Cell-free DNA from nail clippings as source of normal control for genomic studies in hematologic malignancies.

Comprehensive genomic sequencing is becoming a critical component in the assessment of hematologic malignancies, with broad implications for patient management. In this context, unequivocally discriminating somatic from germline events is challenging but greatly facilitated by matched analysis of tumor:normal pairs. In contrast to solid tumors, conventional sources of normal control (peripheral blood, buccal swabs, saliva) could be highly involved by the neoplastic process, rendering them unsuitable. In this work we describe our real-world experience using cell free DNA (cfDNA) isolated from nail clippings as an alternate source of normal control, through the dedicated review of 2,610 tumor:nail pairs comprehensively sequenced by MSK-IMPACT-heme. Overall, we find nail cfDNA is a robust source of germline control for paired genomic studies. In a subset of patients, nail DNA may have tumor DNA contamination, reflecting unique attributes of the hematologic disease and transplant history. Contamination is generally low level, but significantly more common among patients with myeloid neoplasms (20.5%; 304/1482) compared to lymphoid diseases (5.4%; 61/1128) and particularly enriched in myeloproliferative neoplasms with marked myelofibrosis. When identified in patients with lymphoid and plasma-cell neoplasms, mutations commonly reflected a myeloid profile and correlated with a concurrent/evolving clonal myeloid neoplasm. For nails collected after allogeneic stem-cell transplantation, donor DNA was identified in 22% (11/50). In this cohort, an association with recent history of graft-vs-host disease was identified. These findings should be considered as a potential limitation for the use of nail as normal control but could also provide important diagnostic information regarding the disease process.

Genomic profiling identifies somatic mutations predicting thromboembolic risk in patients with solid tumors.

Venous thromboembolism (VTE) associated with cancer (CAT) is a well-described complication of cancer and a leading cause of death in patients with cancer. The purpose of this study was to assess potential associations of molecular signatures with CAT, including tumor-specific mutations and the presence of clonal hematopoiesis. We analyzed deep-coverage targeted DNA-sequencing data of >14 000 solid tumor samples using the Memorial Sloan Kettering-Integrated Mutation Profiling of Actionable Cancer Targets platform to identify somatic alterations associated with VTE. End point was defined as the first instance of cancer-associated pulmonary embolism and/or proximal/distal lower extremity deep vein thrombosis. Cause-specific Cox proportional hazards regression was used, adjusting for pertinent clinical covariates. Of 11 695 evaluable individuals, 72% had metastatic disease at time of analysis. Tumor-specific mutations in KRAS (hazard ratio [HR], 1.34; 95% confidence interval (CI), 1.09-1.64; adjusted P = .08), STK11 (HR, 2.12; 95% CI, 1.55-2.89; adjusted P < .001), KEAP1 (HR, 1.84; 95% CI, 1.21-2.79; adjusted P = .07), CTNNB1 (HR, 1.73; 95% CI, 1.15-2.60; adjusted P = .09), CDKN2B (HR, 1.45; 95% CI, 1.13-1.85; adjusted P = .07), and MET (HR, 1.83; 95% CI, 1.15-2.92; adjusted P = .09) were associated with a significantly increased risk of CAT independent of tumor type. Mutations in SETD2 were associated with a decreased risk of CAT (HR, 0.35; 95% CI, 0.16-0.79; adjusted P = .09). The presence of clonal hematopoiesis was not associated with an increased VTE rate. This is the first large-scale analysis to elucidate tumor-specific genomic events associated with CAT. Somatic tumor mutations of STK11, KRAS, CTNNB1, KEAP1, CDKN2B, and MET were associated with an increased risk of VTE in patients with solid tumors. Further analysis is needed to validate these findings and identify additional molecular signatures unique to individual tumor types.

Antithrombotic Therapy After Venous Interventions: AJR Expert Panel Narrative Review.

