A Novel, Potentially Universal Machine Learning Algorithm to Predict Complications in Total Knee Arthroplasty.
Ontology highlight
ABSTRACT: Background
There remains a lack of accurate and validated outcome-prediction models in total knee arthroplasty (TKA). While machine learning (ML) is a powerful predictive tool, determining the proper algorithm to apply across diverse data sets is challenging. AutoPrognosis (AP) is a novel method that uses automated ML framework to incorporate the best performing stages of prognostic modeling into a single well-calibrated algorithm. We aimed to compare various ML methods to AP in predictive performance of complications after TKA.Methods
Thirty-eight preoperative patient demographics and clinical features from all primary TKAs performed at California-licensed hospitals between 2015 and 2017 were evaluated as predictors of major complications after TKA. Traditional logistic regression (LR), various other ML methods (XGBoost, Gradient Boosting, AdaBoost, and Random Forest), and AP were used for model building to determine discriminative power (area under receiver operating curve), calibration (Brier score), and feature importance.Results
Between 2015 and 2017, there were a total of 156,750 TKAs with 1109 (0.7%) total major complications. AP had the highest discriminative performance with area under receiver operating curve 0.679 compared with LR, XGBoost, Gradient Boosting, AdaBoost, and Random Forest (0.617, 0.601, 0.662, 0.657, and 0.545, respectively). AP (Brier score 0.007) had similar calibration as the other ML methods (0.006, 0.006, 0.022, 0.007, and 0.008, respectively). The variables that are most important for AP differ from those that are most important for LR.Conclusion
Compared to conventional ML algorithms, AP has superior discriminative ability with similar calibration and suggests nonlinear relationships between variables in outcomes of TKA.
SUBMITTER: Devana SK
PROVIDER: S-EPMC8349766 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundAs the prevalence of hip osteoarthritis increases, the number of total hip arthroplasty (THA) procedures performed is also projected to increase. Accurately risk-stratifying patients who undergo THA would be of great utility, given the significant cost and morbidity associated with developing perioperative complications. We aim to develop a novel machine learning (ML)-based ensemble algorithm for the prediction of major complications after THA, as well as compare its performance against standard benchmark ML methods.MethodsThis is a retrospective cohort study of 89,986 adults who underwent primary THA at any California-licensed hospital between 2015 and 2017. The primary outcome was major complications (eg infection, venous thromboembolism, cardiac complication, pulmonary complication). We developed a model predicting complication risk using AutoPrognosis, an automated ML framework that configures the optimally performing ensemble of ML-based prognostic models. We compared our model with logistic regression and standard benchmark ML models, assessing discrimination and calibration.ResultsThere were 545 patients who had major complications (0.61%). Our novel algorithm was well-calibrated and improved risk prediction compared to logistic regression, as well as outperformed the other four standard benchmark ML algorithms. The variables most important for AutoPrognosis (eg malnutrition, dementia, cancer) differ from those that are most important for logistic regression (eg chronic atherosclerosis, renal failure, chronic obstructive pulmonary disease).ConclusionWe report a novel ensemble ML algorithm for the prediction of major complications after THA. It demonstrates superior risk prediction compared to logistic regression and other standard ML benchmark algorithms. By providing accurate prognostic information, this algorithm may facilitate more informed preoperative shared decision-making.
| S-EPMC10371358 | biostudies-literature
Project description:AimsThe use of technology to assess balance and alignment during total knee surgery can provide an overload of numerical data to the surgeon. Meanwhile, this quantification holds the potential to clarify and guide the surgeon through the surgical decision process when selecting the appropriate bone recut or soft tissue adjustment when balancing a total knee. Therefore, this paper evaluates the potential of deploying supervised machine learning (ML) models to select a surgical correction based on patient-specific intra-operative assessments.MethodsBased on a clinical series of 479 primary total knees and 1,305 associated surgical decisions, various ML models were developed. These models identified the indicated surgical decision based on available, intra-operative alignment, and tibiofemoral load data.ResultsWith an associated area under the receiver-operator curve ranging between 0.75 and 0.98, the optimized ML models resulted in good to excellent predictions. The best performing model used a random forest approach while considering both alignment and intra-articular load readings.ConclusionThe presented model has the potential to make experience available to surgeons adopting new technology, bringing expert opinion in their operating theatre, but also provides insight in the surgical decision process. More specifically, these promising outcomes indicated the relevance of considering the overall limb alignment in the coronal and sagittal plane to identify the appropriate surgical decision.
