Defining Clinically Meaningful Subgroups for Risk Stratification in Patients Undergoing Revision Total Hip Arthroplasty: A Combined Unsupervised and Supervised Machine Learning Approach

Machine learning models can define clinically relevant bone density subgroups based on patient-specific calibrated computed tomography scans in patients undergoing reverse shoulder arthroplasty

BACKGROUND

Reduced bone density is recognized as a predictor for potential complications in reverse shoulder arthroplasty (RSA). While humeral and glenoid planning based on preoperative computed tomography (CT) scans assist in implant selection and position, reproducible methods for quantifying the patients' bone density are currently not available. The purpose of this study was to perform bone density analyses including patient-specific calibration in an RSA cohort based on preoperative CT imaging. It was hypothesized that preoperative CT bone density measures would provide objective quantification of the patients' humeral bone quality.

METHODS

This study consisted of 3 parts, (1) analysis of a patient-specific calibration method in cadaveric CT scans, (2) retrospective application in a clinical RSA cohort, and (3) clustering and classification with machine learning (ML) models. Forty cadaveric shoulders were scanned in a clinical CT and compared regarding calibration with density phantoms, air muscle, and fat (patient-specific) or standard Hounsfield unit. Postscan patient-specific calibration was used to improve the extraction of 3-dimensional regions of interest for retrospective bone density analysis in a clinical RSA cohort (n = 345). ML models were used to improve the clustering (Hierarchical Ward) and classification (support vector machine) of low bone densities in the respective patients.

RESULTS

The patient-specific calibration method demonstrated improved accuracy with excellent intraclass correlation coefficients for cylindrical cancellous bone densities (intraclass correlation coefficient >0.75). Clustering partitioned the training data set into a high-density subgroup consisting of 96 patients and a low-density subgroup consisting of 146 patients, showing significant differences between these groups. The support vector machine showed optimized prediction accuracy of low and high bone densities compared to conventional statistics in the training (accuracy = 91.2%; area under curve = 0.967) and testing (accuracy = 90.5%; area under curve = 0.958) data set.

CONCLUSION

Preoperative CT scans can be used to quantify the proximal humeral bone quality in patients undergoing RSA. The use of ML models and patient-specific calibration on bone mineral density demonstrated that multiple three-dimensional bone density scores improved the accuracy of objective preoperative bone quality assessment. The trained model could provide preoperative information to surgeons treating patients with potentially poor bone quality.

Identifying clinically meaningful subgroups following open reduction and internal fixation for proximal humerus fractures: a risk stratification analysis for mortality and 30-day complications using machine learning

Background

Identification of prognostic variables for poor outcomes following open reduction internal fixation (ORIF) of displaced proximal humerus fractures have been limited to singular, linear factors and subjective clinical intuition. Machine learning (ML) has the capability to objectively segregate patients based on various outcome metrics and reports the connectivity of variables resulting in the optimal outcome. Therefore, the purpose of this study was to (1) use unsupervised ML to stratify patients to high-risk and low-risk clusters based on postoperative events, (2) compare the ML clusters to the American Society of Anesthesiologists (ASA) classification for assessment of risk, and (3) determine the variables that were associated with high-risk patients after proximal humerus ORIF.

Methods

The American College of Surgeons-National Surgical Quality Improvement Program database was retrospectively queried for patients undergoing ORIF for proximal humerus fractures between 2005 and 2018. Four unsupervised ML clustering algorithms were evaluated to partition subjects into "high-risk" and "low-risk" subgroups based on combinations of observed outcomes. Demographic, clinical, and treatment variables were compared between these groups using descriptive statistics. A supervised ML algorithm was generated to identify patients who were likely to be "high risk" and were compared to ASA classification. A game-theory-based explanation algorithm was used to illustrate predictors of "high-risk" status.

