Boosting efficiency in a clinical literature surveillance system with LightGBM.

Given the suboptimal performance of Boolean searching to identify methodologically sound and clinically relevant studies in large bibliographic databases, exploring machine learning (ML) to efficiently classify studies is warranted. To boost the efficiency of a literature surveillance program, we used a large internationally recognized dataset of articles tagged for methodological rigor and applied an automated ML approach to train and test binary classification models to predict the probability of clinical research articles being of high methodologic quality. We trained over 12,000 models on a dataset of titles and abstracts of 97,805 articles indexed in PubMed from 2012-2018 which were manually appraised for rigor by highly trained research associates and rated for clinical relevancy by practicing clinicians. As the dataset is unbalanced, with more articles that do not meet the criteria for rigor, we used the unbalanced dataset and over- and under-sampled datasets. Models that maintained sensitivity for high rigor at 99% and maximized specificity were selected and tested in a retrospective set of 30,424 articles from 2020 and validated prospectively in a blinded study of 5253 articles. The final selected algorithm, combining a LightGBM (gradient boosting machine) model trained in each dataset, maintained high sensitivity and achieved 57% specificity in the retrospective validation test and 53% in the prospective study. The number of articles needed to read to find one that met appraisal criteria was 3.68 (95% CI 3.52 to 3.85) in the prospective study, compared with 4.63 (95% CI 4.50 to 4.77) when relying only on Boolean searching. Gradient-boosting ML models reduced the work required to classify high quality clinical research studies by 45%, improving the efficiency of literature surveillance and subsequent dissemination to clinicians and other evidence users.

The McMaster Health Information Research Unit: Over a Quarter-Century of Health Informatics Supporting Evidence-Based Medicine.

Evidence-based medicine (EBM) emerged from McMaster University in the 1980-1990s, which emphasizes the integration of the best research evidence with clinical expertise and patient values. The Health Information Research Unit (HiRU) was created at McMaster University in 1985 to support EBM. Early on, digital health informatics took the form of teaching clinicians how to search MEDLINE with modems and phone lines. Searching and retrieval of published articles were transformed as electronic platforms provided greater access to clinically relevant studies, systematic reviews, and clinical practice guidelines, with PubMed playing a pivotal role. In the early 2000s, the HiRU introduced Clinical Queries-validated search filters derived from the curated, gold-standard, human-appraised Hedges dataset-to enhance the precision of searches, allowing clinicians to hone their queries based on study design, population, and outcomes. Currently, almost 1 million articles are added to PubMed annually. To filter through this volume of heterogenous publications for clinically important articles, the HiRU team and other researchers have been applying classical machine learning, deep learning, and, increasingly, large language models (LLMs). These approaches are built upon the foundation of gold-standard annotated datasets and humans in the loop for active machine learning. In this viewpoint, we explore the evolution of health informatics in supporting evidence search and retrieval processes over the past 25+ years within the HiRU, including the evolving roles of LLMs and responsible artificial intelligence, as we continue to facilitate the dissemination of knowledge, enabling clinicians to integrate the best available evidence into their clinical practice.

Protocol for a living evidence synthesis on variants of concern and COVID-19 vaccine effectiveness.

BACKGROUND: It is evident that COVID-19 will remain a public health concern in the coming years, largely driven by variants of concern (VOC). It is critical to continuously monitor vaccine effectiveness as new variants emerge and new vaccines and/or boosters are developed. Systematic surveillance of the scientific evidence base is necessary to inform public health action and identify key uncertainties. Evidence syntheses may also be used to populate models to fill in research gaps and help to prepare for future public health crises. This protocol outlines the rationale and methods for a living evidence synthesis of the effectiveness of COVID-19 vaccines in reducing the morbidity and mortality associated with, and transmission of, VOC of SARS-CoV-2. METHODS: Living evidence syntheses of vaccine effectiveness will be carried out over one year for (1) a range of potential outcomes in the index individual associated with VOC (pathogenesis); and (2) transmission of VOC. The literature search will be conducted up to May 2023. Observational and database-linkage primary studies will be included, as well as RCTs. Information sources include electronic databases (MEDLINE; Embase; Cochrane, L*OVE; the CNKI and Wangfang platforms), pre-print servers (medRxiv, BiorXiv), and online repositories of grey literature. Title and abstract and full-text screening will be performed by two reviewers using a liberal accelerated method. Data extraction and risk of bias assessment will be completed by one reviewer with verification of the assessment by a second reviewer. Results from included studies will be pooled via random effects meta-analysis when appropriate, or otherwise summarized narratively. DISCUSSION: Evidence generated from our living evidence synthesis will be used to inform policy making, modelling, and prioritization of future research on the effectiveness of COVID-19 vaccines against VOC.

