Artificial neural network prediction of same-day discharge following primary total knee arthroplasty based on preoperative and intraoperative variables

2021 ◽  
Vol 103-B (8) ◽  
pp. 1358-1366
Author(s):  
Chapman Wei ◽  
Theodore Quan ◽  
Kevin Y. Wang ◽  
Alex Gu ◽  
Safa C. Fassihi ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Total Knee Arthroplasty ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Knee Arthroplasty ◽  
Logistic Regression Model ◽  
Ann Model ◽  
Same Day Discharge ◽  
Total Knee

Aims This study used an artificial neural network (ANN) model to determine the most important pre- and perioperative variables to predict same-day discharge in patients undergoing total knee arthroplasty (TKA). Methods Data for this study were collected from the National Surgery Quality Improvement Program (NSQIP) database from the year 2018. Patients who received a primary, elective, unilateral TKA with a diagnosis of primary osteoarthritis were included. Demographic, preoperative, and intraoperative variables were analyzed. The ANN model was compared to a logistic regression model, which is a conventional machine-learning algorithm. Variables collected from 28,742 patients were analyzed based on their contribution to hospital length of stay. Results The predictability of the ANN model, area under the curve (AUC) = 0.801, was similar to the logistic regression model (AUC = 0.796) and identified certain variables as important factors to predict same-day discharge. The ten most important factors favouring same-day discharge in the ANN model include preoperative sodium, preoperative international normalized ratio, BMI, age, anaesthesia type, operating time, dyspnoea status, functional status, race, anaemia status, and chronic obstructive pulmonary disease (COPD). Six of these variables were also found to be significant on logistic regression analysis. Conclusion Both ANN modelling and logistic regression analysis revealed clinically important factors in predicting patients who can undergo safely undergo same-day discharge from an outpatient TKA. The ANN model provides a beneficial approach to help determine which perioperative factors can predict same-day discharge as of 2018 perioperative recovery protocols. Cite this article: Bone Joint J 2021;103-B(8):1358–1366.

The rate and predictors of patient satisfaction after total knee arthroplasty are influenced by the focus of the question

2018 ◽  
Vol 100-B (6) ◽  
pp. 740-748 ◽  
Author(s):  
N. D. Clement ◽  
M. Bardgett ◽  
D. Weir ◽  
J. Holland ◽  
C. Gerrand ◽  
...  
Keyword(s):  
Total Knee Arthroplasty ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Patient Satisfaction ◽  
Back Pain ◽  
Pain Relief ◽  
Logistic Regression Analysis ◽  
Knee Arthroplasty ◽  
Total Knee ◽  
One Year

AimsThe primary aim of this study was to assess the rate of patient satisfaction one year after total knee arthroplasty (TKA) according to the focus of the question asked. The secondary aims were to identify independent predictors of patient satisfaction according to the focus of the question.Patients and MethodsA retrospective cohort of 2521 patients undergoing a primary unilateral TKA were identified from an established regional arthroplasty database. Patient demographics, comorbidities, Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) and 12-Item Short-Form Health Survey (SF-12) scores were collected preoperatively and one year postoperatively. Patient satisfaction was assessed using four questions, which focused on overall outcome, activity, work, and pain. Logistic regression analysis was used to identify independent preoperative predictors of increased stiffness when adjusting for confounding variables.ResultsUsing patient satisfaction with the overall outcome (n = 2265, 89.8%) as the standard, there was no difference in the rate of satisfaction for pain relief (n = 2277, odds ratio (OR) 0.95, 95% confident intervals (CI) 0.79 to 1.14, p = 0.60), but patients were more likely to be dissatisfied with activities (79.3%, n = 2000/2521, OR 2.22, 95% CI 1.96 to 2.70, p < 0.001) and work (85.8%, n = 2163/2521, OR 1.47, 95% CI 1.23 to 1.75, p < 0.001). Logistic regression analysis identified different predictors of satisfaction for each of the focused satisfaction questions. Overall satisfaction was influenced by diabetes (p = 0.03), depression (p = 0.004), back pain (p < 0.001), and SF-12 physical (p = 0.008) and mental (p = 0.01) components. Satisfaction with activities was influenced by depression (p = 0.001), back pain (p < 0.001), WOMAC stiffness score (p = 0.03), and SF-12 physical (p < 0.001) and mental (p < 0.001) components. Satisfaction with work was influenced by depression (p = 0.007), back pain (p < 0.001), WOMAC function (p = 0.04) and stiffness (p = 0.05) scores, and SF-12 physical (p < 0.001) and mental (p < 0.001) components. Satisfaction with pain relief was influenced by diabetes (p < 0.001), back pain (p < 0.001), and SF-12 mental component (p = 0.04).ConclusionThe focus of the satisfaction question significantly influences the rate and the predictors of patient satisfaction after TKA. Cite this article: Bone Joint J 2018;100-B:740–8.

