1
|
Using machine learning to predict venous thromboembolism and major bleeding events following total joint arthroplasty. Sci Rep 2023; 13:2197. [PMID: 36750656 PMCID: PMC9905066 DOI: 10.1038/s41598-022-26032-1] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2022] [Accepted: 12/08/2022] [Indexed: 02/09/2023] Open
Abstract
Venous thromboembolism (VTE) and major bleeding (MBE) are feared complications that are influenced by numerous host and surgical related factors. Using machine learning on contemporary data, our aim was to develop and validate a practical, easy-to-use algorithm to predict risk for VTE and MBE following total joint arthroplasty (TJA). This was a single institutional study of 35,963 primary and revision total hip (THA) and knee arthroplasty (TKA) patients operated between 2009 and 2020. Fifty-six variables related to demographics, comorbidities, operative factors as well as chemoprophylaxis were included in the analysis. The cohort was divided to training (70%) and test (30%) sets. Four machine learning models were developed for each of the outcomes assessed (VTE and MBE). Models were created for all VTE grouped together as well as for pulmonary emboli (PE) and deep vein thrombosis (DVT) individually to examine the need for distinct algorithms. For each outcome, the model that best performed using repeated cross validation was chosen for algorithm development, and predicted versus observed incidences were evaluated. Of the 35,963 patients included, 308 (0.86%) developed VTE (170 PE's, 176 DVT's) and 293 (0.81%) developed MBE. Separate models were created for PE and DVT as they were found to outperform the prediction of VTE. Gradient boosting trees had the highest performance for both PE (AUC-ROC 0.774 [SD 0.055]) and DVT (AUC-ROC 0.759 [SD 0.039]). For MBE, least absolute shrinkage and selection operator (Lasso) analysis had the highest AUC (AUC-ROC 0.803 [SD 0.035]). An algorithm that provides the probability for PE, DVT and MBE for each specific patient was created. All 3 algorithms had good discriminatory capability and cross-validation showed similar probabilities comparing predicted and observed failures indicating high accuracy of the model. We successfully developed and validated an easy-to-use algorithm that accurately predicts VTE and MBE following TJA. This tool can be used in every-day clinical decision making and patient counseling.
Collapse
|
2
|
The Role of Anti-Factor Xa Activity in the Management of Ecchymosis in Patients Receiving Rivaroxaban after Total Knee Arthroplasty. J Clin Med 2023; 12:jcm12031161. [PMID: 36769808 PMCID: PMC9917433 DOI: 10.3390/jcm12031161] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2022] [Revised: 01/30/2023] [Accepted: 01/31/2023] [Indexed: 02/05/2023] Open
Abstract
This study aims to evaluate the efficacy of anti-factor Xa activity (aFXa) in predicting ecchymosis after total knee arthroplasty (TKA). One hundred and two unilateral primary TKA patients were recruited consecutively in this prospective observational study. Participants received rivaroxaban (10 mg p.o. qd) from postoperative day 1 (POD1) to POD35 and were divided into a non-ecchymosis group (group A) and an ecchymosis group (group B). AFXa was assessed as the primary outcome on POD1 and POD3. Prothrombin time (PT), activated partial thromboplastin time (APTT) and thromboelastography (TEG) were recorded both preoperatively and postoperatively (on POD1 and POD3). Other outcomes, including venous thromboembolism (VTE), blood loss and wound complications were also collected and compared. As a result, 27.5% of the participants (n = 28) were allocated into group B. Demographic data were comparable between the two groups. The aFXa levels in group B were significantly higher than those in group A on POD1 and POD3, and the aFXa level was assessed as an independent risk factor for ecchymosis. The cut-off value of aFXa was determined to be 121.38 ng/mL at maximal Youden index, associated with area under the receiver operating characteristics curve of 0.67. Group B experienced significantly more blood loss and wound complications than group A. No statistical difference was detected regarding PT, APTT and TEG parameters. AFXa is a promising parameter to predict ecchymosis after TKA. Patients with aFXa > 121.38 ng/mL should be considered as high-risk population for postoperative ecchymosis and may require intense monitoring or dosage modification of anticoagulants.