Interventions for thrombotic and nonthrombotic venous disorders have increased with technical advances and more trained venous specialists. Antithrombotic therapy is essential to clinical and procedural success; however, postprocedural therapeutic regimens exhibit significant heterogeneity due to limited prospective randomized data and incomplete mechanistic understanding of the critical factors driving long-term patency. Postinterventional antithrombotic therapy for thrombotic venous disorders should adhere to existing venous thromboembolism management guidelines, which include 3-6 months of therapeutic anticoagulation at minimum and consideration of extended therapy in patients with higher risk of thrombosis because of procedural or patient factors. The added benefit of antiplatelet agents in the acute and intermediate period is unknown, having shown improved long-term stent patency in some retrospective studies. Dual- and/or triple-agent therapy should be limited based on individual risks of thrombosis and bleeding. The treatment of nonthrombotic disorders is more heterogeneous, though patients with limited flow, extensive stent material, or underlying prothrombotic states such as malignancy or chronic inflammation may benefit from single-agent or multiagent antithrombotic therapy. However, the agent, dose, and duration of therapy remain indeterminate. Future prospective studies are warranted to improve patient risk stratification and standardize postprocedural anti-thrombotic therapy in patients receiving venous interventions.

Determinants of fatal bleeding during induction therapy for acute promyelocytic leukemia in the ATRA era.

Acute promyelocytic leukemia (APL) is commonly complicated by a complex coagulopathy. Uncertainty remains as to which markers of bleeding risk are independent predictors. Drawing from 5 large clinical trials that included all-trans retinoic acid (ATRA) as part of induction, we assessed known determinants of bleeding at baseline and evaluated them as potential predictors of hemorrhagic death (HD) in the first 30 days of treatment. The studies included were ALLG APML3 (single arm of ATRA + idarubicin ± prednisone), ALLG APML4 (single arm of ATRA + idarubicin + arsenic trioxide + prednisone), CALGB C9710 (single arm of ATRA + cytarabine + daunorubicin), Eastern Cooperative Oncology Group-American College of Radiology Imaging Network (ECOG-ACRIN) E2491 (intergroup I0129, consisting of daunorubicin + cytarabine vs ATRA), and SWOG S0521 (single-arm induction of ATRA + cytarabine + daunorubicin). A total of 1009 patients were included in the original trials, of which 995 had sufficient data to be included in our multivariate analysis. In this final cohort, there were 37 HD cases during the first 30 days following induction, for an estimated cumulative incidence of 3.7% (95% confidence interval [CI], 2.6% to 5.0%). Using multivariate Cox proportional hazards regression, the hazard ratio of HD in the first 30 days was 2.17 (95% CI, 0.84-5.62) for an ECOG performance status of 3-4 vs 0-2 and 5.20 (95% CI, 2.70-10.02) for a white blood cell count of ≥20 000/µL vs <20 000/µL. In this large cohort of APL patients, high white blood cell count emerged as an independent predictor of early HD.

Bleeding Disorders Associated with Cancer.

Cancer can be associated with several distinct coagulation defects which can lead to bleeding complications. The primary hyperfibrinolytic syndrome associated with acute promyelocytic leukemia has been well recognized and is one of the most severe bleeding disorders. Acquired hemophilia, while rare and not only seen in the oncology setting, can be triggered by a malignancy and must be promptly recognized in order to prevent catastrophic hemorrhage. Other, less serious coagulopathic states have been linked to cancer, including acquired von Willebrand disease. Finally, several anti-neoplastic drugs can alter hemostasis and increase the risk of bleeding. A good understanding of this field can help mitigate the risk of complications in the cancer patient.

Enoxaparin dose reduction for thrombocytopenia in patients with cancer: a quality assessment study.

The development of thrombocytopenia in the setting of therapeutic anticoagulation for venous thromboembolic disease (VTE) is common in cancer patients, but guidelines for management are based on limited past data and have not been validated. In 2011, Memorial Sloan Kettering Cancer Center (MSKCC) implemented the following guidelines in this setting: administer full dose enoxaparin for a platelet count > 50,000/mcL, half-dose enoxaparin for a platelet count of 25,000-50,000/mcL, and hold anticoagulation for a platelet count < 25,000/mcL. We now report validation of safety and efficacy of these guidelines. As a Quality Assessment Initiative, we evaluated our guidelines for adult cancer patients at MSKCC who were on therapeutic-dose enoxaparin for VTE during the years 2011 through 2013 and experienced at least one 7-day period of thrombocytopenia (platelet count ≤ 50,000/mcL). We assessed adherence to the enoxaparin dose modification guidelines, major bleeding, clinically relevant non-major bleeding, recurrent VTE, and mortality during the thrombocytopenic episodes. We identified 99 patients with 140 episodes of thrombocytopenia of 7 or more days. The median duration of these thrombocytopenic episodes was 12 days. The enoxaparin dose was modified in 133 of the 140 episodes (95%), reflecting satisfactory adherence to our institutional guidelines. There were no recurrent VTE events or major bleeding episodes when the anticoagulant dose was reduced or held. In this cohort, there was only one major bleeding episode, a trauma-associated retroperitoneal hemorrhage that occurred on the third day of a thrombocytopenic episode, prior to enoxaparin dose modification. There were 13 clinically relevant non-major bleeding episodes. Lastly, 10 patients died of cancer-related causes during an episode of thrombocytopenia. This Quality Assessment Initiative supports the safety and efficacy of our guidelines for therapeutic enoxaparin dose modification.

