RESUMEN
BACKGROUND: How to treat a disease remains to be the most common type of clinical question. Obtaining evidence-based answers from biomedical literature is difficult. Analogical reasoning with embeddings from deep learning (embedding analogies) may extract such biomedical facts, although the state-of-the-art focuses on pair-based proportional (pairwise) analogies such as man:woman::king:queen ("queen = -man +king +woman"). OBJECTIVE: This study aimed to systematically extract disease treatment statements with a Semantic Deep Learning (SemDeep) approach underpinned by prior knowledge and another type of 4-term analogy (other than pairwise). METHODS: As preliminaries, we investigated Continuous Bag-of-Words (CBOW) embedding analogies in a common-English corpus with five lines of text and observed a type of 4-term analogy (not pairwise) applying the 3CosAdd formula and relating the semantic fields person and death: "dagger = -Romeo +die +died" (search query: -Romeo +die +died). Our SemDeep approach worked with pre-existing items of knowledge (what is known) to make inferences sanctioned by a 4-term analogy (search query -x +z1 +z2) from CBOW and Skip-gram embeddings created with a PubMed systematic reviews subset (PMSB dataset). Stage1: Knowledge acquisition. Obtaining a set of terms, candidate y, from embeddings using vector arithmetic. Some n-gram pairs from the cosine and validated with evidence (prior knowledge) are the input for the 3cosAdd, seeking a type of 4-term analogy relating the semantic fields disease and treatment. Stage 2: Knowledge organization. Identification of candidates sanctioned by the analogy belonging to the semantic field treatment and mapping these candidates to unified medical language system Metathesaurus concepts with MetaMap. A concept pair is a brief disease treatment statement (biomedical fact). Stage 3: Knowledge validation. An evidence-based evaluation followed by human validation of biomedical facts potentially useful for clinicians. RESULTS: We obtained 5352 n-gram pairs from 446 search queries by applying the 3CosAdd. The microaveraging performance of MetaMap for candidate y belonging to the semantic field treatment was F-measure=80.00% (precision=77.00%, recall=83.25%). We developed an empirical heuristic with some predictive power for clinical winners, that is, search queries bringing candidate y with evidence of a therapeutic intent for target disease x. The search queries -asthma +inhaled_corticosteroids +inhaled_corticosteroid and -epilepsy +valproate +antiepileptic_drug were clinical winners, finding eight evidence-based beneficial treatments. CONCLUSIONS: Extracting treatments with therapeutic intent by analogical reasoning from embeddings (423K n-grams from the PMSB dataset) is an ambitious goal. Our SemDeep approach is knowledge-based, underpinned by embedding analogies that exploit prior knowledge. Biomedical facts from embedding analogies (4-term type, not pairwise) are potentially useful for clinicians. The heuristic offers a practical way to discover beneficial treatments for well-known diseases. Learning from deep learning models does not require a massive amount of data. Embedding analogies are not limited to pairwise analogies; hence, analogical reasoning with embeddings is underexploited.
RESUMEN
BACKGROUND: Deep Learning opens up opportunities for routinely scanning large bodies of biomedical literature and clinical narratives to represent the meaning of biomedical and clinical terms. However, the validation and integration of this knowledge on a scale requires cross checking with ground truths (i.e. evidence-based resources) that are unavailable in an actionable or computable form. In this paper we explore how to turn information about diagnoses, prognoses, therapies and other clinical concepts into computable knowledge using free-text data about human and animal health. We used a Semantic Deep Learning approach that combines the Semantic Web technologies and Deep Learning to acquire and validate knowledge about 11 well-known medical conditions mined from two sets of unstructured free-text data: 300 K PubMed Systematic Review articles (the PMSB dataset) and 2.5 M veterinary clinical notes (the VetCN dataset). For each target condition we obtained 20 related clinical concepts using two deep learning methods applied separately on the two datasets, resulting in 880 term pairs (target term, candidate term). Each concept, represented by an n-gram, is mapped to UMLS using MetaMap; we also developed a bespoke method for mapping short forms (e.g. abbreviations and acronyms). Existing ontologies were used to formally represent associations. We also create ontological modules and illustrate how the extracted knowledge can be queried. The evaluation was performed using the content within BMJ Best Practice. RESULTS: MetaMap achieves an F measure of 88% (precision 85%, recall 91%) when applied directly to the total of 613 unique candidate terms for the 880 term pairs. When the processing of short forms is included, MetaMap achieves an F measure of 94% (precision 92%, recall 96%). Validation of the term pairs with BMJ Best Practice yields precision between 98 and 99%. CONCLUSIONS: The Semantic Deep Learning approach can transform neural embeddings built from unstructured free-text data into reliable and reusable One Health knowledge using ontologies and content from BMJ Best Practice.
