Development of supervised machine learning algorithms for prediction of satisfaction at 2 years following total shoulder arthroplasty

Predicting patient reported outcome measures: a scoping review for the artificial intelligence-guided patient preference predictor

Background

The algorithmic patient preference predictor (PPP) has been proposed to aid in decision making for incapacitated patients in the absence of advanced directives. Ethical and legal challenges aside, multiple practical barriers exist for building a personalized PPP. Here, we examine previous work using machine learning to predict patient reported outcome measures (PROMs) for capacitated patients undergoing diverse procedures, therapies, and life events. Demonstrating robust performance in predicting PROMs for capacitated patients could suggest opportunities for developing a model tailored to incapacitated ones.

Methods

We performed a scoping review of PubMed, Embase, and Scopus using the PRISMA-ScR guidelines to capture studies using machine learning to predict PROMs following a medical event alongside qualitative studies exploring a theoretical PPP.

Results

Sixty-eight studies used machine learning to evaluate PROMs; an additional 20 studies focused on a theoretical PPP. For PROMs, orthopedic surgeries (n = 33) and spinal surgeries (n = 12) were the most common medical event. Studies used demographic (n = 30), pre-event PROMs (n = 52), comorbidities (n = 29), social determinants of health (n = 30), and intraoperative variables (n = 124) as predictors. Thirty-four different PROMs were used as the target outcome. Evaluation metrics varied by task, but performance was overall poor to moderate for the best reported scores. In models that used feature importance, pre-event PROMs were the most predictive of post-event PROMs. Fairness assessments were rare (n = 6). These findings reinforce the necessity of the integrating patient values and preferences, beyond demographic factors, to improve the development of personalized PPP models for incapacitated patients.

Conclusion

The primary objective of a PPP is to estimate patient-reported quality of life following an intervention. Use of machine learning to predict PROMs for capacitated patients introduces challenges and opportunities for building a personalized PPP for incapacitated patients without advanced directives.

Thresholds for diminishing returns in postoperative range of motion after total shoulder arthroplasty

BACKGROUND

Satisfaction following total shoulder arthroplasty (TSA), which is commonly reported using patient-reported outcome measures (PROMs), is partially dependent upon restoring shoulder range of motion (ROM). We hypothesized there exists a minimum amount of ROM necessary to perform functional tasks queried in PROM questionnaires, beyond which further ROM may provide no further improvement in PROMs.

METHODS

A retrospective review of a multicenter international shoulder arthroplasty database was performed between 2004 and 2020 for patients undergoing anatomic or reverse TSA (aTSA, rTSA), with minimum 2-year follow-up. Our primary outcome was to determine the threshold in postoperative active ROM (abduction, forward elevation [FE], external rotation [ER], and internal rotation [IR] score), whereby additional improvement was not associated with additional improvement in PROMs (Simple Shoulder Test, American Shoulder and Elbow Surgeons score, and the Shoulder Pain and Disability Index). For comparison, we also evaluated the Shoulder Arthroplasty Smart (SAS) score, which is not subject to the ceiling effect.

RESULTS

We included 4459 TSAs (1802 aTSAs, 2657 rTSAs) with minimum 2-year follow-up (mean, 56 ± 32 months). The threshold in postoperative ROM that were associated with no further improvement were active abduction, 107-113° for PROMs vs. 163° for the SAS score; active FE, 149-162° for PROMs vs. 176° for the SAS score; active ER, 50-52° for PROMs vs. 72° for the SAS score; IR score, 4-5 points for all PROMs vs. 6 points for the SAS score. Out of 3508 TSAs with complete postoperative ROM data, 8.5% achieved or exceeded all ROM thresholds (14.5% aTSAs, 4.8% rTSAs).

CONCLUSIONS

Our findings demonstrate that postoperative ROM exceeding 113° of abduction, 162° of FE, 52° of ER, and IR to L1 is associated with minimal additional improvement in PROMs. While individual patient needs vary, the thresholds may provide helpful targets for patients undergoing postoperative rehabilitation.

Predicting early return to the operating room in early-onset scoliosis patients using machine learning techniques

PURPOSE

Surgical treatment of early-onset scoliosis (EOS) is associated with high rates of complications, often requiring unplanned return to the operating room (UPROR). The aim of this study was to create and validate a machine learning model to predict which EOS patients will go on to require an UPROR during their treatment course.

METHODS

A retrospective review was performed of all surgical EOS patients with at least 2 years follow-up. Patients were stratified based on whether they had experienced an UPROR. Ten machine learning algorithms were trained using tenfold cross-validation on an independent training set of patients. Model performance was evaluated on a separate testing set via their area under the receiver operating characteristic curve (AUC). Relative feature importance was calculated for the top-performing model.

RESULTS

257 patients were included in the study. 146 patients experienced at least one UPROR (57%). Five factors were identified as significant and included in model training: age at initial surgery, EOS etiology, initial construct type, and weight and height at initial surgery. The Gaussian naïve Bayes model demonstrated the best performance on the testing set (AUC: 0.79). Significant protective factors against experiencing an UPROR were weight at initial surgery, idiopathic etiology, initial definitive fusion construct, and height at initial surgery.

CONCLUSIONS

The Gaussian naïve Bayes machine learning algorithm demonstrated the best performance for predicting UPROR in EOS patients. Heavier, taller, idiopathic patients with initial definitive fusion constructs experienced UPROR less frequently. This model can be used to better quantify risk, optimize patient factors, and choose surgical constructs.

LEVEL OF EVIDENCE

Prognostic: III.

Artificial intelligence in shoulder and elbow surgery: overview of current and future applications

Artificial intelligence (AI) is amongst the most rapidly growing technologies in orthopedic surgery. With the exponential growth in healthcare data, computing power, and complex predictive algorithms, this technology is poised to aid providers in data processing and clinical decision support throughout the continuum of orthopedic care. Understanding the utility and limitations of this technology is vital to practicing orthopedic surgeons, as these applications will become more common place in everyday practice. AI has already demonstrated its utility in shoulder and elbow surgery for imaging-based diagnosis, predictive modeling of clinical outcomes, implant identification, and automated image segmentation. The future integration of AI and robotic surgery represents the largest potential application of AI in shoulder and elbow surgery with the potential for significant clinical and financial impact. This editorial's purpose is to summarize common AI terms, provide a framework to understand and interpret AI model results, and discuss current applications and future directions within shoulder and elbow surgery.

A practical guide to the implementation of artificial intelligence in orthopaedic research-Part 2: A technical introduction

Recent advances in artificial intelligence (AI) present a broad range of possibilities in medical research. However, orthopaedic researchers aiming to participate in research projects implementing AI-based techniques require a sound understanding of the technical fundamentals of this rapidly developing field. Initial sections of this technical primer provide an overview of the general and the more detailed taxonomy of AI methods. Researchers are presented with the technical basics of the most frequently performed machine learning (ML) tasks, such as classification, regression, clustering and dimensionality reduction. Additionally, the spectrum of supervision in ML including the domains of supervised, unsupervised, semisupervised and self-supervised learning will be explored. Recent advances in neural networks (NNs) and deep learning (DL) architectures have rendered them essential tools for the analysis of complex medical data, which warrants a rudimentary technical introduction to orthopaedic researchers. Furthermore, the capability of natural language processing (NLP) to interpret patterns in human language is discussed and may offer several potential applications in medical text classification, patient sentiment analysis and clinical decision support. The technical discussion concludes with the transformative potential of generative AI and large language models (LLMs) on AI research. Consequently, this second article of the series aims to equip orthopaedic researchers with the fundamental technical knowledge required to engage in interdisciplinary collaboration in AI-driven orthopaedic research.