Joint 2022 European Society of Thoracic Surgeons and The American Association for Thoracic Surgery guidelines for the prevention of cancer-associated venous thromboembolism in thoracic surgery.

BACKGROUND: Venous thromboembolism (VTE), which includes deep vein thrombosis and pulmonary embolism, is a potentially fatal but preventable postoperative complication. Thoracic oncology patients undergoing surgical resection, often after multimodality induction therapy, represent among the highest risk groups for postoperative VTE. Currently there are no VTE prophylaxis guidelines specific to these thoracic surgery patients. Evidenced-based recommendations will help clinicians manage and mitigate risk of VTE in the postoperative period and inform best practice. OBJECTIVE: These joint evidence-based guidelines from The American Association for Thoracic Surgery and the European Society of Thoracic Surgeons aim to inform clinicians and patients in decisions about prophylaxis to prevent VTE in patients undergoing surgical resection for lung or esophageal cancer. METHODS: The American Association for Thoracic Surgery and the European Society of Thoracic Surgeons formed a multidisciplinary guideline panel that included broad membership to minimize potential bias when formulating recommendations. The McMaster University GRADE Centre supported the guideline development process, including updating or performing systematic evidence reviews. The panel prioritized clinical questions and outcomes according to their importance for clinicians and patients. The Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach was used, including GRADE Evidence-to-Decision frameworks, which were subject to public comment. RESULTS: The panel agreed on 24 recommendations focused on pharmacological and mechanical methods for prophylaxis in patients undergoing lobectomy and segmentectomy, pneumonectomy, and esophagectomy, as well as extended resections for lung cancer. CONCLUSIONS: The certainty of the supporting evidence for the majority of recommendations was judged as low or very low, largely due to a lack of direct evidence for thoracic surgery. The panel made conditional recommendations for use of parenteral anticoagulation for VTE prevention, in combination with mechanical methods, over no prophylaxis for cancer patients undergoing anatomic lung resection or esophagectomy. Other key recommendations include: conditional recommendations for using parenteral anticoagulants over direct oral anticoagulants, with use of direct oral anticoagulants suggested only in the context of clinical trials; conditional recommendation for using extended prophylaxis for 28 to 35 days over in-hospital prophylaxis only for patients at moderate or high risk of thrombosis; and conditional recommendations for VTE screening in patients undergoing pneumonectomy and esophagectomy. Future research priorities include the role of preoperative thromboprophylaxis and the role of risk stratification to guide use of extended prophylaxis.

Joint 2022 European Society of Thoracic Surgeons and The American Association for Thoracic Surgery guidelines for the prevention of cancer-associated venous thromboembolism in thoracic surgery.

BACKGROUND: Venous thromboembolism (VTE), which includes deep vein thrombosis and pulmonary embolism, is a potentially fatal but preventable postoperative complication. Thoracic oncology patients undergoing surgical resection, often after multimodality induction therapy, represent among the highest risk groups for postoperative VTE. Currently there are no VTE prophylaxis guidelines specific to these thoracic surgery patients. Evidenced-based recommendations will help clinicians manage and mitigate risk of VTE in the postoperative period and inform best practice. OBJECTIVE: These joint evidence-based guidelines from The American Association for Thoracic Surgery and the European Society of Thoracic Surgeons aim to inform clinicians and patients in decisions about prophylaxis to prevent VTE in patients undergoing surgical resection for lung or esophageal cancer. METHODS: The American Association for Thoracic Surgery and the European Society of Thoracic Surgeons formed a multidisciplinary guideline panel that included broad membership to minimize potential bias when formulating recommendations. The McMaster University GRADE Centre supported the guideline development process, including updating or performing systematic evidence reviews. The panel prioritized clinical questions and outcomes according to their importance for clinicians and patients. The Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach was used, including GRADE Evidence-to-Decision frameworks, which were subject to public comment. RESULTS: The panel agreed on 24 recommendations focused on pharmacological and mechanical methods for prophylaxis in patients undergoing lobectomy and segmentectomy, pneumonectomy, and esophagectomy, as well as extended resections for lung cancer. CONCLUSIONS: The certainty of the supporting evidence for the majority of recommendations was judged as low or very low, largely due to a lack of direct evidence for thoracic surgery. The panel made conditional recommendations for use of parenteral anticoagulation for VTE prevention, in combination with mechanical methods, over no prophylaxis for cancer patients undergoing anatomic lung resection or esophagectomy. Other key recommendations include: conditional recommendations for using parenteral anticoagulants over direct oral anticoagulants, with use of direct oral anticoagulants suggested only in the context of clinical trials; conditional recommendation for using extended prophylaxis for 28 to 35 days over in-hospital prophylaxis only for patients at moderate or high risk of thrombosis; and conditional recommendations for VTE screening in patients undergoing pneumonectomy and esophagectomy. Future research priorities include the role of preoperative thromboprophylaxis and the role of risk stratification to guide use of extended prophylaxis. (J Thorac Cardiovasc Surg 2022;▪:1-31).

