Forsythe, Brian

Abstract As artificial intelligence (AI) Large Language Models (LLM) like ChatGPT become more common in healthcare, patients increasingly use them to find medical information. While ChatGPT may support health literacy, its readability and accuracy compared to established resources remain unclear. The purpose of this study is to evaluate ChatGPT-4 responses on femoroacetabular impingement (FAI) and its surgical management compared to AAOS OrthoInfo content. We hypothesize that ChatGPT may deliver medically accurate information, but its readability may fall short when compared to OrthoInfo. Nine questions based on the OrthoInfo FAI page were submitted to ChatGPT-4, with and without a readability prompt. Topics included anatomy, pathology, cause, symptoms, workup, imaging, treatment, role of hip arthroscopy, and outcomes. Readability was assessed using validated indices. Accuracy was independently rated using a 4-point scale. Statistical comparisons were made using t-tests and ANOVA (P < 0.01 threshold). OrthoInfo content had a mean reading grade level of 8.0 and a Flesch Reading Ease score of 60.7. Unprompted ChatGPT responses were significantly less readable (grade level 16.2; Flesch score 21.7; P < 0.001). Prompting for readability improved ChatGPT outputs (grade level 10.6; Flesch score 58.2), making them comparable to OrthoInfo (P < 0.09). Accuracy was high across all sources, though OrthoInfo's response on FAI causes scored slightly lower (3.5 versus 4.0; P < 0.46). ChatGPT provides accurate information on FAI. However, without prompting, its complexity may hinder patient understanding. Prompting for readability enables ChatGPT to match established resources like OrthoInfo. Tailored prompting is key to using LLM effectively in patient education and promoting health literacy.

Background: Outcomes after arthroscopic rotator cuff repair (RCR) are frequently measured through clinically significant outcomes (CSOs) such as the minimal clinically important difference, the substantial clinical benefit, and the Patient Acceptable Symptom State. Global achievement of CSOs is challenging to predict. Purpose: To determine if unsupervised machine learning can identify distinct patient subgroups based on CSO achievement after elective arthroscopic RCR. Study Design: Case-control study; Level of evidence, 3. Methods: A prospectively collected database was analyzed to identify patients who underwent elective arthroscopic RCR from 2015 to 2017. Tear dimensions were measured on magnetic resonance imaging utilizing a validated technique. CSO achievements on the American Shoulder and Elbow Surgeons, the Single Assessment Numeric Evaluation, and the Constant-Murley subjective score at 2-year follow-up were calculated. An unsupervised random forest algorithm was utilized to develop and internally validate patient subgroups with significantly different rates of CSO achievement. Patient subgroup membership, along with a total of 30 demographic and clinical variables, as well as preoperative patient-reported outcomes, were incorporated into a stepwise multivariable logistic regression to identify factors predictive of optimal CSO achievement. Results: A total of 346 patients (192 male; mean ± SD age, 57.2 ± 9.1 years; body mass index, 30.1 ± 5.4 kg/m 2 ) were eligible for inclusion and followed for a mean of 3.8 years (range, 2.0-6.2 years) Of these, a total of 333 patients were partitioned by the random forest algorithm into 2 subgroups (stability, 0.16; connectivity: 180.8; Dunn: 0.16; silhouette: 0.05), with 176 patients in the optimal achievement subgroup and 157 patients in the suboptimal achievement subgroup. The 2 subgroups differed significantly (all P ≤ .004) in the likelihood of achievement of all CSOs. Stepwise multivariable logistic regression identified an increase of 1 mm in tear size in the sagittal dimension beyond 1.9 cm to predict a 10% increase in the probability of suboptimal achievement. Additional risk factors for suboptimal CSO achievement included increasing number of tendons involved (odds ratio [OR], 14.07; 95% CI, 4.50-44.02; P < .001), subscapularis involvement (OR, 8.67; 95% CI, 2.45-30.71; P = .01), and increased preoperative CMS score (OR, 1.11; 95% CI, 1.04-1.18; P = .001). Protective factors included performance of a subpectoral biceps tenodesis compared with biceps tenotomy (OR, 0.22; 95% CI, 0.05-0.92; P = .03). Conclusion: Clinically meaningful subgroups were uncovered using an unsupervised machine learning algorithm in patients undergoing arthroscopic RCR. Tear size, number of tendons involved, and subscapularis involvement were significant and additive predictors of suboptimal CSO achievement at 2-year minimum follow-up. Treatment of concurrent biceps pathology with tenodesis conferred 78% increased likelihood of CSO achievement compared with tenotomy.