LEVEL OF EVIDENCE

Level IV.

A machine learning analysis of patient and imaging factors associated with achieving clinically substantial outcome improvements following total shoulder arthroplasty: Implications for selecting anatomic or reverse prostheses

Background

Indications for reverse total shoulder arthroplasty(rTSA) continue to expand making it challenging to predict whether patients will benefit more from anatomic TSA(aTSA) or rTSA. The purpose of this study was to determine which factors differ between aTSA and rTSA patients that achieve meaningful outcomes and may influence surgical indication.

Methods

Random Forest dimensionality reduction was applied to reduce 23 features into a model optimizing substantial clinical benefit (SCB) prediction of the American Shoulder and Elbow Surgeon score using 1117 consecutive patients with 2-year follow up. Features were compared between aTSA patients stratified by SCB achievement and subsequently with rTSA SCB achievers.

Results

Eight combined features optimized prediction (accuracy = 87.1%, kappa = 0.73): (1) age, (2) body mass index (BMI), (3) sex, (4) history of rheumatic disease, (5) humeral head subluxation (HH) on computed tomography (CT), (6) HH-acromion distance on X-ray, (7) glenoid retroversion on CT, and (8) Walch classification on CT. A higher proportion of males (65.6% vs. 54.9%, p = 0.022), Walch B-C glenoid morphologies (49.5% vs. 37.9%, p < 0.001), and greater BMI (30.1 vs. 26.5 kg/m2, p = 0.038) were observed in aTSA nonachievers compared with aTSA achievers, while aTSA nonachievers were statistically similar to rTSA achievers.

Discussion

Patients with glenohumeral osteoarthritis and intact rotator cuffs that have a BMI > 30 kg/m2 and exhibit Walch B-C glenoids may be less likely to achieve the SCB following aTSA and should be considered for rTSA.

Emerging Innovations in Preoperative Planning and Motion Analysis in Orthopedic Surgery

In recent years, preoperative planning has undergone significant advancements, with a dual focus: improving the accuracy of implant placement and enhancing the prediction of functional outcomes. These breakthroughs have been made possible through the development of advanced processing methods for 3D preoperative images. These methods not only offer novel visualization techniques but can also be seamlessly integrated into computer-aided design models. Additionally, the refinement of motion capture systems has played a pivotal role in this progress. These "markerless" systems are more straightforward to implement and facilitate easier data analysis. Simultaneously, the emergence of machine learning algorithms, utilizing artificial intelligence, has enabled the amalgamation of anatomical and functional data, leading to highly personalized preoperative plans for patients. The shift in preoperative planning from 2D towards 3D, from static to dynamic, is closely linked to technological advances, which will be described in this instructional review. Finally, the concept of 4D planning, encompassing periarticular soft tissues, will be introduced as a forward-looking development in the field of orthopedic surgery.

Accuracy of machine learning to predict the outcomes of shoulder arthroplasty: a systematic review

BACKGROUND

Artificial intelligence (AI) uses computer systems to simulate cognitive capacities to accomplish goals like problem-solving and decision-making. Machine learning (ML), a branch of AI, makes algorithms find connections between preset variables, thereby producing prediction models. ML can aid shoulder surgeons in determining which patients may be susceptible to worse outcomes and complications following shoulder arthroplasty (SA) and align patient expectations following SA. However, limited literature is available on ML utilization in total shoulder arthroplasty (TSA) and reverse TSA.

METHODS

A systematic literature review in accordance with PRISMA guidelines was performed to identify primary research articles evaluating ML's ability to predict SA outcomes. With duplicates removed, the initial query yielded 327 articles, and after applying inclusion and exclusion criteria, 12 articles that had at least 1 month follow-up time were included.

RESULTS

ML can predict 30-day postoperative complications with a 90% accuracy, postoperative range of motion with a higher-than-85% accuracy, and clinical improvement in patient-reported outcome measures above minimal clinically important differences with a 93%-99% accuracy. ML can predict length of stay, operative time, discharge disposition, and hospitalization costs.

CONCLUSION

ML can accurately predict outcomes and complications following SA and healthcare utilization. Outcomes are highly dependent on the type of algorithms used, data input, and features selected for the model.

LEVEL OF EVIDENCE

III.

Utility of Artificial Intelligence in Orthopedic Surgery Literature Review: A Comparative Pilot Study

OBJECTIVE

Literature reviews are essential to the scientific process and allow clinician researchers to advance general knowledge. The purpose of this study was to evaluate if the artificial intelligence (AI) programs ChatGPT and Perplexity.AI can perform an orthopedic surgery literature review.

MATERIALS AND METHODS

Five different search topics of varying specificity within orthopedic surgery were chosen for each search arm to investigate. A consolidated list of unique articles for each search topic was recorded for the experimental AI search arms and compared with the results of the control arm of two independent reviewers. Articles in the experimental arms were examined by the two independent reviewers for relevancy and validity.

RESULTS

ChatGPT was able to identify a total of 61 unique articles. Four articles were not relevant to the search topic and 51 articles were deemed to be fraudulent, resulting in 6 valid articles. Perplexity.AI was able to identify a total of 43 unique articles. Nineteen were not relevant to the search topic but all articles were able to be verified, resulting in 24 valid articles. The control arm was able to identify 132 articles. Success rates for ChatGPT and Perplexity. AI were 4.6% (6 of 132) and 18.2% (24 of 132), respectively.

CONCLUSION

The current iteration of ChatGPT cannot perform a reliable literature review, and Perplexity.AI is only able to perform a limited review of the medical literature. Any utilization of these open AI programs should be done with caution and human quality assurance to promote responsible use and avoid the risk of using fabricated search results. [Orthopedics. 2024;47(3):e125-e130.].

Re-tear after arthroscopic rotator cuff tear surgery: risk analysis using machine learning

BACKGROUND

Postoperative rotator cuff retear after arthroscopic rotator cuff repair (ARCR) is still a major problem. Various risk factors such as age, gender, and tear size have been reported. Recently, magnetic resonance imaging-based stump classification was reported as an index of rotator cuff fragility. Although stump type 3 is reported to have a high retear rate, there are few reports on the risk of postoperative retear based on this classification. Machine learning (ML), an artificial intelligence technique, allows for more flexible predictive models than conventional statistical methods and has been applied to predict clinical outcomes. In this study, we used ML to predict postoperative retear risk after ARCR.

METHODS

The retrospective case-control study included 353 patients who underwent surgical treatment for complete rotator cuff tear using the suture-bridge technique. Patients who initially presented with retears and traumatic tears were excluded. In study participants, after the initial tear repair, rotator cuff retears were diagnosed by magnetic resonance imaging; Sugaya classification types IV and V were defined as re-tears. Age, gender, stump classification, tear size, Goutallier classification, presence of diabetes, and hyperlipidemia were used for ML parameters to predict the risk of retear. Using Python's Scikit-learn as an ML library, five different AI models (logistic regression, random forest, AdaBoost, CatBoost, LightGBM) were trained on the existing data, and the prediction models were applied to the test dataset. The performance of these ML models was measured by the area under the receiver operating characteristic curve. Additionally, key features affecting retear were evaluated.

RESULTS

The area under the receiver operating characteristic curve for logistic regression was 0.78, random forest 0.82, AdaBoost 0.78, CatBoost 0.83, and LightGBM 0.87, respectively for each model. LightGBM showed the highest score. The important factors for model prediction were age, stump classification, and tear size.

