Longo Umile Giuseppe, Di Naro Calogero, Campisi Simona, Casciaro Carlo, Bandini Benedetta, Pareek Ayoosh, Bruschetta Roberta, Pioggia Giovanni, Cerasa Antonio, Tartarisco Gennaro
Orthopaedic and Trauma Surgery, Fondazione Policlinico Universitario Campus Bio-Medico, Via Alvaro del Portillo 200, 00128 Rome, Italy.
Research Unit of Orthopaedic and Trauma Surgery, Department of Medicine and Surgery, Università Campus Bio-Medico di Roma, Via Alvaro del Portillo 21, 00128 Rome, Italy.
Diagnostics (Basel). 2023 Sep 11;13(18):2915. doi: 10.3390/diagnostics13182915.
The overall aim of this proposal is to ameliorate the care of rotator cuff (RC) tear patients by applying an innovative machine learning approach for outcome prediction after arthroscopic repair.
We applied state-of-the-art machine learning algorithms to evaluate the best predictors of the outcome, and 100 RC patients were evaluated at baseline (T0), after 1 month (T1), 3 months (T2), 6 months (T3), and 1 year (T4) from surgical intervention. The outcome measure was the Costant-Murley Shoulder Score, whereas age, sex, BMI, the 36-Item Short-Form Survey, the Simple Shoulder Test, the Hospital Anxiety and Depression Scale, the American Shoulder and Elbow Surgeons Score, the Oxford Shoulder Score, and the Shoulder Pain and Disability Index were considered as predictive factors. Support vector machine (SVM), k-nearest neighbors (k-NN), naïve Bayes (NB), and random forest (RF) algorithms were employed.
Across all sessions, the classifiers demonstrated suboptimal performance when using both the complete and shrunken sets of features. Specifically, the logistic regression (LR) classifier achieved a mean accuracy of 46.5% ± 6%, while the random forest (RF) classifier achieved 51.25% ± 4%. For the shrunken set of features, LR obtained a mean accuracy of 48.5% ± 6%, and RF achieved 45.5% ± 4.5%. No statistical differences were found when comparing the performance metrics of ML algorithms.
This study underlines the importance of extending the application of AI methods to new predictors, such as neuroimaging and kinematic data, in order to better record significant shifts in RC patients' prognosis.
The data quality within the cohort could represent a limitation, since certain variables, such as smoking, diabetes, and work injury, are known to have an impact on the outcome.
本提议的总体目标是通过应用一种创新的机器学习方法来预测关节镜修复术后的结果，从而改善肩袖（RC）撕裂患者的护理。
我们应用了最先进的机器学习算法来评估结果的最佳预测因素，并在手术干预后的基线期（T0）、1个月后（T1）、3个月后（T2）、6个月后（T3）和1年后（T4）对100例RC患者进行了评估。结果指标为Constant-Murley肩关节评分，而年龄、性别、体重指数、36项简短问卷调查、简易肩关节测试、医院焦虑抑郁量表、美国肩肘外科医生评分、牛津肩关节评分以及肩痛和功能障碍指数被视为预测因素。采用了支持向量机（SVM）、k近邻（k-NN）、朴素贝叶斯（NB）和随机森林（RF）算法。
在所有阶段，当使用完整和精简的特征集时，分类器的表现均未达到最优。具体而言，逻辑回归（LR）分类器的平均准确率为46.5%±6%，而随机森林（RF）分类器为51.25%±4%。对于精简后的特征集，LR的平均准确率为48.5%±6%，RF为45.5%±4.5%。比较机器学习算法的性能指标时未发现统计学差异。
本研究强调了将人工智能方法应用于新的预测因素（如神经影像学和运动学数据）的重要性，以便更好地记录RC患者预后的显著变化。
队列中的数据质量可能是一个限制因素，因为已知某些变量（如吸烟、糖尿病和工伤）会对结果产生影响。
