d-dimer is a predictor of clot resolution in patients with pulmonary thromboembolism: A retrospective cohort study

Predicting 7-day unplanned readmission in elderly patients with coronary heart disease using machine learning

Background

Short-term unplanned readmission is always neglected, especially for elderly patients with coronary heart disease (CHD). However, tools to predict unplanned readmission are lacking. This study aimed to establish the most effective predictive model for the unplanned 7-day readmission in elderly CHD patients using machine learning (ML) algorithms.

Methods

The detailed clinical data of elderly CHD patients were collected retrospectively. Five ML algorithms, including extreme gradient boosting (XGB), random forest, multilayer perceptron, categorical boosting, and logistic regression, were used to establish predictive models. We used the area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, the F1 value, the Brier score, the area under the precision-recall curve (AUPRC), and the calibration curve to evaluate the performance of ML models. The SHapley Additive exPlanations (SHAP) value was used to interpret the best model.

Results

The final study included 834 elderly CHD patients, whose average age was 73.5 ± 8.4 years, among whom 426 (51.08%) were men and 139 had 7-day unplanned readmissions. The XGB model had the best performance, exhibiting the highest AUC (0.9729), accuracy (0.9173), F1 value (0.9134), and AUPRC (0.9766). The Brier score of the XGB model was 0.08. The calibration curve of the XGB model showed good performance. The SHAP method showed that fracture, hypertension, length of stay, aspirin, and D-dimer were the most important indicators for the risk of 7-day unplanned readmissions. The top 10 variables were used to build a compact XGB, which also showed good predictive performance.

Conclusions

In this study, five ML algorithms were used to predict 7-day unplanned readmissions in elderly patients with CHD. The XGB model had the best predictive performance and potential clinical application perspective.

Disposable Voltammetric Immunosensor for D-Dimer Detection as Early Biomarker of Thromboembolic Disease and of COVID-19 Prognosis

In this work, we report on the development of a simple electrochemical immunosensor for the detection of D-dimer protein in human plasma samples. The immunosensor is built by a simple drop-casting procedure of chitosan nanoparticles (CSNPs) as biocompatible support, Protein A (PrA), to facilitate the proper orientation of the antibody sites to epitopes as a capture biomolecule, and the D-dimer antibody onto a carboxyl functionalized multi-walled carbon nanotubes screen printed electrode (MWCNTs-SPE). The CSNPs have been morphologically characterized by Scanning Electron Microscopy (SEM) and Dynamic Light Scattering (DLS) techniques. Successively, the electrochemical properties of the screen-printed working electrode after each modification step have been characterized by differential pulse voltammetry (DPV) and electrochemical impedance spectroscopy (EIS). The resulting MWCNTs-CSNPs-PrA-D-dimer Ab immunosensor displays an optimal and promising platform for antibody immobilization and specific D-dimer detection. DPV has been used to investigate the antigen/antibody interaction at different D-dimer concentrations. The proposed voltammetric immunosensor allowed a linear range from 2 to 500 μg L^-1 with a LOD of 0.6 μg L^-1 and a sensitivity of 1.3 μA L μg^-1 cm^-2. Good stability and a fast response time (5 s) have been reported. Lastly, the performance of the voltammetric immunosensor has been tested in human plasma samples, showing satisfactory results, thus attesting to the promising feasibility of the proposed platform for detecting D-dimer in physiological samples.

Detection of factor VIII and D-dimer biomarkers for venous thromboembolism diagnosis using electrochemistry immunosensor

Venous thromboembolism (VTE) is a serious clinical condition which early and accurate diagnosis may contribute to the reduction of associated morbidity and mortality. VTE occurs when a blood clot (thrombus) blocks the vein blood flow causing deep vein thrombosis (DVT) and, when it migrates to the lungs, it may clog the pulmonary arteries characterizing pulmonary embolism (PE). Analysis using fibrin degradation products or D-dimer and coagulation factor VIII may assist early diagnosis of VTE. Thus, two immunosensors were built using layer-by-layer (LbL) films technique, one containing the anti-D-dimer immobilized on polyethylene imine (PEI) and another the anti-FVIII on silk fibroin (SF). Immunosensor response, the antigen-antibody specific interaction, was investigated using cyclic voltammetry. When immunosensors, PEI/anti-D-dimer and SF/anti-FVIII, were exposed to antigens, D-dimer and Factor VIII, the voltammograms area and current were significantly increased with increasing specific antigen concentration. The specific interaction was confirmed with control experiments, electrodes containing only PEI or SF, that no significant changes in the voltammogram responses were observed and principal component analysis confirmed these results. The films formation and response were verified using scanning electronic microscopy (SEM). The developed immunosensor seems to be a promising and effective early complementary exam to assist in the VTE diagnosis, through the combined response of two biomarkers very sensible.