Machine learning approaches in predicting ambulatory same day discharge patients after total hip arthroplasty

Elevated alkaline phosphatase independently predicts early postoperative complications in noninfectious revision total shoulder arthroplasty

PURPOSE

This study investigates the association between preoperative serum alkaline phosphatase levels and 30 day postoperative complications following noninfectious revision total shoulder arthroplasty (TSA). We hypothesize that elevated alkaline phosphatase levels are significantly associated with an increased 30 day postoperative complication rate.

METHODS

The American College of Surgeons National Surgical Quality Improvement Program database was queried for all patients who underwent noninfectious revision TSA from 2015 to 2022. The study population was divided into two groups based on preoperative serum alkaline phosphatase: normal (44-147 IU/L) and elevated (> 147 IU/L). Logistic regression analysis was conducted to investigate the relationship between elevated alkaline phosphatase levels and postoperative complications.

RESULTS

Compared to normal levels, elevated alkaline phosphatase was independently associated with a significantly greater likelihood of experiencing any complications (odds ratio [OR] 2.54, 95% confidence interval [CI] 1.41-4.55; P = .002), sepsis (OR 9.96, 95% CI 1.67-59.29; P = .012), blood transfusions (OR 3.77, 95% CI 1.48-9.61; P = .005), readmission (OR 3.65, 95% CI 1.48-9.01; P = .005), and length of stay > 2 days (OR 2.37, 95% CI 1.31-4.30; P = .004).

CONCLUSIONS

Elevated preoperative alkaline phosphatase was associated with a greater rate of early postoperative complications following noninfectious revision TSA.

LEVEL OF EVIDENCE

Level III; Retrospective Cohort Comparison; Prognosis Study.

Predicting conversion of ambulatory ACDF patients to inpatient: a machine learning approach

BACKGROUND CONTEXT

Machine learning is a powerful tool that has become increasingly important in the orthopedic field. Recently, several studies have reported that predictive models could provide new insights into patient risk factors and outcomes. Anterior cervical discectomy and fusion (ACDF) is a common operation that is performed as an outpatient procedure. However, some patients are required to convert to inpatient status and prolonged hospitalization due to their condition. Appropriate patient selection and identification of risk factors for conversion could provide benefits to patients and the use of medical resources.

PURPOSE

This study aimed to develop a machine-learning algorithm to identify risk factors associated with unplanned conversion from outpatient to inpatient status for ACDF patients.

STUDY DESIGN/SETTING

This is a machine-learning-based analysis using retrospectively collected data.

PATIENT SAMPLE

Patients who underwent one- or two-level ACDF in an ambulatory setting at a single specialized orthopedic hospital between February 2016 to December 2021.

OUTCOME MEASURES

Length of stay, conversion rates from ambulatory setting to inpatient.

METHODS

Patients were divided into two groups based on length of stay: (1) Ambulatory (discharge within 24 hours) or Extended Stay (greater than 24 hours but fewer than 48 hours), and (2) Inpatient (greater than 48 hours). Factors included in the model were based on literature review and clinical expertise. Patient demographics, comorbidities, and intraoperative factors, such as surgery duration and time, were included. We compared the performance of different machine learning algorithms: Logistic Regression, Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost). We split the patient data into a training and validation dataset using a 70/30 split. The different models were trained in the training dataset using cross-validation. The performance was then tested in the unseen validation set. This step is important to detect overfitting. The performance was evaluated using the area under the curve (AUC) of the receiver operating characteristics analysis (ROC) as the primary outcome. An AUC of 0.7 was considered fair, 0.8 good, and 0.9 excellent, according to established cut-offs.

RESULTS

A total of 581 patients (59% female) were available for analysis. Of those, 140 (24.1%) were converted to inpatient status. The median age was 51 (IQR 44-59), and the median BMI was 28 kg/m2 (IQR 24-32). The XGBoost model showed the best performance with an AUC of 0.79. The most important features were the length of the operation, followed by sex (based on biological attributes), age, and operation start time. The logistic regression model and the SVM showed worse results, with an AUC of 0.71 each.