Collapse
|
3
|
Maradei-Pereira JAR, Sauma ML, Demange MK. Thromboprophylaxis with unilateral pneumatic device led to less edema and blood loss compared to enoxaparin after knee arthroplasty: randomized trial. BMC Musculoskelet Disord 2022; 23:984. [PMCID: PMC9664627 DOI: 10.1186/s12891-022-05910-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/08/2022] [Accepted: 10/25/2022] [Indexed: 11/16/2022] Open
Abstract
Abstract
Background
Pharmacological and mechanical thromboprophylaxis are frequently used together after total knee arthroplasty (TKA). Most studies in this context compare anticoagulants versus a combination of these drugs with an intermittent pneumatic compression device (IPCD). However, there is uncertainty about the need for the combination of both and whether a unilateral IPCD would alone affect other important clinical outcomes: edema and blood loss. We compared the effects of enoxaparin versus unilateral portable IPCD after TKA on edema and blood loss. We hypothesised that unilateral IPCD would cause the same level of edema and the same blood loss as enoxaparin.
Methods
In this open, randomized trial (1:1), adults with no history of coagulation disorders, anticoagulant use, venous thromboembolism, liver or malignant diseases underwent TKA. For 10 days, participants received the IPCD, used 24 h/day on the operated leg from the end of surgery, or 40 mg of enoxaparin, starting 12 h after surgery. All underwent the same rehabilitation and were encouraged to walk on the same day of surgery. We measured edema (thigh, leg and ankle circumference) before and on the third postoperative day. Blood loss (volume accumulated in the suction drain and drop of hemoglobin and hematocrit in 48 h) was a secondary outcome.
Results
We randomized 150 patients and lost 3 to follow-up with enoxaparin and 2 with IPCD. There was no case of symptomatic venous thromboembolism. Four patients needed transfusions (three receiving enoxaparin), one had infection and one hemarthrosis (both in the enoxaparin group). Leg circumference increased by approximately 2 cm for enoxaparin group and 1.5 cm in IPCD (p < 0.001). The increase in ankle circumference was about 1.5 cm in the enoxaparin group (p < 0.001), and almost zero in IPCD (p = 0.447). Enoxaparin group lost 566.1 ml (standard deviation, SD, 174.5) of blood in the first 48 h, versus 420.8 ml (SD 142.5) in the IPCD.
Conclusions
Exclusively mechanical prophylaxis after TKA with portable IPCD only on the operated leg reduces leg and ankle swelling and post-operative blood loss compared to exclusively pharmacological prophylaxis with enoxaparin. Portable devices that can prevent deep vein thrombosis and pulmonary embolism without increasing blood loss or other risks should be further investigated.
Trial registration
REBEC RBR-8k2vpx. Registration date: 06/04/2019.
Collapse
|
4
|
Tang A, Zak S, Lygrisse K, Slover J, Meftah M, Lajam C, Schwarzkopf R, Macaulay W. Discontinued Use of Outpatient Portable Intermittent Pneumatic Compression Devices May Be Safe for Venous Thromboembolism Prophylaxis in Primary Total Knee Arthroplasty Using Low-Dose Aspirin. J Knee Surg 2022; 35:909-915. [PMID: 33241544 DOI: 10.1055/s-0040-1721092] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
Venous thromboembolism (VTE) is a rare, but serious complication following total knee arthroplasty (TKA). Current VTE guidelines recommend pharmacologic agents with or without intermittent pneumatic compression devices (IPCDs). At our institution, both 81-mg aspirin (ASA) twice a day (BID) and portable IPCDs were previously prescribed to TKA patients at standard risk for VTE, but the IPCDs were discontinued and patients were treated with ASA alone going forward. The aim of this study is to determine if discontinued use of outpatient IPCDs is safe and does not increase the rate of VTE or any other related complications in patients following TKA. A retrospective review of 2,219 consecutive TKA cases was conducted, identifying patients with VTE, bleeding complications, infection, and mortality within 90 days postoperatively. Patients were divided into two cohorts. Patients in cohort one received outpatient IPCDs for a period of 14 days (control), while those in cohort two did not (ASA alone). All study patients received inpatient IPCDs and were maintained on 81-mg ASA BID for 28 days. A posthoc power analysis was performed using a noninferiority margin of 0.25 (α = 0.05; power = 80%), which showed that our sample size was fully powered for noninferiority for our reported deep vein thrombosis (DVT) rates, but not for pulmonary embolism (PE) rates. A total of 867 controls and 1,352 patients treated with ASA alone were identified. Only two control patients were diagnosed with a PE (0.23%), while one patient in the ASA alone group had DVT (0.07%). There was no statistical difference between these rates (p = 0.33). Furthermore, no differences were found in bleeding complications (p = 0.12), infection (p = 0.97), or 90-day mortality rates (p = 0.42) between both groups. The discontinued use of outpatient portable IPCDs is noninferior to outpatient IPCD use for DVT prophylaxis. Our findings suggest that this protocol change may be safe and does not increase the rate of VTE in standard risk patients undergoing TKA while using 81-mg ASA BID.
