UNIverse - Public Research Portal

Projects & Collaborations

3 found

Show per page

Evidence-based definition and classification of the etiology of rotator cuff tears in Switzerland

Research Project | 4 Project Members

Rotator cuff tears are common and classified as traumatic or degenerative, yet reliable discrimination remains difficult, particularly in Switzerland where etiology determines insurance coverage. This project aims to improve transparency and consistency in classification by integrating clinical and MRI‑based factors into an evidence‑based prediction model.

Clinical Prediction Models for Surgical Outcomes: Addressing Methodological Challenges in Implementation, Data, and Analysis

Research Project | 8 Project Members

Clinical prediction models can support surgical decision-making by identifying patient profiles that are at an increased risk of poor outcomes. While artificial intelligence (AI)-enabled decision aids demonstrated potential in enhancing shared decision-making and improving patient satisfaction, there remains a significant gap in implementation. Furthermore, few studies describe stakeholders’ preferences regarding the use of clinical prediction models. The adoption of decision support tools needs to be accelerated by (i) improving their transparency and reporting standards, (ii) addressing their implementation barriers, and (iii) aligning their development and implementation with stakeholder expectations to maximize their clinical impact.

Simultaneously, the growing deployment and development of modern machine learning and AI models have sparked debates about their performance in comparison to regression models, particularly when citing issues relevant for surgical databases, including varying sample size, atypical outcome distributions (for example ceiling effects in patient-reported outcome measures), and number and strength of predictive ability of prognostic factors.

The Clinical Prediction Models for Surgical Outcomes (CPMSO) project aims to address the challenges of implementation, data, and analysis by establishing standardized guidelines, ultimately improving the reliability and adoption of AI-driven decision support tools encompassing prediction models for surgical outcomes.

Research Objective (RO) 1: To develop and validate a consensus-driven set of recommendations that support the implementation of prediction models for surgical outcomes in patients with musculoskeletal disorders.
RO2: To assess the impact of data characteristics ((i) sample size, (ii) outcome distribution and (iii) number and predictive ability of prognostic factors) on the performance of machine-learning, regression, and Bayesian models for ordinal/continuous outcomes.

METHODS. In working package (WP) 1 related to RO1, we will (1) systematically map existing evidence on the implementation of prediction models in joint surgery through a scoping review, identifying methodological challenges and factors influencing their clinical adoption. We will also (2) explore the perceptions, needs, and implementation barriers of key stakeholders—including patients, healthcare professionals, and researchers— regarding prediction models for surgical outcomes, using focus group discussions. Based on these findings, we will then (3) develop and assess the relevance of a set of consensus recommendations addressing key issues for the implementation of prediction models for surgical outcomes. In WP2 related to RO2, the apparent and bootstrap-validated overall, discrimination and calibration performance of models predicting ordinal/continuous outcomes will be compared, including machine-learning, regression, and Bayesian models. First, data simulations will be generated, for which key data characteristics will be controlled ((i) sample size, (ii) outcome distribution and (iii) number and strength of predictive ability of prognostic factors). The validity of our findings will then be assessed using four nationwide surgical databases focusing on the prediction of pain (Numeric Rating Scale [0-10]) one year after surgery. Databases will be standardized to the Observational Health Data Sciences and Informatics (OHDSI) format, facilitating the further steps of analyses, which will include handling of missing data, predictor selection, model development, and internal validation.

EXPECTED RESULTS AND IMPACT. RO1, linked to WP1, will produce key recommendations for implementing prediction models for surgical outcomes, a crucial step toward enhanced decision-making and achieving better health and socioeconomic outcomes for patients and the society. RO2, linked to WP2, will provide methodological guidance on selecting optimal models for ordinal/continuous outcomes based on key data characteristics. The findings will be published in peer-reviewed journals and presented at international scientific conferences. The CPMSO project aims also to develop a professional network of experts, and support the integration of currently developed predictive analytics tools supporting surgical decision-making in Europe.

Surgical safety and effectiveness in orthopedics: Swiss-wide multicenter evaluation and prediction of core outcomes in arthroscopic rotator cuff reconstruction

Research Project | 2 Project Members

Valid clinical outcome data are essential to assess the safety and effectiveness of surgical interventions, to perform benchmarking activities and to foster a well-founded decision-making process in orthopedics. In the fields of arthroscopic rotator cuff repair (ARCR), the number of ARCR procedures and published studies has grown exponentially in the last decade, yet reporting standards differ dramatically. This is particularly notable concerning adverse events (AE) as in most fields of orthopedic surgery. In addition, published prognostic studies were methodologically poor, based on small datasets and explored only limited numbers of potentially influencing factors.A prospective multicenter clinical study of a large ARCR patient cohort will be implemented on a representative group of 17 Swiss and one German specialized clinics allowing for the evaluation of targeted core safety, clinical and patient-reported outcomes. The primary objective will be the development of prediction models for individual patients. The primary outcomes will be the patient-reported subjective assessment of shoulder function (Oxford Shoulder Score) and the occurrence of shoulder stiffness up to 12 months after primary repair surgery. Multiple prognostic factors will be investigated including patient baseline demographics, psychological, socioeconomic and clinical factors, rotator cuff integrity and concomitant local findings, operative and postoperative management factors. The secondary objectives are to evaluate the content and applicability of a consensus core set of AEs (CES) considering the patient's perspective, validate a severity classification for AEs, and quantify clinically-relevant ARCR outcomes up to 24 months postoperatively. Prognostic models will also be extended to all secondary outcomes.A sample size of 970 ARCR patients will be included; baseline patient demographics, history, shoulder status, magnetic resonance imaging based diagnosis and operative details will be recorded. Patient outcomes will be documented 6, 12 and 24 months after surgery. Clinical examinations at 6 and 12 months will include shoulder range of motion and strength (Constant Score), as well as the documentation of AEs. Tendon repair integrity status will be assessed by ultrasound examination at 12 months. Patient-reported outcome questionnaires at all follow-up time points will determine functional scores (Subjective Shoulder Value, Oxford Shoulder Score), anxiety and depression scores, working status, quality of life (EuroQol EQ-5D-5L), and AEs. All AEs will be documented according to the consensus CES and classified by their degree of severity; patients will rate the perceived severity and disturbance of experienced AEs. We will use the web-based REDCap data capture system for data management. Intensive central monitoring will be performed and investigator meetings will be coordinated during the study. The adapted AE severity classification will be validated. All data will be tabulated and prediction models will be developed using internationally supported methodology.This project will initiate the development of personalized risk predictions to support the surgical decision process in ARCR. The consensus CES may become an international reference for the reporting of complications in clinical studies and registers. The proposed study will foster the condition towards the development of a Swiss national ARCR register. Such a study and registry is an important step to increasing transparency in orthopedic surgery as requested by the federal strategy in healthcare "Health 2020". Methodological insights gained from this work will be easily transferable to similar initiatives in orthopedics.