METHODS: A systematic literature search for studies with the primary aim of using OSN to detect and track a pandemic was conducted. We conducted an electronic literature search for eligible English articles published between 2004 and 2015 using PUBMED, IEEExplore, ACM Digital Library, Google Scholar, and Web of Science. First, the articles were screened on the basis of titles and abstracts. Second, the full texts were reviewed. All included studies were subjected to quality assessment.
RESULT: OSNs have rich information that can be utilized to develop an almost real-time pandemic surveillance system. The outcomes of OSN surveillance systems have demonstrated high correlations with the findings of official surveillance systems. However, the limitation in using OSN to track pandemic is in collecting representative data with sufficient population coverage. This challenge is related to the characteristics of OSN data. The data are dynamic, large-sized, and unstructured, thus requiring advanced algorithms and computational linguistics.
CONCLUSIONS: OSN data contain significant information that can be used to track a pandemic. Different from traditional surveys and clinical reports, in which the data collection process is time consuming at costly rates, OSN data can be collected almost in real time at a cheaper cost. Additionally, the geographical and temporal information can provide exploratory analysis of spatiotemporal dynamics of infectious disease spread. However, on one hand, an OSN-based surveillance system requires comprehensive adoption, enhanced geographical identification system, and advanced algorithms and computational linguistics to eliminate its limitations and challenges. On the other hand, OSN is probably to never replace traditional surveillance, but it can offer complementary data that can work best when integrated with traditional data.
MATERIALS AND METHODS: A DCN model was developed using pill images captured with mobile phones under unconstraint environments. The performance of the DCN model was compared to two baseline methods of hand-crafted features.
RESULTS: The DCN model outperforms the baseline methods. The mean accuracy rate of DCN at Top-1 return was 95.35%, whereas the mean accuracy rates of the two baseline methods were 89.00% and 70.65%, respectively. The mean accuracy rates of DCN for Top-5 and Top-10 returns, i.e., 98.75% and 99.55%, were also consistently higher than those of the baseline methods.
DISCUSSION: The images used in this study were captured at various angles and under different level of illumination. DCN model achieved high accuracy despite the suboptimal image quality.
CONCLUSION: The superior performance of DCN underscores the potential of Deep Learning model in the application of pill identification and verification.
METHODS: A literature review of existing studies related to HIE efforts from 2005 was undertaken. Four electronic research databases (PubMed, Web of Science, CINAHL, and Academic Search Premiere) were searched for articles addressing different phases of HIE assimilation process.
RESULTS: Two hundred and fifty-four articles were initially selected. Out of 254, 44 studies met the inclusion criteria and were reviewed. The assimilation of HIE is a complicated and a multi-staged process. Our findings indicated that HIE assimilation process consisted of four main phases: initiation, organizational adoption decision, implementation and institutionalization. The data helped us recognize the assimilation pattern of HIE in healthcare organizations.
CONCLUSIONS: The results provide useful theoretical implications for research by defining HIE assimilation pattern. The findings of the study also have practical implications for policy makers. The findings show the importance of raising national awareness of HIE potential benefits, financial incentive programs, use of standard guidelines, implementation of certified technology, technical assistance, training programs and trust between healthcare providers. The study highlights deficiencies in the current policy using the literature and identifies the "pattern" as an indication for a new policy approach.
OBJECTIVE: From the considerable amount of clinical narrative text, natural language processing (NLP) researchers have developed methods for extracting ADEs and their related attributes. This work presents a systematic review of current methods.
METHODOLOGY: Two biomedical databases have been searched from June 2022 until December 2023 for relevant publications regarding this review, namely the databases PubMed and Medline. Similarly, we searched the multi-disciplinary databases IEEE Xplore, Scopus, ScienceDirect, and the ACL Anthology. We adopted the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 statement guidelines and recommendations for reporting systematic reviews in conducting this review. Initially, we obtained 5,537 articles from the search results from the various databases between 2015 and 2023. Based on predefined inclusion and exclusion criteria for article selection, 100 publications have undergone full-text review, of which we consider 82 for our analysis.
RESULTS: We determined the general pattern for extracting ADEs from clinical notes, with named entity recognition (NER) and relation extraction (RE) being the dual tasks considered. Researchers that tackled both NER and RE simultaneously have approached ADE extraction as a "pipeline extraction" problem (n = 22), as a "joint task extraction" problem (n = 7), and as a "multi-task learning" problem (n = 6), while others have tackled only NER (n = 27) or RE (n = 20). We further grouped the reviews based on the approaches for data extraction, namely rule-based (n = 8), machine learning (n = 11), deep learning (n = 32), comparison of two or more approaches (n = 11), hybrid (n = 12) and large language models (n = 8). The most used datasets are MADE 1.0, TAC 2017 and n2c2 2018.
CONCLUSION: Extracting ADEs is crucial, especially for pharmacovigilance studies and patient medications. This survey showcases advances in ADE extraction research, approaches, datasets, and state-of-the-art performance in them. Challenges and future research directions are highlighted. We hope this review will guide researchers in gaining background knowledge and developing more innovative ways to address the challenges.