An ensemble information retrieval method for the biomedical domain (Preprint)

BACKGROUND With the development of biomedicine, the number of biomedical documents has increased rapidly, which brings a great challenge for researchers retrieving the information they need. Information retrieval aims to meet this challenge by searching relevant documents from abundant documents based on the given query. However, sometimes the relevance of search results needs to be evaluated from multiple aspects in some specific retrieval tasks and thereby increases the difficulty of biomedical information retrieval. OBJECTIVE This study aims to find a more systematic method to retrieve relevant scientific literature for a given patient. METHODS In the initial retrieval stage, we supplement query terms through query expansion strategies and apply query boosting to obtain an initial ranking list of relevant documents. In the re-ranking phase, we employ a text classification model and relevance matching model to evaluate documents respectively from different dimensions, then we combine the outputs through logistic regression to re-rank all the documents from the initial ranking list. RESULTS The proposed ensemble method contributes to the improvement of biomedical retrieval performance. Comparing with the existing deep learning-based methods, experimental results show that our method achieves state-of-the-art performance on the data collection provided by TREC 2019 Precision Medicine Track. CONCLUSIONS In this paper, we propose a novel ensemble method based on deep learning. As shown in the experiments, the strategies we used in the initial retrieval phase such as query expansion and query boosting are effective. The application of the text classification model and the relevance matching model can better capture semantic context information and improve retrieval performance.

Computed Tomography Based Radiomics as a Predictor of Survival in Ovarian Cancer Patients: A Systematic Review

The objective of this systematic review was to assess the results of radiomics for prediction of overall survival (OS) and progression free survival (PFS) in ovarian cancer (OC) patients. A secondary objective was to evaluate the findings of papers that based their analyses on inter-site heterogeneity. This systematic review was conducted according to the PRISMA statement. After the initial retrieval of 145 articles, the final systematic review comprised six articles. Association between radiomic features and OS was evaluated in 3/6 studies (50%); all articles showed a significant association between radiomic features and OS. Association with PFS was evaluated in 5/6 (83%) articles; the period of follow-up ranged between six and 36 months. All the articles showed significant association between radiomic models and PFS. Inter-site textural features were used for analysis in 2/6 (33%) articles. They demonstrated that high levels of inter-site textural heterogeneity were significantly associated with incomplete surgical resection in breast cancer gene-negative patients, and that lower heterogeneity was associated with complete resectability. There were some differences among papers in methodology; for example, only 3/6 (50%) articles included validation cohorts. In conclusion, radiomic models have demonstrated promising results as predictors of survival in OC patients, although larger studies are needed to allow clinical applicability.

Lexical and Cognitive Underpinnings of Verbal Fluency: Evidence from Bengali-English Bilingual Aphasia

Research in bilingual healthy controls (BHC) has illustrated that detailed characterization of verbal fluency along with separate measures of executive control stand to inform our understanding of the lexical and cognitive underpinnings of the task. Such data are currently lacking in bilinguals with aphasia (BWA). We aimed to compare the characteristics of verbal fluency performance (semantic, letter) in Bengali–English BWA and BHC, in terms of cross-linguistic differences, variation on the parameters of bilingualism, and cognitive underpinnings. BWA showed significant differences on verbal fluency variables where executive control demands were higher (fluency difference score, number of switches, between-cluster pauses); whilst performed similarly on variables where executive control demands were lower (cluster size, within-cluster pauses). Despite clear cross-linguistic advantage in Bengali for BHC, no cross-linguistic differences were noted in BWA. BWA who were most affected in the independent executive control measures also showed greater impairment in letter fluency condition. Correlation analyses revealed a significant relationship for BWA between inhibitory control and number of correct responses, initial retrieval time, and number of switches. This research contributes to the debate of underlying mechanisms of word retrieval deficits in aphasia, and adds to the nascent literature of BWA in South Asian languages.

After Initial Retrieval Practice, More Retrieval Produces Better Retention Than More Study in the Word Learning of Children With Developmental Language Disorder

Purpose Children with developmental language disorder (DLD) often have difficulty with word learning. Recent studies have shown that incorporating retrieval practice provides a significant benefit to this learning. However, we have not yet discovered the best balance between the amount of retrieval and the amount of study (hearing the word in the presence of the referent) that is provided. In this investigation, we compared a word learning procedure using more retrieval and less study with a procedure that used more study and less retrieval. Method Participants were 13 children with DLD and 13 same-age peers with typical language development (TD). Both groups ranged in age from 4 to 6 years. The children learned two sets of novel words, with each set taught in two sessions. During an initial criterion period, the children had the opportunity to retrieve all of the words. Following this period, the words were either retrieved without further study or studied without additional retrieval. Recall and recognition testing immediately followed the second learning session and was repeated 1 week later. Testing assessed the children's retention of both the word forms and their meanings. Results Better recall both immediately after learning and after 1 week was seen for the more retrieval/less study condition. This was seen for both groups of children for word form recall and for children with DLD for meaning. Group differences were not found. Conclusion This study served as a stringent test of the benefits of retrieval to children's word learning. Continued retrieval after initial retrieval practice appeared to be helpful even when further study was discontinued and when the comparison study condition had also provided retrieval practice in the initial stages. Further refinement of retrieval procedures might lead to the development of useful clinical tools to promote word learning.

Retrieval-Based Learning in Children

Testing oneself with flash cards, using a clicker to respond to a teacher’s questions, and teaching another student are all effective ways to learn information. These learning strategies work, in part, because they require the retrieval of information from memory, a process known to enhance later memory. However, little research has directly examined retrieval-based learning in children. We review the emerging literature on the benefits of retrieval-based learning for preschool and elementary school students and draw on other literatures for further insights. We reveal clear evidence for the benefits of retrieval-based learning in children (starting in infancy). However, we know little about the developmental trajectory. Overall, the benefits are largest when the initial retrieval practice is effortful but successful.