Explore the vast range of titles available.

Spatial relations are a basic part of human cognition. However, they are expressed in natural language in a variety of ways, and previous work has suggested that current vision-and-language models (VLMs) struggle to capture relational information. In this paper, we present Visual Spatial Reasoning (VSR), a dataset containing more than 10k natural text-image pairs with 66 types of spatial relations in English (e.g., under, in front of, facing). While using a seemingly simple annotation format, we show how the dataset includes challenging linguistic phenomena, such as varying reference frames. We demonstrate a large gap between human and model performance: The human ceiling is above 95%, while state-of-the-art models only achieve around 70%. We observe that VLMs’ by-relation performances have little correlation with the number of training examples and the tested models are in general incapable of recognising relations concerning the orientations of objects.

The primary aim of this review was to evaluate the state of knowledge of the geographical distribution of all infectious diseases of clinical significance to humans. A systematic review was conducted to enumerate cartographic progress, with respect to the data available for mapping and the methods currently applied. The results helped define the minimum information requirements for mapping infectious disease occurrence, and a quantitative framework for assessing the mapping opportunities for all infectious diseases. This revealed that of 355 infectious diseases identified, 174 (49%) have a strong rationale for mapping and of these only 7 (4%) had been comprehensively mapped. A variety of ambitions, such as the quantification of the global burden of infectious disease, international biosurveillance, assessing the likelihood of infectious disease outbreaks and exploring the propensity for infectious disease evolution and emergence, are limited by these omissions. An overview of the factors hindering progress in disease cartography is provided. It is argued that rapid improvement in the landscape of infectious diseases mapping can be made by embracing non-conventional data sources, automation of geo-positioning and mapping procedures enabled by machine learning and information technology, respectively, in addition to harnessing labour of the volunteer ‘cognitive surplus’ through crowdsourcing.

Much of the knowledge and information needed for enabling high-quality clinical research is stored in free-text format. Natural language processing (NLP) has been used to extract information from these sources at scale for several decades. This paper aims to present a comprehensive review of clinical NLP for the past 15 years in the UK to identify the community, depict its evolution, analyse methodologies and applications, and identify the main barriers. We collect a dataset of clinical NLP projects ( n  = 94; £  = 41.97 m) funded by UK funders or the European Union’s funding programmes. Additionally, we extract details on 9 funders, 137 organisations, 139 persons and 431 research papers. Networks are created from timestamped data interlinking all entities, and network analysis is subsequently applied to generate insights. 431 publications are identified as part of a literature review, of which 107 are eligible for final analysis. Results show, not surprisingly, clinical NLP in the UK has increased substantially in the last 15 years: the total budget in the period of 2019–2022 was 80 times that of 2007–2010. However, the effort is required to deepen areas such as disease (sub-)phenotyping and broaden application domains. There is also a need to improve links between academia and industry and enable deployments in real-world settings for the realisation of clinical NLP’s great potential in care delivery. The major barriers include research and development access to hospital data, lack of capable computational resources in the right places, the scarcity of labelled data and barriers to sharing of pretrained models.

Background Online news reports are increasingly becoming a source for event-based early warning systems that detect natural disasters. Harnessing the massive volume of information available from multilingual newswire presents as many challanges as opportunities due to the patterns of reporting complex spatio-temporal events. Results In this article we study the problem of utilising correlated event reports across languages. We track the evolution of 16 disease outbreaks using 5 temporal aberration detection algorithms on text-mined events classified according to disease and outbreak country. Using ProMED reports as a silver standard, comparative analysis of news data for 13 languages over a 129 day trial period showed improved sensitivity, F1 and timeliness across most models using cross-lingual events. We report a detailed case study analysis for Cholera in Angola 2010 which highlights the challenges faced in correlating news events with the silver standard. Conclusions The results show that automated health surveillance using multilingual text mining has the potential to turn low value news into high value alerts if informed choices are used to govern the selection of models and data sources. An implementation of the C2 alerting algorithm using multilingual news is available at the BioCaster portal http://born.nii.ac.jp/?page=globalroundup .