Purpose To perform a prospective, double‐blind, randomized controlled trial to assess differences in integration and patient‐reported outcomes metrics (PROMs) of osteochondral allograft transplantation with and without bone marrow aspirate concentrate (BMAC) augmentation. Methods Patients (n = 36) undergoing osteochondral allograft transplantation of the knee were consented and enrolled in this prospective study. They were randomized to either iliac crest BMAC or sham incision groups and blinded to their allocation. Computerized tomography (CT) scans of the knee were obtained at 6 months postoperatively after the index transplantation and graded by the semiquantitative assessment CT osteochondral allograft system. PROMs, including the International Knee Documentation Committee and Knee injury and Osteoarthritis Outcome Score–Joint Replacement, were obtained at 6 months, 1 year, and 2 years postoperatively. Results On 6‐month postoperative CT scans, patients receiving BMAC‐treated grafts were more likely to have small cystic changes ( P = .01), with an associated trend toward reduction in large cyst formation ( P = .06), but equal osseous integration, graft signal density, and presence of discernible clefts and intra‐articular fragments. The BMAC group was less likely to undergo subsequent surgery for graft debridement or revision (5.3% vs 35.3%; P = .02). There were no significant differences in PROMs between the 2 groups preoperatively or postoperatively at 6 months, 1 year, or 2 years. Patients receiving BMAC trended toward a higher rate of achievement of Knee Documentation Committee and Knee injury and Osteoarthritis Outcome Score–Joint Replacement minimal clinically important difference (88% vs 55%; P = .076). Conclusions Patients receiving BMAC‐treated grafts were more likely to have small cystic changes and were less likely to undergo subsequent surgery for persistent or new symptoms after the index procedure. No difference in postoperative PROMs was shown at the 6‐month, 1‐year, and 2‐year follow‐ups between the 2 groups. Level of Evidence Level I, prospective, randomized controlled trial.

Purpose To assess the relation between tendon migration, as measured by radiostereometric analysis, and patient‐reported outcome measures (PROMs) after biceps tenodesis (BT); to determine the likelihood of achieving clinically significant outcomes (CSOs) after BT; and to identify factors that impact CSO achievement. Methods Patients undergoing arthroscopic suprapectoral or open subpectoral BT at a single, high‐volume academic medical center were prospectively enrolled. A tantalum bead sutured to the tenodesis construct was used as a radiopaque marker. Biceps tendon migration was measured on calibrated radiographs at 12 weeks postoperatively. PROMs (Constant‐Murley, Single Assessment Numeric Evaluation [SANE], and Patient‐Reported Outcomes Measurement Information System–Upper Extremity [PROMIS‐UE] scores) were collected preoperatively and at minimum 2‐year follow‐up. Results Of 115 patients enrolled, 94 (82%) were included (median age, 52 years; median body mass index, 31.4). At a mean follow‐up of 2.9 years, the median Constant‐Murley, SANE, and PROMIS‐UE scores were 33 (interquartile range [IQR], 26‐35), 90 (IQR, 80‐99), and 47 (IQR, 42‐58), respectively. Median tantalum bead migration was 6.5 mm (IQR, 1.8‐13.8 mm). There were significant correlations between migration and Constant‐Murley score ( r 2 = 0.222; β = –0.554 [95% confidence interval (CI), –1.027 to –0.081]; P = .022), SANE score ( r 2 = 0.238; β = –0.198 [95% CI, –0.337 to –0.058]; P = .006), and PROMIS‐UE score ( r 2 = 0.233; β = –0.406 [95% CI, –0.707 to –0.104]; P = .009). On univariable analysis, higher body mass index was associated with achievement of substantial clinical benefit (unadjusted odds ratio [OR], 1.078 [95% CI, 1.007 to 1.161]; P = .038). Greater bead migration was negatively associated with achievement of the minimal clinically important difference (unadjusted OR, 0.969 [95% CI, 0.943 to 0.993]; P = .014) and patient acceptable symptomatic state (unadjusted OR, 0.965 [95% CI, 0.937 to 0.989]; P = .008) on all 3 instruments. Conclusions A 1‐cm increase in post‐tenodesis biceps tendon migration was associated with a decrease in the Constant‐Murley, SANE, and PROMIS‐UE scores of 6, 2, and 4 points, respectively, at a mean of 2.9 years after surgery. Most patients achieved CSOs for these PROMs by latest follow‐up, and greater biceps tendon construct migration was negatively associated with the likelihood of CSO achievement. Level of Evidence Level IV, retrospective case series.