Risk Factors for Surgical-Site Infection Following Primary Total Knee Arthroplasty

2004 ◽  
Vol 25 (6) ◽  
pp. 477-480 ◽  
Author(s):  
Brian Minnema ◽  
Mary Vearncombe ◽  
Anne Augustin ◽  
Jeffrey Gollish ◽  
Andrew E. Simor
Keyword(s):  
Risk Factors ◽  
Total Knee Arthroplasty ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Knee Arthroplasty ◽  
Site Infection ◽  
Suction Drainage ◽  
Closed Suction ◽  
Closed Suction Drainage ◽  
Total Knee

AbstractObjective:To identify risk factors associated with the development of surgical-site infection (SSI) following total knee arthroplasty (TKA).Design:A case-control study.Setting:A 1,100-bed, university-affiliated, tertiary-care teaching hospital.Methods:Case-patients with SSI occurring up to 1 year following primary TKA performed between January 1999 and December 2001 were identified prospectively by infection control practitioners using National Nosocomial Infections Surveillance (NNIS) System methods. Three control-patients were selected for each case-patient, matched by date of surgery. Stepwise logistic regression analysis was used to determine the relation of potential risk factors to the development of infection.Results:Twenty-two patients with infections (6 superficial and 16 deep) were identified. Infection rates per year were 0.95%, 1.07%, and 1.19% in 1999, 2000, and 2001, respectively. Logistic regression analysis identified two variables independently associated with the development of infection: the use of closed suction drainage (odds ratio [OR], 7.0; 95% confidence interval [CI95], 2.1-25.0; P = .0015) and increased international normalized ratio (INR) (OR, 2.4; CI95, 1.1-5.7; P = .035). Factors not statistically associated with the development of infection included age, NNIS System risk index score, presence of various comorbidities, surgeon, duration of procedure or tourniquet time, type of bone cement or prosthesis used, or receipt of blood product transfusions.Conclusions:The use of closed suction drainage and a high postoperative INR were associated with the development of SSI following TKA. Avoiding the use of surgical drains and careful monitoring of anticoagulant prophylaxis in patients undergoing TKA should reduce the risk of infection.

Construction and Comparison of Predictive Models for Length of Stay after Total Knee Arthroplasty: Regression Model and Machine Learning Analysis Based on 1,826 Cases in a Single Singapore Center

2020 ◽  
Author(s):  
Hui Li ◽  
Juyang Jiao ◽  
Shutao Zhang ◽  
Haozheng Tang ◽  
Xinhua Qu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Total Knee Arthroplasty ◽  
Logistic Regression ◽  
Length Of Stay ◽  
Knee Arthroplasty ◽  
Predictive Models ◽  
Prediction Models ◽  
Univariate Analysis ◽  
Machine Learning Algorithms ◽  
Total Knee

AbstractThe purpose of this study was to develop a predictive model for length of stay (LOS) after total knee arthroplasty (TKA). Between 2013 and 2014, 1,826 patients who underwent TKA from a single Singapore center were enrolled in the study after qualification. Demographics of patients with normal and prolonged LOS were analyzed. The risk variables that could affect LOS were identified by univariate analysis. Predictive models for LOS after TKA by logistic regression or machine learning were constructed and compared. The univariate analysis showed that age, American Society of Anesthesiologist level, diabetes, ischemic heart disease, congestive heart failure, general anesthesia, and operation duration were risk factors that could affect LOS (p < 0.05). Comparing with logistic regression models, the machine learning model with all variables was the best model to predict LOS after TKA, of whose area of operator characteristic curve was 0.738. Machine learning algorithms improved the predictive performance of LOS prediction models for TKA patients.

Intra-articular administration of vancomycin and tobramycin during primary cementless total knee arthroplasty

2021 ◽  
Vol 103-B (11) ◽  
pp. 1702-1708
Author(s):  
Charles Murray Lawrie ◽  
Gregory S. Kazarian ◽  
Toby Barrack ◽  
Ryan M. Nunley ◽  
Robert L. Barrack
Keyword(s):  
Total Knee Arthroplasty ◽  
Knee Arthroplasty ◽  
Joint Infection ◽  
Venous Blood ◽  
Primary Total Knee Arthroplasty ◽  
Final Analysis ◽  
Serum Levels ◽  
Poor Renal Function ◽  
Same Day Discharge ◽  
Total Knee

Aims Intra-articular administration of antibiotics during primary total knee arthroplasty (TKA) may represent a safe, cost-effective strategy to reduce the risk of acute periprosthetic joint infection (PJI). Vancomycin with an aminoglycoside provides antimicrobial cover for most organisms isolated from acute PJI after TKA. However, the intra-articular doses required to achieve sustained therapeutic intra-articular levels while remaining below toxic serum levels is unknown. The purpose of this study is to determine the intra-articular and serum levels of vancomycin and tobramycin over the first 24 hours postoperatively after intra-articular administration in primary cementless TKA. Methods A prospective cohort study was performed. Patients were excluded if they had poor renal function, known allergic reaction to vancomycin or tobramycin, received intravenous vancomycin, or were scheduled for same-day discharge. All patients received 600 mg tobramycin and 1 g of vancomycin powder suspended in 25 cc of normal saline and injected into the joint after closure of the arthrotomy. Serum from peripheral venous blood and drain fluid samples were collected at one, four, and 24 hours postoperatively. All concentrations are reported in µg per ml. Results A total of 22 patients were included in final analysis. At one, four, and 24 hours postoperatively, mean (95% confidence interval (CI)) serum concentrations were 2.4 (0.7 to 4.1), 5.0 (3.1 to 6.9), and 4.8 (2.8 to 6.9) for vancomycin and 4.9 (3.4 to 6.3), 7.0 (5.8 to 8.2), and 1.3 (0.8 to 1.8) for tobramycin; intra-articular concentrations were 1,900.6 (1,492.5 to 2,308.8), 717.9 (485.5 to 950.3), and 162.2 (20.5 to 304.0) for vancomycin and 2,105.3 (1,389.9 to 2,820.6), 403.2 (266.6 to 539.7), and 98.8 (0 to 206.5) for tobramycin. Conclusion Intra-articular administration of 1 g of vancomycin and 600 mg of tobramycin as a solution after closure of the arthrotomy in primary cementless TKA achieves therapeutic intra-articular concentrations over the first 24 hours postoperatively and does not reach sustained toxic levels in peripheral blood. Cite this article: Bone Joint J 2021;103-B(11):1702–1708.

Sign in / Sign up

Export Citation Format

Share Document