Evaluating compliance of extended venous thromboembolism prophylaxis following abdominopelvic surgery for cancer: A multidisciplinary quality improvement project.

BACKGROUND AND OBJECTIVES: Despite quality evidence supporting postoperative extended venous thromboembolism prophylaxis (eVTEp) following abdominopelvic cancer surgery, baseline use of eVTEp at our institution was 3%. Our project aim was to improve the proportion of patients prescribed eVTEp following surgery for gynecologic, hepatobiliary, and colorectal cancers by a 30% absolute increase. METHODS: We performed an interrupted time series study using quality improvement methodology. Postoperative order sets, pre-printed prescriptions, process checklists, and multimodal education were introduced. Process and outcome data were collected and analyzed on statistical process control charts. RESULTS: We included 324 patients with gynecologic and hepatobiliary cancers. Despite efforts to include them, the colorectal team did not participate. The monthly mean order set-use was 58% (SD = 14%), by specialty: gynecology 79%, hepatobiliary 47%. The proportion of patients prescribed eVTEp increased from 3% to 70% (SD = 14%). The target goal was surpassed and sustained by both cohorts. Patient compliance was 73% (n = 117/160, SD = 16%). Of those who stopped eVTEp early, 45% (n = 14/31) objected because of the injectable nature. Bleeding events were infrequent (0.6%, n = 2/324). CONCLUSIONS: Three process changes and multimodal education resulted in a significant increase in eVTEp use. Failure to identify improvement champions limited project expansion to colorectal patients. Patient compliance was largely limited by the injectable nature of the medication.

A Deep Learning Approach to Refine the Identification of High-Quality Clinical Research Articles From the Biomedical Literature: Protocol for Algorithm Development and Validation.

BACKGROUND: A barrier to practicing evidence-based medicine is the rapidly increasing body of biomedical literature. Use of method terms to limit the search can help reduce the burden of screening articles for clinical relevance; however, such terms are limited by their partial dependence on indexing terms and usually produce low precision, especially when high sensitivity is required. Machine learning has been applied to the identification of high-quality literature with the potential to achieve high precision without sacrificing sensitivity. The use of artificial intelligence has shown promise to improve the efficiency of identifying sound evidence. OBJECTIVE: The primary objective of this research is to derive and validate deep learning machine models using iterations of Bidirectional Encoder Representations from Transformers (BERT) to retrieve high-quality, high-relevance evidence for clinical consideration from the biomedical literature. METHODS: Using the HuggingFace Transformers library, we will experiment with variations of BERT models, including BERT, BioBERT, BlueBERT, and PubMedBERT, to determine which have the best performance in article identification based on quality criteria. Our experiments will utilize a large data set of over 150,000 PubMed citations from 2012 to 2020 that have been manually labeled based on their methodological rigor for clinical use. We will evaluate and report on the performance of the classifiers in categorizing articles based on their likelihood of meeting quality criteria. We will report fine-tuning hyperparameters for each model, as well as their performance metrics, including recall (sensitivity), specificity, precision, accuracy, F-score, the number of articles that need to be read before finding one that is positive (meets criteria), and classification probability scores. RESULTS: Initial model development is underway, with further development planned for early 2022. Performance testing is expected to star in February 2022. Results will be published in 2022. CONCLUSIONS: The experiments will aim to improve the precision of retrieving high-quality articles by applying a machine learning classifier to PubMed searching. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/29398.

