ABSTRACT

STUDY DESIGN: A retrospective cohort study.

OBJECTIVES: Venous thromboembolism (VTE) is a potentially high-risk complication for patients undergoing spine surgery. Although guidelines for assessing VTE risk in this population have been established, development of new techniques that target different aspects of the medical history may prove to be of further utility. The goal of this study was to develop a predictive machine learning (ML) model to identify nontraditional risk factors for predicting VTE in spine surgery patients.

SUMMARY OF BACKGROUND DATA: A cohort of 63 patients was identified who had undergone spine surgery at a single center from 2015 to 2021. Thirty-one patients had a confirmed VTE, while 32 had no VTE. A total of 113 attributes were defined and collected via chart review. Attribute categories included demographics, medications, labs, past medical history, operative history, and VTE diagnosis.

METHODS: The Waikato Environment for Knowledge Analysis (WEKA) software was used in creating and evaluating the ML models. Six classifier models were tested with 10-fold cross-validation and statistically evaluated using t tests.

RESULTS: Comparing the predictive ML models to the control model (ZeroR), all predictive models were significantly better than the control model at predicting VTE risk, based on the 113 attributes (P<0.001).

CONCLUSION: Further development of these tools may provide high diagnostic value and may guide chemoprophylaxis treatment in this setting of high-risk patients.

PMID:37482644 | DOI:10.1097/BSD.0000000000001498

15:01

Photo

Not included, change data exporting settings to download.

1200×1200, 39.0 KB

15:01

In reply to this message

PubMed articles on: Cancer & VTE/PE

Automated detection and segmentation of pulmonary embolisms on computed tomography pulmonary angiography (CTPA) using deep learning but without manual outlining

Med Image Anal. 2023 Jul 14;89:102882. doi: 10.1016/j.media.2023.102882. Online ahead of print.

ABSTRACT

We present a novel computer algorithm to automatically detect and segment pulmonary embolisms (PEs) on computed tomography pulmonary angiography (CTPA). This algorithm is based on deep learning but does not require manual outlines of the PE regions. Given a CTPA scan, both intra- and extra-pulmonary arteries were firstly segmented. The arteries were then partitioned into several parts based on size (radius). Adaptive thresholding and constrained morphological operations were used to identify suspicious PE regions within each part. The confidence of a suspicious region to be PE was scored based on its contrast in the arteries. This approach was applied to the publicly available RSNA Pulmonary Embolism CT Dataset (RSNA-PE) to identify three-dimensional (3-D) PE negative and positive image patches, which were used to train a 3-D Recurrent Residual U-Net (R2-Unet) to automatically segment PE. The feasibility of this computer algorithm was validated on an independent test set consisting of 91 CTPA scans acquired from a different medical institute, where the PE regions were manually located and outlined by a thoracic radiologist (>18 years' experience). An R2-Unet model was also trained and validated on the manual outlines using a 5-fold cross-validation method. The CNN model trained on the high-confident PE regions showed a Dice coefficient of 0.676±0.168 and a false positive rate of 1.86 per CT scan, while the CNN model trained on the manual outlines demonstrated a Dice coefficient of 0.647±0.192 and a false positive rate of 4.20 per CT scan. The former model performed significantly better than the latter model (p<0.01).

PMID:37482032 | DOI:10.1016/j.media.2023.102882

15:01

Photo

Not included, change data exporting settings to download.

1200×1200, 39.0 KB

15:01

In reply to this message

PubMed articles on: Cancer & VTE/PE

Polygenic risk scores for prediction of cancer-associated venous thromboembolism in the UK Biobank cohort study

J Thromb Haemost. 2023 Jul 20:S1538-7836(23)00571-8. doi: 10.1016/j.jtha.2023.07.009. Online ahead of print.

ABSTRACT

BACKGROUND: Guidelines recommend thromboprophylaxis for cancer patients at high risk of venous thromboembolism (VTE). Polygenic risk scores may improve VTE prediction, but have not yet been evaluated in cancer patients.