CONCLUSIONS

This study demonstrated a novel approach to predicting conversion to inpatient status in eligible patients for ambulatory surgery. The XGBoost model showed good predictive capabilities, superior to the older machine learning approaches. This model also revealed the importance of surgical duration time, BMI, and age as risk factors for patient conversion. A developing field of study is using machine learning in clinical decision-making. Our findings contribute to this field by demonstrating the feasibility and accuracy of such methods in predicting outcomes and identifying risk factors, although external and multi-center validation studies are needed.

Predicting 30-day unplanned hospital readmission after revision total knee arthroplasty: machine learning model analysis of a national patient cohort

Revision total knee arthroplasty (TKA) is associated with a higher risk of readmission than primary TKA. Identifying individual patients predisposed to readmission can facilitate proactive optimization and increase care efficiency. This study developed machine learning (ML) models to predict unplanned readmission following revision TKA using a national-scale patient dataset. A total of 17,443 revision TKA cases (2013-2020) were acquired from the ACS NSQIP database. Four ML models (artificial neural networks, random forest, histogram-based gradient boosting, and k-nearest neighbor) were developed on relevant patient variables to predict readmission following revision TKA. The length of stay, operation time, body mass index (BMI), and laboratory test results were the strongest predictors of readmission. Histogram-based gradient boosting was the best performer in distinguishing readmission (AUC: 0.95) and estimating the readmission probability for individual patients (calibration slope: 1.13; calibration intercept: -0.00; Brier score: 0.064). All models produced higher net benefit than the default strategies of treating all or no patients, supporting the clinical utility of the models. ML demonstrated excellent performance for the prediction of readmission following revision TKA. Optimization of important predictors highlighted by our model may decrease preventable hospital readmission following surgery, thereby leading to reduced financial burden and improved patient satisfaction.

Can machine learning models predict prolonged length of hospital stay following primary total knee arthroplasty based on a national patient cohort data?

INTRODUCTION

The total length of stay (LOS) is one of the biggest determinators of overall care costs associated with total knee arthroplasty (TKA). An accurate prediction of LOS could aid in optimizing discharge strategy for patients in need and diminishing healthcare expenditure. The aim of this study was to predict LOS following TKA using machine learning models developed on a national-scale patient cohort.

METHODS

The ACS-NSQIP database was queried to acquire 267,966 TKA cases from 2013 to 2020. Four machine learning models-artificial neural network (ANN), random forest, histogram-based gradient boosting, and k-nearest neighbor were trained and tested on the dataset for the prediction of prolonged LOS (LOS exceeded the 75th of all values in the cohort). The model performance was assessed by discrimination (area under the receiver operating characteristic curve [AUC]), calibration, and clinical utility.

RESULTS

ANN delivered the best performance among the four models. ANN distinguished prolonged LOS in the study cohort with an AUC of 0.71 and accurately predicted the probability of prolonged LOS for individual patients (calibration slope: 0.82; calibration intercept: 0.03; Brier score: 0.089). All models demonstrated clinical utility by generating positive net benefits in decision curve analyses. Operation time, pre-operative transfusion, pre-operative laboratory tests (hematocrit, platelet count, and white blood cell count), and BMI were the strongest predictors of prolonged LOS.

CONCLUSION

ANN demonstrated modest discrimination capacity and excellent performance in calibration and clinical utility for the prediction of prolonged LOS following TKA. Clinical application of the machine learning models has the potential to improve care coordination and discharge planning for patients at high risk of extended hospitalization after surgery. Incorporating more relevant patient factors may further increase the models' prediction strength.

Machine Learning Models Based on a National-Scale Cohort Identify Patients at High Risk for Prolonged Lengths of Stay Following Primary Total Hip Arthroplasty

BACKGROUND

Existing machine learning models that predicted prolonged lengths of stay (LOS) following primary total hip arthroplasty (THA) were limited by the small training volume and exclusion of important patient factors. This study aimed to develop machine learning models using a national-scale data set and examine their performance in predicting prolonged LOS following THA.

METHODS

A total of 246,265 THAs were analyzed from a large database. Prolonged LOS was defined as exceeding the 75th percentile of all LOSs in the cohort. Candidate predictors of prolonged LOS were selected by recursive feature elimination and used to construct four machine learning models-artificial neural network, random forest, histogram-based gradient boosting, and k-nearest neighbor. The model performance was assessed by discrimination, calibration, and utility.

