Fear of falling (FoF) is a major concern among older adults and is associated with negative outcomes, such as decreased quality of life and increased risk of falls. Despite several systematic reviews conducted on various specific domains of FoF and its related interventions, the research area has only been minimally covered by scoping reviews, and a comprehensive scoping review mapping the range and scope of the research area is still lacking. This review aims to provide such a comprehensive investigation of the existing literature and identify main topics, gaps in the literature, and potential opportunities for bridging different strains of research. Using the PRISMA-ScR guidelines, we searched the Cochrane Database of Systematic Reviews, CINAHL, Embase, MEDLINE, PsycInfo, Scopus, and Web of Science databases. Following the screening process, 969 titles and abstracts were chosen for the review. Pre-processing steps included stop word removal, stemming, and term frequency-inverse document frequency vectorization. Using the Non-negative Matrix Factorization algorithm, we identified seven main topics and created a conceptual mapping of FoF research. The analysis also revealed that most studies focused on physical health-related factors, particularly balance and gait, with less attention paid to cognitive, psychological, social, and environmental factors. Moreover, more research could be done on demographic factors beyond gender and age with an interdisciplinary collaboration with social sciences. The review highlights the need for more nuanced and comprehensive understanding of FoF and calls for more research on less studied areas.

Software engineering artifact extraction from natural language requirements without human intervention is a challenging task. Out of these artifacts, the use case plays a prominent role in software design and development. In the literature, most of the approaches are either semi-automated or necessitate formalism or make use of restricted natural language for the extraction of use cases from textual requirements. In this paper, we resolve the challenge of automated artifact extraction from natural language requirements. We propose an automated approach to generate use cases, actors, and their relationships from natural language requirements. Our proposed approach involves no human intervention or formalism. To automate the proposed approach, we have used Natural Language Processing and Network Science. Our proposed approach provides promising results for the extraction of use case elements from natural language requirements. We validate the proposed approach using several literature-based case studies. The proposed approach significantly improves the results in comparison to an existing approach. On average, the proposed approach achieves around 71.5% accuracy (F-Measure), whereas the baseline method achieves around 16% accuracy (F-Measure) on average. The evaluation of the proposed approach on the literature-based case studies shows its significance for the extraction of use case elements from natural language requirements. The approach reduces human effort in software design and development.

To develop and apply a natural language processing algorithm for characterization of patients diagnosed with chronic pancreatitis in a diverse integrated U.S. healthcare system.

To reduce adverse drug events (ADEs), hospitals need a system to support them in monitoring ADE occurrence routinely, rapidly, and at scale. Natural language processing (NLP), a computerized approach to analyze text data, has shown promising results for the purpose of ADE detection in the context of pharmacovigilance. However, a detailed qualitative assessment and critical appraisal of NLP methods for ADE detection in the context of ADE monitoring in hospitals is lacking. Therefore, we have conducted a scoping review to close this knowledge gap, and to provide directions for future research and practice. We included articles where NLP was applied to detect ADEs in clinical narratives within electronic health records of inpatients. Quantitative and qualitative data items relating to NLP methods were extracted and critically appraised. Out of 1,065 articles screened for eligibility, 29 articles met the inclusion criteria. Most frequent tasks included named entity recognition (n = 17; 58.6%) and relation extraction/classification (n = 15; 51.7%). Clinical involvement was reported in nine studies (31%). Multiple NLP modelling approaches seem suitable, with Long Short Term Memory and Conditional Random Field methods most commonly used. Although reported overall performance of the systems was high, it provides an inflated impression given a steep drop in performance when predicting the ADE entity or ADE relation class. When annotating corpora, treating an ADE as a relation between a drug and non-drug entity seems the best practice. Future research should focus on semi-automated methods to reduce the manual annotation effort, and examine implementation of the NLP methods in practice.

