A decision support system on surgical treatments for rotator cuff tears

Guo, Weihong; Jin, Jesse S.; Paynabar, Kamran; Miller, Bruce S.; Carpenter, James E.

doi:10.1080/19488300.2015.1065935

Cited by 4 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…19,36,37,51 Prognostic models can be used to develop individual risk prediction for supporting treatment decisions, and 1 model has already identified patients likely to benefit from early surgical repair of a rotator cuff tear. 26 A more recent model was developed to predict shoulder functional outcomes 2 years after full-thickness ARCR. 21 Furthermore, a prediction model for shoulder stiffness was developed within the setting of a prospective cohort study, 35 yet rotator cuff repairs represented only 30% of the population that underwent various shoulder surgeries.…”

mentioning

confidence: 99%

Prediction of Shoulder Stiffness After Arthroscopic Rotator Cuff Repair

et al. 2021

View full text Add to dashboard Cite

Background: Postoperative shoulder stiffness (POSS) is a prevalent adverse event after arthroscopic rotator cuff repair (ARCR) that is associated with major limitations in everyday activities and prolonged rehabilitation. Purpose/Hypothesis: The purpose was to develop a predictive model for determining the risk of POSS within 6 months after primary ARCR. We hypothesized that sufficient discrimination ability of such a model could be achieved using a local institutional database. Study Design: Case-control study; Level of evidence, 3. Methods: Consecutive primary ARCRs documented in a local clinical registry between 2013 and 2017 were included, and patients who experienced POSS before the final clinical 6-month follow-up were identified. A total of 29 prognostic factor candidates were considered, including patient-related factors (n = 7), disease-related factors (n = 9), rotator cuff integrity factors (n = 6), and operative details (n = 7). We used imputed data for the primary analysis, and a sensitivity analysis was conducted using complete case data. Logistic regression was applied to develop a model based on clinical relevance and statistical criteria. To avoid overfitting in the multivariable model, highly correlated predictors were not included together in any model. A final prognostic model with a maximum of 8 prognostic factors was considered. The model’s predictive accuracy was assessed by the area under the receiver operating characteristic curve (AUC). Internal validation was performed using bootstrapping. Results: Of 1330 ARCR cases (N = 1330 patients), 112 (8.4%) patients had POSS. Our final model had a moderate predictive ability with an AUC of 0.67. The predicted risks of POSS ranged from 2.3% to 38.9% and were significantly higher in women; patients with partial tears, low baseline passive shoulder abduction, and lack of tendon degeneration; and when no acromioplasty was performed. Conclusion: A prognostic model for POSS was developed for patients with ARCR, offering a personalized risk evaluation to support the future decision process for surgery and rehabilitation.

show abstract

mentioning

confidence: 99%

Prediction of Shoulder Stiffness After Arthroscopic Rotator Cuff Repair

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For example, in the design of a clinic decision support system, a user-centered learning functionality with risk informed decisions is highly demanded to meet the physicians’ clinic needs and minimize the users training time and to continuously improve user decision performance and risk awareness for few human errors. 98 Moreover, for computer aided decision-making from multiple alternatives, a trade-off among multiple competing decision factors can be quantitatively considered, in which a user-centered interface is desirable to dynamically show the weights of individual decision factors to help humans adaptively adjust the decisions according to the feedback of responses. 99 Moreover, human experience, decision time pressure, and task complexity should also be considered in the evaluation of the human decision performance.…”