Outcomes after inferior vena cava filter placement in cancer patients diagnosed with pulmonary embolism: risk for recurrent venous thromboembolism.

Venous thromboembolism (VTE) is a common complication in cancer patients and anticoagulation (AC) remains the standard of care for treatment. Inferior vena cava (IVC) filters may also used to reduce the risk of pulmonary embolism, either alone or in addition to AC. Although widely used, data are limited on the safety and efficacy of IVC filters in cancer patients. We performed a retrospective review of outcomes after IVC filter insertion in a database of 1270 consecutive patients with cancer-associated pulmonary embolism (PE) at our institution between 2008 and 2009. Outcomes measured included rate of all recurrent VTE, recurrent PE, and overall survival within 12 months. 317 (25%) of the 1270 patients with PE had IVC filters placed within 30 days of the index PE event or prior to the index PE in the setting of prior DVT. Patients with IVC filters had markedly lower overall survival (7.3 months) than the non-IVC filter patients (13.2 months). Filter patients also had a lower rate of AC use at time of initial PE. There was a trend towards higher recurrent VTE in patients with IVC filters (11.9%) compared to non-filter patients (7.7%), but this was not significant (p = 0.086). The risk of recurrent PE was similar between the IVC filter cohort (3.5%) and non-filter group (3.5%, p = 0.99). Cancer patients receiving IVC filters had a similar risk of recurrent PE, but a trend towards more overall recurrent VTE. The filter patients had poorer overall survival, which may reflect a poorer cancer prognosis, and had greater contraindication to AC; therefore these patients likely had a higher inherent risk for recurrent VTE. A prospective study would be helpful for further clarification on the partial reduction in the recurrent PE risk by IVC filter placement in cancer patients.

Safe and effective use of rivaroxaban for treatment of cancer-associated venous thromboembolic disease: a prospective cohort study.

Low-molecular weight heparin (LMWH) has been the standard of care for treatment of venous thromboembolism (VTE) in patients with cancer. Rivaroxaban was approved in 2012 for the treatment of pulmonary embolism (PE) and deep vein thrombosis (DVT), but no prior studies have been reported specifically evaluating the efficacy and safety of rivaroxaban for cancer-associated thrombosis (CAT). Under a Quality Assessment Initiative (QAI), we established a Clinical Pathway to guide rivaroxaban use for CAT and now report a validation analysis of our first 200 patients. A 200 patient cohort with CAT (PE or symptomatic, proximal DVT), whose full course of anticoagulation was with rivaroxaban, were accrued. In competing risk analysis, primary endpoints at 6 months included new or recurrent PE or symptomatic proximal lower extremity DVT, major bleeding, clinically-relevant non-major bleeding leading to discontinuation of rivaroxaban, or death. In competing risk analysis, the 6 months cumulative incidence of new or recurrent VTE was 4.4 % (95 % CI = 1.4-7.4 %), major bleeding was 2.2 % (95 % CI = 0-4.2 %) and all-cause mortality 17.6 % (95 % CI = 11.7-23.0 %). In this cohort of 200 patients with active cancer and CAT the rates of new or recurrent VTE and major bleeding were comparable to the cancer subgroup analysis from the EINSTEIN studies. The results of our Clinical Pathway provide guidance on Rivaroxaban use for treatment of CAT, and suggest that safety and efficacy is preserved, compared with past-published experience with LMWH.

What's new in the pathogenesis of the coagulopathy in acute promyelocytic leukemia?