METHODS: We assessed the performance of the 5-SNP, 37-SNP, 297-SNP, extended 297-SNP (additionally including factor V Leiden and prothrombin G20210A), and 100-SNP scores in predicting cancer-associated VTE in the UK Biobank, a population-based, prospective cohort study. The primary outcome was VTE during 12 months after cancer diagnosis. Cancer and VTE diagnosis were based on ICD-10 codes. Discrimination was evaluated by c-indices and subdistribution hazard ratios (SHR) in the upper vs three lower quartiles of the scores in a competing risk model. As a comparison, the c-index was calculated for the Khorana cancer type risk classification.

FINDINGS: Of 36,150 cancer patients (median age, 66 years; 48.7% females), 1,018 (2.8%) developed VTE. C-indices at 12 months ranged from 0.56 (95%CI, 0.54-0.58) for the 5-SNP to 0.60 (95%CI, 0.58-0.62) for the extended 297-SNP scores. SHRs ranged from 1.36 (95%CI, 1.19-1.56) for the 5-SNP to 1.90 (95%CI, 1.68-2.16) for the extended 297-SNP scores, and were consistent after adjusting for cancer type. For the Khorana cancer type classification the c-index was 0.60 (95%CI, 0.58-0.61), which increased to 0.65 (95%CI, 0.63-0.67; +0.05, 95%CI, 0.04-0.07) when combined with the extended 297-SNP score.

INTERPRETATION: These findings demonstrate that polygenic VTE risk scores can identify cancer patients with a 1.9-fold higher VTE risk independent of cancer type. Combined clinical-genetic scores to improve cancer-associated VTE prediction should be evaluated further.

PMID:37481074 | DOI:10.1016/j.jtha.2023.07.009

15:01

Photo

Not included, change data exporting settings to download.

1200×1200, 39.0 KB

15:01

Photo

Not included, change data exporting settings to download.

1200×1200, 39.0 KB

15:01

In reply to this message

PubMed articles on: Cancer & VTE/PE

Neutrophil extracellular trap formation is an independent risk factor for occult cancer in patients presenting with VTE

J Thromb Haemost. 2023 Jul 19:S1538-7836(23)00565-2. doi: 10.1016/j.jtha.2023.07.007. Online ahead of print.

ABSTRACT

BACKGROUND: Venous thromboembolism (VTE), particularly unprovoked VTE, is associated with occult cancer. Current guidelines recommend limited cancer screening in patients presenting with unprovoked VTE. Only half of the underlying cancer cases are detected by cancer screening, and the optimal screening regimen remains controversial. Neutrophil extracellular traps (NETs) are implicated in cancer-associated thrombosis and elevated biomarkers of NET formation are associated with poor prognosis.

OBJECTIVES AND METHODS: This prospective cohort study investigated the association between blood biomarkers associated with NETs and neutrophil activation (circulating nucleosomal citrullinated histone H3 [H3Cit-DNA], cell-free DNA, and neutrophil elastase) and cancer during a one-year follow-up.

RESULTS AND CONCLUSIONS: Four-hundred-sixty VTE patients were included. Two hundred and twenty-one (48%) had isolated deep vein thrombosis, and 220 (48%) of all VTE cases were unprovoked. Cancer was diagnosed in 29 (7.0%) VTE patients during the follow-up period, and 43 patients had a known active cancer. After adjustment for age and unprovoked VTE, the hazard ratio of cancer during follow-up per 500 ng/ml increase of H3Cit-DNA was 1.79 [95% CI 1.03-3.10] suggesting that H3Cit-DNA is potentially a useful diagnostic marker for cancer in patients with VTE. Furthermore, patients with cancer-associated VTE (known active cancer or cancer diagnosed during follow-up) had higher levels of H3Cit-DNA compared to cancer-free patients with VTE after adjustment for age, hemoglobin, gender, chronic obstructive pulmonary disease, prior cancer and start of anticoagulant treatment (odds ratio 2.06 per 500 ng/ml increase of H3Cit-DNA [95% CI 1.35-3.13]), indicating that elevated NET formation is a hallmark of cancer-associated VTE.