Asunto(s)
Aprendizaje Profundo , Bases del Conocimiento , Salud Única , PubMed , Semántica , Revisiones Sistemáticas como Asunto , Veterinarios , Ontologías BiológicasRESUMEN
We investigate the application of distributional semantics models for facilitating unsupervised extraction of biomedical terms from unannotated corpora. Term extraction is used as the first step of an ontology learning process that aims to (semi-)automatic annotation of biomedical concepts and relations from more than 300K PubMed titles and abstracts. We experimented with both traditional distributional semantics methods such as Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA) as well as the neural language models CBOW and Skip-gram from Deep Learning. The evaluation conducted concentrates on sepsis, a major life-threatening condition, and shows that Deep Learning models outperform LSA and LDA with much higher precision.
Asunto(s)
Aprendizaje Automático , PubMed , Semántica , Sepsis , Humanos , Almacenamiento y Recuperación de la Información , Procesamiento de Lenguaje NaturalRESUMEN
INTRODUCTION: Tolerability and convenience are crucial aspects for the long-term success of combined antiretroviral therapy (cART). The aim of this study was to investigate the impact in routine clinical practice of switching to the single tablet regimen (STR) RPV/FTC/TDF in patients with intolerance to previous cART, in terms of patients' well-being, assessed by several validated measures. METHODS: Prospective, multicenter study. Adult HIV-infected patients with viral load under 1.000 copies/mL while receiving a stable ART for at least the last three months and switched to RPV/FTC/TDF due to intolerance of previous regimen, were included. Analyses were performed by ITT. Presence/magnitude of symptoms (ACTG-HIV Symptom Index), quality of life (EQ-5D, EUROQoL & MOS-HIV), adherence (SMAQ), preference of treatment and perceived ease of medication (ESTAR) through 48 weeks were performed. RESULTS: Interim analysis of 125 patients with 16 weeks of follow up was performed. 100 (80%) were male, mean age 46 years. Mean CD4 at baseline was 629.5±307.29 and 123 (98.4%) had viral load <50 copies/mL; 15% were HCV co-infected. Ninety two (73.6%) patients switched from a NNRTI (84.8% from EFV/FTC/TDF) and 33 (26.4%) from a PI/r. The most frequent reasons for switching were psychiatric disorders (51.2%), CNS adverse events (40.8%), gastrointestinal (19.2%) and metabolic disorders (19.2%). At the time of this analysis (week 16), four patients (3.2%) discontinued treatment: one due to adverse events, two virologic failures and one with no data. A total of 104 patients (83.2%) were virologically suppressed (<50 copies/mL). The average degree of discomfort in the ACTG-HIV Symptom Index significantly decreased from baseline (21±15.55) to week 4 (10.89±12.36) & week 16 (10.81±12.62), p<0.001. In all the patients, quality of life tools showed a significant benefit in well-being of the patients (Table 1). Adherence to therapy significantly and progressively increased (SMAQ) from baseline (54.4%) to week 4 (68%), p<0.001 and to week 16 (72.0%), p<0.001. CONCLUSIONS: Switching to RPV/FTC/TDF from another ARV regimen due to toxicity, significantly improved the quality of life of HIV-infected patients, both in mental and physical components, and improved adherence to therapy while maintaining a good immune and virological response.