Electronic health records and scientific articles possess differing linguistic characteristics that may impact the performance of natural language processing tools developed for one or the other. In this paper, we investigate the performance of four extant concept recognition tools: the clinical Text Analysis and Knowledge Extraction System (cTAKES), the National Center for Biomedical Ontology (NCBO) Annotator, the Biomedical Concept Annotation System (BeCAS) and MetaMap. Each of the four concept recognition systems is applied to four different corpora: the i2b2 corpus of clinical documents, a PubMed corpus of Medline abstracts, a clinical trails corpus and the ShARe/CLEF corpus. In addition, we assess the individual system performances with respect to one gold standard annotation set, available for the ShARe/CLEF corpus. Furthermore, we built a silver standard annotation set from the individual systems' output and assess the quality as well as the contribution of individual systems to the quality of the silver standard. Our results demonstrate that mainly the NCBO annotator and cTAKES contribute to the silver standard corpora (F1-measures in the range of 21% to 74%) and their quality (best F1-measure of 33%), independent from the type of text investigated. While BeCAS and MetaMap can contribute to the precision of silver standard annotations (precision of up to 42%), the F1-measure drops when combined with NCBO Annotator and cTAKES due to a low recall. In conclusion, the performances of individual systems need to be improved independently from the text types, and the leveraging strategies to best take advantage of individual systems' annotations need to be revised. The textual content of the PubMed corpus, accession numbers for the clinical trials corpus, and assigned annotations of the four concept recognition systems as well as the generated silver standard annotation sets are available from http://purl.org/phenotype/resources. The textual content of the ShARe/CLEF (https://sites.google.com/site/shareclefehealth/data) and i2b2 (https://i2b2.org/NLP/DataSets/) corpora needs to be requested with the individual corpus providers.

Background Accurate and timely detection of public health events of international concern is necessary to help support risk assessment and response and save lives. Novel event-based methods that use the World Wide Web as a signal source offer potential to extend health surveillance into areas where traditional indicator networks are lacking. In this paper we address the issue of systematically evaluating online health news to support automatic alerting using daily disease-country counts text mined from real world data using BioCaster. For 18 data sets produced by BioCaster, we compare 5 aberration detection algorithms (EARS C2, C3, W2, F-statistic and EWMA) for performance against expert moderated ProMED-mail postings. Results We report sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), mean alerts/100 days and F1, at 95% confidence interval (CI) for 287 ProMED-mail postings on 18 outbreaks across 14 countries over a 366 day period. Results indicate that W2 had the best F1 with a slight benefit for day of week effect over C2. In drill down analysis we indicate issues arising from the granular choice of country-level modeling, sudden drops in reporting due to day of week effects and reporting bias. Automatic alerting has been implemented in BioCaster available from http://born.nii.ac.jp. Conclusions Online health news alerts have the potential to enhance manual analytical methods by increasing throughput, timeliness and detection rates. Systematic evaluation of health news aberrations is necessary to push forward our understanding of the complex relationship between news report volumes and case numbers and to select the best performing features and algorithms.

Background Most previous relation extraction (RE) studies have focused on intra sentence relations and have ignored relations that span sentences, i.e. inter sentence relations. Such relations connect entities at the document level rather than as relational facts in a single sentence. Extracting facts that are expressed across sentences leads to some challenges and requires different approaches than those usually applied in recent intra sentence relation extraction. Despite recent results, there are still limitations to be overcome. Results We present a novel representation for a sequence of consecutive sentences, namely document subgraph, to extract inter sentence relations. Experiments on the BioCreative V Chemical-Disease Relation corpus demonstrate the advantages and robustness of our novel system to extract both intra- and inter sentence relations in biomedical literature abstracts. The experimental results are comparable to state-of-the-art approaches and show the potential by demonstrating the effectiveness of graphs, deep learning-based model, and other processing techniques. Experiments were also carried out to verify the rationality and impact of various additional information and model components. Conclusions Our proposed graph-based representation helps to extract ∼50 % of inter sentence relations and boosts the model performance on both precision and recall compared to the baseline model.

