Background: The posts related to Adverse Drug Reaction (ADR) on social websites are believed to be valuableresource for post-marketing drug surveillance. Beyond domain feature, the aim of this study was to find amore effective method to detect ADR related post. Methods: We conducted experiment on posts using sentiment features from March 8 to May 20 in 2016 inShanghai of China. Firstly, the diabetes posts were collected; the 1814 posts were annotated by hand. Secondly, sentiment features set were generated and the2  (CHI) statistics were used to select feature. Finally, we evaluatedthe effectiveness of our method using the different feature sets. Results: By comparing the posts detection performance of different feature sets, using sentiment features byCHI statistics can improve ADR related post detection performance. By comparing the ADR-related groupwith the non-ADR group, performance of ADR related post detection was better than the performance of non-ADR post detection. We could obtain highest performance owing to introducing sentiment feature and usingCHI feature selection technique, and the method was proved to be effective during detecting post related toADR. Conclusion: By using sentiment feature and CHI feature selection technique, we can get an effective methodto detect post related to ADR.

Identifying and controlling adverse drug reactions (ADRs) is a challenging problem in the pharmacological field. For instance, the drug Rosiglitazone has been associated with adverse reactions that were only recognized after its release. Due to such experiences, pharmacists are now more interested in using computational methods to predict ADRs. The performance of computational methods is contingent upon the defined dataset. In some studies, the known drug-adverse reaction associations are regarded as positive while the unknown drug-adverse reaction associations are regarded as negative data. This consequently creates an unbalanced dataset, which can lead to inaccurate predictions from models and cause the classifiers to be flawed. We propose a framework named Adverse Drug Reaction using the Voting Ensemble Training Approach (ADRP-VETA) for ADR problem to overcome unbalanced dataset challenges. We construct the similarity vector of each drug with other drugs based on chemical structure as a drug feature. Also, the similarity vector of each ADR with other ADRs is computed based on the Unified Medical Language System (UMLS) as adverse reaction feature. With this approach, we can leverage the similarity of the features to more accurately capture the intricate relationships between drugs and adverse reactions. We compare ADRP-VETA to three state-of-the-art models and find that it outperforms them, achieving an AUC-ROC of 91% and an AUC-PR of 89.8%. Furthermore, we assess ADRP-VETA’s ability to predict rare adverse reactions, and find that its AUC-ROC and AUC-PR are 83.3% and 92.2%, respectively. As a case study, we focus on the associations between liver-injury adverse reactions and three drugs.

Background: Cancer is among the leading causes of mortality in India. Studies have reported antineoplastic agents as the common class of drugs causing Adverse Drug Reactions (ADRs). The present study aimed to conduct active surveillance of ADRs of anticancer drugs in the hematology department. Methods: A prospective observational study was conducted in 136 patients with cancer and the incidence and frequency of ADRs were assessed. The study was conducted in 6 months in a multispecialty hospital. Results: Among 136 cancer patients, All was more prevalent (39. 70%); CLL, Non-Hodgkin’ s Lymphoma were less prevalent (0. 73%). ADRs were more prevalent in the Pediatrics department, i. e., 18. 53% of ADRs were observed in patients aged <10 years. ADRs in male patients constituted 54. 39%, whereas it was 45. 60% in female patients. Cytarabine caused the highest number of ADRs (34. 48%). The most prevalent ADR was anemia (25. 60%). Conclusion: Multiple ADRs were detected in cancer patients. We found that hematological ADRs were more prevalent. Most of the ADRs were possible reactions according to Naranjo and the World Health Organization (WHO) scales.

Background: Adverse drug reactions (ADR) are ranked as some of the major causes of patient morbidity and mortality. Spontaneous reporting of ADRs has remained the cornerstone of pharmacovigilance and is important in maintaining patient safety. This study was conducted to assess the nurses’ knowledge and attitude towards pharmacovigilance, reasons for not reporting ADRs, and their pharmacovigilance practice.Materials and Methods: A questionnaire was prepared to investigate knowledge, attitude and practice (KAP) of nurses regarding ADR reporting. In November 2009, the questionnaires were given to 500 nurses of a teaching hospital in Tehran.Findings: Knowledge and practice of participants were not satisfying, however, their attitude towards pharmacovigilance was at a high level. About 91% of the nurses had never reported an ADR. Most nurses liked to report the ADRs to the physicians (87.1%) and pharmacists in hospital’s ADR center (1.8%) rather than the ADR National Center. The main cause of under-reporting of the suspected ADRs was unawareness about the existence of such a national center. Among nurses who had reported ADR for at least once, the majority preferred using phone (10 out of 50) or Yellow Cards (7 out of 50). Only 1 person out of 50 preferred using internet for submitting the reports.Conclusions: Since the nurses in this study had little knowledge and poor practice regarding the pharmacovigilance and spontaneous reporting system, interventions such as holding pharmacovigilance workshops in the hospitals focusing on the aims of pharmacovigilance, completing the Yellow Card and clarifying the reporting criteria are strongly recommended.

Objective: Health-related studies have been recently at the heart attention of the media. Social media, such as Twitter, has become a valuable online tool to describe the early detection of various adverse drug reactions (ADRs). Different medications have adverse effects on various cells and tissues, sometimes more than one cell population would be adversely affected. These types of side effect are occasionally associated with the direct or indirect influence of prescribed drugs but do not have general unfavorable mutagenic consequences on patients. This study aimed to demonstrate a quick and accurate method to collect and classify information based on the distribution of approved data on Twitter. Materials and Methods: In this classification method, we selected "ask a patient" dataset and combination of Twitter "Ask a Patient" datasets that comprised of 6, 623, 26, 934, and 11, 623 reviews. We used deep learning methods with the word2vec to classify ADR comments posted by the users and present an architecture by HAN, FastText, and CNN. Results: Natural language processing (NLP) deep learning is able to address more advanced peculiarity in learning information compared to other types of machine learning. Moreover, the current study highlighted the advantage of incorporating various semantic features, including topics and concepts. Conclusion: Our approach predicts drug safety with the accuracy of 93% (the combination of Twitter and "Ask a Patient" datasets) in a binary manner. Despite the apparent benefit of various conventional classifiers, deep learningbased text classification methods seem to be precise and influential tools to detect ADR.