PURPOSE OF REVIEW: Acute promyelocytic leukemia (APL) is associated with a complex coagulopathy. In spite of substantial recent improvements in treatment regimens, hemorrhagic death remains the main cause of induction failure. In this review, we delineate recent understanding of the pathophysiology and management of the hemorrhagic diathesis of APL. RECENT FINDINGS: Laboratory and clinical data suggest that the malignant leukocytes mediate the hemorrhagic diathesis associated with APL through multiple mechanisms which lead to a combination of consumptive coagulopathy and primary hyperfibrinolysis. Exposure of tissue factor and Annexin II by the leukemic blasts is the main determinants of these processes. Promyelocyte-derived microparticles have recently been implicated in the coagulopathy as well. Total white cell count and platelet count have emerged as good general predictors of hemorrhagic death, along with the different routine hemostatic parameters. Prompt treatment with all-trans retinoic acid, with or without arsenic trioxide, is the most important step in preventing bleeding complications. Repletion of coagulation factors and platelets with blood products remains the mainstay of supportive treatment, whereas the role of recombinant soluble thrombomodulin is currently being investigated. SUMMARY: The coagulopathy of APL is multifactorial, with both disseminated intravascular coagulation and primary hyperfibrinolysis mediated largely by the malignant leukocytes.

Ovarian vein thrombosis after debulking surgery for ovarian cancer: epidemiology and clinical significance.

OBJECTIVE: Ovarian vein thrombosis is associated with pregnancy and pelvic surgery. Postpartum ovarian vein thrombosis is associated with infection and a high morbidity rate and is treated with anticoagulant and intravenous antibiotic therapy. The natural history of such thrombotic events after debulking surgery for ovarian cancer has not been well described. Our objective was to characterize the presentation and outcomes for patients with this condition at our institution. STUDY DESIGN: We conducted a retrospective study of patients who underwent surgical debulking for ovarian cancer at Memorial Sloan Kettering Cancer Center between the years 2001 and 2010. Patients were included if contrast computed tomography scans of both the abdomen and pelvis were performed within 12 weeks before and 12 weeks after the surgery. The images were reviewed to assess for the presence and extent of a new postoperative ovarian vein thrombosis. When available, subsequent studies were assessed for thrombus progression. Medical records were reviewed to determine whether anticoagulation was used for treatment of the thrombotic episode and to record the occurrence of any new significant venous thromboembolic event in the next year. RESULTS: One hundred fifty-nine patients had satisfactory imaging. New ovarian vein thrombosis was a common complication of debulking surgery, as found in 41 of patients (25.8%). Only 5 women with ovarian vein thrombosis were started on anticoagulation, of which 2 individuals had an independent venous thromboembolic event as indication for treatment. Only 2 of the ovarian vein thromboses (4.9%) progressed to the inferior vena cava or left renal vein on subsequent scan. The estimated cumulative incidence of venous thromboembolism 1 year after the first postoperative scan was 17.1% for patients in the new ovarian vein thrombosis group vs 15.3% of individuals for the group without a postoperative ovarian vein thrombosis (P = .78). CONCLUSION: Ovarian vein thrombosis is commonly encountered after debulking surgery for ovarian cancer. Anticoagulation is usually not indicated, and clinically meaningful thrombus progression rarely occurs.

Indirect comparison of dabigatran, rivaroxaban, apixaban and edoxaban for the treatment of acute venous thromboembolism.

