Citations

Purpose To determine whether conventional logistic regression or machine learning algorithms were more precise in identifying the risk factors for unplanned overnight admission after medial patellofemoral ligament (MPFL) reconstruction. Methods A retrospective review of the prospectively collected National Surgical Quality Improvement Program database was performed to identify patients who underwent outpatient MPFL reconstruction from 2006–2018. Patients admitted overnight were identified as those with length of stay of 1 or more days. Models were generated using random forest, extreme gradient boosting, adaptive boosting, or elastic net penalized logistic regression, and an additional model was produced as a weighted ensemble of the 4 final algorithms. The predictive capacity of these models was compared to that of logistic regression. Results Of the 1307 patients identified, 221 (16.9%) required at least one overnight stay after MPFL reconstruction. Multivariate logistic regression found the following variables to be predictors of inpatient admission: age (odds ratio [OR] = 1.03 [95% confidence interval {CI} 1.02‐1.04]; P <.001), spinal anesthesia (OR = 3.42 [95% CI 1.98‐6.08]; P < .001), American Society of Anesthesiologists (ASA) class 3/4 (OR = 1.96 [95% CI 1.25‐3.06]; P < .001), history of chronic obstructive pulmonary disease (COPD) (OR = 6.44 [95% CI 1.58‐26.17]; P = .02), and body mass index (BMI) (OR = 1.03 [95% CI 1.01‐1.05]; P < .001). The ensemble model achieved the best performance based on discrimination assessed via internal validation (area under the curve = 0.722). The variables determined most important by the ensemble model were increasing BMI, increasing age, ASA class, anesthesia, smoking, hypertension, lateral release, and history of COPD. Conclusions An internally validated machine learning algorithm outperformed logistic regression modeling in predicting the need for unplanned overnight hospitalization after MPFL reconstruction. In this model, the most significant risk factors for admission were age, BMI, ASA class, smoking status, hypertension, lateral release, and history of COPD. This tool can be deployed to augment provider assessment to identify high‐risk candidates and appropriately set postoperative expectations for patients. Clinical Relevance Identifying and mitigating patient risk factors to prevent adverse surgical outcomes and hospitalizations is one of our primary goals. There may be a key role for machine learning algorithms to help successfully and efficiently risk stratify patients to decrease costs, appropriately set postoperative expectations, and increase the quality of delivered care.

Background: Clinically significant outcomes (CSOs) connect patient-reported outcome measures data to patient-perceived benefit. Although investigators have established threshold values for various CSOs, the timeline to achieve these outcomes after isolated biceps tenodesis (BT) has yet to be defined. Purpose: To define the time-dependent nature of minimal clinically important difference (MCID), substantial clinical benefit (SCB), and Patient Acceptable Symptom State (PASS) achievement after isolated BT. Study Design: Case series; Level of evidence, 4. Methods: The American Shoulder and Elbow Surgeons score (ASES), the Single Assessment Numeric Evaluation, and the Constant-Murley score (CMS) were administered preoperatively and at 6 and 12 months postoperatively to patients undergoing isolated BT between 2014 and 2018 at our institution. Cumulative probabilities for achieving MCID, SCB, and PASS were calculated using Kaplan-Meier survival analysis. Weibull parametric regression evaluated the hazard ratios (HRs) of achieving earlier MCID, SCB, and PASS. Results: Overall cohort (N = 190) achievement rates ranged between 77.8% and 83.2% for MCID, between 42.2% and 80.2% for SCB, and between 59.7% and 62.9% for PASS. Median achievement time was 5.3 to 6.1 months for MCID, 5.9 to 6.4 months for SCB, and 6.07 to 6.1 months for PASS. Multivariate Weibull parametric regression identified older age, male sex, higher body mass index, preoperative thyroid disease, smoking history, and higher preoperative CMS as predictors of delayed CSO achievement (HR, 1.01-6.41), whereas normal tendon on arthroscopy, defined as absence of tenosynovitis or tendon tear on arthroscopy, predicted earlier CSO achievement (HR, 0.19-0.46). Location of tenodesis and worker compensation status did not significantly predict the time to achieve CSOs on multivariate analysis. Conclusion: After isolated BT, patients can expect to attain CSO by 13 months postoperatively, with most patients achieving this between 5 and 8 months. Patients tend to take longer to achieve PASS than MCID and SCB.