CONCLUSIONS

The ML classifier model predicted retears after ARCR with high accuracy, and the AI model showed that the most important characteristics affecting retears were age and imaging findings, including stump classification. This model may be able to predict postoperative rotator cuff retears based on clinical features.

Evaluating the fairness and accuracy of machine learning-based predictions of clinical outcomes after anatomic and reverse total shoulder arthroplasty

BACKGROUND

Machine learning (ML)-based clinical decision support tools (CDSTs) make personalized predictions for different treatments; by comparing predictions of multiple treatments, these tools can be used to optimize decision making for a particular patient. However, CDST prediction accuracy varies for different patients and also for different treatment options. If these differences are sufficiently large and consistent for a particular subcohort of patients, then that bias may result in those patients not receiving a particular treatment. Such level of bias would deem the CDST "unfair." The purpose of this study is to evaluate the "fairness" of ML CDST-based clinical outcomes predictions after anatomic (aTSA) and reverse total shoulder arthroplasty (rTSA) for patients of different demographic attributes.

METHODS

Clinical data from 8280 shoulder arthroplasty patients with 19,249 postoperative visits was used to evaluate the prediction fairness and accuracy associated with the following patient demographic attributes: ethnicity, sex, and age at the time of surgery. Performance of clinical outcome and range of motion regression predictions were quantified by the mean absolute error (MAE) and performance of minimal clinically important difference (MCID) and substantial clinical benefit classification predictions were quantified by accuracy, sensitivity, and the F1 score. Fairness of classification predictions leveraged the "four-fifths" legal guideline from the US Equal Employment Opportunity Commission and fairness of regression predictions leveraged established MCID thresholds associated with each outcome measure.

RESULTS

For both aTSA and rTSA clinical outcome predictions, only minor differences in MAE were observed between patients of different ethnicity, sex, and age. Evaluation of prediction fairness demonstrated that 0 of 486 MCID (0%) and only 3 of 486 substantial clinical benefit (0.6%) classification predictions were outside the 20% fairness boundary and only 14 of 972 (1.4%) regression predictions were outside of the MCID fairness boundary. Hispanic and Black patients were more likely to have ML predictions out of fairness tolerance for aTSA and rTSA. Additionally, patients <60 years old were more likely to have ML predictions out of fairness tolerance for rTSA. No disparate predictions were identified for sex and no disparate regression predictions were observed for forward elevation, internal rotation score, American Shoulder and Elbow Surgeons Standardized Shoulder Assessment Form score, or global shoulder function.

CONCLUSION

The ML algorithms analyzed in this study accurately predict clinical outcomes after aTSA and rTSA for patients of different ethnicity, sex, and age, where only 1.4% of regression predictions and only 0.3% of classification predictions were out of fairness tolerance using the proposed fairness evaluation method and acceptance criteria. Future work is required to externally validate these ML algorithms to ensure they are equally accurate for all legally protected patient groups.

Initial clinical experience with a predictive clinical decision support tool for anatomic and reverse total shoulder arthroplasty

PURPOSE

Clinical decision support tools (CDSTs) are software that generate patient-specific assessments that can be used to better inform healthcare provider decision making. Machine learning (ML)-based CDSTs have recently been developed for anatomic (aTSA) and reverse (rTSA) total shoulder arthroplasty to facilitate more data-driven, evidence-based decision making. Using this shoulder CDST as an example, this external validation study provides an overview of how ML-based algorithms are developed and discusses the limitations of these tools.

METHODS

An external validation for a novel CDST was conducted on 243 patients (120F/123M) who received a personalized prediction prior to surgery and had short-term clinical follow-up from 3 months to 2 years after primary aTSA (n = 43) or rTSA (n = 200). The outcome score and active range of motion predictions were compared to each patient's actual result at each timepoint, with the accuracy quantified by the mean absolute error (MAE).

RESULTS

The results of this external validation demonstrate the CDST accuracy to be similar (within 10%) or better than the MAEs from the published internal validation. A few predictive models were observed to have substantially lower MAEs than the internal validation, specifically, Constant (31.6% better), active abduction (22.5% better), global shoulder function (20.0% better), active external rotation (19.0% better), and active forward elevation (16.2% better), which is encouraging; however, the sample size was small.

CONCLUSION

A greater understanding of the limitations of ML-based CDSTs will facilitate more responsible use and build trust and confidence, potentially leading to greater adoption. As CDSTs evolve, we anticipate greater shared decision making between the patient and surgeon with the aim of achieving even better outcomes and greater levels of patient satisfaction.

Enabling Personalized Medicine in Orthopaedic Surgery Through Artificial Intelligence: A Critical Analysis Review

» The application of artificial intelligence (AI) in the field of orthopaedic surgery holds potential for revolutionizing health care delivery across 3 crucial domains: (I) personalized prediction of clinical outcomes and adverse events, which may optimize patient selection, surgical planning, and enhance patient safety and outcomes; (II) diagnostic automated and semiautomated imaging analyses, which may reduce time burden and facilitate precise and timely diagnoses; and (III) forecasting of resource utilization, which may reduce health care costs and increase value for patients and institutions.» Computer vision is one of the most highly studied areas of AI within orthopaedics, with applications pertaining to fracture classification, identification of the manufacturer and model of prosthetic implants, and surveillance of prosthesis loosening and failure.» Prognostic applications of AI within orthopaedics include identifying patients who will likely benefit from a specified treatment, predicting prosthetic implant size, postoperative length of stay, discharge disposition, and surgical complications. Not only may these applications be beneficial to patients but also to institutions and payors because they may inform potential cost expenditure, improve overall hospital efficiency, and help anticipate resource utilization.» AI infrastructure development requires institutional financial commitment and a team of clinicians and data scientists with expertise in AI that can complement skill sets and knowledge. Once a team is established and a goal is determined, teams (1) obtain, curate, and label data; (2) establish a reference standard; (3) develop an AI model; (4) evaluate the performance of the AI model; (5) externally validate the model, and (6) reinforce, improve, and evaluate the model's performance until clinical implementation is possible.» Understanding the implications of AI in orthopaedics may eventually lead to wide-ranging improvements in patient care. However, AI, while holding tremendous promise, is not without methodological and ethical limitations that are essential to address. First, it is important to ensure external validity of programs before their use in a clinical setting. Investigators should maintain high quality data records and registry surveillance, exercise caution when evaluating others' reported AI applications, and increase transparency of the methodological conduct of current models to improve external validity and avoid propagating bias. By addressing these challenges and responsibly embracing the potential of AI, the medical field may eventually be able to harness its power to improve patient care and outcomes.

Current clinical applications of artificial intelligence in shoulder surgery: what the busy shoulder surgeon needs to know and what's coming next

Background

Artificial intelligence (AI) is a continuously expanding field with the potential to transform a variety of industries-including health care-by providing automation, efficiency, precision, accuracy, and decision-making support for simple and complex tasks. Basic knowledge of the key features as well as limitations of AI is paramount to understand current developments in this field and to successfully apply them to shoulder surgery. The purpose of the present review is to provide an overview of AI within orthopedics and shoulder surgery exploring current and forthcoming AI applications.

Methods

PubMed and Scopus databases were searched to provide a narrative review of the most relevant literature on AI applications in shoulder surgery.

Results

Despite the enormous clinical and research potential of AI, orthopedic surgery has been a relatively late adopter of AI technologies. Image evaluation, surgical planning, aiding decision-making, and facilitating patient evaluations over time are some of the current areas of development with enormous opportunities to improve surgical practice, research, and education. Furthermore, the advancement of AI-driven strategies has the potential to create a more efficient medical system that may reduce the overall cost of delivering and implementing quality health care for patients with shoulder pathology.