Double Blind Pilot Randomized Trial Comparing Extended Anticoagulation to Placebo Following Major Lung Resection for Cancer.

Venous thromboembolism (VTE), which comprises pulmonary embolus (PE) and deep vein thrombosis (DVT), is a significant cause of postoperative morbidity and mortality. This pilot randomized control trial (RCT) evaluated the feasibility of a full-scale RCT investigating extended thromboprophylaxis in patients undergoing oncological lung resections. Patients undergoing oncological lung resections in 2 tertiary centers received in-hospital, thromboprophylaxis and were randomized to receive post-discharge low-molecular-weight heparin (LMWH) or placebo injections once-daily for 30 days. At 30 days postoperatively, all patients underwent chest computed tomography with PE protocol and bilateral leg venous ultrasound. Primary outcomes included feasibility and safety; VTE incidence and 90-day survival were secondary outcomes. Between December 2015 and June 2018, 619 patients were screened, of whom 62.7% (165/263) of eligible patients consented to participate, and 133 (81%) were randomized. One-hundred and 3 patients, (77.4%), completed the 90-day study follow-up. Reasons for non-participation pre-randomization included patient discomfort and LMWH/placebo administration challenges. Post-randomization withdrawals were due to patient preference, surgeon preference and minor adverse events. Six asymptomatic VTE events (5 PE and 1 DVT) were detected within 30 days (3 in each group), for an overall incidence of 7%. There were 3 minor and no major adverse events. This study is the first to demonstrate the feasibility and safety of a full-scale extended thromboprophylaxis RCT in thoracic surgical oncology. Our results demonstrate that, while recruitment and retention rates were modest, the study design is feasible and with minimal adverse events and no intervention-related mortality.

Posthospital discharge venous thromboembolism prophylaxis among colorectal and hepatobiliary surgeons: A practice survey.

BACKGROUND: Recent practice guidelines recommend venous thromboembolism prophylaxis for 28 days after cancer surgery. We sought to characterize and compare awareness, agreement, adoption, and adherence to these guidelines among surgeons. METHODS: We electronically surveyed Canadian hepatobiliary surgeons registered with the Canadian Hepatopancreatobiliary Association, general and colorectal surgeons registered with the College of Physicians and Surgeons of Ontario and the Canadian Society of Colorectal Surgeons who provide colorectal cancer care with a pilot-tested questionnaire. Attitudes to relevant guideline recommendations and perceived barriers to postdischarge venous thromboembolism prophylaxis were assessed on a 5-point Likert scale. RESULTS: There were 128 responses (response rate 60%, 128 of 213), including 60 general/colorectal and 68 hepatobiliary surgeons. Most surgeons were aware (122 of 128, 95%), agreed (101 of 122, 83%), adopted (78 of 101, 77%), and adhered (74 of 78, 95%) with guidelines. Preexisting venous thromboembolism-prophylaxis hospital programs, hepatobiliary surgeons, and geographical region were associated with increased likelihood of adherence. Among respondents that did not agree, insufficient evidence (median Likert: 4, interquartile range 3-5) and low incidence of venous thromboembolism (median Likert: 4, interquartile range 3-4) were cited as the strongest barriers. Surgeons who agreed but did not adopt these programs reported that the most significant barriers were "drug cost" (median Likert: 4, interquartile range 3-4) and "subcutaneous injections" (median Likert: 4, interquartile range 3-4). Surgeons that adhered additionally reported "logistical challenges of prescribing" as the greatest implementation barrier. CONCLUSION: Surgeons who remain apprehensive about postdischarge venous thromboembolism prophylaxis cite poor evidence and cost of the medication as the major barriers. Adherence was higher among hepatobiliary surgeons and at hospitals with existing venous thromboembolism-prophylaxis programs.

Challenging anticoagulation cases: A case of acute pulmonary embolism in a patient with chronic thrombocytopenia.

We present a case of acute pulmonary embolism in a patient with myelofibrosis and thrombocytopenia. The patient had a history of portal vein thrombosis and had taken warfarin for the past six years. At the time of his pulmonary embolism diagnosis, his INR was 1.5 and platelet count 58 × 109/L. This article discusses how to balance the risk of thrombosis against the risk of bleeding, and reviews the options for pulmonary embolism treatment including transition to low-molecular-weight heparin, direct oral anticoagulants and/or inferior vena cava filters.

