A Multimodal Retrieval and Ranking Method for Scientific Documents Based on HFS and XLNet

Aiming at the defects of traditional full-text retrieval models in dealing with mathematical expressions, which are special objects different from ordinary texts, a multimodal retrieval and ranking method for scientific documents based on hesitant fuzzy sets (HFS) and XLNet is proposed. This method integrates multimodal information, such as mathematical expression images and context text, as keywords to realize the retrieval of scientific documents. In the image modal, the images of mathematical expressions are recognized, and the hesitancy fuzzy set theory is introduced to calculate the hesitancy fuzzy similarity between mathematical query expressions and the mathematical expressions in candidate scientific documents. Meanwhile, in the text mode, XLNet is used to generate word vectors of the mathematical expression context to obtain the similarity between the query text and the mathematical expression context of the candidate scientific documents. Finally, the multimodal evaluation is integrated, and the hesitation fuzzy set is constructed at the document level to obtain the final scores of the scientific documents and corresponding ranked output. The experimental results show that the recall and precision of this method are 0.774 and 0.663 on the NTCIR dataset, respectively, and the average normalized discounted cumulative gain (NDCG) value of the top-10 ranking results is 0.880 on the Chinese scientific document (CSD) dataset.

P120 The burden of the management of cerebral aneurysms in Africa: a scoping review

Introduction In Africa, the epidemiology, management, and prognosis of cerebral aneurysms remain poorly understood. Cerebral aneurysms are still highly underdiagnosed and inadequately treated in Africa due to a lack of vascular neurosurgeons and infrastructure. In this review we mapped the burden and management of intracerebral aneurysm in Africa. Methods A full systematic search on articles published in Africa on brain aneurysms was performed in PubMed, African Journals Online, Google Scholar, WHO Global Health Library and LILACS with no language restrictions. The search results were merged, uploaded into Rayyan software, (FDT, USK, IN, NDAB) independently based on the pre-defined inclusion and exclusion criteria. The full text of the remaining articles were then retrieved and screened by three reviewers independently (FDT, USK, NDAB). Conflicts were resolved by mutual agreement. From all included documents, we extracted information regarding study design, socio-demographic characteristics, clinical findings, type of treatment and outcome results. Results We included 28 articles in our full text retrieval. These studies totaled 1181 patients managed for cerebral aneurysm in Africa. Half (50.0%; n = 14) of all studies had been published in the past 5 years and nearly half (46.4%; n = 13) of these studies were conducted in two countries: eight in Morocco and five in South Africa, we didn’t found any publication on cerebral aneurysm for nearly 80% of African countries. Also, there was a female predominance among cerebral aneurysm study participants (62.5%), and the mean time from diagnosis to surgery was 12.1 days. Cerebral aneurysms were most often located in the internal carotid artery (29.6%) and anterior cerebral artery (23.2%). Microneurosurgery (67%) was the most widely used option in these studies ahead of coiling (7.9%). Patient outcomes were judged favorable in 64.2% of cases, and the mortality rate following surgical (open vascular and endovascular) intervention was 19.4%. Conclusion The management of intracerebral aneurysms remains suboptimal in Africa. There are few peer-reviewed reports of aneurysm practice.

A161 PREVALENCE OF FINANCIAL CONFLICTS OF INTEREST (FCOI) AMONG PROPENSITY-SCORE MATCHED RETROSPECTIVE STUDIES EVALUATING BIOLOGIC THERAPEUTICS FOR IBD

Background Inflammatory Bowel Disease (IBD) studies have commonly relied on real-world evidence to evaluate different therapies. An emerging idea has been the use of propensity score matching as a statistical method to account for baseline characteristics in IBD patients. In retrospective studies, propensity score matching of patients helps reduce treatment assignment bias and mimic the effects of randomization. Recently, propensity-score matching has become an important tool in IBD studies comparing biologic therapeutics. Biologic medications are among the highest-grossing drugs worldwide, and their pharmaceutical producers make considerable payments to physicians to market them. In spite of this, there is a lack of evidence examining the role of undue industry influence among propensity-score matched comparative studies evaluating biologic therapeutics for IBD. Aims Given the documented association between IBD biologics and FCOI, we hypothesize a high burden of FCOI in propensity-score matched studies. The aim of this study was to evaluate the prevalence of disclosed & undisclosed financial conflicts of Interest (FCOI) in propensity-score matched comparison studies evaluating biologics for IBD. Methods We developed & ran a librarian-reviewed systematic search on EMBASE, MEDLINE, and Cochrane Library databases for all propensity-score matched retrospective studies comparing biologics for the treatment of IBD. Full-text retrieval & screening was performed on all studies in duplicate. 16 articles were identified. Industry payments to authors were only considered FCOI if they were made by a company producing a biologic that was included in the comparison study. Disclosed FCOI were identified by authors’ interests disclosures in full-texts. Any undisclosed FCOI among US authors were identified using the Centre for Medicare and Medicaid Services (CMS) Open Payments Database, which collects industry payments to physicians. Results Based on a preliminary analysis of 16 studies, there was at least one author with a relevant FCOI in 14 (88%) of the 16 studies. 14 studies (88%) had at least one disclosed FCOI, while 6 studies (37.5%) had at least one undisclosed FCOI. Among studies with disclosed FCOI, a mean of 40.2% (SD = 23.4%) of authors/study reported FCOI. Among studies with undisclosed FCOI, a mean of 18.8% (SD = 7.0%) of authors/study reported FCOI. The total dollar value of FCOIs was $1,974,328.3. The median conflict dollar value was $5,576.6 (IQR: $321.6 to $36,394.9). Conclusions We found a high burden of undisclosed FCOI (37.5%) among authors of propensity-score matched studies evaluating IBD biologics. Given the potential for undue industry influence stemming from such payments, authors should ensure better transparency with industry relationships. Funding Agencies None