Collapse
Affiliation(s)
- Alex Tang
- Department of Orthopedic Surgery, NYU Langone Health, New York, New York
| | - Stephen Zak
- Department of Orthopedic Surgery, NYU Langone Health, New York, New York
| | - Katherine Lygrisse
- Department of Orthopedic Surgery, NYU Langone Health, New York, New York
| | - James Slover
- Department of Orthopedic Surgery, NYU Langone Health, New York, New York
| | - Morteza Meftah
- Department of Orthopedic Surgery, NYU Langone Health, New York, New York
| | - Claudette Lajam
- Department of Orthopedic Surgery, NYU Langone Health, New York, New York
| | - Ran Schwarzkopf
- Department of Orthopedic Surgery, NYU Langone Health, New York, New York
| | - William Macaulay
- Department of Orthopedic Surgery, NYU Langone Health, New York, New York
| |
Collapse
|
5
|
|
6
|
|
7
|
Shohat N, Ludwick L, Goh GS, Streicher S, Chisari E, Parvizi J. Aspirin Thromboprophylaxis Is Associated With Less Major Bleeding Events Following Total Joint Arthroplasty. J Arthroplasty 2022; 37:379-384.e2. [PMID: 34648924 DOI: 10.1016/j.arth.2021.10.001] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/15/2021] [Revised: 09/27/2021] [Accepted: 10/04/2021] [Indexed: 02/02/2023] Open
Abstract
BACKGROUND There is ongoing debate on what is optimal prophylactic agent to reduce venous thromboembolism (VTE) following total joint arthroplasty (TJA). Although many studies assess the efficacy of these agents in VTE prevention, no attention is given to their adverse effect on major bleeding events (MBEs). This study compared the incidence of MBE in patients receiving aspirin as VTE prophylaxis vs other chemoprophylaxis. METHODS A single-institution, retrospective study of 35,860 patients undergoing TJA between 2009 and 2020 was conducted. Demographic variables, co-morbidities, type of chemoprophylaxis, and intraoperative factors were collected. MBE was defined using the 2010 criteria for major bleeding in surgical patients presented by the Scientific and Standardization Committee of the International Society on Thrombosis and Haemostasis. To enhance capture rate, comprehensive queries utilizing MBE keywords were conducted in clinical notes, physician dictations, and phone call logs. Univariate followed by multivariate regression was performed as well as propensity score matched analysis. RESULTS Overall, 270 patients (0.75%) in this cohort developed MBE. The MBE rate was 0.5% in the aspirin group and 1.2% in the non-aspirin group. After adjusting for confounders, multiple logistic regression and propensity score matched analysis revealed almost 2 times lower odds of MBE in patients who received aspirin. Variables independently associated with increased MBE risk included increasing age, body mass index, American Society of Anesthesiologists score, revision surgery, peptic ulcer disease, coagulopathy, intraoperative blood transfusion, and active smoking. CONCLUSION Administration of aspirin for VTE prophylaxis, compared to other chemoprophylaxis agents may have an association with lower risk of major bleeding following TJA. Future randomized controlled trials should examine these findings.