Four target-specific oral anticoagulants (TSOA's) have been compared to a vitamin K antagonist for the treatment of acute venous thromboembolism (VTE): dabigatran (D), rivaroxaban (R), apixaban (A) and edoxaban (E). We performed an indirect comparison of the TSOA's, based on the six phase III trials identified (RE-COVER I, RE-COVER II, EINSTEIN-DVT, EINSTEIN-PE, AMPLIFY and Hokusai-VTE). There was no statistically significant difference in risk of recurrent VTE or all-cause mortality between the TSOA's. For major bleeding, the RR of an event was 0.42 (95% CI 0.21-0.87, p = 0.02) for A versus D, compared with 0.57 (95% CI 0.29-1.15, p = 0.12) for A versus R, 0.37 (95% CI 0.19-0.73, p < 0.001) for A versus E, 0.74 (95% CI 0.42-1.30, p = 0.30) for R versus D, 0.64 (95% CI 0.38-1.08, p = 0.10) for R versus E and 1.15 (95% CI 0.66-2.00, p = 0.62) for E versus D. For the composite endpoint of major or clinically relevant nonmajor bleeding, the RR was 0.71 (95% CI 0.53-0.96, p = 0.02) for A versus D, 0.47 (95% CI 0.37-0.61, p < 0.001) for A versus R, 0.54 (95% CI 0.42-0.70, p < 0.001) for A versus E, 1.50 (95% CI 1.17-1.92, p = 0.001) for R versus D, 1.15 (95% CI 0.95-1.39, p = 0.16) for R versus E and 1.31 (95% CI 1.02-1.68, p = 0.04) for E versus D. Overall, apixaban appears to be associated with a lower risk of bleeding than the other TSOA's. This analysis may be helpful to the clinician in trying to balance risk versus benefit in selecting a new anticoagulant. A dedicated randomized trial directly comparing the new agents would be required to confirm these results.

Use of romiplostim for antineoplastic therapy-induced thrombocytopenia in gynecologic and breast cancers.

Objective: Romiplostim is used to treat chemotherapy-induced thrombocytopenia in a variety of tumor types; however, few studies have examined its use in breast and gynecologic cancers. We evaluated platelet response and durability of response to romiplostim in patients with gynecologic or breast cancer complicated by chemotherapy-induced thrombocytopenia. Methods: We retrospectively identified 33 patients with gynecologic or breast cancer who received romiplostim between 07/1/2021-07/31/2022 at an academic cancer center. Results: Thirty-three patients met inclusion criteria; 26 (79 %) had breast cancer, 4 (12 %) had ovarian cancer, and 3 (9 %) had endometrial cancer. Twenty patients (61 %) experienced treatment delays and 12 (36 %) required dose reductions prior to starting romiplostim for chemotherapy-induced thrombocytopenia, with some patients experiencing both. Eleven patients (33 %) did not undergo a dose reduction or delay prior to initiation of romiplostim. Median platelet count prior to romiplostim therapy was 53 k/mcL (range, 40.5-78.8). Median platelet count within 3 weeks following initiation of romiplostim was 147 k/mcL (range, 31-562). Twenty-one patients (64 %) achieved platelet correction within 3 weeks, of whom 10 (48 %) resumed anticancer therapy and maintained platelet levels above 100 k/mcL at 8 weeks. Twelve patients did not achieve platelet correction within 3 weeks of romiplostim initiation; 4 (33 %) required a treatment change secondary to persistent thrombocytopenia, 3 (25 %) required a treatment dose reduction, 3 (25 %) were deemed too ill to continue therapy, and 2 (17 %) required a treatment delay. Conclusions: Romiplostim facilitated the resumption of anticancer therapy in 64 % of patients with gynecologic or breast cancer complicated by chemotherapy-induced thrombocytopenia.

Machine learning natural language processing for identifying venous thromboembolism: systematic review and meta-analysis.

ABSTRACT: Venous thromboembolism (VTE) is a leading cause of preventable in-hospital mortality. Monitoring VTE cases is limited by the challenges of manual medical record review and diagnosis code interpretation. Natural language processing (NLP) can automate the process. Rule-based NLP methods are effective but time consuming. Machine learning (ML)-NLP methods present a promising solution. We conducted a systematic review and meta-analysis of studies published before May 2023 that use ML-NLP to identify VTE diagnoses in the electronic health records. Four reviewers screened all manuscripts, excluding studies that only used a rule-based method. A meta-analysis evaluated the pooled performance of each study's best performing model that evaluated for pulmonary embolism and/or deep vein thrombosis. Pooled sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) with confidence interval (CI) were calculated by DerSimonian and Laird method using a random-effects model. Study quality was assessed using an adapted TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) tool. Thirteen studies were included in the systematic review and 8 had data available for meta-analysis. Pooled sensitivity was 0.931 (95% CI, 0.881-0.962), specificity 0.984 (95% CI, 0.967-0.992), PPV 0.910 (95% CI, 0.865-0.941) and NPV 0.985 (95% CI, 0.977-0.990). All studies met at least 13 of the 21 NLP-modified TRIPOD items, demonstrating fair quality. The highest performing models used vectorization rather than bag-of-words and deep-learning techniques such as convolutional neural networks. There was significant heterogeneity in the studies, and only 4 validated their model on an external data set. Further standardization of ML studies can help progress this novel technology toward real-world implementation.