Conclusion

AI is an expanding field with the potential for broad clinical and research applications in orthopedic surgery. Many challenges still need to be addressed to fully leverage the potential of AI to clinical practice and research such as privacy issues, data ownership, and external validation of the proposed models.

Developing a machine learning algorithm to predict the probability of aseptic loosening of the glenoid component after anatomical total shoulder arthroplasty: protocol for a retrospective, multicentre study

INTRODUCTION

Despite technological advancements in recent years, glenoid component loosening remains a common complication after anatomical total shoulder arthroplasty (ATSA) and is one of the main causes of revision surgery. Increasing emphasis is placed on the prevention of glenoid component failure. Previous studies have successfully predicted range of motion, patient-reported outcomes and short-term complications after ATSA using machine learning methods, but an accurate predictive model for (glenoid component) revision is currently lacking. This study aims to use a large international database to accurately predict aseptic loosening of the glenoid component after ATSA using machine learning algorithms.

METHODS AND ANALYSIS

For this multicentre, retrospective study, individual patient data will be compiled from previously published studies reporting revision of ATSA. A systematic literature search will be performed in Medline (PubMed) identifying all studies reporting outcomes of ATSA. Authors will be contacted and invited to participate in the Machine Learning Consortium by sharing their anonymised databases. All databases reporting revisions after ATSA will be included, and individual patients with a follow-up less than 2 years or a fracture as the indication for ATSA will be excluded. First, features (predictive variables) will be identified using a random forest feature selection. The resulting features from the compiled database will be used to train various machine learning algorithms (stochastic gradient boosting, random forest, support vector machine, neural network and elastic-net penalised logistic regression). The developed and validated algorithms will be evaluated across discrimination (c-statistic), calibration, the Brier score and the decision curve analysis. The best-performing algorithm will be used to create an open-access online prediction tool.

ETHICS AND DISSEMINATION

Data will be collected adhering to the WHO regulation on data sharing. An Institutional Review Board review is not applicable. The study results will be published in a peer-reviewed journal.

Challenges and Opportunities for the Use of Patient-Reported Outcome Measures in Orthopaedic Pediatric and Sports Medicine Surgery

Patient-reported outcome measures (PROMs) are essential tools in assessing treatment response, informing clinical decision making, driving healthcare policy, and providing important prognostic data regarding patient health status change. These tools become essential in orthopaedic disciplines, such as pediatrics and sports medicine, given the diversity of patient populations and procedures. However, the creation and routine administration of standard PROMs alone do not suffice to appropriately facilitate the aforementioned functions. Indeed, both the interpretation and optimal application of PROMs are essential to provide to achieve greatest clinical benefit. Contemporary developments and technologies surrounding PROMs may help augment this benefit, including the application of artificial intelligence, novel PROM structure with improved interpretability and validity, and PROM delivery methods that provide increased access to patients resulting in greater compliance and data acquisition yields. Despite these exciting innovations, several challenges remain in this realm that must be addressed to continue to advance the clinical usefulness and subsequent benefit of PROMs. This review will highlight the opportunities and challenges surrounding contemporary PROM use in the orthopaedic subspecialties of pediatrics and sports medicine.

Technological innovations in shoulder replacement: current concepts and the future of robotics in total shoulder arthroplasty

BACKGROUND

Total shoulder arthroplasty (TSA) has been rapidly evolving over the last several decades, with innovative technological strategies being investigated and developed in order to achieve optimal component precision and joint alignment and stability, preserve implant longevity, and improve patient outcomes. Future advancements such as robotic-assisted surgeries, augmented reality, artificial intelligence, patient-specific instrumentation (PSI) and other peri- and preoperative planning tools will continue to revolutionize TSA. Robotic-assisted arthroplasty is a novel and increasingly popular alternative to the conventional arthroplasty procedure in the hip and knee but has not yet been investigated in the shoulder. Therefore, the purpose of this study was to conduct a narrative review of the literature on the evolution and projected trends of technological advances and robotic assistance in total shoulder arthroplasty.

METHODS

A narrative synthesis method was employed for this review, rather than a meta-analysis or systematic review of the literature. This decision was based on 2 primary factors: (1) the lack of eligible, peer-reviewed studies with high-quality level of evidence available for review on robotic-assisted shoulder arthroplasty, and (2) a narrative review allows for a broader scope of content analysis, including a comprehensive review of all technological advances-including robotics-within the field of TSA. A general literature search was performed using PubMed, Embase, and Cochrane Library databases. These databases were queried by 2 independent reviewers from database inception through November 11, 2022, for all articles investigating the role of robotics and technology assistance in total shoulder arthroplasty. Inclusion criteria included studies describing "shoulder arthroplasty" and "robotics."

RESULTS

After exclusion criteria were applied, 4 studies on robotic-assisted TSA were described in the review. Given the novelty of this technology and limited data on robotics in TSA, these studies consisted of a literature review, nonvalidated experimental biomechanical studies in sawbones models, and preclinical proof-of-concept cadaveric studies using prototype robotic technology primarily in conjunction with PSI. The remaining studies described the technological advancements in TSA, including PSI, computer-assisted navigation, artificial intelligence, machine learning, and virtual, augmented, and mixed reality. Although not yet commercially available, robotic-assisted TSA confers the theoretical advantages of precise humeral head cuts for restoration of proximal humerus anatomy, more accurate glenoid preparation, and improved soft-tissue assessment in limited early studies.

CONCLUSION

The evidence for the use of robotics in total hip arthroplasty and total knee arthroplasty demonstrates improved component accuracy, more precise radiographic measurements, and improved early/mid-term patient-reported and functional outcomes. Although no such data currently exist for shoulder arthroplasty given that the technology has not yet been commercialized, the lessons learned from robotic hip and knee surgery in conjunction with its rapid adoption suggests robotic-assisted TSA is on the horizon of innovation. By achieving a better understanding of the past, present, and future innovations in TSA through this narrative review, orthopedic surgeons can be better prepared for future applications.

Artificial Intelligence for Automated Implant Identification in Total Hip Arthroplasty: A Multicenter External Validation Study Exceeding Two Million Plain Radiographs

BACKGROUND

The surgical management of complications after total hip arthroplasty (THA) necessitates accurate identification of the femoral implant manufacturer and model. Automated image processing using deep learning has been previously developed and internally validated; however, external validation is necessary prior to responsible application of artificial intelligence (AI)-based technologies.

METHODS

We trained, validated, and externally tested a deep learning system to classify femoral-sided THA implants as one of the 8 models from 2 manufacturers derived from 2,954 original, deidentified, retrospectively collected anteroposterior plain radiographs across 3 academic referral centers and 13 surgeons. From these radiographs, 2,117 were used for training, 249 for validation, and 588 for external testing. Augmentation was applied to the training set (n = 2,117,000) to increase model robustness. Performance was evaluated by area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy. Implant identification processing speed was calculated.

RESULTS

The training and testing sets were drawn from statistically different populations of implants (P < .001). After 1,000 training epochs by the deep learning system, the system discriminated 8 implant models with a mean area under the receiver operating characteristic curve of 0.991, accuracy of 97.9%, sensitivity of 88.6%, and specificity of 98.9% in the external testing dataset of 588 anteroposterior radiographs. The software classified implants at a mean speed of 0.02 seconds per image.