Background: Integrin family are known as key gears in focal adhesion for triple-negative breast cancer (TNBC) metastasis. However, the integrin independent factor TLN1 remains vague in TNBC. Methods: Bioinformatics analysis was performed based on TCGA database and Shengjing Hospital cohort. Western blot and RT-PCR were used to detect the expression of TLN1 and integrin pathway in cells. A small-molecule C67399 was screened for blocking TLN1 and integrin β1 through a novel computational screening approach by targeting the protein-protein binding interface. Drug pharmacodynamics were determined through xenograft assay. Results: Upregulation of TLN1 in TNBC samples correlates with metastasis and worse prognosis. Silencing TLN1 in TNBC cells significantly attenuated the migration of tumour cells through interfering the dynamic formation of focal adhesion with integrin β1, thus regulating FAK-AKT signal pathway and epithelial-mesenchymal transformation. Targeting the binding between TLN1 and integrin β1 by C67399 could repress metastasis of TNBC. Conclusions: TLN1 overexpression contributes to TNBC metastasis and C67399 targeting TLN1 may hold promise for TNBC treatment. Funding: This study was supported by grants from the National Natural Science Foundation of China (No. 81872159, 81902607, 81874301), Liaoning Colleges Innovative Talent Support Program (Name: Cancer Stem Cell Origin and Biological Behaviour), Outstanding Scientific Fund of Shengjing Hospital (201803), and Outstanding Young Scholars of Liaoning Province (2019-YQ-10).

Purpose To construct an algorithm to optimize clinical outcomes in subacromial impingement based on current, high‐level evidence. Methods A systematic review of all clinical trials on subacromial impingement published from 1999 to 2020 was performed. Demographic, clinical, range of motion (ROM), and patient‐reported outcome measure (PROM) data were collected. Interventions were compared via arm‐based Bayesian network meta‐analysis in a random‐effects model and treatments ranked via surface under the cumulative ranking curves with respect to 3 domains: pain, PROMs, and ROM. Results A total of 35 studies comprising 3,643 shoulders (42% female, age 50 ± 5 years) were included. Arthroscopic decompression with acromioplasty ranked much greater than arthroscopic decompression alone for pain relief and PROM improvement, but the difference in absolute PROMs was not statistically significant. Corticosteroid injection (CSI) alone demonstrated inferior outcomes across all 3 domains (pain, PROMs, and ROM) with low cumulative rankings. Physical therapy (PT) with CSI demonstrated moderate‐to‐excellent clinical improvement across all 3 domains whereas PT alone demonstrated excellent ROM and low‐moderate outcomes in pain and PROM domains. PT with nonsteroidal anti‐inflammatory drugs or alternative therapies ranked highly for PROM outcomes and moderate for pain and ROM domains. Finally, platelet‐rich plasma injections demonstrated moderate outcomes for pain, forward flexion, and abduction with very low‐ranking outcomes for PROMs and external rotation. Conclusions Arthroscopic decompression with acromioplasty and PT demonstrated superior outcomes whereas CSI demonstrated poor outcomes in all 3 domains (pain, PROMs, and ROM). For patients with significant symptoms, the authors recommend PT with CSI as a first‐line treatment, followed by acromioplasty and PT if conservative treatment fails. For patients with symptoms limited to 1 to 2 domains, the authors recommend a shared decision‐making approach focusing on treatment rankings within domains pertinent to individual patient symptomatology. Level of Evidence I, systematic review and network meta‐analysis of Level I studies.

Purpose To review the literature on postoperative corticosteroid injections (CSIs) following primary rotator cuff repair (RCR) to evaluate efficacy and adverse effects. Methods A systematic review of the MEDLINE, EMBASE, and Cochrane databases were performed to identify all studies published within the last 15 years, which reported on outcomes of postoperative CSIs following RCR. Studies including patients who received only preoperative CSIs and revision RCRs were excluded. Included studies were evaluated for study methodology, patient demographics, outcome measures, physical examination parameters, results of imaging studies, and adverse effects or clinical complications. Results Seven studies comprising 5,528 patients satisfied inclusion criteria. Among included patients, 54.8% were female and mean age range from 52.3 ± 13.0 to 62.7 ± 6.6 years. Only 1 included investigation was a Level I study. Overall, 4 of 5 studies reported significant improvements in pain and outcome scores (Constant score, American Shoulder and Elbow Surgeons score) compared with controls. Across all studies, the majority of these effects were statistically significant at 3 months postoperatively but not beyond this time point. Five of the 6 included investigations reported no increased rate of retears after postoperative CSIs. One study did find an increase in retear in patients receiving postoperative CSIs but was unable to determine whether these retears were present before the patient received the CSI. Another investigation reported an increased rate of infection only if the CSI was administered in the first postoperative month. Conclusions Postoperative CSIs may improve pain and function for up to 3 months following primary RCR but not at later follow‐up time points. CSIs should be administered only after the first postoperative month to minimize the potential risk for adverse events. Level of Evidence Systematic review of level I‐IV studies.