RESULTS

All models exhibited excellent performance in discrimination (area under the receiver operating characteristic curve [AUC] = 0.72 to 0.74) and calibration (slope: 0.83 to 1.18, intercept: -0.01 to 0.11, Brier score: 0.185 to 0.192) during both training and testing sessions. The artificial neural network was the best performer with an AUC of 0.73, calibration slope of 0.99, calibration intercept of -0.01, and Brier score of 0.185. All models showed great utility by producing higher net benefits than the default treatment strategies in the decision curve analyses. Age, laboratory tests, and surgical variables were the strongest predictors of prolonged LOS.

CONCLUSION

The excellent prediction performance of machine learning models demonstrated their capacity to identify patients prone to prolonged LOS. Many factors contributing to prolonged LOS can be optimized to minimize hospital stay for high-risk patients.

Daring discourse: artificial intelligence in pain medicine, opportunities and challenges

Artificial intelligence (AI) tools are currently expanding their influence within healthcare. For pain clinics, unfettered introduction of AI may cause concern in both patients and healthcare teams. Much of the concern stems from the lack of community standards and understanding of how the tools and algorithms function. Data literacy and understanding can be challenging even for experienced healthcare providers as these topics are not incorporated into standard clinical education pathways. Another reasonable concern involves the potential for encoding bias in healthcare screening and treatment using faulty algorithms. And yet, the massive volume of data generated by healthcare encounters is increasingly challenging for healthcare teams to navigate and will require an intervention to make the medical record manageable in the future. AI approaches that lighten the workload and support clinical decision-making may provide a solution to the ever-increasing menial tasks involved in clinical care. The potential for pain providers to have higher-quality connections with their patients and manage multiple complex data sources might balance the understandable concerns around data quality and decision-making that accompany introduction of AI. As a specialty, pain medicine will need to establish thoughtful and intentionally integrated AI tools to help clinicians navigate the changing landscape of patient care.

Total joint replacement in ambulatory surgery

Total joint arthroplasty is one of the most commonly performed surgical procedures in the United States, and projected numbers are expected to double in the next ten years. From 2018 to 2020, total hip and knee arthroplasty were removed from the United States' Center for Medicare and Medicaid Services "inpatient-only" list, accelerating this migration to the ambulatory setting. Appropriate patient selection, including age, body mass index, comorbidities, and adequate social support, is critical for successful ambulatory total joint arthroplasty. General anesthesia and neuraxial anesthesia are both safe and effective anesthetic choices, and recent studies in this population have found no difference in outcomes. Multimodal analgesia, including acetaminophen, nonsteroidal anti-inflammatory drugs, local infiltration analgesia, and peripheral nerve blocks, is the foundation for adequate pain control. Common reasons for "failure to launch" include postoperative urinary retention, postoperative nausea and vomiting, inadequate analgesia, and hypotension.

Prediction of suitable outpatient candidates following revision total knee arthroplasty using machine learning

Aims

To identify variables independently associated with same-day discharge (SDD) of patients following revision total knee arthroplasty (rTKA) and to develop machine learning algorithms to predict suitable candidates for outpatient rTKA.

Methods

Data were obtained from the American College of Surgeons National Quality Improvement Programme (ACS-NSQIP) database from the years 2018 to 2020. Patients with elective, unilateral rTKA procedures and a total hospital length of stay between zero and four days were included. Demographic, preoperative, and intraoperative variables were analyzed. A multivariable logistic regression (MLR) model and various machine learning techniques were compared using area under the curve (AUC), calibration, and decision curve analysis. Important and significant variables were identified from the models.

Results

Of the 5,600 patients included in this study, 342 (6.1%) underwent SDD. The random forest (RF) model performed the best overall, with an internally validated AUC of 0.810. The ten crucial factors favoring SDD in the RF model include operating time, anaesthesia type, age, BMI, American Society of Anesthesiologists grade, race, history of diabetes, rTKA type, sex, and smoking status. Eight of these variables were also found to be significant in the MLR model.

Conclusion

The RF model displayed excellent accuracy and identified clinically important variables for determining candidates for SDD following rTKA. Machine learning techniques such as RF will allow clinicians to accurately risk-stratify their patients preoperatively, in order to optimize resources and improve patient outcomes.