Collapse
Affiliation(s)
- Noam Shohat
- Rothman Orthopaedic Institute at Thomas Jefferson University, Philadelphia, PA; Sackler Faculty of Medicine, Tel Aviv University, Ramat Aviv, Israel
| | - Leanne Ludwick
- Rothman Orthopaedic Institute at Thomas Jefferson University, Philadelphia, PA
| | - Graham S Goh
- Rothman Orthopaedic Institute at Thomas Jefferson University, Philadelphia, PA
| | - Sydney Streicher
- Rothman Orthopaedic Institute at Thomas Jefferson University, Philadelphia, PA
| | - Emanuele Chisari
- Rothman Orthopaedic Institute at Thomas Jefferson University, Philadelphia, PA
| | - Javad Parvizi
- Rothman Orthopaedic Institute at Thomas Jefferson University, Philadelphia, PA
| |
Collapse
|
8
|
Amarase C, Tanavalee A, Larbpaiboonpong V, Lee MC, Crawford RW, Matsubara M, Zhou Y. Asia-Pacific venous thromboembolism consensus in knee and hip arthroplasty and hip fracture surgery: Part 2. Mechanical venous thromboembolism prophylaxis. Knee Surg Relat Res 2021; 33:20. [PMID: 34193307 PMCID: PMC8243471 DOI: 10.1186/s43019-021-00101-7] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/22/2021] [Accepted: 04/04/2021] [Indexed: 12/28/2022] Open
Affiliation(s)
- Chavarin Amarase
- Department of Orthopaedics, Faculty of Medicine, King Chulalongkorn Memorial Hospital, Chulalongkorn University, Bangkok, Thailand
| | - Aree Tanavalee
- Department of Orthopaedics, Faculty of Medicine, King Chulalongkorn Memorial Hospital, Chulalongkorn University, Bangkok, Thailand.
| | | | - Myung Chul Lee
- Department of Orthopedic Surgery, Seoul National University Hospital, Seoul, South Korea
| | - Ross W Crawford
- Orthopaedic Research Unit, Queensland University of Technology, Brisbane, Australia
| | - Masaaki Matsubara
- epartment of Orthopaedic Surgery, Nissan Tamagawa Hospital, Tokyo, Japan
| | - Yixin Zhou
- Department of Orthopaedic Surgery, Beijing Jishuitan Hospital, Fourth Clinical College of Peking University, Beijing, China
| | | |
Collapse
|
9
|
Crawford DA, Andrews RL, Morris MJ, Hurst JM, Lombardi AV, Berend KR. Ambulatory Portable Pneumatic Compression Device as Part of a Multimodal Aspirin-Based Approach in Prevention of Venous Thromboembolism in Outpatient Total Knee Arthroplasty. Arthroplast Today 2020; 6:378-380. [PMID: 32577481 PMCID: PMC7303536 DOI: 10.1016/j.artd.2020.05.007] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/24/2020] [Revised: 05/04/2020] [Accepted: 05/08/2020] [Indexed: 12/19/2022] Open
Abstract
Background The purpose of this study is to review the incidence of symptomatic venous thromboembolism (VTE) in patients undergoing outpatient primary total knee arthroplasty (TKA) who used a portable pneumatic compression device as part of their VTE prophylaxis protocol. Methods A retrospective review of all outpatient primary TKA procedures in which patients used ambulatory pneumatic compression pumps as part of their multimodal VTE prophylaxis was performed from 2016 through 2018. This yielded a cohort of 1131 patients (1453 TKAs). An aspirin (ASA)-based protocol was used in patients with standard VTE risk receiving either 81 mg or 325 mg of ASA twice daily for 6 weeks postoperatively. High-risk patients received a stronger chemoprophylaxis for 2 weeks followed by ASA for 4 weeks. Pneumatic compression pumps were worn for 23 hours/day for 14 days. Results VTE prophylaxis medication was 81-mg ASA in 56% of patients, 325-mg ASA in 10% of patients, and stronger chemoprophylaxis in 34% of patients. Patients were considered morbidly obese (body mass index >40 kg/m2) in 267 (18.4%) procedures. Ninety-seven (6.7%) patients had a preoperative history of VTE event. Forty-nine duplex ultrasounds were performed (3.3% of TKAs). Confirmed VTE events were documented in only 5 (0.3%) patients. All VTEs occurred in high-risk patients who were discharged on stronger chemoprophylaxis. The time (days) to VTE was 3, 3, 7, 45, and 88 days. Conclusion The use of portable pneumatic compression pumps as part of a multimodal VTE prophylaxis protocol aided in a very low rate of symptomatic VTE events in patients undergoing outpatient primary TKA.