High-risk and silent clonal hematopoietic genotypes in patients with nonhematologic cancer.

ABSTRACT: Clonal hematopoiesis (CH) identified by somatic gene variants with variant allele fraction (VAF) ≥ 2% is associated with an increased risk of hematologic malignancy. However, CH defined by a broader set of genotypes and lower VAFs is ubiquitous in older individuals. To improve our understanding of the relationship between CH genotype and risk of hematologic malignancy, we analyzed data from 42 714 patients who underwent blood sequencing as a normal comparator for nonhematologic tumor testing using a large cancer-related gene panel. We cataloged hematologic malignancies in this cohort using natural language processing and manual curation of medical records. We found that some CH genotypes including JAK2, RUNX1, and XPO1 variants were associated with high hematologic malignancy risk. Chronic disease was predicted better than acute disease suggesting the influence of length bias. To better understand the implications of hematopoietic clonality independent of mutational function, we evaluated a set of silent synonymous and noncoding mutations. We found that silent CH, particularly when multiple variants were present or VAF was high, was associated with increased risk of hematologic malignancy. We tracked expansion of CH mutations in 26 hematologic malignancies sequenced with the same platform. JAK2 and TP53 VAF consistently expanded at disease onset, whereas DNMT3A and silent CH VAFs mostly decreased. These data inform the clinical and biological interpretation of CH in the context of nonhematologic cancer.

Prediction and prevention of thromboembolic events with enoxaparin in cancer patients with elevated tissue factor-bearing microparticles: a randomized-controlled phase II trial (the Microtec study).

Elevated levels of circulating tissue factor-bearing microparticles (TFMP) have been associated with an increased risk of developing venous thromboembolism (VTE) in cancer patients. We performed a randomized phase II study to evaluate the cumulative incidence of VTE in advanced cancer patients with lower levels of TFMP not receiving thromboprophylaxis and those with higher levels of circulating TFMP randomized to enoxaparin or observation. The cumulative incidence of VTE at 2 months in the higher TFMP group randomized to enoxaparin (N = 23) was 5·6% while the higher TFMP group observation arm (N = 11) was 27·3% (Gray test P = 0·06). The cumulative incidence of VTE in the low TFMP was 7·2% (N = 32). No major haemorrhages were observed in the enoxaparin arm. The median survival for patients with higher levels of TFMP followed by observation was 11·8 months compared with 17·8 months on enoxaparin (P = 0·58). In a prospective randomized trial, increased numbers of circulating TFMP detected by impedance flow cytometry identified cancer patients with a high incidence of VTE. Enoxaparin demonstrated a clear trend towards reducing the rate of VTE in patients with elevated levels of TFMP, with an overall rate of VTE similar in magnitude to the lower TFMP group.

Target-specific oral anticoagulants in atrial fibrillation: results of phase III trials and comments on sub-analyses.

Dabigatran, rivaroxaban, apixaban and edoxaban administered in fixed doses and without routine laboratory monitoring have been compared to warfarin for the prevention of stoke in patients with nonvalvular atrial fibrillation (AF). Phase III data is currently available for dabigatran, rivaroxaban and apixaban. It is derived from three randomized controlled trials: RE-LY, ROCKET AF and ARISTOTLE. Dabigatran and apixaban appeared to be superior to warfarin for the primary endpoint of stroke or systemic embolism, while rivaroxaban was deemed non-inferior. The risk of major bleeding was modestly decreased overall with the new agents, while the risk of intracranial hemorrhage was substantially reduced. The results of ENGAGE AF-TIMI 48 comparing edoxaban to warfarin are still pending. Large, well designed clinical trials support the use of three new target-specific oral anticoagulants for the prevention of stroke in individuals with nonvalvular AF.

Tumor Genomic Profile Is Associated With Arterial Thromboembolism Risk in Patients With Solid Cancer.

