A Highly Accurate Adverse Drug Reactions (ADR) Detection from Medical Forum Comments Using Long Short-Term Memory Networks Anjali Basagodu Veeresh, Ravikumar Guralamata Krishnegowda, Shashikala Salekoppalu Venkataramu Frontiers in Biomedical Technologies, 2024 Purpose: Adverse Drug Reactions (ADR) classification is useful in modern medical diagnostics and related applications. ADR is an example of how medical information is frequently accessible on social media platforms for healthcare, where people can share their experiences with treatments on desktop computers and mobile devices. Many researchers are interested in gathering valuable medical data from social media for the ADR system training and classification process.Materials and Methods: This research explores the effects of three aspects on recognizing ADR mentions in social media for the medical field and proposes a deep neural network of Long Short-Term Memory (LSTM) neural networks to do so. The comments are collected from various social media platforms to implement the ADR system with proper training and testing processes. The texts from the dataset are initially preprocessed by using a data filtering and clustering process to remove the input data's redundant information to increase the training process's quality. Characteristic features, such as semantic features and text statistics, are extracted from the input text using the American Standard Code for Information Interchange (ASCII) array. Further, the features are converted and fed to LSTM networks for training and validation.Results and Conclusion: This work is evaluated using two datasets, CODEC, and ADR Corpus datasets are used to evaluate the performance of the proposed ADR technique via multiple angles. Via extensive experiments, this work achieved 99.79 accuracy, 98.37 sensitivity, 97.63 specificity, 99.72 precision, 98.39 recall, 97.62 F1-score for the CODEC dataset, 98.16 for accuracy, 99.19 for sensitivity, 98.49 for specificity, 99.49 for precision, 96.72 for recall, and 93.16 for F1-score for ADR corpus, respectively.
A Broad Review on Adverse Drug Reaction Detection using Social Media Data Anjali B.V, Ravi Kumar G.K Proceedings 2022 6th International Conference on Intelligent Computing and Control Systems Iciccs 2022, 2022 Adverse Drug Reactions (ADRs)" monitoring is characterized as one of the critical issues which have prior attention in medical research field. Purpose: Identification of ADR in hospitals provides an opportunity to discover severe ADRs ensuing in hospitalization. This paper introduces a comprehensive review based on social data representations for a better understanding of state-of-the-art ADR techniques. Within each category, several representative algorithms are selected for evaluation and comparison. In this study, various existing researches are reviewed and categorized based on the techniques used such as the machine learning, deep learning and other methods for ADR detection methods. : The performance of the review study is analyzed through performance metrics such as Accuracy and F1_score respectively. The deep learning with optimization-based ADR detection methods provides the best result which will be suggested to use in detection purpose to attain the best results.
Detection of Counterfeit News Using Machine Learning B Anjali, R Reshma, V Geetha Lekshmy 2019 2nd International Conference on Intelligent Computing Instrumentation and Control Technologies Icicict 2019, 2019 Counterfeit news or hoax news has been one of the prevalent problems that global society has faced. The differentiation between counterfeit news and real news has stayed one of the hardest problems to tackle. The proposed system comes up with models of different machine learning techniques for differentiating fake news and real news. This approach utilizes four different models of machine learning: Neural Network, Naive Bayesian, Support Vector Machine (SVM) and Long and Short-Term Memory(LSTM). The dataset that we are using is obtained from Kaggle(Fake News). We start with text normalization of the data(news) in the dataset. Text normalization includes stopping words removing, removing punctuations and other diacritics, converting all letters to lowercase, etc. The second step is feature extraction. Doc2vec model is used in order to represent the data as feature vectors. These vectors are the inputs of Naive Bayes, SVM, Neural network and LSTM. Every one of these algorithms will be assessed to determine which algorithm will yield the most accurate result. Among the four algorithms, LSTM proved to be the best with an accuracy of (92%).
RECENT SCHOLAR PUBLICATIONS
Design an Optimized Deep Learning Architecture to Identify Clinical Implications of Adverse Drug Reaction Anjali B.V, Ravikumar G.K Journal of Information Systems Engineering and Management 10 (15(s)), 10 , 2025 2025
A Highly Accurate Adverse Drug Reactions (ADR) Detection from Medical Forum Comments Using Long Short-Term Memory Networks Anjali B.V, Ravikumar G.K Frontiers in Biomedical Technologies Journal 11 (4), 10 , 2024 2024
Enhancing Data Security and Cloud Performance with Confidentiality-Based Classification-As-A-Service(C2aas) for Big Data Processing and Storage S.Noor Mohammed,Anjali B V, G K Ravi Kumar ,S.Sampath, M V Laxmiprasanna International International Conference on Emerging Research in Computing … , 2024 2024
Hybrid Deep Learning Approach for Adverse Drug Reaction Detection using RNN-Bi-LSTM with Advanced Feature Extraction Techniques SSV Anjali B.V, Ravikumar G.K International Conference on Advanced Data-Driven Intelligence and … , 2024 2024
A broad review on adverse drug reaction detection using social media data RK B V, Anjali 2022 6th International Conference on Intelligent Computing and Control … , 2022 2022 Citations: 3
MOST CITED SCHOLAR PUBLICATIONS
A broad review on adverse drug reaction detection using social media data RK B V, Anjali 2022 6th International Conference on Intelligent Computing and Control … , 2022 2022 Citations: 3
Design an Optimized Deep Learning Architecture to Identify Clinical Implications of Adverse Drug Reaction Anjali B.V, Ravikumar G.K Journal of Information Systems Engineering and Management 10 (15(s)), 10 , 2025 2025
A Highly Accurate Adverse Drug Reactions (ADR) Detection from Medical Forum Comments Using Long Short-Term Memory Networks Anjali B.V, Ravikumar G.K Frontiers in Biomedical Technologies Journal 11 (4), 10 , 2024 2024
Enhancing Data Security and Cloud Performance with Confidentiality-Based Classification-As-A-Service(C2aas) for Big Data Processing and Storage S.Noor Mohammed,Anjali B V, G K Ravi Kumar ,S.Sampath, M V Laxmiprasanna International International Conference on Emerging Research in Computing … , 2024 2024
Hybrid Deep Learning Approach for Adverse Drug Reaction Detection using RNN-Bi-LSTM with Advanced Feature Extraction Techniques SSV Anjali B.V, Ravikumar G.K International Conference on Advanced Data-Driven Intelligence and … , 2024 2024