CONCLUSION

An AI-based software demonstrated excellent internal and external validation. Although continued surveillance is necessary with implant library expansion, this software represents responsible and meaningful clinical application of AI with immediate potential to globally scale and assist in preoperative planning prior to revision THA.

Artificial intelligence-based applications in shoulder surgery leaves much to be desired: a systematic review

Background

Artificial intelligence (AI) aims to simulate human intelligence using automated computer algorithms. There has been a rapid increase in research applying AI to various subspecialties of orthopedic surgery, including shoulder surgery. The purpose of this review is to assess the scope and validity of current clinical AI applications in shoulder surgery literature.

Methods

A systematic literature review was conducted using PubMed for all articles published between January 1, 2010 and June 10, 2022. The search query used the terms as follows: (artificial intelligence OR machine learning OR deep learning) AND (shoulder OR shoulder surgery OR rotator cuff). All studies that examined AI application models in shoulder surgery were included and evaluated for model performance and validation (internal, external, or both).

Results

A total of 45 studies were included in the final analysis. Eighteen studies involved shoulder arthroplasty, 13 rotator cuff, and 14 other areas. Studies applying AI to shoulder surgery primarily involved (1) automated imaging analysis including identifying rotator cuff tears and shoulder implants (2) risk prediction analyses including perioperative complications, functional outcomes, and patient satisfaction. Highest model performance area under the curve ranged from 0.681 (poor) to 1.00 (perfect). Only 2 studies reported external validation.

Conclusion

Applications of AI in the field of shoulder surgery are expanding rapidly and offer patient-specific risk stratification for shared decision-making and process automation for resource preservation. However, model performance is modest and external validation remains to be demonstrated, suggesting increased scientific rigor is warranted prior to deploying AI-based clinical applications.

Prediction of total healthcare cost following total shoulder arthroplasty utilizing machine learning

BACKGROUND

Given the increase in demand in treatment of glenohumeral arthritis with anatomic total (aTSA) and reverse shoulder arthroplasty (RTSA), it is imperative to improve quality of patient care while controlling costs as private and federal insurers continue its gradual transition toward bundled payment models. Big data analytics with machine learning shows promise in predicting health care costs. This is significant as cost prediction may help control cost by enabling health care systems to appropriately allocate resources that help mitigate the cause of increased cost.

METHODS

The Nationwide Readmissions Database (NRD) was accessed in 2018. The database was queried for all primary aTSA and RTSA by International Classification of Diseases, Tenth Revision (ICD-10) procedure codes: 0RRJ0JZ and 0RRK0JZ for aTSA and 0RRK00Z and 0RRJ00Z for RTSA. Procedures were categorized by diagnoses: osteoarthritis (OA), rheumatoid arthritis (RA), avascular necrosis (AVN), fracture, and rotator cuff arthropathy (RCA). Costs were calculated by utilizing the total hospital charge and each hospital's cost-to-charge ratio. Hospital characteristics were included, such as volume of procedures performed by the respective hospital for the calendar year and wage index, which represents the relative average hospital wage for the respective geographic area. Unplanned readmissions within 90 days were calculated using unique patient identifiers, and cost of readmissions was added to the total admission cost to represent the short-term perioperative health care cost. Machine learning algorithms were used to predict patients with immediate postoperative admission costs greater than 1 standard deviation from the mean, and readmissions.

RESULTS

A total of 49,354 patients were isolated for analysis, with an average patient age of 69.9 ± 9.6 years. The average perioperative cost of care was $18,843 ± $10,165. In total, there were 4279 all-cause readmissions, resulting in an average cost of $13,871.00 ± $14,301.06 per readmission. Wage index, hospital volume, patient age, readmissions, and diagnosis-related group severity were the factors most correlated with the total cost of care. The logistic regression and random forest algorithms were equivalent in predicting the total cost of care (area under the receiver operating characteristic curve = 0.83).

CONCLUSION

After shoulder arthroplasty, there is significant variability in cumulative hospital costs, and this is largely affected by readmissions. Hospital characteristics, such as geographic area and volume, are key determinants of overall health care cost. When accounting for this, machine learning algorithms may predict cases with high likelihood of increased resource utilization and/or readmission.

Surgeon confidence in planning total shoulder arthroplasty improves after consulting a clinical decision support tool

PURPOSE

Software algorithms are increasingly available as clinical decision support tools (CDSTs) to support shared decision-making. We sought to understand if patient-specific predictions from a CDST would impact orthopedic surgeons' preoperative planning decisions and corresponding confidence.

METHODS

We performed a survey study of orthopedic surgeons with at minimum of 2 years of independent shoulder arthroplasty experience. We generated patient profiles for 18 faux cases presenting with glenohumeral osteoarthritis and emailed 93 surgeons requesting their recommendation for anatomic or reverse total shoulder arthroplasty for each case and their certainty in their recommendation on a 4-point Likert scale. The thirty respondents were later sent a second survey with the same cases that now included predicted patient-specific outcomes and complication rates generated by a CDST.

RESULTS

Initial recommendations and changes in recommendation varied widely by surgeon and by case. After viewing the results of the CDST, surgeons switched from anatomic to reverse recommendations in 46 instances (12% of initial anatomic) and from reverse to anatomic in 22 instances (6% of initial reverse). Overall, surgeon change in confidence increased significantly across all responses (p = 0.0001), with certain cases and certain surgeons having significant changes. Change in confidence did not correlate with surgeon-specific factors, including years in practice.

CONCLUSION

The addition of CDST reports to preoperative planning for anatomic and reverse total shoulder arthroplasty informed decision-making but did not direct recommendations uniformly. However, the CDST information provided did increase surgeon confidence regardless of implant selection and irrespective of surgeon experience.

Research on artificial intelligence in shoulder and elbow surgery is increasing

Background

Total health care spending in the United States is increasing. In order to improve our delivery of high-quality, patient-centric, and cost-effective care, artificial intelligence (AI) and its subsets are being increasingly explored and utilized in medicine. Applications of AI in orthopedic surgery, including shoulder and elbow surgery, are being actively studied and have stirred much discussion. However, the trends of research on AI applications in shoulder and elbow surgery have not yet been quantified. Thus, the purpose of this study is to explore the general trends of research in applying AI to shoulder and elbow surgery and to examine characteristics of these research publications.

Methods

A literature search was conducted using PubMed for all articles published between January 1, 2000 and May 12, 2022. The primary search query used was as follows: (shoulder) and (AI OR machine learning OR deep learning OR neural networks). Exclusion criteria were as follows: (1) not pertinent to orthopedic surgeons (2) not pertaining to shoulder or elbow surgery, and (3) not pertaining to AI, machine learning, and deep learning. Selected articles in high-impact and relevant orthopedic journals were further characterized and analyzed.

Results

The annual number of articles increased from 1 article in 2006 to 24 articles in 2021. There was a 4-fold increase in publications between 2019 and 2021, and a 6-fold increase between 2018 and 2021. The average number of publications per year increased exponentially from 2010 to 2021 (R2 = 0.608; P = .003). The three journals with the most publications were Journal of Shoulder and Elbow Surgery (12), followed by Arthroscopy (2), and Clinical Orthopaedics and Related Research (2).

Conclusion

This study provides quantitative evidence for the first time that publications applying AI and its subsets to shoulder and elbow surgery are growing exponentially since the year 2010, with the most rapid growth beginning between the years of 2019 and 2020.