Discovering technology opportunities from the opinion of users can promote successful technological development by satisfying the needs of users. However, although previous approaches using opinion mining only have classified various needs of users into positive or negative categories, they cannot derive the main reasons for their opinion. To solve this problem, this research proposes an approach to exploring technology opportunity by structuring user needs with a concept of opinion trigger of objects and functions of the technology-based products. To discover technology opportunity, first, an opinion trigger is identified from review data using Naïve Base classifier and natural language processing. Second, the opinion triggers and patent keywords that have a similar meaning in context are clustered to discover the needs of the user and need-related technology. Then, the sentimental values of needs are calculated through graph-based semi-supervised learning. Finally, the needs of the user are classified in resolving the problem of vacant technology to discover technology opportunity. Then, an R&D strategy of each opportunity is suggested based on opinion triggers, patent keywords, and their property. Based on the concept of opinion trigger-based methodology, a case study is conducted on automobile-related reviews, extracting the customer needs and presenting important R&D projects such as an extracted need (cargo transportation) and its R&D strategy (resolving contradiction). The proposed approach can analyze the needs of user at a functional level to discover new technology opportunities.

Self-harm occurring within pregnancy and the postnatal year ("perinatal self-harm") is a clinically important yet under-researched topic. Current research likely under-estimates prevalence due to methodological limitations. Electronic healthcare records (EHRs) provide a source of clinically rich data on perinatal self-harm.

With the novel COVID-19 pandemic disrupting and threatening the lives of millions, researchers and clinicians have been recently conducting clinical trials at an unprecedented rate to learn more about the virus and potential drugs/treatments/vaccines to treat its infection. As a result of the influx of clinical trials, researchers, clinicians, and the lay public, now more than ever, face a significant challenge in keeping up-to-date with the rapid rate of discoveries and advances. To remedy this problem, this research mined the ClinicalTrials.gov corpus to extract COVID-19 related clinical trials, produce unique reports to summarize findings and make the meta-data available via Application Programming Interfaces (APIs). Unique reports were created for each drug/intervention, Medical Subject Heading (MeSH) term, and Human Phenotype Ontology (HPO) term. These reports, which have been run over multiple time points, along with APIs to access meta-data, are freely available at http://covidresearchtrials.com. The pipeline, reports, association of COVID-19 clinical trials with MeSH and HPO terms, insights, public repository, APIs, and correlations produced are all novel in this work. The freely available, novel resources present up-to-date relevant biological information and insights in a robust, accessible manner, illustrating their invaluable potential to aid researchers overcome COVID-19 and save hundreds of thousands of lives.

In this study, we demonstrate the use of natural language processing methods to extract, from nanomedicine literature, numeric values of biomedical property terms of poly(amidoamine) dendrimers. We have developed a method for extracting these values for properties taken from the NanoParticle Ontology, using the General Architecture for Text Engineering and a Nearly-New Information Extraction System. We also created a method for associating the identified numeric values with their corresponding dendrimer properties, called NanoSifter. We demonstrate that our system can correctly extract numeric values of dendrimer properties reported in the cancer treatment literature with high recall, precision, and f-measure. The micro-averaged recall was 0.99, precision was 0.84, and f-measure was 0.91. Similarly, the macro-averaged recall was 0.99, precision was 0.87, and f-measure was 0.92. To our knowledge, these results are the first application of text mining to extract and associate dendrimer property terms and their corresponding numeric values.