Maximum 24-hour platelet count fall: Metric for improving the diagnosis of heparin-induced thrombocytopenia among patients with intermediate probability 4Ts scores.

BACKGROUND: Most patients with suspected heparin-induced thrombocytopenia (HIT) and an intermediate probability 4Ts score do not have HIT. We aimed to develop a metric based on the rate of platelet count fall to aid in discriminating HIT status among patients with an intermediate 4Ts score. METHODS: We derived a measure of the maximum 24-hour percentage decrease in platelet count (Fallmax ) in a cohort of patients with suspected HIT and an intermediate 4Ts score at the University of Pennsylvania. We validated this metric in a prospectively collected cohort of patients with suspected HIT and an intermediate 4Ts score from four hospitals in Hamilton, Ontario. RESULTS: One hundred fifty-eight and 139 patients were included in the analysis from the derivation and validation cohorts, respectively. Fallmax was significantly higher in HIT-positive patients in the derivation cohort (49.6% versus 38.6%, P = .009) and validation cohort (43.5% versus 29.3%, P = .027). The area under the receiver operating characteristic curve was 0.68 (95% confidence interval [CI] 0.57-0.78) and 0.71 (0.59-0.83) in the two cohorts, respectively. At Fallmax  ≥ 30%, sensitivity and specificity were 95.5% and 29.4% in the derivation cohort and 80.0% and 52.7% in the validation cohort. CONCLUSIONS: Among patients with suspected HIT and an intermediate 4Ts score, Fallmax aided in discriminating HIT-negative from HIT-positive patients. Using a measure that accounts for the rate of platelet count fall may help to avoid unnecessary suspension of heparin and treatment with an alternative anticoagulant in HIT-negative patients with an intermediate probability 4Ts score, though further evaluation is warranted.

International Delphi survey of the ESTS/AATS/ISTH task force on venous thromboembolism prophylaxis in thoracic surgery: the role of extended post-discharge prophylaxis.

OBJECTIVES: Venous thromboembolic events can be successfully prevented with chemical and/or mechanical prophylaxis measures, but evidence-based guidelines in thoracic surgery are limited, particularly regarding extended post-discharge prophylaxis. This study attempts to gather an international consensus on best practices to inform the development of such guidelines. METHODS: A series of 3 surveys was distributed to the ESTS/AATS/ISTH (European Society of Thoracic Surgeons, American Association of Thoracic Surgeons, International Society for Thrombosis and Haemostasis) venous thromboembolic events prophylaxis working group starting January 2017. This iterative Delphi consensus process sought to gather a consensus on (i) risk factors; (ii) preferred agents; (iii) duration; and (iv) perceived barriers to an extended thromboprophylaxis approach. Participant responses were expressed on a 10-point scale, and the results were summarized and circulated to all respondents in subsequent rounds. A coefficient of variance of ≤0.3 was identified pre hoc to identify agreement. RESULTS: A total of 21 Working Group members completed the surveys, composed of 19% non-surgeon thrombosis experts, and 48% from North America. Respondents largely saw agreement regarding risk factors that indicate a need for extended thromboprophylaxis. The group agreed that low-molecular-weight heparin is a suitable agent for use post-discharge, but there was a wide variety in response regarding agents, duration and barriers to extended prophylaxis, where no consensus was observed across the three rounds. CONCLUSIONS: There is strong agreement around indications for extended venous thromboembolic events thromboprophylaxis after thoracic surgery, but there is little consensus regarding the agents and duration to be employed. Further research is required to better inform guideline development.

Venous thromboembolism prophylaxis in thoracic surgery patients: an international survey.

