Development of a predictive model of venous thromboembolism recurrence in anticoagulated cancer patients using machine learning.

INTRODUCTION: Patients with cancer and venous thromboembolism (VTE) show a high risk of VTE recurrence during anticoagulant treatment. This study aimed to develop a predictive model to assess the risk of VTE recurrence within 6 months at the moment of primary VTE diagnosis in these patients. MATERIALS AND METHODS: Using the EHRead® technology, based on Natural Language Processing (NLP) and machine learning (ML), the unstructured data in electronic health records from 9 Spanish hospitals between 2014 and 2018 were extracted. Both clinically- and ML-driven feature selection were performed to identify predictors for VTE recurrence. Logistic regression (LR), decision tree (DT), and random forest (RF) algorithms were used to train different prediction models, which were subsequently validated in a hold-out data set. RESULTS: A total of 16,407 anticoagulated cancer patients with diagnosis of VTE were identified (54.4 % male and median age 70). Deep vein thrombosis, pulmonary embolism and metastases were observed in 67.2 %, 26.6 %, and 47.7 % of the patients, respectively. During the study follow-up, 11.4 % of the patients developed a recurrent VTE, being more frequent in patients with lung cancer. Feature selection and model training based on ML identified primary pulmonary embolism, deep vein thrombosis, metastasis, adenocarcinoma, hemoglobin and serum creatinine levels, platelet and leukocyte count, family history of VTE, and patients' age as predictors of VTE recurrence within 6 months of VTE diagnosis. The LR model had an AUC-ROC (95 % CI) of 0.66 (0.61, 0.70), the DT of 0.69 (0.65, 0.72) and the RF of 0.68 (0.63, 0.72). CONCLUSIONS: This is the first ML-based predictive model designed to predict 6-months VTE recurrence in patients with cancer. These results hold great potential to assist clinicians to identify the high-risk patients and improve their clinical management.

Cardiovascular Progerin Suppression and Lamin A Restoration Rescue Hutchinson-Gilford Progeria Syndrome.

BACKGROUND: Hutchinson-Gilford progeria syndrome (HGPS) is a rare disorder characterized by premature aging and death mainly because of myocardial infarction, stroke, or heart failure. The disease is provoked by progerin, a variant of lamin A expressed in most differentiated cells. Patients look healthy at birth, and symptoms typically emerge in the first or second year of life. Assessing the reversibility of progerin-induced damage and the relative contribution of specific cell types is critical to determining the potential benefits of late treatment and to developing new therapies. METHODS: We used CRISPR-Cas9 technology to generate LmnaHGPSrev/HGPSrev (HGPSrev) mice engineered to ubiquitously express progerin while lacking lamin A and allowing progerin suppression and lamin A restoration in a time- and cell type-specific manner on Cre recombinase activation. We characterized the phenotype of HGPSrev mice and crossed them with Cre transgenic lines to assess the effects of suppressing progerin and restoring lamin A ubiquitously at different disease stages as well as specifically in vascular smooth muscle cells and cardiomyocytes. RESULTS: Like patients with HGPS, HGPSrev mice appear healthy at birth and progressively develop HGPS symptoms, including failure to thrive, lipodystrophy, vascular smooth muscle cell loss, vascular fibrosis, electrocardiographic anomalies, and precocious death (median lifespan of 15 months versus 26 months in wild-type controls, P<0.0001). Ubiquitous progerin suppression and lamin A restoration significantly extended lifespan when induced in 6-month-old mildly symptomatic mice and even in severely ill animals aged 13 months, although the benefit was much more pronounced on early intervention (84.5% lifespan extension in mildly symptomatic mice, P<0.0001, and 6.7% in severely ill mice, P<0.01). It is remarkable that major vascular alterations were prevented and lifespan normalized in HGPSrev mice when progerin suppression and lamin A restoration were restricted to vascular smooth muscle cells and cardiomyocytes. CONCLUSIONS: HGPSrev mice constitute a new experimental model for advancing knowledge of HGPS. Our findings suggest that it is never too late to treat HGPS, although benefit is much more pronounced when progerin is targeted in mice with mild symptoms. Despite the broad expression pattern of progerin and its deleterious effects in many organs, restricting its suppression to vascular smooth muscle cells and cardiomyocytes is sufficient to prevent vascular disease and normalize lifespan.

Prelamin A causes progeria through cell-extrinsic mechanisms and prevents cancer invasion.

Defining the relationship between ageing and cancer is a crucial but challenging task. Mice deficient in Zmpste24, a metalloproteinase mutated in human progeria and involved in nuclear prelamin A maturation, recapitulate multiple features of ageing. However, their short lifespan and serious cell-intrinsic and cell-extrinsic alterations restrict the application and interpretation of carcinogenesis protocols. Here we present Zmpste24 mosaic mice that lack these limitations. Zmpste24 mosaic mice develop normally and keep similar proportions of Zmpste24-deficient (prelamin A-accumulating) and Zmpste24-proficient (mature lamin A-containing) cells throughout life, revealing that cell-extrinsic mechanisms are preeminent for progeria development. Moreover, prelamin A accumulation does not impair tumour initiation and growth, but it decreases the incidence of infiltrating oral carcinomas. Accordingly, silencing of ZMPSTE24 reduces human cancer cell invasiveness. Our results support the potential of cell-based and systemic therapies for progeria and highlight ZMPSTE24 as a new anticancer target.