Search Results

Display Omitted

Many approaches in biomedical informatics (BMI) rely on the ability to define, gather, and manipulate biomedical data to support health through a cyclical research-practice lifecycle. Researchers within this field are often fortunate to work ...

We aimed to investigate how errors from automatic speech recognition (ASR) systems affect dementia classification accuracy, specifically in the “Cookie Theft” picture description task. We aimed to assess whether imperfect ASR-...

Display Omitted

• Post-editing methods can enhance Automatic speech recognition (ASR) performance.
• ASR errors can provide important information for downstream dementia classification.
• Our error analysis provides new insights into linguistic ...

Speech-based diaries from mobile phones can capture paralinguistic patterns that help detect mental illness symptoms such as suicidal ideation. However, previous studies have primarily evaluated machine learning models on a single dataset, making their ...

The complex linguistic structures and specialized terminology of expert-authored content limit the accessibility of biomedical literature to the general public. Automated methods have the potential to render this literature more interpretable to ...

Display Omitted

• Problem: Automated lay summary generation can improve the accessibility of health information, but is challenging because of the need to provide background information absent in source documents.
• What is already known: Current models ...

Mobile phone sensing is increasingly being used in clinical research studies to assess a variety of mental health conditions (e.g., depression, psychosis). However, in-the-wild speech analysis -- beyond conversation detecting -- is a missing component of ...

Display Omitted

Online health communities (OHCs) have emerged as prominent platforms for behavior modification, and the digitization of online peer interactions has afforded researchers with unique opportunities to model multilevel mechanisms that ...

Display Omitted

• Quantifying coherence in speech identifies formal thought disorder automatically.

Formal thought disorder (ThD) is a clinical sign of schizophrenia amongst other serious mental health conditions. ThD can be recognized by observing incoherent speech - speech in which it is difficult to perceive connections between ...

In the decade since 2010, successes in artificial intelligence have been at the forefront of computer science and technology, and vector space models have solidified a position at the forefront of artificial intelligence. At the same time, quantum ...

Display Omitted

• Distributed representations (embeddings) are derived from ADE report data.
• ...

Adverse Drug Events (ADEs) are prevalent, costly, and sometimes preventable. Post-marketing drug surveillance aims to monitor ADEs that occur after a drug is released to market. Reports of such ADEs are aggregated by reporting systems, ...

Display Omitted

• Drug safety research asks causal questions but must rely on observational data.

Drug safety research asks causal questions but relies on observational data. Confounding bias threatens the reliability of studies using such data. The successful control of confounding requires knowledge of ...

Display Omitted

• Compare relational and attributional similarity to find drugs that target genes.

Display Omitted We develop a neural-probabilistic approach to represent semantic predications.This is compared to a prior representational approach across a number of tasks.Application areas are pharmacovigilance and drug repurposing.The neural-...

Display Omitted TopicalMeSH representation combines information from topic models and MeSH terms.TopicalMeSH has better document retrieval performance than MeSH.TopicalMeSH has better classification performance than MeSH and several alternatives. ...

Display Omitted We evaluate PSI-based identification of relationships between drugs and ADRs.PSI can incorporate relations and concepts and infer reasoning pathways.PSI is more predictive than a co-occurrence based model.Reasoning pathways suggest ...

Enormous advances in information technology have permeated essentially all facets of life in the past two decades. Formidable challenges remain in fostering tools that enhance productivity but are sensitive to work practices. Cognitive Informatics (CI) ...

This paper explores a new technique for encoding structured information into a semantic model, for the construction of vector representations of words and sentences. As an illustrative application, we use this technique to compose robust representations ...

Online social networks as behavior change support systems have been rapidly gaining in popularity. These networks have been studied by public health specialists from the point of view of traditional behavior change theories. However, scant research ...

Objective: Information in critical care environments is distributed across multiple sources, such as paper charts, electronic records, and support personnel. For decision-making tasks, physicians have to seek, gather, filter and organize information ...

Graphical abstractDisplay Omitted Highlights Innovative tool to access cognitive reasoning and decision-making was developed. Avatar-based assessment tool developed to train physicians to diagnose MDD and PTSD. Assessed diagnostic and management ...

Graphical abstractDisplay Omitted Highlights PSI represents concepts and relations in hyperdimensional space. PSI is used to infer discovery patterns from known therapeutic relationships. These patterns are used to recover therapeutic relationships for ...