Accurate, automated extraction of clinical stroke information from unstructured text has several important applications. ICD-9/10 codes can misclassify ischemic stroke events and do not distinguish acuity or location. Expeditious, accurate data extraction could provide considerable improvement in identifying stroke in large datasets, triaging critical clinical reports, and quality improvement efforts. In this study, we developed and report a comprehensive framework studying the performance of simple and complex stroke-specific Natural Language Processing (NLP) and Machine Learning (ML) methods to determine presence, location, and acuity of ischemic stroke from radiographic text. We collected 60,564 Computed Tomography and Magnetic Resonance Imaging Radiology reports from 17,864 patients from two large academic medical centers. We used standard techniques to featurize unstructured text and developed neurovascular specific word GloVe embeddings. We trained various binary classification algorithms to identify stroke presence, location, and acuity using 75% of 1,359 expert-labeled reports. We validated our methods internally on the remaining 25% of reports and externally on 500 radiology reports from an entirely separate academic institution. In our internal population, GloVe word embeddings paired with deep learning (Recurrent Neural Networks) had the best discrimination of all methods for our three tasks (AUCs of 0.96, 0.98, 0.93 respectively). Simpler NLP approaches (Bag of Words) performed best with interpretable algorithms (Logistic Regression) for identifying ischemic stroke (AUC of 0.95), MCA location (AUC 0.96), and acuity (AUC of 0.90). Similarly, GloVe and Recurrent Neural Networks (AUC 0.92, 0.89, 0.93) generalized better in our external test set than BOW and Logistic Regression for stroke presence, location and acuity, respectively (AUC 0.89, 0.86, 0.80). Our study demonstrates a comprehensive assessment of NLP techniques for unstructured radiographic text. Our findings are suggestive that NLP/ML methods can be used to discriminate stroke features from large data cohorts for both clinical and research-related investigations.

Limited health literacy is a barrier to optimal healthcare delivery and outcomes. Current measures requiring patients to self-report limitations are time-consuming and may be considered intrusive by some. This makes widespread classification of patient health literacy challenging. The objective of this study was to develop and validate "literacy profiles" as automated indicators of patients' health literacy to facilitate a non-intrusive, economic and more comprehensive characterization of health literacy among a health care delivery system's membership. To this end, three literacy profiles were generated based on natural language processing (combining computational linguistics and machine learning) using a sample of 283,216 secure messages sent from 6,941 patients to their primary care physicians. All patients were participants in Kaiser Permanente Northern California's DISTANCE Study. Performance of the three literacy profiles were compared against a gold standard of patient self-reported health literacy. Associations were analyzed between each literacy profile and patient demographics, health outcomes and healthcare utilization. T-tests were used for numeric data such as A1C, Charlson comorbidity index and healthcare utilization rates, and chi-square tests for categorical data such as sex, race, poor adherence and severe hypoglycemia. Literacy profiles varied in their test characteristics, with C-statistics ranging from 0.61-0.74. Relations between literacy profiles and health outcomes revealed patterns consistent with previous health literacy research: patients identified via literacy profiles indicative of limited health literacy: (a) were older and more likely of minority status; (b) had poorer medication adherence and glycemic control; and (c) exhibited higher rates of hypoglycemia, comorbidities and healthcare utilization. This represents the first successful attempt to employ natural language processing to estimate health literacy. Literacy profiles can offer an automated and economical way to identify patients with limited health literacy and greater vulnerability to poor health outcomes.

Child physical abuse is a leading cause of traumatic injury and death in children. In 2017, child abuse was responsible for 1688 fatalities in the United States, of 3.5 million children referred to Child Protection Services and 674,000 substantiated victims. While large referral hospitals maintain teams trained in Child Abuse Pediatrics, smaller community hospitals often do not have such dedicated resources to evaluate patients for potential abuse. Moreover, identification of abuse has a low margin of error, as false positive identifications lead to unwarranted separations, while false negatives allow dangerous situations to continue. This context makes the consistent detection of and response to abuse difficult, particularly given subtle signs in young, non-verbal patients. Here, we describe the development of artificial intelligence algorithms that use unstructured free-text in the electronic medical record-including notes from physicians, nurses, and social workers-to identify children who are suspected victims of physical abuse. Importantly, only the notes from time of first encounter (e.g.: birth, routine visit, sickness) to the last record before child protection team involvement were used. This allowed us to develop an algorithm using only information available prior to referral to the specialized child protection team. The study was performed in a multi-center referral pediatric hospital on patients screened for abuse within five different locations between 2015 and 2019. Of 1123 patients, 867 records were available after data cleaning and processing, and 55% were abuse-positive as determined by a multi-disciplinary team of clinical professionals. These electronic medical records were encoded with three natural language processing (NLP) algorithms-Bag of Words (BOW), Word Embeddings (WE), and Rules-Based (RB)-and used to train multiple neural network architectures. The BOW and WE encodings utilize the full free-text, while RB selects crucial phrases as identified by physicians. The best architecture was selected by average classification accuracy for the best performing model from each train-test split of a cross-validation experiment. Natural language processing coupled with neural networks detected cases of likely child abuse using only information available to clinicians prior to child protection team referral with average accuracy of 0.90±0.02 and average area under the receiver operator characteristic curve (ROC-AUC) 0.93±0.02 for the best performing Bag of Words models. The best performing rules-based models achieved average accuracy of 0.77±0.04 and average ROC-AUC 0.81±0.05, while a Word Embeddings strategy was severely limited by lack of representative embeddings. Importantly, the best performing model had a false positive rate of 8%, as compared to rates of 20% or higher in previously reported studies. This artificial intelligence approach can help screen patients for whom an abuse concern exists and streamline the identification of patients who may benefit from referral to a child protection team. Furthermore, this approach could be applied to develop computer-aided-diagnosis platforms for the challenging and often intractable problem of reliably identifying pediatric patients suffering from physical abuse.

