA staging, implant migration detection, and 3D modeling of the TMC joint are exclusively used for research purposes. Any future clinical use of these tools, including evaluation under Swissmedic (Swiss Agency for Therapeutic Products) regulations, will be part of a separate project.

Inclusion criteria:

Patients will be included in the study if they have provided written general consent for the use of their clinical data and meet the requirements of one of the following two groups:

TMC OA group:

• Patients who received a Touch implant for TMC joint arthroplasty and are documented in our clinical registry

Other clinical conditions:

• Patients who underwent radiographic imaging for one of the following conditions, with a clearly visible TMC joint, for example: Distal radius fracture, carpal fracture, finger dislocation, or similar.

Exclusion Criteria:

The exclusion criteria are defined based on the two inclusion groups:

TMC OA group:

• Patients with posttraumatic OA.
• Patients with rheumatoid arthritis.

Other clinical conditions:

• Eaton Littler score higher than one.
• Prior surgery affecting the trapezium or the first metacarpal.
• Clinical condition resulting in abnormal TMC joint morphology.

Furthermore, patients will also be excluded if they revoke their consent in writing or via verbal withdrawal.

The study population consists of patients treated at Schulthess Klinik Zürich with available radiographic imaging of the TMC joint. Data are derived from two cohorts: (1) patients enrolled in the TMC arthroplasty registry (BASEC number: 2019-02096) who received a Touch implant since 2018, and (2) patients with other wrist-related conditions requiring radiographs in which the TMC joint is clearly visible. The combined cohorts provide a balanced representation across the spectrum of TMC joint OA severity, from healthy joints to end-stage disease.

IPD will not be shared. The study involves sensitive clinical data that is subject to privacy protections and institutional regulations. Ownership of the data remains with the clinic, and confidentiality requirements prevent making these data publicly available.