Predicting 30-Day Venous Thromboembolism Following Total Joint Arthroplasty: Adjusting for Trends in Annual Length of Stay
Background: Venous thromboembolism (VTE) following total hip arthroplasty and total knee arthroplasty (TKA) is linked to immobility, and preoperative prediction remains difficult. We aimed to evaluate whether annual mean length of stay (LOS) is associated with the incidence of VTE and develop a gene...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Arthroplasty Today |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352344124001766 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850249172149600256 |
|---|---|
| author | Johnathan R. Lex, MBChB, MASc Robert Koucheki, MD, MEng Aazad Abbas, MD Jesse I. Wolfstadt, MD, MSc, FRCSC, FAAOS Alexander S. McLawhorn, MD, MBA Bheeshma Ravi, MD, PhD, FRCSC |
| author_facet | Johnathan R. Lex, MBChB, MASc Robert Koucheki, MD, MEng Aazad Abbas, MD Jesse I. Wolfstadt, MD, MSc, FRCSC, FAAOS Alexander S. McLawhorn, MD, MBA Bheeshma Ravi, MD, PhD, FRCSC |
| author_sort | Johnathan R. Lex, MBChB, MASc |
| collection | DOAJ |
| description | Background: Venous thromboembolism (VTE) following total hip arthroplasty and total knee arthroplasty (TKA) is linked to immobility, and preoperative prediction remains difficult. We aimed to evaluate whether annual mean length of stay (LOS) is associated with the incidence of VTE and develop a generalizable machine learning model to preoperatively predict the incidence of symptomatic VTE following total hip and TKA using National Surgical Quality Improvement Program. Methods: Annual incidence of 30-day postoperative VTE, deep vein thrombosis, and pulmonary embolism was calculated over 6 years and tested for trend. Correlation between annual VTE rates and mean LOS was calculated. Predictive models (logistic regression, random forest, and XGBoost) were trained and tested based on year of surgery with different oversampling algorithms used to address data imbalance. Results: A total of 498,314 patients were included, with 0.88% developing a VTE within 30 days. VTE rates decreased from 1.11% in 2014 to 0.76% in 2019 (P < .001). There was a strong correlation between the yearly incidence of VTE, pulmonary embolism, and deep vein thrombosis and mean LOS (r = 0.96, 0.87, and 0.98, respectively). Univariate analysis demonstrated that TKA, inpatient setting, American Society of Anesthesiologists classification, and various patient comorbidities were significantly associated with VTE. The logistic regression model trained on all data with a balanced loss scoring function performed the best (area under the curve = 0.600). Conclusions: This study revealed declining VTE rates strongly correlated to decreasing postoperative LOS and identified patient and surgery-specific factors associated with VTE risk. Development of more accurate machine learning models for VTE prediction may improve risk stratification, prevention, and monitoring for arthroplasty patients. |
| format | Article |
| id | doaj-art-35fbc36e2a424b7a83dce456c00747b1 |
| institution | OA Journals |
| issn | 2352-3441 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Arthroplasty Today |
| spelling | doaj-art-35fbc36e2a424b7a83dce456c00747b12025-08-20T01:58:33ZengElsevierArthroplasty Today2352-34412024-12-013010149110.1016/j.artd.2024.101491Predicting 30-Day Venous Thromboembolism Following Total Joint Arthroplasty: Adjusting for Trends in Annual Length of StayJohnathan R. Lex, MBChB, MASc0Robert Koucheki, MD, MEng1Aazad Abbas, MD2Jesse I. Wolfstadt, MD, MSc, FRCSC, FAAOS3Alexander S. McLawhorn, MD, MBA4Bheeshma Ravi, MD, PhD, FRCSC5Temerty Faculty of Medicine, Division of Orthopaedic Surgery, Department of Surgery, University of Toronto, Toronto, Canada; Institute of Biomedical Engineering, University of Toronto, Toronto, Canada; Corresponding author. Division of Orthopaedic Surgery, University of Toronto, 149 College Street, Room 508-A, Toronto, ON M5T 1P5, Canada.Temerty Faculty of Medicine, Division of Orthopaedic Surgery, Department of Surgery, University of Toronto, Toronto, Canada; Institute of Biomedical Engineering, University of Toronto, Toronto, CanadaTemerty Faculty of Medicine, Division of Orthopaedic Surgery, Department of Surgery, University of Toronto, Toronto, CanadaTemerty Faculty of Medicine, Division of Orthopaedic Surgery, Department of Surgery, University of Toronto, Toronto, Canada; Granovsky Gluskin Division of Orthopaedic Surgery, Mount Sinai Hospital, Sinai Health, Toronto, CanadaDepartment of Orthopedic Surgery, Hospital for