Development and benchmarking of machine learning models to classify patients suitable for outpatient lower extremity joint arthroplasty

STUDY OBJECTIVE

Performing hip or knee arthroplasty as an outpatient surgery has been shown to be operationally and financially beneficial for selected patients. By applying machine learning models to predict patients suitable for outpatient arthroplasty, health care systems can better utilize resources efficiently. The goal of this study was to develop predictive models for identifying patients likely to be discharged same-day following hip or knee arthroplasty.

DESIGN

Model performance was assessed with 10-fold stratified cross-validation, evaluated over baseline determined by the proportion of eligible outpatient arthroplasty over sample size. The models used for classification were logistic regression, support vector classifier, balanced random forest, balanced bagging XGBoost classifier, and balanced bagging LightGBM classifier.

SETTING

The patient records were sampled from arthroplasty procedures at a single institution from October 2013 to November 2021.

PATIENTS

The electronic intake records of 7322 knee and hip arthroplasty patients were sampled for the dataset. After data processing, 5523 records were kept for model training and validation.

INTERVENTIONS

None.

MEASUREMENTS

The primary measures for the models were the F1-score, area under the receiver operating characteristic curve (ROCAUC), and area under the precision-recall curve. To measure feature importance, the SHapley Additive exPlanations value (SHAP) were reported from the model with the highest F1-score.

RESULTS

The best performing classifier (balanced random forest classifier) achieved an F1-score of 0.347: an improvement of 0.174 over baseline and 0.031 over logistic regression. The ROCAUC for this model was 0.734. Using SHAP, the top determinant features of the model included patient sex, surgical approach, surgery type, and body mass index.

CONCLUSIONS

Machine learning models may utilize electronic health records to screen arthroplasty procedures for outpatient eligibility. Tree-based models demonstrated superior performance in this study.

A Machine Learning-Based Online Prediction Tool for Predicting Short-Term Postoperative Outcomes Following Spinal Tumor Resections

Background: Preoperative prediction of short-term postoperative outcomes in spinal tumor patients can lead to more precise patient care plans that reduce the likelihood of negative outcomes. With this study, we aimed to develop machine learning algorithms for predicting short-term postoperative outcomes and implement these models in an open-source web application. Methods: Patients who underwent surgical resection of spinal tumors were identified using the American College of Surgeons, National Surgical Quality Improvement Program. Three outcomes were predicted: prolonged length of stay (LOS), nonhome discharges, and major complications. Four machine learning algorithms were developed and integrated into an open access web application to predict these outcomes. Results: A total of 3073 patients that underwent spinal tumor resection were included in the analysis. The most accurately predicted outcomes in terms of the area under the receiver operating characteristic curve (AUROC) was the prolonged LOS with a mean AUROC of 0.745 The most accurately predicting algorithm in terms of AUROC was random forest, with a mean AUROC of 0.743. An open access web application was developed for getting predictions for individual patients based on their characteristics and this web application can be accessed here: huggingface.co/spaces/MSHS-Neurosurgery-Research/NSQIP-ST. Conclusion: Machine learning approaches carry significant potential for the purpose of predicting postoperative outcomes following spinal tumor resections. Development of predictive models as clinically useful decision-making tools may considerably enhance risk assessment and prognosis as the amount of data in spinal tumor surgery continues to rise.

Artificial intelligence and machine learning as a viable solution for hip implant failure diagnosis-Review of literature and in vitro case study

The digital health industry is experiencing fast-paced research which can provide digital care programs and technologies to enhance the competence of healthcare delivery. Orthopedic literature also confirms the applicability of artificial intelligence (AI) and machine learning (ML) models to medical diagnosis and clinical decision-making. However, implant monitoring after primary surgery often happens with a wellness visit or when a patient complains about it. Neglecting implant design and other technical errors in this scenario, unmonitored circumstances, and lack of post-surgery monitoring may ultimately lead to the implant system's failure and leave us with the only option of high-risk revision surgery. Preventive maintenance seems to be a good choice to identify the onset of an irreversible prosthesis failure. Considering all these aspects for hip implant monitoring, this paper explores existing studies linking ML models and intelligent systems for hip implant diagnosis. This paper explores the feasibility of an alternative continuous monitoring technique for post-surgery implant monitoring backed by an in vitro ML case study. Tribocorrosion and acoustic emission (AE) data are considered based on their efficacy in determining irreversible alteration of implant material to prevent total failures. This study also facilitates the relevance of developing an artificially intelligent implant monitoring methodology that can function with daily patient activities and how it can influence the digital orthopedic diagnosis. AI-based non-invasive hip implant monitoring system enabling point-of-care testing.