Violation of expectations is correlated with satisfaction following hip arthroscopy

PURPOSE

The mechanism by which preoperative expectations may be associated with patient satisfaction and procedural outcomes following hip preservation surgery (HPS) is far from simple or linear. The purpose of this study is to better understand patient expectations regarding HPS and their relationship with patient-reported outcomes (PROs) and satisfaction using machine learning (ML) algorithms.

METHODS

Patients scheduled for hip arthroscopy completed the Hip Preservation Surgery Expectations Survey (HPSES) and the pre- and a minimum 2 year postoperative International Hip Outcome Tool (iHOT-33). Patient demographics, including age, gender, occupation, and body mass index (BMI), were also collected. At the latest follow-up, patients were evaluated for subjective satisfaction and postoperative complications. ML algorithms and standard statistics were used.

RESULTS

A total of 69 patients were included in this study (mean age 33.7 ± 13.1 years, 62.3% males). The mean follow-up period was 27 months. The mean HPSES score, patient satisfaction, preoperative, and postoperative iHOT-33 were 83.8 ± 16.5, 75.9 ± 26.9, 31.6 ± 15.8, and 73 ± 25.9, respectively. Fifty-nine patients (86%) reported that they would undergo the surgery again, with no significant difference with regards to expectations. A significant difference was found with regards to expectation violation (p < 0.001). Expectation violation scores were also found to be significantly correlated with satisfaction.

CONCLUSION

ML algorithms utilized in this study demonstrate that violation of expectations plays an important predictive role in postoperative outcomes and patient satisfaction and is associated with patients' willingness to undergo surgery again.

LEVEL OF EVIDENCE

IV.

Online Education Satisfaction Assessment Based on Machine Learning Model in Wireless Network Environment

With the development of wireless network technology, the transformation of educational concepts, the upgrading of users' educational needs, and the transformation of lifestyles, online education has made great strides forward. However, due to the rapid growth of online education in my country, many regulatory systems have not kept pace with the development of online education, resulting in low user experience and satisfaction with online education. The establishment of a user satisfaction model is beneficial for attracting attention and thinking about research in the field of online education service quality, assisting enterprises in recognizing the specific impact of various factors in services, accelerating service quality improvement, and assisting in the formulation of industry norms and improving enterprise competitiveness, all of which help students acquire knowledge more easily. In the era of big data, traditional satisfaction evaluation methods have many drawbacks, so more and more machine learning methods are applied to satisfaction evaluation models. This paper takes the research of machine learning algorithm as the core to carry out the research work, uses the cost-sensitive idea to improve the decision tree, considers the cost of different types of classification errors, and uses the random forest principle to integrate the generated decision tree, thereby improving the accuracy of the model. The model has better stability, and the validity of the model is verified by experiments. For a follow-up in-depth investigation of online education satisfaction rating technology, the linked work of this paper has certain reference and reference value.

Machine Learning Algorithms Predict Achievement of Clinically Significant Outcomes After Orthopaedic Surgery: A Systematic Review

PURPOSE

To determine what subspecialties have applied machine learning (ML) to predict clinically significant outcomes (CSOs) within orthopaedic surgery and to determine whether the performance of these models was acceptable through assessing discrimination and other ML metrics where reported.

METHODS

The PubMed, EMBASE, and Cochrane Central Register of Controlled Trials databases were queried for articles that used ML to predict achievement of the minimal clinically important difference (MCID), patient acceptable symptomatic state (PASS), or substantial clinical benefit (SCB) after orthopaedic surgical procedures. Data pertaining to demographic characteristics, subspecialty, specific ML algorithms, and algorithm performance were analyzed.

RESULTS

Eighteen articles met the inclusion criteria. Seventeen studies developed novel algorithms, whereas one study externally validated an established algorithm. All studies used ML to predict MCID achievement, whereas 3 (16.7%) predicted SCB achievement and none predicted PASS achievement. Of the studies, 7 (38.9%) concerned outcomes after spine surgery; 6 (33.3%), after sports medicine surgery; 3 (16.7%), after total joint arthroplasty (TJA); and 2 (11.1%), after shoulder arthroplasty. No studies were found regarding trauma, hand, elbow, pediatric, or foot and ankle surgery. In spine surgery, concordance statistics (C-statistics) ranged from 0.65 to 0.92; in hip arthroscopy, 0.51 to 0.94; in TJA, 0.63 to 0.89; and in shoulder arthroplasty, 0.70 to 0.95. Most studies reported C-statistics at the upper end of these ranges, although populations were heterogeneous.

CONCLUSIONS

Currently available ML algorithms can discriminate the propensity to achieve CSOs using the MCID after spine, TJA, sports medicine, and shoulder surgery with a fair to good performance as evidenced by C-statistics ranging from 0.6 to 0.95 in most analyses. Less evidence is available on the ability of ML to predict achievement of SCB, and no evidence is available for achievement of the PASS. Such algorithms may augment shared decision-making practices and allow clinicians to provide more appropriate patient expectations using individualized risk assessments. However, these studies remain limited by variable reporting of performance metrics, CSO quantification methods, and adherence to predictive modeling guidelines, as well as limited external validation.

LEVEL OF EVIDENCE

Level III, systematic review of Level III studies.

Efficacy and Applications of Artificial Intelligence and Machine Learning Analyses in Total Joint Arthroplasty: A Call for Improved Reporting

BACKGROUND

There has been a considerable increase in total joint arthroplasty (TJA) research using machine learning (ML). Therefore, the purposes of this study were to synthesize the applications and efficacies of ML reported in the TJA literature, and to assess the methodological quality of these studies.

METHODS

PubMed, OVID/MEDLINE, and Cochrane libraries were queried in January 2021 for articles regarding the use of ML in TJA. Study demographics, topic, primary and secondary outcomes, ML model development and testing, and model presentation and validation were recorded. The TRIPOD (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis) guidelines were used to assess the methodological quality.

RESULTS

Fifty-five studies were identified: 31 investigated clinical outcomes and resource utilization; 11, activity and motion surveillance; 10, imaging detection; and 3, natural language processing. For studies reporting the area under the receiver operating characteristic curve (AUC), the median AUC (and range) was 0.80 (0.60 to 0.97) among 26 clinical outcome studies, 0.99 (0.83 to 1.00) among 6 imaging-based studies, and 0.88 (0.76 to 0.98) among 3 activity and motion surveillance studies. Twelve studies compared ML to logistic regression, with 9 (75%) reporting that ML was superior. The average number of TRIPOD guidelines met was 11.5 (range: 5 to 18), with 38 (69%) meeting greater than half of the criteria. Presentation and explanation of the full model for individual predictions and assessments of model calibration were poorly reported (<30%).

CONCLUSIONS

The performance of ML models was good to excellent when applied to a wide variety of clinically relevant outcomes in TJA. However, reporting of certain key methodological and model presentation criteria was inadequate. Despite the recent surge in TJA literature utilizing ML, the lack of consistent adherence to reporting guidelines needs to be addressed to bridge the gap between model development and clinical implementation.

Using machine learning to predict internal rotation after anatomic and reverse total shoulder arthroplasty

BACKGROUND

Improvement in internal rotation (IR) after anatomic (aTSA) and reverse (rTSA) total shoulder arthroplasty is difficult to predict, with rTSA patients experiencing greater variability and more limited IR improvements than aTSA patients. The purpose of this study is to quantify and compare the IR score for aTSA and rTSA patients and create supervised machine learning that predicts IR after aTSA and rTSA at multiple postoperative time points.