Special Surgery, New York, NY, USATemerty Faculty of Medicine, Division of Orthopaedic Surgery, Department of Surgery, University of Toronto, Toronto, Canada; Division of Orthopaedic Surgery, Sunnybrook Health Sciences Centre, Toronto, CanadaBackground: Venous thromboembolism (VTE) following total hip arthroplasty and total knee arthroplasty (TKA) is linked to immobility, and preoperative prediction remains difficult. We aimed to evaluate whether annual mean length of stay (LOS) is associated with the incidence of VTE and develop a generalizable machine learning model to preoperatively predict the incidence of symptomatic VTE following total hip and TKA using National Surgical Quality Improvement Program. Methods: Annual incidence of 30-day postoperative VTE, deep vein thrombosis, and pulmonary embolism was calculated over 6 years and tested for trend. Correlation between annual VTE rates and mean LOS was calculated. Predictive models (logistic regression, random forest, and XGBoost) were trained and tested based on year of surgery with different oversampling algorithms used to address data imbalance. Results: A total of 498,314 patients were included, with 0.88% developing a VTE within 30 days. VTE rates decreased from 1.11% in 2014 to 0.76% in 2019 (P < .001). There was a strong correlation between the yearly incidence of VTE, pulmonary embolism, and deep vein thrombosis and mean LOS (r = 0.96, 0.87, and 0.98, respectively). Univariate analysis demonstrated that TKA, inpatient setting, American Society of Anesthesiologists classification, and various patient comorbidities were significantly associated with VTE. The logistic regression model trained on all data with a balanced loss scoring function performed the best (area under the curve = 0.600). Conclusions: This study revealed declining VTE rates strongly correlated to decreasing postoperative LOS and identified patient and surgery-specific factors associated with VTE risk. Development of more accurate machine learning models for VTE prediction may improve risk stratification, prevention, and monitoring for arthroplasty patients.http://www.sciencedirect.com/science/article/pii/S2352344124001766Machine learningVenous thromboembolismOutcome predictionTotal hip arthroplastyTotal knee arthroplasty |
| spellingShingle | Johnathan R. Lex, MBChB, MASc Robert Koucheki, MD, MEng Aazad Abbas, MD Jesse I. Wolfstadt, MD, MSc, FRCSC, FAAOS Alexander S. McLawhorn, MD, MBA Bheeshma Ravi, MD, PhD, FRCSC Predicting 30-Day Venous Thromboembolism Following Total Joint Arthroplasty: Adjusting for Trends in Annual Length of Stay Arthroplasty Today Machine learning Venous thromboembolism Outcome prediction Total hip arthroplasty Total knee arthroplasty |
| title | Predicting 30-Day Venous Thromboembolism Following Total Joint Arthroplasty: Adjusting for Trends in Annual Length of Stay |
| title_full | Predicting 30-Day Venous Thromboembolism Following Total Joint Arthroplasty: Adjusting for Trends in Annual Length of Stay |
| title_fullStr | Predicting 30-Day Venous Thromboembolism Following Total Joint Arthroplasty: Adjusting for Trends in Annual Length of Stay |
| title_full_unstemmed | Predicting 30-Day Venous Thromboembolism Following Total Joint Arthroplasty: Adjusting for Trends in Annual Length of Stay |
| title_short | Predicting 30-Day Venous Thromboembolism Following Total Joint Arthroplasty: Adjusting for Trends in Annual Length of Stay |
| title_sort | predicting 30 day venous thromboembolism following total joint arthroplasty adjusting for trends in annual length of stay |
| topic | Machine learning Venous thromboembolism Outcome prediction Total hip arthroplasty Total knee arthroplasty |
| url | http://www.sciencedirect.com/science/article/pii/S2352344124001766 |
| work_keys_str_mv | AT johnathanrlexmbchbmasc predicting30dayvenousthromboembolismfollowingtotaljointarthroplastyadjustingfortrendsinannuallengthofstay AT robertkouchekimdmeng predicting30dayvenousthromboembolismfollowingtotaljointarthroplastyadjustingfortrendsinannuallengthofstay AT aazadabbasmd predicting30dayvenousthromboembolismfollowingtotaljointarthroplastyadjustingfortrendsinannuallengthofstay AT jesseiwolfstadtmdmscfrcscfaaos predicting30dayvenousthromboembolismfollowingtotaljointarthroplastyadjustingfortrendsinannuallengthofstay AT alexandersmclawhornmdmba predicting30dayvenousthromboembolismfollowingtotaljointarthroplastyadjustingfortrendsinannuallengthofstay AT bheeshmaravimdphdfrcsc predicting30dayvenousthromboembolismfollowingtotaljointarthroplastyadjustingfortrendsinannuallengthofstay |