Background: Patients with cancer have an increased risk for arterial thromboembolism (ATE). Scant data exist about the impact of cancer-specific genomic alterations on the risk for ATE. Objectives: The aim of this study was to determine whether individual solid tumor somatic genomic alterations influence the incidence of ATE. Methods: A retrospective cohort study was conducted using tumor genetic alteration data from adults with solid cancers who underwent Memorial Sloan Kettering-Integrated Mutation Profiling of Actionable Cancer Targets testing between 2014 and 2016. The primary outcome, ATE, was defined as myocardial infarction, coronary revascularization, ischemic stroke, peripheral arterial occlusion, or limb revascularization and identified through systematic electronic medical record assessments. Patients were followed from date of tissue-matched blood control accession to first ATE event or death, for up to 1 year. Cause-specific Cox proportional hazards regression was used to determine HRs of ATE for individual genes adjusted for pertinent clinical covariates. Results: Among 11,871 eligible patients, 74% had metastatic disease, and there were 160 ATE events. A significantly increased risk for ATE independent of tumor type was noted for the KRAS oncogene (HR: 1.98; 95% CI: 1.34-2.94; multiplicity-adjusted P = 0.015) and the STK11 tumor suppressor gene (HR: 2.51; 95% CI: 1.44-4.38; multiplicity-adjusted P = 0.015). Conclusions: In a large genomic tumor-profiling registry of patients with solid cancers, alterations in KRAS and STK11 were associated with an increased risk for ATE independent of cancer type. Further investigation is needed to elucidate the mechanism by which these mutations contribute to ATE in this high-risk population.

Application of Machine Learning to the Prediction of Cancer-Associated Venous Thromboembolism.

Venous thromboembolism (VTE) is a common and impactful complication of cancer. Several clinical prediction rules have been devised to estimate the risk of a thrombotic event in this patient population, however they are associated with limitations. We aimed to develop a predictive model of cancer-associated VTE using machine learning as a means to better integrate all available data, improve prediction accuracy and allow applicability regardless of timing for systemic therapy administration. A retrospective cohort was used to fit and validate the models, consisting of adult patients who had next generation sequencing performed on their solid tumor for the years 2014 to 2019. A deep learning survival model limited to demographic, cancer-specific, laboratory and pharmacological predictors was selected based on results from training data for 23,800 individuals and was evaluated on an internal validation set including 5,951 individuals, yielding a time-dependent concordance index of 0.72 (95% CI = 0.70-0.74) for the first 6 months of observation. Adapted models also performed well overall compared to the Khorana Score (KS) in two external cohorts of individuals starting systemic therapy; in an external validation set of 1,250 patients, the C-index was 0.71 (95% CI = 0.65-0.77) for the deep learning model vs 0.66 (95% CI = 0.59-0.72) for the KS and in a smaller external cohort of 358 patients the C-index was 0.59 (95% CI = 0.50-0.69) for the deep learning model vs 0.56 (95% CI = 0.48-0.64) for the KS. The proportions of patients accurately reclassified by the deep learning model were 25% and 26% respectively. In this large cohort of patients with a broad range of solid malignancies and at different phases of systemic therapy, the use of deep learning resulted in improved accuracy for VTE incidence predictions. Additional studies are needed to further assess the validity of this model.

Cancer genetic alterations and risk of venous thromboembolism.

Cancer has long been known to incur an increased risk of venous thromboembolism (VTE). Multiple risk factors for cancer-associated thrombosis (CAT) have been identified, and several pathophysiological mechanisms elucidated. However, until recently there was scant data available about the influence of cancer-specific somatic genetic alterations on the risk of venous thromboembolism. In the last few years, several gene loci were found to modulate the risk of CAT, usually causing an increase in risk but sometimes found to have a protective effect. Notably, cancer-specific somatic genetic alterations in KRAS, IDH1, ALK and ROS1 have been found to alter the risk of CAT by independent groups. Work in this field is limited by the high-dimensionality and often sparse nature of genomic datasets. Also, early data suggest that for certain genes the effect on VTE risk can be tumor type-specific, which suggests that predictive models must factor such interactions in order to optimally leverage genetic information. Notably, individual gene effects appear to be often small and no one gene explains most of the variability of CAT risk. Ultimately, improved knowledge of the genetic determinants of CAT will help ameliorate risk stratification for this complication and hopefully provide mechanistic insights. Better risk stratification could lead to enhanced pharmacological VTE prophylaxis, while advancements in the understanding of the biology of CAT could conceivably lead to non-anticoagulant targeted therapies for thrombosis.