| S-EPMC7677727 | biostudies-literature
Project description:BACKGROUND:The study of localized immune-related factors has proven beneficial for a variety of conditions, and one area of interest in the field of orthopaedics is the impact of implants and localized infections on immune response. Several cytokines have shown increased systemic concentrations (in serum/plasma) in response to implants and infection, but tissue-level cytokines have not been investigated as thoroughly. METHODS:This exploratory study investigated tissue-level cytokines in a cohort of patients (N?=?17) in response to total knee arthroplasty and total knee revision to better understand the immune response to implants and localized infection (e.g., prosthetic joint infection). The overall goal of this study was to provide insight into the localized cytokine response of tissues and identify tissue-level markers specific to inflammation caused by implants vs. inflammation caused by infection. Tissues were collected across several anatomical locations and assayed with a panel of 20 human inflammatory cytokines to understand spatial differences in cytokine levels. RESULTS:In this study, six cytokines were elevated in implanted joints, as compared to native joints: IL-10, IL-12p70, IL-13, IL-17A, IL-4, and TNF-? (p?<?0.05). Seven cytokines showed infection-dependent increases in localized tissues: IL-1?, IL-1?, IL-6, IL-8, MCP-1, MIP-1?, and MIP-1? (p?<?0.05). CONCLUSIONS:This study demonstrated that differences exist in tissue-level cytokines in response to presence of implant, and some cytokines were specifically elevated for infection; these responses may be informative of overall tissue health. These results highlight the utility of investigating localized cytokine concentrations to offer novel insights for total knee arthroplasty and total knee revision procedures, as well as their complications. Ultimately, this information could provide additional, quantitative measurements of tissue to aid clinical decision making and patient treatment options.
| S-EPMC7461261 | biostudies-literature
Project description:BackgroundPatients with diabetes have increased risk of infections and wound complications after total knee arthroplasty (TKA). Glycemic markers identifying patients at risk for complications after TKA have not yet been elucidated.Questions/purposesWe aimed to determine the correlations among four commonly used glycemic markers and to identify the glycemic markers most strongly associated with the occurrence of surgical site infections and postoperative wound complications in patients with diabetes mellitus after undergoing TKA.MethodsOur retrospective study included 462 patients with diabetes, who underwent a total of 714 TKAs. Blood levels of glycemic markers, including preoperative fasting blood glucose (FBG), postprandial glucose (PPG2), glycated hemoglobin (HbA1c), and levels obtained from random glucose testing on postoperative days 2, 5, and 14, were collected on all patients as part of a medical clearance program and an established clinical pathway for patients with diabetes at our center. Complete followup was available on 93% (462 of 495) of the patients. Correlations among markers were assessed. Associations between the markers and patient development of complications were analyzed using multivariate regression analyses of relevant cutoff values. We considered any of the following as complications potentially related to diabetes, and these were considered study endpoints: surgical site infection (superficial and deep) and wound complications (drainage, hemarthrosis, skin necrosis, and dehiscence). During the period of study, there were no fixed criteria applied to what levels of glycemic control patients with diabetes needed to achieve before undergoing arthroplasty, and there were wide ranges in the levels of all glycemic markers; for example, whereas the mean HbA1c level was 7%, the range was 5% to 11.3%.ResultsThere were positive correlations among the levels of the four glycemic markers; the strongest correlation was found between the preoperative HbA1c and PPG2 levels (R = 0.502, p < 0.001). After controlling for potential confounding variables using multivariate analysis, the HbA1c cutoff level of 8 (odds ratio [OR], 6.1; 95% confidence interval [CI], 1.6-23.4; p = 0.008) and FBG 200 mg/dL or higher (OR, 9.2; 95% CI, 2.2-38.2; p = 0.038) were associated with superficial surgical site infection after TKA.ConclusionsIn general, there is a positive correlation among the various available glycemic markers among patients with diabetes undergoing TKA, and patients undergoing surgery with HbA1c ? 8 and/or FBG ? 200 mg/dL were associated with superficial surgical site infection. These findings should be considered in patient selection and preoperative counseling for patients with diabetes undergoing TKA.Level of evidenceLevel III, prognostic study.