Anti-cancer effects of Vernonia amygdalina: A systematic review

Purpose: To systematically review all the studies that have addressed the anti-cancer activities of the VA leaf extract in vitro to determine the strength of evidence of its anti-cancer effects and whether it can be used as an effective cancer therapy.Methods: The databases of Scopus, Science Direct, PubMed, Springer, and Directory of Open Access Journals were searched for relevant articles. Only articles published in the English language from January 2000 to November 2018 were selected for full-text retrieval and review, before being included in the final review.Results: From a total of 28 articles identified for full-text retrieval, only 17 fulfilled the inclusion criteria. The papers reviewed showed that VA decreases cell viability, inhibits DNA synthesis and causes DNA damage in cancer cells. VA also induces apoptosis and cell cycle arrest in cancer cells via gene regulation. All in all, there is evidence showing that VA possesses time- and concentration-dependent anti-cancer activity.Conclusion: The VA leaf extract has the potential to be developed into cancer therapeutics. However, more research is needed on its effect on normal cells before VA is developed into a cancer therapeutic. Keywords: Vernonia amygdalina, Anti-cancer effect, DNA damage, Apoptosis

Recommendation Based on Java Code Analysis and Search

How to improve the efficiency and quality of software development is an ongoing concern in the field of software engineering. As a useful auxiliary function, code recommendation is embedded in almost all integrated development environments. There has been increasing interest and research in the area of code recommendation in recent years due to its convenience for project development. Existing research has made a lot of contributions to this field, but there are still many issues that need further study. One of the key points is the low success rate of recommendation. Focusing on this problem, this paper proposes a method to recommend Java source code after parsing massive amounts of source code information. We propose a new source code analysis algorithm for the scraped source code data. A source file is parsed into classes, methods, and attributes as recommendation objects. At the same time, the annotation information is bound to the annotated objects. Finally, the parsed information is indexed at the project, class, and method levels for code recommendations in a hierarchical recommendation manner. A code recommendation system is implemented by combining this with full-text retrieval technology for class library, class, and method level recommendation. The experimental results show that the method proposed in this paper has better performance in recommendation accuracy than existing code recommendation engines.

Artificial Intelligence Applications in Otology: A State of the Art Review

Objective Recent advances in artificial intelligence (AI) are driving innovative new health care solutions. We aim to review the state of the art of AI in otology and provide a discussion of work underway, current limitations, and future directions. Data Sources Two comprehensive databases, MEDLINE and EMBASE, were mined using a directed search strategy to identify all articles that applied AI to otology. Review Methods An initial abstract and title screening was completed. Exclusion criteria included nonavailable abstract and full text, language, and nonrelevance. References of included studies and relevant review articles were cross-checked to identify additional studies. Conclusion The database search identified 1374 articles. Abstract and title screening resulted in full-text retrieval of 96 articles. A total of N = 38 articles were retained. Applications of AI technologies involved the optimization of hearing aid technology (n = 5; 13% of all articles), speech enhancement technologies (n = 4; 11%), diagnosis and management of vestibular disorders (n = 11; 29%), prediction of sensorineural hearing loss outcomes (n = 9; 24%), interpretation of automatic brainstem responses (n = 5; 13%), and imaging modalities and image-processing techniques (n = 4; 10%). Publication counts of the included articles from each decade demonstrated a marked increase in interest in AI in recent years. Implications for Practice This review highlights several applications of AI that otologists and otolaryngologists alike should be aware of given the possibility of implementation in mainstream clinical practice. Although there remain significant ethical and regulatory challenges, AI powered systems offer great potential to shape how healthcare systems of the future operate and clinicians are key stakeholders in this process.

An Intelligent Approval System for City Construction based on Cloud Computing and Big Data

On the theoretical basis of cloud services, big data technology and case-based reasoning technology (CBR), the authors propose an Intelligent Approval System for City Construction (IASCC). The paper introduces the concept of ‘case approval cloud' and puts forward the city construction approval model based on CBR, by which the storage and computation of the urban construction approval data are concentrated in the cloud. In this system, the authors use the distributed database of HBase, making the data storage capacity of the system with high scalability, design the intelligent approval system based on CBR using the distributed programming framework of MapReduce, making full use of the large amount of historical approval data, and use the distributed full-text retrieval system of SorCloud to retrieve the approval data with a high response speed. IASCC adopts Hadoop as the development platform, using HBase, Solr and MapReduce technology to complete the prototype development of an intelligent approval system. Finally, the authors give the implementation of the system and the performance tests of some key modules.