Machine Learning as a Diagnostic and Prognostic Tool for Predicting Thrombosis in Cancer Patients: A Systematic Review.

Khorana score (KS) is an established risk assessment model for predicting cancer-associated thrombosis. However, it ignores several risk factors and has poor predictability in some cancer types. Machine learning (ML) is a novel technique used for the diagnosis and prognosis of several diseases, including cancer-associated thrombosis, when trained on specific diagnostic modalities. Consolidating the literature on the use of ML for the prediction of cancer-associated thrombosis is necessary to understand its diagnostic and prognostic abilities relative to KS. This systematic review aims to evaluate the current use and performance of ML algorithms to predict thrombosis in cancer patients. This study was conducted per Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. Databases Medline, EMBASE, Cochrane, and ClinicalTrials.gov, were searched from inception to September 15, 2023, for studies evaluating the use of ML models for the prediction of thrombosis in cancer patients. Search terms "machine learning," "artificial intelligence," "thrombosis," and "cancer" were used. Studies that examined adult cancer patients using any ML model were included. Two independent reviewers conducted study selection and data extraction. Three hundred citations were screened, of which 29 studies underwent a full-text review, and ultimately, 8 studies with 22,893 patients were included. Sample sizes ranged from 348 to 16,407 patients. Thrombosis was characterized as venous thromboembolism (n = 6) or peripherally inserted central catheter thrombosis (n = 2). The types of cancer included breast, gastric, colorectal, bladder, lung, esophageal, pancreatic, biliary, prostate, ovarian, genitourinary, head-neck, and sarcoma. All studies reported outcomes on the ML's predictive capacity. The extreme gradient boosting appears to be the best-performing model, and several models outperform KS in their respective datasets.

Incidence and risk factors of venous and arterial thromboembolic events among patients with ovarian cancer- data from a large Canadian database.

OBJECTIVES: To determine the incidence of thromboembolic events (TEEs) in ovarian cancer patients and to identify risk factors that are significantly associated with the development of venous thromboembolism (VTE), arterial thromboembolism (ATE), or overall TEEs in this population. METHODS: This is a retrospective cohort study of 4491 patients with epithelial ovarian cancer identified in the British Columbia cancer registry between 1996 and 2017. The presence of TEEs and risk factors were identified in administrative health records from fee-for-service provider visits and hospital data using ICD-9-CM and ICD-10-CM billing codes. Statistical analysis was performed using Chi-squared test and Fischer's exact test. RESULTS: Of 4491 patients with epithelial ovarian cancer included in this study, 1.74% experienced ATE and (9.44%) experienced VTE. There was a significant association found between the occurrence of TEEs and all-cause mortality. Sepsis was significantly associated with both venous and arterial thromboembolism. The top three risk factors for arterial thromboembolism included peripheral vascular disease (PVD), open wound, and aneurysm. CONCLUSIONS: Risk factors predictive of thrombosis in ovarian cancer patients are not consistent between ATE and VTE, thus thrombotic events should not be combined for analysis. Differential thrombosis risk assessment is needed to improve prevention strategies and guide thromboprophylaxis for these patients.

Assessing hypercoagulability and VTE risk using thromboelastography and Khorana score in women with cancers receiving chemotherapy.

Venous thromboembolism (VTE) is a common occurrence in cancer and chemotherapy increases thrombosis risk. Current risk assessment models such as the Khorana score (KS) and its modifications have limitations in female cancers. We assessed the coagulation profile of a group of women cancer patients under chemotherapy using thromboelastography (TEG) to determine if this can inform VTE risk assessment. Cancer patients who planned to receive chemotherapy were recruited. Baseline demographics, cancer data, BMI, Khorana Score (KS), and VTE risk factors were recorded and patients were followed for 6 months, for any thrombotic events. A total of 36 patients aged 35-85 (18 breast, 11 endometrial, 7 ovarian cancer) were evaluated. Hypercoagulability was detected in 63% of patients post-chemo cycle 1 and 75% post-cycle 2, with a significant increase in MA (maximum amplitude) and CI (clotting index), reduction in R (reaction time), K (clot kinetics), and LY30 (lysis time after 30 min of MA). KS showed only 7% of patients were high risk, 23% were low, and 70% were intermediate risk. MA and CI significantly increased in patients with intermediate and high-risk KS when compared with the low-risk patients and MA was positively correlated with KS. Five patients developed actual VTE; 100% of the tested ones were hypercoagulable either post-cycle 1 or 2 and 80% were KS intermediate risk. TEG is a hypercoagulability marker and TEG-MA and CI can potentially assess VTE risk. Larger studies are needed to assess the utility of TEG as an adjuvant to KS to better predict VTE in specific female cancers.

Management of Venous and Arterial Thrombosis.

A thrombus is a hemostatic plug localized in a blood vessel [...].

Report of the ISTH registry on pregnancy and COVID-19-associated coagulopathy (COV-PREG-COAG).

Background: Concerns about COVID-19-associated coagulopathy (CAC) in pregnant individuals were raised in early pandemic. Methods: An ISTH-sponsored COVID-19 coagulopathy in pregnancy (COV-PREG-COAG) international registry was developed to describe incidence of coagulopathy, VTE, and anticoagulation in this group. Results: All pregnant patients with COVID-19 from participating centers were entered, providing 430 pregnancies for the first pandemic wave. Isolated abnormal coagulation parameters were seen in 20%; more often with moderate/severe disease than asymptomatic/mild disease (49% vs 15%; p < 0.0001). No one met the ISTH criteria for disseminated intravascular coagulopathy (DIC), though 5/21 (24%) met the pregnancy DIC score. There was no difference in antepartum hemorrhage (APH) with asymptomatic/mild disease versus moderate/severe disease (3.4% vs 7.7%; p = 0.135). More individuals with moderate/severe disease experienced postpartum hemorrhage (PPH) (22.4% vs 9.3%; p = 0.006). There were no arterial thrombotic events. Only one COVID-associated venous thromboembolism (VTE) was reported. Conclusions: Low rates of coagulopathy, bleeding, and thrombosis were observed among pregnant people in the first pandemic wave.