Concerns surrounding application of artificial intelligence in hip and knee arthroplasty

Literature surrounding artificial intelligence (AI)-related applications for hip and knee arthroplasty has proliferated. However, meaningful advances that fundamentally transform the practice and delivery of joint arthroplasty are yet to be realized, despite the broad range of applications as we continue to search for meaningful and appropriate use of AI. AI literature in hip and knee arthroplasty between 2018 and 2021 regarding image-based analyses, value-based care, remote patient monitoring, and augmented reality was reviewed. Concerns surrounding meaningful use and appropriate methodological approaches of AI in joint arthroplasty research are summarized. Of the 233 AI-related orthopaedics articles published, 178 (76%) constituted original research, while the rest consisted of editorials or reviews. A total of 52% of original AI-related research concerns hip and knee arthroplasty (n = 92), and a narrative review is described. Three studies were externally validated. Pitfalls surrounding present-day research include conflating vernacular (“AI/machine learning”), repackaging limited registry data, prematurely releasing internally validated prediction models, appraising model architecture instead of inputted data, withholding code, and evaluating studies using antiquated regression-based guidelines. While AI has been applied to a variety of hip and knee arthroplasty applications with limited clinical impact, the future remains promising if the question is meaningful, the methodology is rigorous and transparent, the data are rich, and the model is externally validated. Simple checkpoints for meaningful AI adoption include ensuring applications focus on: administrative support over clinical evaluation and management; necessity of the advanced model; and the novelty of the question being answered.

Cite this article: Bone Joint J 2022;104-B(12):1292–1303.

Bone metastasis risk and prognosis assessment models for kidney cancer based on machine learning

Background

Bone metastasis is a common adverse event in kidney cancer, often resulting in poor survival. However, tools for predicting KCBM and assessing survival after KCBM have not performed well.

Methods

The study uses machine learning to build models for assessing kidney cancer bone metastasis risk, prognosis, and performance evaluation. We selected 71,414 kidney cancer patients from SEER database between 2010 and 2016. Additionally, 963 patients with kidney cancer from an independent medical center were chosen to validate the performance. In the next step, eight different machine learning methods were applied to develop KCBM diagnosis and prognosis models while the risk factors were identified from univariate and multivariate logistic regression and the prognosis factors were analyzed through Kaplan-Meier survival curve and Cox proportional hazards regression. The performance of the models was compared with current models, including the logistic regression model and the AJCC TNM staging model, applying receiver operating characteristics, decision curve analysis, and the calculation of accuracy and sensitivity in both internal and independent external cohorts.

Results

Our prognosis model achieved an AUC of 0.8269 (95%CI: 0.8083-0.8425) in the internal validation cohort and 0.9123 (95%CI: 0.8979-0.9261) in the external validation cohort. In addition, we tested the performance of the extreme gradient boosting model through decision curve analysis curve, Precision-Recall curve, and Brier score and two models exhibited excellent performance.

Conclusion

Our developed models can accurately predict the risk and prognosis of KCBM and contribute to helping improve decision-making.

The impact of hypoalbuminemia on postoperative outcomes after outpatient surgery: a national analysis of the NSQIP database

PURPOSE

Hypoalbuminemia has been described as a modifiable factor to optimize postoperative outcomes after major inpatient surgeries. Nevertheless, the role of hypoalbuminemia on outpatient procedures is not well defined. The purpose of this study was to examine the impact of hypoalbuminemia on postoperative outcomes of patients undergoing low-risk outpatient surgery.

METHODS

Patients were extracted from the American College of Surgeons National Surgical Quality Improvement Program database who had outpatient surgery from 2018 and recorded preoperative albumin levels. The primary outcome was a composite of any major complications including: 1) unplanned intubation, 2) pulmonary embolism, 3) ventilator use > 48 hr, 4) progressive renal failure, 5) acute renal failure, 6) stroke/cerebrovascular accident, 7) cardiac arrest, 8) myocardial infarction, 9) sepsis, 10) septic shock, 11) deep venous thrombosis, and 12) transfusion. Death, any infection, and readmissions were secondary outcomes.