Results

Overall, 4670 patients were included, of which 202 were partitioned into the "high-risk" cluster, while the remaining (4468 patients) were partitioned into the "low-risk" cluster. Patients in the "high-risk" cluster demonstrated significantly increased rates of the following complications: 30-day mortality, 30-day readmission rates, 30-day reoperation rates, nonroutine discharge rates, length of stay, and rates of all surgical and medical complications assessed with the exception of urinary tract infection (P < .001). The best performing supervised machine learning algorithm for preoperatively identifying "high-risk" patients was the extreme-gradient boost (XGBoost), which achieved an area under the receiver operating characteristics curve of 76.8%, while ASA classification had an area under the receiver operating characteristics curve of 61.7%. Shapley values identified the following predictors of "high-risk" status: greater body mass index, increasing age, ASA class 3, increased operative time, male gender, diabetes, and smoking history.

Conclusion

Unsupervised ML identified that "high-risk" patients have a higher risk of complications (8.9%) than "low-risk" groups (0.4%) with respect to 30-day complication rate. A supervised ML model selected greater body mass index, increasing age, ASA class 3, increased operative time, male gender, diabetes, and smoking history to effectively predict "high-risk" patients.

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.

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.

Achieving High Accuracy in Predicting the Probability of Periprosthetic Joint Infection From Synovial Fluid in Patients Undergoing Hip or Knee Arthroplasty: The Development and Validation of a Multivariable Machine Learning Algorithm

Background and objective The current periprosthetic joint infection (PJI) diagnostic guidelines require clinicians to interpret and integrate multiple criteria into a complex scoring system. Also, PJI classifications are often inconclusive, failing to provide a clinical diagnosis. Machine learning (ML) models could be leveraged to reduce reliance on these complex systems and thereby reduce diagnostic uncertainty. This study aimed to develop an ML algorithm using synovial fluid (SF) test results to establish a PJI probability score. Methods We used a large clinical laboratory's dataset of SF samples, aspirated from patients with hip or knee arthroplasty as part of a PJI evaluation. Patient age and SF biomarkers [white blood cell count, neutrophil percentage (%PMN), red blood cell count, absorbance at 280 nm wavelength, C-reactive protein (CRP), alpha-defensin (AD), neutrophil elastase, and microbial antigen (MID) tests] were used for model development. Data preprocessing, principal component analysis, and unsupervised clustering (K-means) revealed four clusters of samples that naturally aggregated based on biomarker results. Analysis of the characteristics of each of these four clusters revealed three clusters (n=13,133) with samples having biomarker results typical of a PJI-negative classification and one cluster (n=4,032) with samples having biomarker results typical of a PJI-positive classification. A decision tree model, trained and tested independently of external diagnostic rules, was then developed to match the classification determined by the unsupervised clustering. The performance of the model was assessed versus a modified 2018 International Consensus Meeting (ICM) criteria, in both the test cohort and an independent unlabeled validation set of 5,601 samples. The SHAP (SHapley Additive exPlanations) method was used to explore feature importance. Results The ML model showed an area under the curve of 0.993, with a sensitivity of 98.8%, specificity of 97.3%, positive predictive value (PPV) of 92.9%, and negative predictive value (NPV) of 99.8% in predicting the modified 2018 ICM diagnosis among test set samples. The model maintained its diagnostic accuracy in the validation cohort, yielding 99.1% sensitivity, 97.1% specificity, 91.9% PPV, and 99.9% NPV. The model's inconclusive rate (diagnostic probability between 20-80%) in the validation cohort was only 1.3%, lower than that observed with the modified 2018 ICM PJI classification (7.4%; p<0.001). The SHAP analysis found that AD was the most important feature in the model, exhibiting dominance among >95% of "infected" and "not infected" diagnoses. Other important features were the sum of the MID test panel, %PMN, and SF-CRP. Conclusions Although defined methods and tools for diagnosis of PJI using multiple biomarker criteria are available, they are not consistently applied or widely implemented. There is a need for algorithmic interpretation of these biomarkers to enable consistent interpretation of the results to drive treatment decisions. The new model, using clinical parameters measured from a patient's SF sample, renders a preoperative probability score for PJI which performs well compared to a modified 2018 ICM definition. Taken together with other clinical signs, this model has the potential to increase the accuracy of clinical evaluations and reduce the rate of inconclusive classification, thereby enabling more appropriate and expedited downstream treatment decisions.