Background Micro-blogging services such as Twitter offer the potential to crowdsource epidemics in real-time. However, Twitter posts (‘tweets’) are often ambiguous and reactive to media trends. In order to ground user messages in epidemic response we focused on tracking reports of self-protective behaviour such as avoiding public gatherings or increased sanitation as the basis for further risk analysis. Results We created guidelines for tagging self protective behaviour based on Jones and Salathé (2009)’s behaviour response survey. Applying the guidelines to a corpus of 5283 Twitter messages related to influenza like illness showed a high level of inter-annotator agreement (kappa 0.86). We employed supervised learning using unigrams, bigrams and regular expressions as features with two supervised classifiers (SVM and Naive Bayes) to classify tweets into 4 self-reported protective behaviour categories plus a self-reported diagnosis. In addition to classification performance we report moderately strong Spearman’s Rho correlation by comparing classifier output against WHO/NREVSS laboratory data for A(H1N1) in the USA during the 2009-2010 influenza season. Conclusions The study adds to evidence supporting a high degree of correlation between pre-diagnostic social media signals and diagnostic influenza case data, pointing the way towards low cost sensor networks. We believe that the signals we have modelled may be applicable to a wide range of diseases.

The objective of Web-based expert epidemic intelligence systems is to detect health threats. The Global Health Security Initiative (GHSI) Early Alerting and Reporting (EAR) project was launched to assess the feasibility and opportunity for pooling epidemic intelligence data from seven expert systems. EAR participants completed a qualitative survey to document epidemic intelligence strategies and to assess perceptions regarding the systems performance. Timeliness and sensitivity were rated highly illustrating the value of the systems for epidemic intelligence. Weaknesses identified included representativeness, completeness and flexibility. These findings were corroborated by the quantitative analysis performed on signals potentially related to influenza A/H5N1 events occurring in March 2010. For the six systems for which this information was available, the detection rate ranged from 31% to 38%, and increased to 72% when considering the virtual combined system. The effective positive predictive values ranged from 3% to 24% and F1-scores ranged from 6% to 27%. System sensitivity ranged from 38% to 72%. An average difference of 23% was observed between the sensitivities calculated for human cases and epizootics, underlining the difficulties in developing an efficient algorithm for a single pathology. However, the sensitivity increased to 93% when the virtual combined system was considered, clearly illustrating complementarities between individual systems. The average delay between the detection of A/H5N1 events by the systems and their official reporting by WHO or OIE was 10.2 days (95% CI: 6.7-13.8). This work illustrates the diversity in implemented epidemic intelligence activities, differences in system's designs, and the potential added values and opportunities for synergy between systems, between users and between systems and users.

Internet-based biosurveillance systems have been developed to detect health threats using information available on the Internet, but system performance has not been assessed relative to end-user needs and perspectives. Infectious disease events from the French Institute for Public Health Surveillance (InVS) weekly international epidemiological bulletin published in 2010 were used to construct the gold-standard official dataset. Data from six biosurveillance systems were used to detect raw signals (infectious disease events from informal Internet sources): Argus, BioCaster, GPHIN, HealthMap, MedISys and ProMED-mail. Crude detection rates (C-DR), crude sensitivity rates (C-Se) and intrinsic sensitivity rates (I-Se) were calculated from multivariable regressions to evaluate the systems' performance (events detected compared to the gold-standard) 472 raw signals (Internet disease reports) related to the 86 events included in the gold-standard data set were retrieved from the six systems. 84 events were detected before their publication in the gold-standard. The type of sources utilised by the systems varied significantly (p<0001). I-Se varied significantly from 43% to 71% (p=0001) whereas other indicators were similar (C-DR: p=020; C-Se, p=013). I-Se was significantly associated with individual systems, types of system, languages, regions of occurrence, and types of infectious disease. Conversely, no statistical difference of C-DR was observed after adjustment for other variables. Although differences could result from a biosurveillance system's conceptual design, findings suggest that the combined expertise amongst systems enhances early detection performance for detection of infectious diseases. While all systems showed similar early detection performance, systems including human moderation were found to have a 53% higher I-Se (p=00001) after adjustment for other variables. Overall, the use of moderation, sources, languages, regions of occurrence, and types of cases were found to influence system performance.