Hematologic characteristics and coagulopathy in pregnancy with COVID-19 succeeding the first wave: a multicenter retrospective cross-sectional study.

Background: Early reports have demonstrated an association of COVID-19 infection during pregnancy and postpartum period with coagulopathy and bleeding complications and indicated that pregnant people with COVID-19 are more likely to experience coagulopathy and venous thromboembolism. A recent report concerning such complications during the first wave of the pandemic was reassuring; however, no publications have evaluated these issues in the context of increased illness severity with the emergence of SARS-CoV-2 variants of concern. Objectives: We performed a retrospective, multinational cohort study in Canada, Romania, and the United Kingdom, aiming to provide a comprehensive analysis of the hematologic test characteristics of pregnancies affected by COVID-19 after the first wave of the pandemic. Results: Three-hundred-seventy patients were evaluated. Markers of inflammation and endothelial dysfunction were significantly elevated, in keeping with observations in the nonpregnant population. Reassuringly, despite more severe disease noted in succeeding waves of the pandemic, there was no significant evidence of COVID-19-associated coagulopathy, and overall, no association was demonstrated between isolated coagulation abnormalities and bleeding risk. Notably, fibrinogen below 2g/L was again linked with the risk of postpartum hemorrhage. Finally, venous thromboembolism risk was low but noted more frequently in those with severe illness despite thromboprophylaxis. Conclusion: Our findings add valuable insights into the nature of hematologic test characteristics, bleeding, and thrombotic complications for those affected with COVID-19 in pregnancy, reassuring readers of the low incidence of bleeding and thrombotic complications but inviting further debate as to the degree of thromboprophylaxis that may benefit the subgroup with severe disease.

Standardization of definition and management for bleeding disorder of unknown cause: communication from the SSC of the ISTH.

In many patients referred with significant bleeding phenotype, laboratory testing fails to define any hemostatic abnormalities. Clinical practice with respect to diagnosis and management of this patient cohort poses significant clinical challenges. We recommend that bleeding history in these patients should be objectively assessed using the International Society on Thrombosis and Haemostasis (ISTH) bleeding assessment tool. Patients with increased bleeding assessment tool scores should progress to hemostasis laboratory testing. To diagnose bleeding disorder of unknown cause (BDUC), normal complete blood count, prothrombin time, activated partial thromboplastin time, thrombin time, von Willebrand factor antigen, von Willebrand factor function, coagulation factors VIII, IX, and XI, and platelet light transmission aggregometry should be the minimum laboratory assessment. In some laboratories, additional specialized hemostasis testing may be performed to identify other rare causes of bleeding. We recommend that patients with a significant bleeding phenotype but normal laboratory investigations should be registered with a diagnosis of BDUC in preference to other terminology. Global hemostatic tests and markers of fibrinolysis demonstrate variable abnormalities, and their clinical significance remains uncertain. Targeted genomic sequencing examining candidate hemostatic genes has a low diagnostic yield. Underlying BDUC should be considered in patients with heavy menstrual bleeding since delays in diagnosis often extend to many years and negatively impact quality of life. Treatment options for BDUC patients include tranexamic acid, desmopressin, and platelet transfusions.

Evaluation of Surface Properties of Two Remineralizing Agents after Modification by Chitosan Nano Particles: An In vitro Study.

Background: Calcium phosphate-based systems have been introduced as promising bio-mimetic materials due to their close resemblance to the enamel. Chitosan and its derivatives have been an emerging biomaterial due to their additional antibacterial effect and promising re-mineralizing ability. Aim: The aim of this study is to evaluate the effect of chitosan nanoparticles on the remineralization of the demineralized enamel surface after being added to nano-hydroxyapatite and nano-calcium phosphate materials. Setting and Design: This was in vitro study. Materials and Methods: Twenty specimens of extracted permanent molars were collected, and then immersed in demineralizing solution, then distributed into four groups according to the remineralizing material. Group 1: Treated with Nano-beta-tricalcium phosphate (Nß-TCP) gel, Group 2: Treated with Nß-TCP with chitosan gel, Group 3: Treated with Nanohydroxyapatite (NHA) gel, and Group 4: Treated with NHA with chitosan gel. The surface hardness of the teeth was measured at baseline, after demineralization, and after remineralization. The structural changes in each group were analyzed using the scanning electron microscopy. Statistical Analysis: Shapiro-Wilk's test, one-way ANOVA followed by Tukey's post hoc test was used. Results: In all groups, there was a significant difference in mean Vickers hardness number (VHN) at different intervals, with the highest value found after treatment (301.64-395.65) VHN, followed by the baseline (236.97-276.15) VHN, while the lowest value was detected after demineralization (121.23-124.39) VHN. It was also indicated that baseline treatment, the Hardness percentage change (%) of the nano NHA + Chitosan group showed the highest significant value (55.10%), while the Nß-TCP group exhibited the lowest significant value (9.56%). Conclusions: It can be concluded that NHA and NΒ-TCP modified by chitosan NPs as remineralizing agents of enamel surface hold promising results.