PMID:37479035 | DOI:10.1016/j.jtha.2023.07.007

15:01

Photo

Not included, change data exporting settings to download.

1200×1200, 39.0 KB

15:01

In reply to this message

PubMed articles on: Cancer & VTE/PE

Antithrombotic secondary prophylaxis with low dose of apixaban or rivaroxaban in the onco-hematologic patients: comparison with non-neoplastic patients

Ann Hematol. 2023 Jul 21. doi: 10.1007/s00277-023-05369-1. Online ahead of print.

ABSTRACT

Management of cancer-associated thrombosis (CAT) is usually performed employing low molecular weight heparin (LMWH) or direct oral anticoagulants (DOACs). Low-intensity DOACs are the mainstay for extended duration therapy for VTE in non-oncologic patients. The aim of our study was to evaluate the efficacy and the safety of low doses of apixaban or rivaroxaban as secondary prophylaxis in patients affected by hematological malignancies with follow-up > 12 months. We report an observational, retrospective, single-center study that evaluated consecutive patients referred to our center between January 2016 and January 2023. The DOACs were administered at full dose during the acute phase of VTE and then at low dose for the extended phase. We included 154 patients: 53 patients affected by hematological malignancies compared to 101 non-neoplastic patients. During full-dose treatment, no thrombotic recurrences were observed in the two groups. During low-dose therapy, 2 (1.9%) thrombotic events (tAE) were observed in the control group. During full-dose treatment, the rate of bleeding events (bAE) was 9/154 (5.8%): 6/53 (11%) in hematological patients and 3/101 (2.9%) in non-hematological patients (p = 0.0003). During low-dose therapy, 4/154 (2.6%) bAE were observed: 3/53 (5.5%) in the hematologic group and 1 (1%) in the control group (p = 0.07). We found encouraging data on the safety and efficacy of low doses of DOACs as secondary prophylaxis in the onco-hematologic setting; no thrombotic complications were observed, and the incidence of hemorrhagic events was low.

PMID:37479891 | DOI:10.1007/s00277-023-05369-1

15:01

Photo

Not included, change data exporting settings to download.

1200×1200, 39.0 KB

15:01

Photo

Not included, change data exporting settings to download.

1200×1200, 39.0 KB

15:01

In reply to this message

PubMed articles on: Cancer & VTE/PE

Risk of thromboembolic events in patients with metastatic solid tumors treated with PARP inhibitors: A systematic review and meta-analysis of phase 3 randomized controlled trials

Cancer Treat Rev. 2023 Jul 17;119:102601. doi: 10.1016/j.ctrv.2023.102601. Online ahead of print.

ABSTRACT

BACKGROUND AND SCOPE: Poly(ADP-ribose) polymerase inhibitors (PARPi) have revolutionized cancer treatment in recent years. These drugs present a favorable safety profile, even though the potential risk of thromboembolic events (TEs) during their use has not been addressed yet. In addition, PARPi have been involved in an active scientific debate regarding non-oncologic indications, particularly during the Coronavirus Disease 2019 pandemic, including potential anti-thromboembolic effect.

METHODS: To clarify whether patients treated with PARPi for metastatic solid tumors are either at increased or decreased risk of TEs, we conducted a systematic review of the literature and meta-analysis, including all phase 3 randomized controlled trials (RCTs) which investigated PARPi in this setting. Search was conducted through Medline, EMBASE, Pubmed, SCOPUS and Google Scholar in February 2023, including the proceedings of the principal oncology meetings of the last 10 years, with no time restriction. For each included study, frequencies of TEs in experimental and control arm were collected.