RESULTS

A total of 65,192 (21%) surgical outpatients had albumin collected preoperatively and 3,704 (1.2%) patients had levels below 3.5 g⋅dL-1. In the albumin cohort, 394/65,192 (0.6%) patients had a major medical complication and 68/65,192 (0.1%) patients died within 30 days after surgery. Albumin values < 3.5 g⋅dL-1 were associated with major complications (adjusted odds ratio [aOR], 1.92; 95% confidence interval [CI], 1.44 to 2.57; P < 0.001; death-adjusted OR, 3.03; 95% CI, 1.72 to 5.34; P < 0.001); any infection (aOR, 1.49; 95% CI, 1.23 to 1.82; P < 0.001); and readmissions (aOR, 1.82; 95% CI, 1.56 to 2.14; P < 0.001). In addition, when evaluated as a continuous variable in a multivariate analysis, for each increase in albumin of 0.10 g⋅dL-1, there was an associated reduction of major complications (aOR, 0.94; 95% CI, 0.92 to 0.96; P < 0.001).

CONCLUSIONS

Hypoalbuminemia is associated with major complications and death in outpatient surgery. Since hypoalbuminemia is a potential modifiable intervention, future clinical trials to evaluate the impact of optimizing preoperative albumin levels before outpatient surgery are warranted.

Relative Contribution of Outpatient Arthroplasty Risk Assessment Score Medical Comorbidities to Same-Day Discharge After Primary Total Joint Arthroplasty

BACKGROUND

Selection of patients who can safely undergo outpatient total joint arthroplasty (TJA) is an increasing priority given the growth of ambulatory TJA. This study quantified the relative contribution and weight of 52 medical comorbidities comprising the Outpatient Arthroplasty Risk Assessment (OARA) score as predictors of safe same-day discharge (SDD).

METHODS

The medical records of 2748 primary TJAs consecutively performed between 2014 and 2020 were reviewed to record the presence or absence of medical comorbidities in the OARA score. After controlling for patients not offered SDD due to OARA scores and patients who were offered but declined SDD, the final analysis sample consisted of 631 cases, 92.1% of whom achieved SDD and 7.9% of whom did not achieve SDD. Odds ratios were calculated to quantify the extent to which each comorbidity is associated with achieving SDD.

RESULTS

Demographic characteristics of analysis cases were consistent with a high-volume TJA practice in a US metropolitan area. Among testable OARA comorbidities, 53% significantly decreased the likelihood of SDD by 2.3 (body mass index [BMI] ≥40 kg/m²) to 12 (history of post-operative confusion and pacemaker dependence) times. BMI between 30 and 39 kg/m² did not affect the likelihood of SDD (P = .960), and BMI ≥40 kg/m² had the smallest odds ratio in our study (2.28, 95% confidence interval 1.11-4.67, P = .025).

CONCLUSION

Study findings contribute to the refinement of the OARA score as a successful predictor of safe SDD following primary TJA while maintaining low 90-day readmission rates.

An Overview of Commonly Used Data Sources in Observational Research in Anesthesia

Anesthesia research using existing databases has drastically expanded over the last decade. The most commonly used data sources in multi-institutional observational research are administrative databases and clinical registries. These databases are powerful tools to address research questions that are difficult to answer with smaller samples or single-institution information. Given that observational database research has established itself as valuable field in anesthesiology, we systematically reviewed publications in 3 high-impact North American anesthesia journals in the past 5 years with the goal to characterize its scope. We identified a wide range of data sources used for anesthesia-related research. Research topics ranged widely spanning questions regarding optimal anesthesia type and analgesic protocols to outcomes and cost of care both on a national and a local level. Researchers should choose their data sources based on various factors such as the population encompassed by the database, ability of the data to adequately address the research question, budget, acceptable limitations, available data analytics resources, and pipeline of follow-up studies.

Health Services Research in Anesthesia: A Brief Overview of Common Methodologies

The use of large data sources such as registries and claims-based data sets to perform health services research in anesthesia has increased considerably, ultimately informing clinical decisions, supporting evaluation of policy or intervention changes, and guiding further research. These observational data sources come with limitations that must be addressed to effectively examine all aspects of health care services and generate new individual- and population-level knowledge. Several statistical methods are growing in popularity to address these limitations, with the goal of mitigating confounding and other biases. In this article, we provide a brief overview of common statistical methods used in health services research when using observational data sources, guidance on their interpretation, and examples of how they have been applied to anesthesia-related health services research. Methods described involve regression, propensity scoring, instrumental variables, difference-in-differences, interrupted time series, and machine learning.

