Purpose: Poly-medicated patients, especially those over 65, have increased. Multiple drug use and inappropriate prescribing increase drug-drug interactions, adverse drug reactions, morbidity, and mortality. This issue was addressed with several CDSS alerts. Health professionals have not followed these systems due to their poor alert quality and incomplete databases. Methods: Recent research shows a growing interest in using Text Mining via NLP to extract drug-drug interactions from unstructured data sources to support clinical prescribing decisions. NLP text mining and machine learning classifier training for drug relation extraction were used in this process. Results: In this context, the proposed solution allows to develop an extraction system for drug-drug interactions from unstructured data sources. The system produces structured information, which can be inserted into a database that contains information acquired from three different data sources. Conclusion: The architecture outlined for the drug-drug interaction extraction system is capable of receiving unstructured text, identifying drug entities sentence by sentence, and determining whether or not there are interactions between them.
Online Social Networks (OSNs) have grown exponentially in the last few years due to their applications in real life like marketing, recommendation systems, and social awareness campaigns. One of the most important research areas in this field is Influence Maximization (IM). IM pertains to finding methods to maximize the spread of information (or influence) across a social network. Previous works in IM have focused on using a pre-defined edge propagation probability or using the Hurst exponent (H) to identify which nodes to be activated. This is calculated on the basis of self-similarity in the time series depicting a user’s (node) past temporal interaction behaviour. In this work, we propose a Time Series Characteristic based Hurst-based Diffusion Model (TSC-HDM). The model calculates Hurst Exponent (H) based on the stationary or non-stationary characteristic of the time series. Furthermore, our model selects a handful of seed nodes and activates every seed node’s inactive successor only if H>0.5 . The process is continued until the activation of successor nodes is not possible. The proposed model was tested on 4 datasets - UC Irvine messages, Email EU-Core, Math Overflow 3, and Linux Kernel mailing list. We have also compared the results against 4 other Influence Maximisation models - Independent Cascade (IC), Weighted Cascade (WC), Trivalency (TV), and Hurst-based Influence Maximisation (HBIM). Our model achieves as much as 590% higher expected influence spread as compared to the other models. Moreover, our model attained 344% better average influence spread than other state-of-the-art models.
The prediction of news popularity is having substantial importance for the digital advertisement community in terms of selecting and engaging users. Traditional approaches are based on empirical data collected through surveys and applied statistical measures to prove a hypothesis. However, predicting news popularity based on statistical measures applied to past data is highly questionable. Therefore, in this paper, we predict news popularity using machine learning classification models and deep residual neural network models. Articles are usually made up of textual content and in many cases, images are also used. Although it is evident that the appropriate amount of textual data is required to extract features and create models, image data is also helpful in gaining useful information. In this paper, we present a novel multimodal online news popularity prediction model based on ensemble learning. This research work acts as a guide for extensive feature engineering, feature extraction, feature selection, and effective modeling to create a robust news popularity Prediction Model. Three kinds of features – meta features, text features, and image features are used to design an influential and robust model. The performance measure Root Mean Squared logarithmic error (RMSLE) is used to validate the outcome of the proposed model. Further, the most important features are sought out for the proposed model to verify the dependence of the model on text and image features.
Background: Due to the highly coarse chromatin, multi-dimensionality of the histo image, irregularity of shape and size, texture, and appearance, nuclei extraction is challenging. To address these complexities, a deep learning algorithm called a stacked sparse autoencoder had been considered a research factor in this paper. Methods and Material: This paper focuses on detecting the epithelial regions and extracting high-level features to segment the patches based on the nuclei and classify the biomarkers concerning the nuclei patches. We used 6,53,400 microscopic image patches of 363 patients sourced from the BreakHis database, of which 4,90,050 prominent image patches containing only nuclei were utilized for Biomarker classification (Basically eliminating the non-nuclei patches from 363 Whole slide Images (WSI)). The non-nuclei patches were eliminated due to imbalanced class distribution. Results: The classifier finally classifies if the nuclei detected based on the features are benign or malignant, or normal with an accuracy of 99.73%, using which the early prediction is performed by extracting and classifying the biomarkers HER2 and ER. The overall classification rate of classifying HER-2 and ER is 97.52%. Conclusion: The HER2 +ve was classified with intensity above 23%, and Total nuclei in the range 150-1000 are termed ER positive. Based on these 40 patients with HER2 +ve and 25 patients with ER +ve were detected out of 363 patients. From the observation, it is concluded that 25-40 patients are risked of breast cancer in the next 5 years due to the cell proliferation rate of 7000.