RESULTS: Our search identified 2,369 reports, of which 20 were lastly selected. A total of 4,946 patients were included, across 12 different RCTs. The meta-analysis did not demonstrate either an increased or a reduced risk in TEs in patients treated with PARPi for metastatic disease (OR 1.50, range: 1.00-2.24; 95% CI; P = 0.050), with low heterogeneity and low publication bias.

CONCLUSION: Although our research did not confirm either increased or decreased risk of TEs for PARPi use, no safety alerts emerged. Thromboembolic risk assessment models should always be integrated in daily clinical routine, to identify high-risk patients.

PMID:37473517 | DOI:10.1016/j.ctrv.2023.102601

15:01

In reply to this message

PubMed articles on: Cancer & VTE/PE

Venous thromboembolism and breast cancer

Bull Cancer. 2023 Jul 18:S0007-4551(23)00296-5. doi: 10.1016/j.bulcan.2023.06.001. Online ahead of print.

ABSTRACT

Breast cancer is the most common cancer in women. Patients with breast cancer have a 4-fold increased risk of venous thromboembolism (VTE) compared to age- and sex-matched controls without cancer. VTE remains the second leading cause of death in cancer patients and an independent risk factor for mortality. In women with breast cancer, the main risk factors for developing VTE are increasing age, obesity, disease stage, central catheter placement and cancer treatments, including surgery, chemotherapy, hormonotherapy and cyclin-dependent kinase 4/6 inhibitors. In women receiving tamoxifen, the risk of VTE is particularly increased within the first 6 months after initiation of hormonotherapy, although some evidence suggests that this risk may persist through the first 2 years of treatment. The risk of VTE appears to be lower in patients receiving aromatase inhibitors. In breast cancer patients receiving cyclin-dependent kinase 4/6 inhibitors, the rate of VTE is approximately 6%. Current clinical practice guidelines for the treatment and prevention of VTE in patients with cancer suggest that thromboprophylaxis should not be used routinely in ambulatory cancer patients receiving chemotherapy or hormonotherapy. The risk-benefit ratio of thromboprophylaxis should be assessed on a case-by-case basis and be the subject of multidisciplinary discussion.

PMID:37474353 | DOI:10.1016/j.bulcan.2023.06.001

15:01

Photo

Not included, change data exporting settings to download.

1200×1200, 39.0 KB

15:01

Photo

Not included, change data exporting settings to download.

1200×1200, 39.0 KB

15:01

In reply to this message

PubMed articles on: Cancer & VTE/PE

Primary prevention of cancer-associated venous thrombosis: Rationale and challenges in clinical practice

Curr Res Transl Med. 2023 Jul 13;71(3):103405. doi: 10.1016/j.retram.2023.103405. Online ahead of print.

ABSTRACT

Cancer-associated venous thrombosis (CAT) is a common, multifactor event known to complicate the course of cancer and jeopardize a patient's prognosis. The current guidelines regarding the prevention of CAT are sometimes considered insufficiently precise about specific situations, or are poorly applied. The expected benefits of thromboprophylaxis are balanced by the risk of major bleeding induced by anticoagulation, which implies a need to accurately identify ambulatory patients at high risk of thrombosis or hemorrhage. The Khorana score is commonly used for this, but is limited by the non-reproducibility of predicted performance across cancer types, and by the fact that antitumor treatment and cardiovascular risks are not included. The COMPASS-CAT score, which includes those two aspects, was found to be a more accurate predictor of venous thromboembolism in patients with lung cancer, and to better distinguish between patients at low or high risk of thrombosis. The frailty of patients with cancer is also a major issue, and should be taken into account when thromboprophylaxis is considered. According to current guidelines, CAT prophylaxis should be considered for hospitalized patients, those for whom surgery is scheduled, or those with pancreatic cancers. In ambulatory patients, decisions should be made according to patient, cancer and antitumoral treatment characteristics. Low molecular weight heparin is the gold standard of CAT prophylaxis. Despite increased risks of bleeding or drug-drug interactions in cancer patients, direct oral anticoagulants could be alternate options for high-risk ambulatory patients that should be accompanied by a careful global analysis of benefits, harms, and patient preferences.