METHODS

Clinical data from 2270 aTSA and 4198 rTSA patients were analyzed using 3 supervised machine learning techniques to create predictive models for internal rotation as measured by the IR score at 6 postoperative time points. Predictions were performed using the full input feature set and 2 minimal input feature sets. The mean absolute error (MAE) quantified the difference between actual and predicted IR scores for each model at each time point. The predictive accuracy of the XGBoost algorithm was also quantified by its ability to distinguish which patients would achieve clinical improvement greater than the minimal clinically important difference (MCID) and substantial clinical benefit (SCB) patient satisfaction thresholds for IR score at 2-3 years after surgery.

RESULTS

rTSA patients had significantly lower mean IR scores and significantly less mean IR score improvement than aTSA patients at each postoperative time point. Both aTSA and rTSA patients experienced significant improvements in their ability to perform activities of daily living (ADLs); however, aTSA patients were significantly more likely to perform these ADLs. Using a minimal feature set of preoperative inputs, our machine learning algorithms had equivalent accuracy when predicting IR score for both aTSA (0.92-1.18 MAE) and rTSA (1.03-1.25 MAE) from 3 months to >5 years after surgery. Furthermore, these predictive algorithms identified with 90% accuracy for aTSA and 85% accuracy for rTSA which patients will achieve MCID IR score improvement and predicted with 85% accuracy for aTSA patients and 77% accuracy for rTSA which patients will achieve SCB IR score improvement at 2-3 years after surgery.

DISCUSSION

Our machine learning study demonstrates that active internal rotation can be accurately predicted after aTSA and rTSA at multiple postoperative time points using a minimal feature set of preoperative inputs. These predictive algorithms accurately identified which patients will, and will not, achieve clinical improvement in IR score that exceeds the MCID and SCB patient satisfaction thresholds.

Development of a Machine Learning Algorithm for Prediction of Complications and Unplanned Readmission Following Reverse Total Shoulder Arthroplasty

Background

Reverse total shoulder arthroplasty (rTSA) offers tremendous promise for the treatment of complex pathologies beyond the scope of anatomic total shoulder arthroplasty but is associated with a higher rate of major postoperative complications. We aimed to design and validate a machine learning (ML) model to predict major postoperative complications or readmission following rTSA.

Methods

We retrospectively reviewed California's Office of Statewide Health Planning and Development database for patients who underwent rTSA between 2015 and 2017. We implemented logistic regression (LR), extreme gradient boosting (XGBoost), gradient boosting machines, adaptive boosting, and random forest classifiers in Python and trained these models using 64 binary, continuous, and discrete variables to predict the occurrence of at least one major postoperative complication or readmission following primary rTSA. Models were validated using the standard metrics of area under the receiver operating characteristic (AUROC) curve, area under the precision–recall curve (AUPRC), and Brier scores. The key factors for the top-performing model were determined.

Results

Of 2799 rTSAs performed during the study period, 152 patients (5%) had at least 1 major postoperative complication or 30-day readmission. XGBoost had the highest AUROC and AUPRC of 0.681 and 0.129, respectively. The key predictive features in this model were patients with a history of implant complications, protein-calorie malnutrition, and a higher number of comorbidities.

Conclusion

Our study reports an ML model for the prediction of major complications or 30-day readmission following rTSA. XGBoost outperformed traditional LR models and also identified key predictive features of complications and readmission.

Development and Internal Validation of Machine Learning Algorithms for Predicting Hyponatremia After TJA

BACKGROUND

The development of hyponatremia after total joint arthroplasty (TJA) may lead to several adverse events and is associated with prolonged inpatient length of stay as well as increased hospital costs. The purpose of this study was to develop and internally validate machine learning algorithms for predicting hyponatremia after TJA.

METHODS

A consecutive cohort of 30,703 TJA patients from an institutional registry at a large, tertiary academic hospital were included. A total of 19 potential predictor variables were collected. Hyponatremia was defined as a serum sodium concentration of <135 mEq/L. Five machine learning algorithms were developed using a training set and internally validated using an independent testing set. Algorithm performance was evaluated through discrimination, calibration, decision-curve analysis, and Brier score.

RESULTS

The charts of 30,703 patients undergoing TJA were reviewed. Of those patients, 5,480 (17.8%) developed hyponatremia postoperatively. A combination of 6 variables were demonstrated to optimize algorithm prediction: preoperative serum sodium concentration, age, intraoperative blood loss, procedure time, body mass index (BMI), and American Society of Anesthesiologists (ASA) score. Threshold values that were associated with greater hyponatremia risk were a preoperative serum sodium concentration of ≤138 mEq/L, an age of ≥73 years, an ASA score of >2, intraoperative blood loss of >407 mL, a BMI of ≤26 kg/m2, and a procedure time of >111 minutes. The stochastic gradient boosting (SGB) algorithm demonstrated the best performance (c-statistic: 0.75, calibration intercept: -0.02, calibration slope: 1.02, and Brier score: 0.12). This algorithm was turned into a tool that can provide real-time predictions (https://orthoapps.shinyapps.io/Hyponatremia_TJA/).

CONCLUSIONS

The SGB algorithm demonstrated the best performance for predicting hyponatremia after TJA. The most important factors for predicting hyponatremia were preoperative serum sodium concentration, age, intraoperative blood loss, procedure time, BMI, and ASA score. A real-time hyponatremia risk calculator was developed, but it is imperative to perform external validation of this model prior to using this calculator in clinical practice.

LEVEL OF EVIDENCE

Prognostic Level IV. See Instructions for Authors for a complete description of levels of evidence.

Does preoperative disease severity influence outcomes in reverse shoulder arthroplasty for cuff tear arthropathy?

BACKGROUND

The degree of symptomatic disease and functional burden has been demonstrated to influence patient results and satisfaction in total hip and knee arthroplasty. Although the relationship between preoperative diagnosis and patient outcomes has been an area of study for reverse total shoulder arthroplasty (RTSA), the influence of the progression of cuff tear arthropathy (CTA) has not yet been examined. The purpose of this study was to evaluate whether preoperative radiographic disease burden and scapular geometry impact patient outcomes and satisfaction in a cohort of patients with CTA treated with RTSA.

METHODS

Eighty-six patients were treated for CTA with RTSA performed by the senior author (B.G.) between September 2016 and September 2018 and were enrolled in an institutional registry. At the time of initial evaluation, the baseline American Shoulder and Elbow Surgeons (ASES) score, patient demographic characteristics, history of shoulder surgery, and presence of pseudoparalysis were collected. Radiographs were obtained to evaluate the critical shoulder angle, acromial index, and progression of CTA as assessed by Hamada grading and the Seebauer classification. Patients were contacted to reassess the ASES score and their satisfaction with the improvement in their shoulder function.

RESULTS

A total of 79 patients (91.6%) were available for evaluation at a minimum of 24 months of follow-up. Multivariate logistic regression modeling revealed that scapular geometry measurements (critical shoulder angle and acromial index) and the degree of CTA (Seebauer and Hamada classifications) were not associated with worse outcomes as assessed by the ASES score. However, degenerative changes as assessed by the Hamada grade (odds ratio, 0.13 [95% confidence interval, 0.02-0.86]; P = .03) and preoperative ASES score (odds ratio, 1.04 [95% confidence interval, 1.01-1.07]; P = .008) were independently associated with higher satisfaction at 24 months of follow-up.

CONCLUSION

The results indicate that patients with greater CTA disease progression did not show differing outcomes after RTSA compared with patients with milder disease. In contrast, both poorer preoperative function and degenerative changes as assessed by the Hamada classification were associated with greater satisfaction after RTSA for CTA. Given the broad spectrum of disease in CTA, there is likely a corresponding range in patient expectations that requires further study to maximize patient satisfaction.