Heart failure (HF) is a major cause of morbidity and mortality. However, much of the clinical data is unstructured in the form of radiology reports, while the process of data collection and curation is arduous and time-consuming.

The risk stratification of patients in the emergency department begins at triage. It is vital to stratify patients early based on their severity, since undertriage can lead to increased morbidity, mortality and costs. Our aim was to present a new approach to assist healthcare professionals at triage in the stratification of patients and in identifying those with higher risk of ICU admission. Adult patients assigned Manchester Triage System (MTS) or Emergency Severity Index (ESI) 1 to 3 from a Portuguese and a United States Emergency Departments were analyzed. Variables routinely collected at triage were used and natural language processing was applied to the patient chief complaint. Stratified random sampling was applied to split the data in train (70%) and test (30%) sets and 10-fold cross validation was performed for model training. Logistic regression, random forests, and a random undersampling boosting algorithm were used. We compared the performance obtained with the reference model-using only triage priorities-with the models using additional variables. For both hospitals, a logistic regression model achieved higher overall performance, yielding areas under the receiver operating characteristic and precision-recall curves of 0.91 (95% CI 0.90-0.92) and 0.30 (95% CI 0.27-0.33) for the United States hospital and of 0.85 (95% CI 0.83-0.86) and 0.06 (95% CI 0.05-0.07) for the Portuguese hospital. Heart rate, pulse oximetry, respiratory rate and systolic blood pressure were the most important predictors of ICU admission. Compared to the reference models, the models using clinical variables and the chief complaint presented higher recall for patients assigned MTS/ESI 3 and can identify patients assigned MTS/ESI 3 who are at risk for ICU admission.

Prospective surveillance of invasive mold diseases (IMDs) in haematology patients should be standard of care but is hampered by the absence of a reliable laboratory prompt and the difficulty of manual surveillance. We used a high throughput technology, natural language processing (NLP), to develop a classifier based on machine learning techniques to screen computed tomography (CT) reports supportive for IMDs.

Communicative interactions involve a kind of procedural knowledge that is used by the human brain for processing verbal and nonverbal inputs and for language production. Although considerable work has been done on modeling human language abilities, it has been difficult to bring them together to a comprehensive tabula rasa system compatible with current knowledge of how verbal information is processed in the brain. This work presents a cognitive system, entirely based on a large-scale neural architecture, which was developed to shed light on the procedural knowledge involved in language elaboration. The main component of this system is the central executive, which is a supervising system that coordinates the other components of the working memory. In our model, the central executive is a neural network that takes as input the neural activation states of the short-term memory and yields as output mental actions, which control the flow of information among the working memory components through neural gating mechanisms. The proposed system is capable of learning to communicate through natural language starting from tabula rasa, without any a priori knowledge of the structure of phrases, meaning of words, role of the different classes of words, only by interacting with a human through a text-based interface, using an open-ended incremental learning process. It is able to learn nouns, verbs, adjectives, pronouns and other word classes, and to use them in expressive language. The model was validated on a corpus of 1587 input sentences, based on literature on early language assessment, at the level of about 4-years old child, and produced 521 output sentences, expressing a broad range of language processing functionalities.