OBJECTIVES: Venous thromboembolic events (VTE) after thoracic surgery (TS) can be prevented with mechanical and chemical prophylaxis. Unlike other surgical specialties, TS lacks evidence-based guidelines. In the process of developing these guidelines, an understanding of the current prophylaxis methods practiced internationally is necessary and is described in this article. METHODS: A 26-item survey was distributed to members of the European Society of Thoracic Surgeons (ESTS), American Association of Thoracic Surgery (AATS), Japanese Association for Chest Surgery (JACS) and Chinese Society for Thoracic and Cardiovascular Surgery (CSTCS) electronically or in person. Participants were asked to report their current prophylaxis selection, timing of initiation and duration of prophylaxis, perceived risk factors and the presence and adherence to institutional VTE guidelines for patients undergoing TS for malignancies. RESULTS: In total, 1613 surgeons anonymously completed the survey with an overall 36% response rate. Respondents were senior surgeons working in large academic hospitals (≥70%, respectively). More than 83.5% of ESTS, AATS and JACS respondents report formal TS thromboprophylaxis protocols in their institutions, but 53% of CSTCS members report not having such a protocol. The regions varied in the approaches utilized for VTE prophylaxis, the timing of initiation perioperatively and the use and type of extended prophylaxis. Respondents reported that multiple risk factors and sources of information impact their VTE prophylaxis decision-making processes, and these factors vastly diverge regionally. CONCLUSIONS: There is little agreement internationally on the optimal approach to thromboprophylaxis in the TS population, and guidelines will be helpful and vastly welcomed.

Systematic review of fondaparinux for heparin-induced thrombocytopenia: When there are no randomized controlled trials.

BACKGROUND: Fondaparinux is commonly used for treatment of heparin-induced thrombocytopenia (HIT) despite lack of approval for this indication. High quality randomized controlled trials of this agent are unlikely to be forthcoming. OBJECTIVES: The objective of this systematic review is to update the literature on the efficacy and safety of fondaparinux for treatment of confirmed and probable HIT based on the available evidence. METHODS: Primary articles were identified using Web of Science and PubMed database searches for English-language studies from January 2006 to November 2017. Selected studies enrolled consecutive adult patients who received fondaparinux as the primary anticoagulant to treat acute HIT; confirmed the diagnosis by serological testing with a serotonin-release assay; heparin-induced platelet activation assay or enzyme-linked immunosorbent assay; provided clinical criteria used to define HIT and reported clinically important outcomes. RESULTS: A total of 9 studies were identified with 154 HIT positive patients. Ten experienced a new thrombotic event while receiving fondaparinux (6.5%, 95% CI, 3.4 to 11.7%) and 26 experienced major bleeding (16.9%, 95% CI, 11.7 to 23.6%). Mortality due to thrombosis or bleeding was reported in 5 patients (3.2%, 95% CI, 1.2 to 7.6%). CONCLUSIONS: Fondaparinux appears to be an effective and safe anticoagulant for treatment of acute HIT despite the absence of randomized trials. Caution should exercised when using fondaparinux in patients with renal insufficiency.

Venous Thromboembolic Events Following Major Pelvic and Abdominal Surgeries for Cancer: A Prospective Cohort Study.

OBJECTIVE: The aim of this study was to evaluate the incidence and risk factors for post-hospital discharge venous thromboembolism (VTE) following abdominal cancer surgery without post-discharge prophylaxis. METHODS: This was a single-center, prospective cohort study. Patients were evaluated at 1, 3, and 6 months from surgery for the presence of proximal deep vein thrombosis (DVT; screening ultrasound at 1 month and questionnaire at each visit). Cumulative VTE incidence with 95% confidence interval (CI) was estimated using Kaplan-Meier methods, and multivariable analysis was performed using a Cox proportional hazards model. RESULTS: Of 284 patients enrolled, 79 (28%) underwent colorectal laparotomy, 97 (34%) underwent hepatobiliary laparotomy, 100 (35%) underwent gynecological laparotomy, and 8 (3%) underwent exploratory laparotomy without resection. All patients received pre- and postoperative inpatient prophylaxis. The cumulative incidence of VTE at 1 month was 0.35% (95% CI 0.05-2.48), 2.5% at 3 months (95% CI 1.19-5.15), and 7.2% at 6 months (95% CI 4.72-10.97). Screening ultrasound performed 4 weeks after surgery in 50% of patients was negative for thrombosis in all cases. Event distribution was similar according to the type of surgery (open/laparoscopic) and type of cancer. Seventeen (6.6%) patients died (95% CI 3.5-9.4) (two had a VTE-related death). Postoperative chemotherapy and Caprini score were significantly associated with VTE [hazard ratios 3.77 (95% CI 1.56-9.12) and 1.17 (95% CI 1.02-1.34), respectively]. CONCLUSION: The incidence of post-hospital discharge proximal DVT and/or symptomatic VTE following abdominal and pelvic cancer surgery appears to be low. The cumulative number of events increased at 6 months, but this was likely due to additional risk factors that were not related to surgery. Postoperative chemotherapy increases the risk of VTE.