Validation and performance of a machine-learning derived prediction guide for total knee arthroplasty component sizing

INTRODUCTION

Anticipation of patient-specific component sizes prior to total knee arthroplasty (TKA) is essential to avoid excessive cost associated with additional surgical trays and morbidity associated with imperfect sizing. Current methods of size prediction, including templating, are inconsistent and time-consuming. Machine learning (ML) algorithms may allow for accurate TKA component size prediction with the ability to make predictions in real-time.

METHODS

Consecutive patients receiving primary TKA between 2012 and 2020 from two large tertiary academic and six community hospitals were identified. The primary outcomes were the final femoral and tibial component sizes extracted from automated inventory systems. Five ML algorithms were trained with routinely corrected demographic variables (age, height, weight, body mass index, and sex) using 80% of the study population and internally validated on an independent set of the remaining 20% of patients. Algorithm performance was evaluated through accuracy, mean absolute error (MAE), and root mean-squared error (RMSE).

RESULTS

A total of 17,283 patients that received one of 9 TKA implants from independent manufacturers were included. The SGB model accuracy for predicting ± 4-mm of the true femoral anteroposterior diameter was 83.6% and for ± 1 size of the true femoral component size was 95.0%. The SGB model accuracy for predicting ± 4-mm of the true tibial medial/lateral diameter was 83.0% and for ± 1 size of the true tibial component size was 97.8%. Patient sex was the most influential feature in terms of informing the SGB model predictions for both femoral and tibial component sizing. A TKA implant sizing application was subsequently created.

CONCLUSION

Novel machine learning algorithms demonstrated good to excellent performance for predicting TKA component size. Patient sex appears to contribute an important role in predicting TKA size. A web-based real-time prediction application was created capable of integrating patient specific data to predict TKA size, which will require external validation prior to clinical use.

Risk factors for complications and revision surgery after anatomic and reverse total shoulder arthroplasty

BACKGROUND

Complications and revisions following anatomic (aTSA) and reverse (rTSA) total shoulder arthroplasty have deleterious effects on patient function and satisfaction. The purpose of this study is to evaluate patient-specific, implant-specific and technique-specific risk factors for intraoperative complications, postoperative complications, and the occurrence of revisions after aTSA and rTSA.

METHODS

A total of 2964 aTSA and 5616 rTSA patients were enrolled in an international database of primary shoulder arthroplasty. Intra- and postoperative complications, as well as revisions, were reported and evaluated. Multivariate analyses were performed to quantify the risk factors associated with complications and revisions.

RESULTS

aTSA patients had a significantly higher complication rate (P = .0026) and a significantly higher revision rate (P < .0001) than rTSA patients, but aTSA patients also had a significantly longer average follow-up (P < .0001) than rTSA patients. No difference (P = .2712) in the intraoperative complication rate was observed between aTSA and rTSA patients. Regarding intraoperative complications, female sex (odds ratio [OR] 2.0, 95% confidence interval [CI] 1.17-3.68) and previous shoulder surgery (OR 2.9, 95% CI 1.73-4.90) were identified as significant risk factors. In regard to postoperative complications, younger age (OR 0.987, 95% CI 0.977-0.996), diagnosis of rheumatoid arthritis (OR 1.76, 95% 1.12-2.65), and previous shoulder surgery (OR 1.42, 95% CI 1.16-1.72) were noted to be risks factors. Finally, in regard to revision surgery, younger age (OR 0.964, 95% CI 0.933-0.998), more glenoid retroversion (OR 1.03, 95% CI 1.001-1.058), larger humeral stem size (OR 1.09, 95% CI 1.01-1.19), larger humeral liner thickness or offset (OR 1.50, 95% CI 1.18-1.96), larger glenosphere diameter (OR 1.16, 95% CI 1.07-1.26), and more intraoperative blood loss (OR 1.002, 95% CI 1.001-1.004) were noted to be risk factors.

CONCLUSIONS

Studying the impact of numerous patient- and implant-specific risk factors and determining their impact on complications and revision shoulder arthroplasty can assist surgeons in counseling patients and guide patient expectations following aTSA or rTSA. Care should be taken in patients with a history of previous shoulder surgery, who are at increased risk of both intra- and postoperative complications.

Application of Machine Learning Methods on Patient Reported Outcome Measurements for Predicting Outcomes: A Literature Review

The field of patient-centred healthcare has, during recent years, adopted machine learning and data science techniques to support clinical decision making and improve patient outcomes. We conduct a literature review with the aim of summarising the existing methodologies that apply machine learning methods on patient-reported outcome measures datasets for predicting clinical outcomes to support further research and development within the field. We identify 15 articles published within the last decade that employ machine learning methods at various stages of exploiting datasets consisting of patient-reported outcome measures for predicting clinical outcomes, presenting promising research and demonstrating the utility of patient-reported outcome measures data for developmental research, personalised treatment and precision medicine with the help of machine learning-based decision-support systems. Furthermore, we identify and discuss the gaps and challenges, such as inconsistency in reporting the results across different articles, use of different evaluation metrics, legal aspects of using the data, and data unavailability, among others, which can potentially be addressed in future studies.

Development and Internal Validation of Supervised Machine Learning Algorithms for Predicting Clinically Significant Functional Improvement in a Mixed Population of Primary Hip Arthroscopy

PURPOSE

To (1) develop and validate a machine learning algorithm to predict clinically significant functional improvements after hip arthroscopy for femoroacetabular impingement syndrome and to (2) develop a digital application capable of providing patients with individual risk profiles to determine their propensity to gain clinically significant improvements in function.

METHODS

A retrospective review of consecutive hip arthroscopy patients who underwent cam/pincer correction, labral preservation, and capsular closure between January 2012 and 2017 from 1 large academic and 3 community hospitals operated on by a single high-volume hip arthroscopist was performed. The primary outcome was the minimal clinically important difference (MCID) for the Hip Outcome Score (HOS)-Activities of Daily Living (ADL) at 2 years postoperatively, which was calculated using a distribution-based method. A total of 21 demographic, radiographic, and patient-reported outcome measures were considered as potential covariates. An 80:20 random split was used to create training and testing sets from the patient cohort. Five supervised machine learning algorithms were developed using 3 iterations of 10-fold cross-validation on the training set and assessed by discrimination, calibration, Brier score, and decision curve analysis on an independent testing set of patients.

RESULTS

A total of 818 patients with a median (interquartile range) age of 32.0 (22.0-42.0) and 69.2% female were included, of whom 74.3% achieved the MCID for the HOS-ADL. The best-performing algorithm was the stochastic gradient boosting model (c-statistic = 0.84, calibration intercept = 0.20, calibration slope = 0.83, and Brier score = 0.13). Of the initial 21 candidate variables, the 8 most important features for predicting the MCID for the HOS-ADL included in model training were body mass index, age, preoperative HOS-ADL score, preoperative pain level, sex, Tönnis grade, symptom duration, and drug allergies. The algorithm was subsequently transformed into a digital application using local explanations to provide customized risk assessment: https://orthoapps.shinyapps.io/HPRG_ADL/.

CONCLUSIONS

The stochastic boosting gradient model conferred excellent predictive ability for propensity to gain clinically significant improvements in function after hip arthroscopy. An open-access digital application was created, which may augment shared decision-making and allow for preoperative risk stratification. External validation of this model is warranted to confirm the performance of these algorithms, as the generalizability is currently unknown.

LEVEL OF EVIDENCE

IV, Case series.