Purpose To develop a machine learning algorithm to predict total charges after ambulatory hip arthroscopy and create a risk‐adjusted payment model based on patient comorbidities. Methods A retrospective review of the New York State Ambulatory Surgery and Services database was performed to identify patients who underwent elective hip arthroscopy between 2015 and 2016. Features included in initial models consisted of patient characteristics, medical comorbidities, and procedure‐specific variables. Models were generated to predict total charges using 5 algorithms. Model performance was assessed by the root‐mean‐square error, root‐mean‐square logarithmic error, and coefficient of determination. Global variable importance and partial dependence curves were constructed to show the impact of each input feature on total charges. For performance benchmarking, the best candidate model was compared with a multivariate linear regression using the same input features. Results A total of 5,121 patients were included. The median cost after hip arthroscopy was $19,720 (interquartile range, $12,399‐$26,439). The gradient‐boosted ensemble model showed the best performance (root‐mean‐square error, $3,800 [95% confidence interval, $3,700‐$3,900]; logarithmic root‐mean‐square error, 0.249 [95% confidence interval, 0.24‐0.26]; R 2 = 0.73). Major cost drivers included total hours in facility less than 12 or more than 15, longer procedure time, performance of a labral repair, age younger than 30 years, Elixhauser Comorbidity Index (ECI) of 1 or greater, African American race, residence in extreme urban and rural areas, and higher household and neighborhood income. Conclusions The gradient‐boosted ensemble model effectively predicted total charges after hip arthroscopy. Few modifiable variables were identified other than anesthesia type; nonmodifiable drivers of total charges included duration of care less than 12 hours or more than 15 hours, operating room time more than 100 minutes, age younger than 30 years, performance of a labral repair, and ECI greater than 0. Stratification of patients based on the ECI highlighted the increased financial risk borne by physicians via flat reimbursement schedules given variable degrees of comorbidities. Level of Evidence Level III, retrospective cohort study.

Purpose To develop and internally validate a machine‐learning algorithm to reliably predict cost after anterior cruciate ligament reconstruction (ACLR). Methods A retrospective review of the New York State Ambulatory Surgery and Services database was performed to identify patients who underwent elective ACLR from 2015 to 2016. Features included in initial models consisted of patient characteristics (age, sex, insurance status, income, medical comorbidities as classified by the Clinical Classifications Software diagnosis code) as well as intraoperative variables (type of anesthesia and procedure‐specific factors). Models were generated to predict total charges using 4 algorithms: random forest, extreme gradient boost, elastic net penalized regression, and support vector machines with radial kernels. Training was performed with 10‐fold cross‐validation followed by internal validation via 0.632 bootstrapping. Model discriminative performance was assessed by area under the receiver operating characteristic curve, calibration, and the Brier score. Decision curve analysis was performed to demonstrate the net benefit of using the final model in practice. Results In total, 7,311 patients undergoing ambulatory ACLR were included. The random forest model demonstrated the best performance assessed via internal validation (area under the curve = 0.85), calibration, and the Brier score (0.208). Cost incurred was influenced by anesthesia type, operating room time, and number of chronic comorbidities. Decision curve analysis revealed a net benefit for use of the random forest model and the model was integrated into a web‐based open‐access application. Conclusions The random forest model predicted cost after ambulatory ACLR using a large, statewide database with good performance. The top variables found to predict increased charges were general anesthesia, operating room time, meniscal repair, self‐pay insurance, patient neighborhood characteristics, and number of chronic conditions. Level of Evidence III, retrospective cohort study.

Background: Management of anterior shoulder instability (ASI) aims to reduce risk of future recurrence and prevent complications via nonoperative and surgical management. Machine learning may be able to reliably provide predictions to improve decision making for this condition. Purpose: To develop and internally validate a machine-learning model to predict the following outcomes after ASI: (1) recurrent instability, (2) progression to surgery, and (3) the development of symptomatic osteoarthritis (OA) over long-term follow-up. Study Design: Cohort study (prognosis); Level of evidence, 2. Methods: An established geographic database of >500,000 patients was used to identify 654 patients aged <40 years with an initial diagnosis of ASI between 1994 and 2016; the mean follow-up was 11.1 years. Medical records were reviewed to obtain patient information, and models were generated to predict the outcomes of interest. Five candidate algorithms were trained in the development of each of the models, as well as an additional ensemble of the algorithms. Performance of the algorithms was assessed using discrimination, calibration, and decision curve analysis. Results: Of the 654 included patients, 443 (67.7%) experienced multiple instability events, 228 (34.9%) underwent surgery, and 39 (5.9%) developed symptomatic OA. The ensemble gradient-boosted machines achieved the best performances based on discrimination (via area under the receiver operating characteristic curve [AUC]: AUC recurrence = 0.86), AUC surgery = 0.76, AUC OA = 0.78), calibration, decision curve analysis, and Brier score (Brier recurrence = 0.138, Brier surgery = 0.185, Brier OA = 0.05). For demonstration purposes, models were integrated into a single web-based open-access application able to provide predictions and explanations for practitioners and researchers. Conclusion: After identification of key features, including time from initial instability, age at initial instability, sports involvement, and radiographic findings, machine-learning models were developed that effectively and reliably predicted recurrent instability, progression to surgery, and the development of OA in patients with ASI. After careful external validation, these models can be incorporated into open-access digital applications to inform patients, clinicians, and researchers regarding quantifiable risks of relevant outcomes in the clinic.