Section: Big Data Analytics For Cdssmentioning

confidence: 99%

Prospects and Challenges for Clinical Decision Support in the Era of Big Data

Naqa

Kosorok

Jin

et al. 2018

JCO Clinical Cancer Informatics

View full text Add to dashboard Cite

Recently, there has been burgeoning interest in developing more effective and robust clinical decision support systems (CDSSs) for oncology. This has been primarily driven by the demands for more personalized and precise medical practice in oncology in the era of so-called big data (BD), an era that promises to harness the power of large-scale data flow to revolutionize cancer treatment. This interest in BD analytics has created new opportunities as well as new unmet challenges. These include: routine aggregation and standardization of clinical data, patient privacy, transformation of current analytical approaches to handle such noisy and heterogeneous data, and expanded use of advanced statistical learning methods on the basis of confluence of modern statistical methods and machine learning algorithms. In this review, we present the current status of CDSSs in oncology, the prospects and current challenges of BD analytics, and the promising role of integrated modern statistics and machine learning algorithms in predicting complex clinical end points, individualizing treatment rules, and optimizing dynamic personalized treatment regimens. We discuss issues pertaining to these topics and present application examples from an aggregate of experiences. We also discuss the role of human factors in improving the use and acceptance of such enhanced CDSSs and how to mitigate possible sources of human error to achieve optimal performance and wider acceptance.

show abstract

“…Several clinical studies have used linear and logistic regression methods to develop prognostic models for identifying risk factors and supporting treatment decisions [2, 5, 26]. A more recent model was built to predict postoperative shoulder stiffness (POSS) and evaluate the potential personalized risk factors [8]. One model was developed to identify patients likely to benefit from early surgical repair of a rotator cuff tear [12].…”

Section: Introductionmentioning

confidence: 99%

Machine learning model successfully identifies important clinical features for predicting outpatients with rotator cuff tears

Alike

Hou

et al. 2023

Knee Surg Sports Traumatol Arthrosc

View full text Add to dashboard Cite

Purpose The aim of this study is to develop a machine learning model to identify important clinical features related to rotator cuf tears (RCTs) using explainable artiicial intelligence (XAI) for eiciently predicting outpatients with RCTs. Methods A retrospective review of a local clinical registry dataset was performed to include patients with shoulder pain and dysfunction who underwent questionnaires and physical examinations between 2019 and 2022. RCTs were diagnosed by shoulder arthroscopy. Six machine-learning algorithms (Stacking, Gradient Boosting Machine, Bagging, Random Forest, Extreme Gradient Boost (XGBoost), and Adaptive Boosting) were developed for the prediction. The performance of the models was assessed by the area under the receiver operating characteristic curve (AUC), Brier scores, and Decision curve. The interpretability of the predicted outcomes was evaluated using Shapley additive explanation (SHAP) values. Results A total of 1684 patients who completed questionnaires and clinical tests were included, and 417 patients with RCTs underwent shoulder arthroscopy. In six machining learning algorithms for predicting RCTs, the accuracy, AUC values, and Brier scores were in the range of 0.81-0.86, 0.75-0.92, and 0.15-0.19, respectively. The XGBoost model showed superior performance with accuracy, AUC, and Brier scores of 0.85(95% conidence interval, 0.82-0.87), 0.92 (95% conidence interval,0.90-0.94), and 0.15 (95% conidence interval,0.14-0.16), respectively. The Shapley plot showed the impact of the clinical features on predicting RCTs. The most important variables were Jobe test, Bear hug test, and age for prediction, with mean SHAP values of 1.458, 0.950, and 0.790, respectively. Conclusion The machine learning model successfully identiied important clinical variables for predicting patients with RCTs. In addition, the best algorithm was also integrated into a digital application to provide predictions in outpatient settings. This tool may assist patients in reducing their pain experience and providing prompt treatments. Level of Evidence Level III.

show abstract

A decision support system on surgical treatments for rotator cuff tears

Cited by 4 publications

References 19 publications

Prediction of Shoulder Stiffness After Arthroscopic Rotator Cuff Repair

Prediction of Shoulder Stiffness After Arthroscopic Rotator Cuff Repair

Prospects and Challenges for Clinical Decision Support in the Era of Big Data

Machine learning model successfully identifies important clinical features for predicting outpatients with rotator cuff tears

Contact Info

Product

Resources

About