A Surgeon's Guide to Understanding Artificial Intelligence and Machine Learning Studies in Orthopaedic Surgery

PURPOSE OF REVIEW

In recent years, machine learning techniques have been increasingly utilized across medicine, impacting the practice and delivery of healthcare. The data-driven nature of orthopaedic surgery presents many targets for improvement through the use of artificial intelligence, which is reflected in the increasing number of publications in the medical literature. However, the unique methodologies utilized in AI studies can present a barrier to its widespread acceptance and use in orthopaedics. The purpose of our review is to provide a tool that can be used by practitioners to better understand and ultimately leverage AI studies.

RECENT FINDINGS

The increasing interest in machine learning across medicine is reflected in a greater utilization of AI in recent medical literature. The process of designing machine learning studies includes study design, model choice, data collection/handling, model development, training, testing, and interpretation. Recent studies leveraging ML in orthopaedics provide useful examples for future research endeavors. This manuscript intends to create a guide discussing the use of machine learning and artificial intelligence in orthopaedic surgery research. Our review outlines the process of creating a machine learning algorithm and discusses the different model types, utilizing examples from recent orthopaedic literature to illustrate the techniques involved.

Machine Learning Model Developed to Aid in Patient Selection for Outpatient Total Joint Arthroplasty

Background

Patient selection for outpatient total joint arthroplasty (TJA) is important for optimizing patient outcomes. This study develops machine learning models that may aid in patient selection for outpatient TJA based on medical comorbidities and demographic factors.

Methods

This study queried elective total knee arthroplasty (TKA) and total hip arthroplasty (THA) cases during 2010-2018 in the American College of Surgeons National Surgical Quality Improvement Program. Artificial neural network models predicted same-day discharge and length of stay (LOS) fewer than 2 days (short LOS). Multiple linear and logistic regression analyses were used to identify variables significantly associated with predicted outcomes.

Results

A total of 284,731 TKA cases and 153,053 THA cases met inclusion criteria. For TKA, prediction of short LOS had an area under the receiver operating characteristic curve (AUC) of 0.767 and accuracy of 84.1%; prediction of same-day discharge had an AUC of 0.802 and accuracy of 89.2%. For THA, prediction of short LOS had an AUC of 0.757 and accuracy of 70.6%; prediction of same-day discharge had an AUC of 0.814 and accuracy of 78.8%.

Conclusion

This study developed machine learning models for aiding patient selection for outpatient TJA, through accurately predicting short LOS or outpatient vs inpatient cases. As outpatient TJA expands, it will be important to optimize preoperative patient selection and effectively screen surgical candidates from a broader patient population. Incorporating models such as these into electronic medical records could aid in decision-making and resource planning in real time.

Preoperative and Perioperative Predictors of Length of Hospital Stay after Primary Total Hip Arthroplasty-Our Experience on 743 Cases

The aim of this retrospective investigation is to evaluate the correlation between several preoperative and perioperative factors and the length of hospital stay in patients that underwent elective total hip arthroplasty with overnight admission. Medical records of patients that underwent THA from the beginning of 2016 to the end of 2018 were retrospectively screened. Demographics, comorbidities, whole blood count, intraoperative details, and length of postoperative stay were retrieved. The association between clinical, laboratory and surgical factors and the length of hospital stay was explored by means of negative binomial and logistic regression models. The median length of postoperative hospital stay was four days (Inter Quartile Range, IQR 3, 5). After univariate regression a stepwise multivariate regression showed that operative time (p = 0.001), the preoperative serum creatinine (p < 0.001), the intraoperative blood loss (p = 0.04) and the use of an anterolateral approach (p < 0.001) were found to correlate significantly with the increase of the hospitalization length, while no significant correlation was found for all the other features. Multivariable model fitted through logistic regression (LOS below or over the median value of four days) had an Area Under the Curve (AUC) of 0.748. Our analysis suggests a significant role played by different preoperative and perioperative variables in influencing the length of hospital stay.