| S-EPMC4385343 | biostudies-literature
Project description:BackgroundDespite reasonable accuracy with preoperative templating, the search for an optimal planning tool remains an unsolved dilemma. The purpose of the present study was to apply machine learning (ML) using preoperative demographic variables to predict mismatch between templating and final component size in primary total knee arthroplasty (TKA) cases.MethodsThis was a retrospective case-control study of primary TKA patients between September 2012 and April 2018. The primary outcome was mismatch between the templated and final implanted component sizes extracted from the operative database. The secondary outcome was mismatch categorized as undersized and oversized. Five supervised ML algorithms were trained using 6 demographic features. Prediction accuracies were obtained as a metric of performance for binary mismatch (yes/no) and multilevel (undersized/correct/oversized) classifications.ResultsA total of 1801 patients were included. For binary classification, the best-performing algorithm for predicting femoral and tibial mismatch was the stochastic gradient boosting model (area under the curve: 0.76/0.72, calibration intercepts: 0.05/0.05, calibration slopes: 0.55/0.7, and Brier scores: 0.20/0.21). For multiclass classification, the best-performing algorithms had accuracies of 83.9% and 82.9% for predicting the concordance/mismatch of the femoral and tibial implant, respectively. Model predictions of greater than 51.0% and 47.9% represented high-risk thresholds for femoral and tibial sizing mismatch, respectively.ConclusionsML algorithms predicted templating mismatch with good accuracy. External validation is necessary to confirm the performance and reliability of these algorithms. Predicting sizing mismatch is the first step in using ML to aid in the prediction of final TKA component sizes. Further studies to optimize parameters and predictions for the algorithms are ongoing.
| S-EPMC8167319 | biostudies-literature
Project description:Ischaemic preconditioning is a method of protecting tissue against ischaemia-reperfusion injury. It is an innate protective mechanism that increases a tissue's tolerance to prolonged ischaemia when it is first subjected to short burst of ischaemia and reperfusion. It is thought to provide this protection by increasing the tissue's tolerance to ischaemia, therby reducing oxidative stress, inflammation and apoptosis in the preconditioned tissue. We used microarrays to investigate the genomic response induced by ischaemic preconditioning in muscle biopsies taken from the operative leg of total knee arthroplasty patients in order to gain insight into the ischaemic preconditioning mechanism. Patients undergoing primary knee arthroplasty were randomised to control and treatment (ischaemic preconditioning) groups. Patients in the treatment group received a preconditioning stimulus immediately prior to surgery. The ischaemic preconditioning stimulus consisted of three five-minute periods of tourniquet insufflation on the lower operative limb, interrupted by five minute periods of reperfusion. All patients had a tourniquet applied to the lower limb after the administration of spinal anaesthesia, as per normal protocol for knee arthroplasty surgery. Muscle biopsies were taken from the quadriceps muscle of the operative knee at the immediate onset of surgery (T0) and at 1 hour into surgery (T1). Total RNA was extracted from biospies of four control and four treatment patients and hybridised to the Affymetrix Human U133 2.0 chip.
2010-04-12 | E-GEOD-21164 | biostudies-arrayexpress
Project description:BackgroundArtificial intelligence (AI) and machine learning (ML) modeling in hip and knee arthroplasty (total joint arthroplasty [TJA]) is becoming more commonplace. This systematic review aims to quantify the accuracy of current AI- and ML-based application for cognitive support and decision-making in TJA.MethodsA comprehensive search of publications was conducted through the EMBASE, Medline, and PubMed databases using relevant keywords to maximize the sensitivity of the search. No limits were placed on level of evidence or timing of the study. Findings were reported according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Analysis of variance testing with post-hoc Tukey test was applied to compare the area under the curve (AUC) of the models.ResultsAfter application of inclusion and exclusion criteria, 49 studies were included in this review. The application of AI/ML-based models and average AUC is as follows: cost prediction-0.77, LOS and discharges-0.78, readmissions and reoperations-0.66, preoperative patient selection/planning-0.79, adverse events and other postoperative complications-0.84, postoperative pain-0.83, postoperative patient-reported outcomes measures and functional outcome-0.81. Significant variability in model AUC across the different decision support applications was found (P < .001) with the AUC for readmission and reoperation models being significantly lower than that of the other decision support categories.ConclusionsAI/ML-based applications in TJA continue to expand and have the potential to optimize patient selection and accurately predict postoperative outcomes, complications, and associated costs. On average, the AI/ML models performed best in predicting postoperative complications, pain, and patient-reported outcomes and were less accurate in predicting hospital readmissions and reoperations.
| S-EPMC8426157 | biostudies-literature
Project description:Ischaemic preconditioning is a method of protecting tissue against ischaemia-reperfusion injury. It is an innate protective mechanism that increases a tissue's tolerance to prolonged ischaemia when it is first subjected to short burst of ischaemia and reperfusion. It is thought to provide this protection by increasing the tissue's tolerance to ischaemia, therby reducing oxidative stress, inflammation and apoptosis in the preconditioned tissue. We used microarrays to investigate the genomic response induced by ischaemic preconditioning in muscle biopsies taken from the operative leg of total knee arthroplasty patients in order to gain insight into the ischaemic preconditioning mechanism.
