A deep learning model predicts the presence of diverse cancer types using circulating tumor cells.

Circulating tumor cells (CTCs) are cancer cells that detach from the primary tumor and intravasate into the bloodstream. Thus, non-invasive liquid biopsies are being used to analyze CTC-expressed genes to identify potential cancer biomarkers. In this regard, several studies have used gene expression changes in blood to predict the presence of CTC and, consequently, cancer. However, the CTC mRNA data has not been used to develop a generic approach that indicates the presence of multiple cancer types. In this study, we developed such a generic approach. Briefly, we designed two computational workflows, one using the raw mRNA data and deep learning (DL) and the other exploiting five hub gene ranking algorithms (Degree, Maximum Neighborhood Component, Betweenness Centrality, Closeness Centrality, and Stress Centrality) with machine learning (ML). Both workflows aim to determine the top genes that best distinguish cancer types based on the CTC mRNA data. We demonstrate that our automated, robust DL framework (DNNraw) more accurately indicates the presence of multiple cancer types using the CTC gene expression data than multiple ML approaches. The DL approach achieved average precision of 0.9652, recall of 0.9640, f1-score of 0.9638 and overall accuracy of 0.9640. Furthermore, since we designed multiple approaches, we also provide a bioinformatics analysis of the gene commonly identified as top-ranked by the different methods. To our knowledge, this is the first study wherein a generic approach has been developed to predict the presence of multiple cancer types using raw CTC mRNA data, as opposed to other models that require a feature selection step.

Non-Invasive Solutions to Identify Distinctions Between Healthy and Mild Cognitive Impairments Participants.

Mild cognitive impairment (MCI) is a condition characterized by impairment in a single cognitive domain or mild deficit in several cognitive domains. MCI patients are at increased risk of progression to dementia with almost 50% of MCI patients developing dementia within five years. Early detection can play an important role in early intervention, prevention, and appropriate treatments. In this study, we examined heart rate variability (HRV) as a novel physiological biomarker for identifying individuals at higher risk of MCI. We investigated if measuring HRV using non-invasive sensors might offer reliable, non-invasive techniques to distinguish MCI patients from healthy controls. Twenty-one MCI patients were recruited to examine this possibility. HRV was assessed using CorSense wearable device. HRV indices were analyzed and compared in rest between MCI and healthy controls. The significance of difference of numerical data between two groups was assessed using parametric unpaired t-test or non-parametric Wilcoxon rank sum test based on the fulfilment of unpaired t-test assumptions. Multiple linear regression models were performed to assess the association between individual HRV parameter with the cognitive status adjusting for gender and age. Time-domain parameters i.e., the standard deviation of NN intervals (SDNN), and the root mean square of successive differences between normal heartbeats (RMSSD) were significantly lower in MCI patients compared with healthy controls. Prediction accuracy for the logistic regression using 10-fold cross-validation was 76.5%, Specificity was 0.8571, while sensitivity was 0.8095. Our study demonstrated that healthy participants have higher HRV indices compared to older adults with MCI using non-invasive biosensors technologies. Our results are of clinical importance in terms of showing the possibility that MCI of older people can be predicted using only HRV PPG-based data.