Background: Studies suggest that similar clinical results are achieved via arthroscopic and open biceps tenodesis (BT) techniques. Purpose: To quantify the postoperative migration of the BT construct between arthroscopic suprapectoral BT (ASPBT) and open subpectoral BT (OSPBT) techniques via interference screw (IS) or single-suture suture anchor (SSSA) fixation using radiostereometric analysis. Study Design: Cohort study; Level of evidence, 2. Methods: Distal migration of the biceps tendon after OSPBT with a polyetheretherketone IS, OSPBT with 1 SSSA, ASPBT with polyetheretherketone IS, and ASPBT with 2 SSSAs was measured prospectively. Patients with symptomatic biceps tendinopathy and preoperative patient-reported outcome measures (PROMs) including Constant-Murley subjective, Single Assessment Numeric Evaluation, or Patient-Reported Outcomes Measurement Information System–Upper Extremity scores were included. A tantalum bead was sutured on the proximal end of the long head of the biceps tendon before fixation of tendon tissue. Anteroposterior radiographs were performed immediately postoperatively, at 1 week, and at 3 months. Bead migration was measured, and preoperative PROMs were compared with those at latest follow-up. Results: Of 115 patients, 94 (82%) were available for final follow-up. IS fixation yielded the least tendon migration with no difference between the open and arthroscopic approaches (4.31 vs 5.04 mm; P = .70). Fixation with 1 suture anchor demonstrated significantly greater migration than that achieved with an IS at both 1 week (6.47 vs 0.1 mm, 6.47 vs 1.75 mm, P < .001;) and 3 months (14.76 vs 4.31 mm, 14.76 vs 5.04 mm, P < .001) postoperatively. Two-suture anchor fixation yielded significantly greater migration than IS fixation at 1 week (7.02 vs 0.1 mm, P < .001; 7.02 vs 1.75 mm, P = .003) but not 3 months postoperatively (8.06 vs 4.31 mm, P = .10; 8.06 vs 5.04 mm, P = .07). Four patients with suture anchor fixation (3 patients in the OSPBT 1 SSSA group, 9.4%, and 1 patient in the ASPBT 2 SSSAs group, 3.8%) developed a Popeye deformity, whereas no Popeye deformities occurred in the IS groups. Mean 3-month bead migration in patients with and without a Popeye deformity was 60.8 and 11.2 mm, respectively ( P < .0001). PROMs did not differ among groups at final follow-up. Conclusion: Interference screw fixation yielded the least tendon migration whether achieved arthroscopically or open. The available data indicated that fixation with 1 SSSA but not 2 SSSAs resulted in significantly greater migration than that achieved with an IS. Despite variations in tendon migration, PROMs were similar among all groups. When SSSAs are used, tendon migration may be minimized by using ≥2 anchors.

Background: In professional sports, injuries resulting in loss of playing time have serious implications for both the athlete and the organization. Efforts to quantify injury probability utilizing machine learning have been met with renewed interest, and the development of effective models has the potential to supplement the decision-making process of team physicians. Purpose/Hypothesis: The purpose of this study was to (1) characterize the epidemiology of time-loss lower extremity muscle strains (LEMSs) in the National Basketball Association (NBA) from 1999 to 2019 and (2) determine the validity of a machine-learning model in predicting injury risk. It was hypothesized that time-loss LEMSs would be infrequent in this cohort and that a machine-learning model would outperform conventional methods in the prediction of injury risk. Study Design: Case-control study; Level of evidence, 3. Methods: Performance data and rates of the 4 major muscle strain injury types (hamstring, quadriceps, calf, and groin) were compiled from the 1999 to 2019 NBA seasons. Injuries included all publicly reported injuries that resulted in lost playing time. Models to predict the occurrence of a LEMS were generated using random forest, extreme gradient boosting (XGBoost), neural network, support vector machines, elastic net penalized logistic regression, and generalized logistic regression. Performance was compared utilizing discrimination, calibration, decision curve analysis, and the Brier score. Results: A total of 736 LEMSs resulting in lost playing time occurred among 2103 athletes. Important variables for predicting LEMS included previous number of lower extremity injuries; age; recent history of injuries to the ankle, hamstring, or groin; and recent history of concussion as well as 3-point attempt rate and free throw attempt rate. The XGBoost machine achieved the best performance based on discrimination assessed via internal validation (area under the receiver operating characteristic curve, 0.840), calibration, and decision curve analysis. Conclusion: Machine learning algorithms such as XGBoost outperformed logistic regression in the prediction of a LEMS that will result in lost time. Several variables increased the risk of LEMS, including a history of various lower extremity injuries, recent concussion, and total number of previous injuries.

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.

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.