PMID:37478777 | DOI:10.1016/j.retram.2023.103405

15:01

Photo

Not included, change data exporting settings to download.

1200×1200, 39.0 KB

15:01

In reply to this message

PubMed articles on: Cancer & VTE/PE

Comment on: Silent Pulmonary Thromboembolism in Patients Undergoing Craniotomy for Brain Tumor

Turk Neurosurg. 2023;33(4):711. doi: 10.5137/1019-5149.JTN.44181-23.0.

NO ABSTRACT

PMID:37470514 | DOI:10.5137/1019-5149.JTN.44181-23.0

15:01

In reply to this message

PubMed articles on: Cancer & VTE/PE

Clinical Presentation and Outcomes of Patients With Cancer-Associated Isolated Distal Deep Vein Thrombosis

J Clin Oncol. 2023 Jul 20:JCO2300429. doi: 10.1200/JCO.23.00429. Online ahead of print.

ABSTRACT

PURPOSE: Patients with isolated distal deep vein thrombosis (DVT) have lower rates of adverse outcomes (death, venous thromboembolism [VTE] recurrence or major bleeding) than those with proximal DVT. It is uncertain if such findings are also observed in patients with cancer.

METHODS: Using data from the international Registro Informatizado de la Enfermedad TromboEmbolica venosa registry, we compared the risks of adverse outcomes at 90 days (adjusted odds ratio [aOR]; 95% CI) and 1 year (adjusted hazard ratio [aHR; 95% CI]) in 886 patients with cancer-associated distal DVT versus 5,196 patients with cancer-associated proximal DVT and 5,974 patients with non-cancer-associated distal DVT.

RESULTS: More than 90% of patients in each group were treated with anticoagulants for at least 90 days. At 90 days, the adjusted risks of death, VTE recurrence, or major bleeding were lower in patients with non-cancer-associated distal DVT than in patients with cancer-associated distal DVT (reference): aOR = 0.16 (0.11-0.22), aOR = 0.34 (0.22-0.54), and aOR = 0.47 (0.27-0.80), respectively. The results were similar at 1-year follow-up: aHR = 0.12 (0.09-0.15), aHR = 0.39 (0.28-0.55), and aHR = 0.51 (0.32-0.82), respectively. Risks of death, VTE recurrence, and major bleeding were not statistically different between patients with cancer-associated proximal versus distal DVT, both at 90 days: aOR = 1.11 (0.91-1.36), aOR = 1.10 (0.76-1.62), and aOR = 1.18 (0.76-1.83), respectively, and 1 year: aHR = 1.01 (0.89-1.15), aHR = 1.02 (0.76-1.35), and aHR = 1.10 (0.76-1.61), respectively. However, more patients with cancer-associated proximal DVT, compared with cancer-associated distal DVT, developed fatal pulmonary embolism (PE) during follow-up: The risk difference was 0.40% (95% CI, 0.23 to 0.58).

CONCLUSION: Cancer-associated distal DVT has serious and relatively comparable outcomes compared with cancer-associated proximal DVT. The lower risk of fatal PE from cancer-associated distal DVT needs further investigation.

PMID:37471683 | DOI:10.1200/JCO.23.00429

15:01

In reply to this message

PubMed articles on: Cancer & VTE/PE

Inferior Vena Cava Filters: Adherence to Clinical Practice Guidelines Recommendations, Retrieval Rates, and Filter Complications in a Tertiary Hospital

Angiology. 2023 Jul 20:33197231190184. doi: 10.1177/00033197231190184. Online ahead of print.