2010-04-02 | GSE21164 | GEO
Project description:BackgroundPostoperative delirium is a challenging complication due to its adverse outcome such as long hospital stay. The aims of this study were: 1) to identify preoperative risk factors of postoperative delirium following knee arthroplasty, and 2) to develop a machine-learning prediction model.MethodA total of 3,980 patients from two hospitals were included in this study. The model was developed and trained with 1,931 patients from one hospital and externally validated with 2,049 patients from another hospital. Twenty preoperative variables were collected using electronic hospital records. Feature selection was conducted using the sequential feature selection (SFS). Extreme Gradient Boosting algorithm (XGBoost) model as a machine-learning classifier was applied to predict delirium. A tenfold-stratified area under the curve (AUC) served as the metric for variable selection and internal validation.ResultsThe incidence rate of delirium was 4.9% (n = 196). The following seven key predictors of postoperative delirium were selected: age, serum albumin, number of hypnotics and sedatives drugs taken preoperatively, total number of drugs (any kinds of oral medication) taken preoperatively, neurologic disorders, depression, and fall-down risk (all p < 0.05). The predictive performance of our model was good for the developmental cohort (AUC: 0.80, 95% CI: 0.77-0.84). It was also good for the external validation cohort (AUC: 0.82, 95% CI: 0.80-0.83). Our model can be accessed at https://safetka.connecteve.com .ConclusionsA web-based predictive model for delirium after knee arthroplasty was developed using a machine-learning algorithm featuring seven preoperative variables. This model can be used only with information that can be obtained from pre-operative electronic hospital records. Thus, this model could be used to predict delirium before surgery and may assist physician's effort on delirium prevention.
| S-EPMC9235137 | biostudies-literature
Project description:To study 90-day complications following total hip arthroplasty (THA) or total knee arthroplasty (TKA).In a population-based cohort of all Olmsted County residents who underwent a THA or TKA (1994-2008), we assessed 90-day occurrence and predictors of cardiac complications (myocardial infarction, cardiac arrhythmia or congestive heart failure), thromboembolic complications (deep venous thrombosis or pulmonary embolism) and mortality.90-day complication rates after THA and TKA were: cardiac, 6.9% and 6.7%; thromboembolic, 4.0% and 4.9%; and mortality, 0.7% and 0.4%, respectively. In multivariable-adjusted logistic regression analyses, ASA class III-IV (OR 6.1, 95% CI:1.6-22.8) and higher Deyo-Charlson comorbidity score (OR 1.2, 95% CI:1.0-1.4) were significantly associated with odds of 90-day cardiac event post-THA in patients with no known previous cardiac event. In those with known previous cardiac disease, ASA class III-IV (OR 4.4, 95% CI:2.0-9.9), male gender (OR 0.5, 95% CI:0.3-0.9) and history of thromboembolic disease (OR 3.2; 95% CI:1.4-7.0) were significantly associated with odds of cardiac complication 90 days post-THA. No significant predictors of thromboembolism were found in THA patients. In TKA patients with no previous cardiac history, age >65 years (OR 4.1, 95% CI:1.2-14.0) and in TKA patients with known cardiac disease, ASA class III-IV (OR 3.2, 95% CI:1.8-5.7) was significantly associated with odds of 90-day cardiac events. In TKA patients with no previous thromboembolic disease, male gender (OR 0.5, 95% CI:0.2-0.9) and higher Charlson index (OR 1.2, 95% CI:1.1-1.3) and in patients with known thromboembolic disease, higher Charlson index score (OR 1.2, 95% CI:1.1-1.4) was associated with odds of 90-day thromboembolic events.Older age, higher comorbidity, higher ASA class and previous history of cardiac/thromboembolic disease were associated with an increased risk.
| S-EPMC3315837 | biostudies-literature