Collapse
Affiliation(s)
| | | | - Michael J Morris
- Joint Implant Surgeons, Inc., New Albany, OH, USA.,Mount Carmel Health System, New Albany, OH, USA
| | - Jason M Hurst
- Joint Implant Surgeons, Inc., New Albany, OH, USA.,Mount Carmel Health System, New Albany, OH, USA
| | - Adolph V Lombardi
- Joint Implant Surgeons, Inc., New Albany, OH, USA.,Mount Carmel Health System, New Albany, OH, USA.,Department of Orthopaedics, The Ohio State University Wexner Medical Center, Columbus, OH, USA
| | - Keith R Berend
- Joint Implant Surgeons, Inc., New Albany, OH, USA.,Mount Carmel Health System, New Albany, OH, USA
| |
Collapse
|
10
|
Pennestrì F, Maffulli N, Sirtori P, Perazzo P, Negrini F, Banfi G, Peretti GM. Blood management in fast-track orthopedic surgery: an evidence-based narrative review. J Orthop Surg Res 2019; 14:263. [PMID: 31429775 PMCID: PMC6701001 DOI: 10.1186/s13018-019-1296-5] [Citation(s) in RCA: 26] [Impact Index Per Article: 5.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/09/2019] [Accepted: 07/25/2019] [Indexed: 12/18/2022] Open
Abstract
BACKGROUND AND PURPOSE Innovations able to maintain patient safety while reducing the amount of transfusion add value to orthopedic procedures. Opportunities for improvement arise especially in elective procedures, as long as room for planning is available. Although many strategies have been proposed, there is no consensus about the most successful combination. The purpose of this investigation is to identify information to support blood management strategies in fast-track total joint arthroplasty (TJA) pathway, to (i) support clinical decision making according to current evidence and best practices, and (ii) identify critical issues which need further research. METHODS AND MATERIALS We identified conventional blood management strategies in elective orthopedic procedures. We performed an electronic search about blood management strategies in fast-track TJA. We designed tables to match every step of the former with the latter. We submitted the findings to clinicians who operate using fast-track surgery protocols in TJA at our research hospital. RESULTS Preoperative anemia detection and treatment, blood anticoagulants/aggregants consumption, transfusion trigger, anesthetic technique, local infiltration analgesia, drainage clamping and removals, and postoperative multimodal thromboprophylaxis are the factors which can add best value to a fast-track pathway, since they provide significant room for planning and prediction. CONCLUSION The difference between conventional and fast-track pathways does not lie in the contents of blood management, which are related to surgeons/surgeries, materials used and patients, but in the way these contents are integrated into each other, since elective orthopedic procedures offer significant room for planning. Further studies are needed to identify optimal regimens.
Collapse
Affiliation(s)
| | - Nicola Maffulli
- Department of Musculoskeletal Disorders, School of Medicine and Surgery, University of Salerno, Fisciano, Italy. .,San Giovanni di Dio e Ruggi D'Aragona Hospital "Clinica Orthopedica" Department, Hospital of Salerno, Salerno, Italy. .,Queen Mary University of London, Barts and the London School of Medicine and Dentistry, Centre for Sports and Exercise Medicine, London, England.
| | - Paolo Sirtori
- IRCCS Orthopedic Institute Galeazzi, Scientific Direction, Milan, Italy
| | - Paolo Perazzo
- IRCCS Orthopedic Institute Galeazzi, Scientific Direction, Milan, Italy
| | - Francesco Negrini
- IRCCS Orthopedic Institute Galeazzi, Scientific Direction, Milan, Italy
| | - Giuseppe Banfi
- IRCCS Orthopedic Institute Galeazzi, Scientific Direction, Milan, Italy.,Vita-Salute San Raffaele University, Scientific Direction, Milan, Italy
| | - Giuseppe M Peretti
- IRCCS Orthopedic Institute Galeazzi, Scientific Direction, Milan, Italy.,University of Milan, Department of Biomedical Sciences for Health, Milan, Italy
| |
Collapse
|