Natural sleep provides a powerful model system for studying the neuronal correlates of awareness and state changes in the human brain. To quantitatively map the nature of sleep-induced modulations in sensory responses we presented participants with auditory stimuli possessing different levels of linguistic complexity. Ten participants were scanned using functional magnetic resonance imaging (fMRI) during the waking state and after falling asleep. Sleep staging was based on heart rate measures validated independently on 20 participants using concurrent EEG and heart rate measurements and the results were confirmed using permutation analysis. Participants were exposed to three types of auditory stimuli: scrambled sounds, meaningless word sentences and comprehensible sentences. During non-rapid eye movement (NREM) sleep, we found diminishing brain activation along the hierarchy of language processing, more pronounced in higher processing regions. Specifically, the auditory thalamus showed similar activation levels during sleep and waking states, primary auditory cortex remained activated but showed a significant reduction in auditory responses during sleep, and the high order language-related representation in inferior frontal gyrus (IFG) cortex showed a complete abolishment of responses during NREM sleep. In addition to an overall activation decrease in language processing regions in superior temporal gyrus and IFG, those areas manifested a loss of semantic selectivity during NREM sleep. Our results suggest that the decreased awareness to linguistic auditory stimuli during NREM sleep is linked to diminished activity in high order processing stations.

In addition to the typical motor symptoms, a majority of patients suffering from Parkinson's disease experience language impairments. Deep Brain Stimulation of the subthalamic nucleus robustly reduces motor dysfunction, but its impact on language skills remains ambiguous.

This longitudinal study tracked the neuro-cognitive changes associated with second language (L2) grammar learning in adults in order to investigate how L2 processing is shaped by a learner's first language (L1) background and L2 proficiency. Previous studies using event-related potentials (ERPs) have argued that late L2 learners cannot elicit a P600 in response to L2 grammatical structures that do not exist in the L1 or that are different in the L1 and L2. We tested whether the neuro-cognitive processes underlying this component become available after intensive L2 instruction. Korean- and Chinese late-L2-learners of English were tested at the beginning and end of a 9-week intensive English-L2 course. ERPs were recorded while participants read English sentences containing violations of regular past tense (a grammatical structure that operates differently in Korean and does not exist in Chinese). Whereas no P600 effects were present at the start of instruction, by the end of instruction, significant P600s were observed for both L1 groups. Latency differences in the P600 exhibited by Chinese and Korean speakers may be attributed to differences in L1-L2 reading strategies. Across all participants, larger P600 effects at session 2 were associated with: 1) higher levels of behavioural performance on an online grammaticality judgment task; and 2) with correct, rather than incorrect, behavioural responses. These findings suggest that the neuro-cognitive processes underlying the P600 (e.g., "grammaticalization") are modulated by individual levels of L2 behavioural performance and learning.

Automatically inferring user demographics from social media posts is useful for both social science research and a range of downstream applications in marketing and politics. We present the first extensive study where user behaviour on Twitter is used to build a predictive model of income. We apply non-linear methods for regression, i.e. Gaussian Processes, achieving strong correlation between predicted and actual user income. This allows us to shed light on the factors that characterise income on Twitter and analyse their interplay with user emotions and sentiment, perceived psycho-demographics and language use expressed through the topics of their posts. Our analysis uncovers correlations between different feature categories and income, some of which reflect common belief e.g. higher perceived education and intelligence indicates higher earnings, known differences e.g. gender and age differences, however, others show novel findings e.g. higher income users express more fear and anger, whereas lower income users express more of the time emotion and opinions.

Rolandic epilepsy (RE) is a childhood epilepsy with centrotemporal (rolandic) spikes, that is increasingly associated with language impairment. In this study, we tested for a white matter (connectivity) correlate, employing diffusion weighted MRI and language testing.