Dataset Information

DeepTag: inferring diagnoses from veterinary clinical notes.

ABSTRACT: Large scale veterinary clinical records can become a powerful resource for patient care and research. However, clinicians lack the time and resource to annotate patient records with standard medical diagnostic codes and most veterinary visits are captured in free-text notes. The lack of standard coding makes it challenging to use the clinical data to improve patient care. It is also a major impediment to cross-species translational research, which relies on the ability to accurately identify patient cohorts with specific diagnostic criteria in humans and animals. In order to reduce the coding burden for veterinary clinical practice and aid translational research, we have developed a deep learning algorithm, DeepTag, which automatically infers diagnostic codes from veterinary free-text notes. DeepTag is trained on a newly curated dataset of 112,558 veterinary notes manually annotated by experts. DeepTag extends multitask LSTM with an improved hierarchical objective that captures the semantic structures between diseases. To foster human-machine collaboration, DeepTag also learns to abstain in examples when it is uncertain and defers them to human experts, resulting in improved performance. DeepTag accurately infers disease codes from free-text even in challenging cross-hospital settings where the text comes from different clinical settings than the ones used for training. It enables automated disease annotation across a broad range of clinical diagnoses with minimal preprocessing. The technical framework in this work can be applied in other medical domains that currently lack medical coding resources.

SUBMITTER: Nie A

PROVIDER: S-EPMC6550285 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

DeepTag: inferring diagnoses from veterinary clinical notes.

Nie Allen A Zehnder Ashley A Page Rodney L RL Zhang Yuhui Y Pineda Arturo Lopez AL Rivas Manuel A MA Bustamante Carlos D CD Zou James J

NPJ digital medicine 20181024

Large scale veterinary clinical records can become a powerful resource for patient care and research. However, clinicians lack the time and resource to annotate patient records with standard medical diagnostic codes and most veterinary visits are captured in free-text notes. The lack of standard coding makes it challenging to use the clinical data to improve patient care. It is also a major impediment to cross-species translational research, which relies on the ability to accurately identify pat ...[more]

PMID: 31304339

Similar Datasets

Project description:BackgroundDeep 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.ResultsMetaMap 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%.ConclusionsThe 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.

Project description:BackgroundEosinophilia is associated with various conditions, including allergic, infectious, and neoplastic disorders. The diagnostic differential is broad, and data on hypereosinophilia in pediatric patients are limited.ObjectiveThe objectives of this study were to identify cases of hypereosinophilia in a tertiary pediatric medical center, determine clinical characteristics and disease associations, and estimate the incidence of hypereosinophilia in the hospital and geographic populations.MethodsA retrospective chart review included patients younger than 18 years presenting to a tertiary pediatric medical center (January 1, 2008, to May 31, 2017) with absolute eosinophil counts (AECs) greater than or equal to 1.50 thousand eosinophils/microliter (K/μL) recorded on at least 2 occasions at least 4 weeks apart (N = 176). Clinical characteristics, laboratory values, treatment course, and associated diagnoses were evaluated.ResultsThe most common cause of hypereosinophilia in this cohort was secondary hypereosinophilia. Atopic dermatitis, graft-versus-host disease, sickle cell disease, and parasitic infections were the most common conditions associated with hypereosinophilia. Median age at diagnosis was 4.6 (interquartile range, 1.5-10.5) years. Median peak AEC was 3.16 (2.46-4.78) K/μL. Hypereosinophilia occurred most frequently in patients aged between 6 and 11 years (24.4%) and younger than 1 year (18.2%). Patients with neoplasms and immune deficiencies had significantly higher peak AECs than did patients with overlap hypereosinophilic syndrome and atopic diseases (P < .0001).ConclusionsPediatric hypereosinophilia has an incidence of 54.4 per 100,000 persons per year, with children younger than 1 year and aged 6 to 11 years accounting for most affected patients. Pediatric hypereosinophilia is not uncommon and remains underrecognized, highlighting a need for clinicians to identify patients who meet criteria for hypereosinophilia and to pursue a thorough evaluation.

Project description:ObjectivesWhen air irrigation is used for caloric stimulation in patients with a perforated ear, warm irrigation may elicit a nystagmus that initially beats in the opposite direction of what is expected for warm irrigations, which is referred to as "caloric inversion". This study aimed to investigate the disease group in which caloric inversion appeared in patients who underwent caloric testing and to classify the patterns of caloric inversion.MethodsWe conducted a retrospective review of bithermal caloric test results that were collected in our dizziness clinic between 2005 and 2022. Caloric inversion was defined when nystagmus induced by caloric stimulation appeared in the opposite direction to that expected. The incidence of caloric inversion among all patients who underwent bithermal caloric tests was calculated. To confirm the clinical diagnoses of the patients with caloric inversion, their clinical records were reviewed.ResultsOut of 9923 patients who underwent bithermal caloric tests, 29 patients (0.29%) showed a caloric inversion. The most common clinical diagnosis was chronic otitis media (21 of 29, 72%). Of the 21 patients with chronic otitis media, 20 patients showed a caloric inversion by warm air irrigation and one patient showed caloric inversion by cold air stimulation. Patients with clinical diagnoses other than chronic otitis media such as sudden sensorineural hearing loss, benign paroxysmal vertigo of childhood and recurrent vestibulopathy showed caloric inversion by warm air irrigation. Caloric inversion by warm water irrigation was observed in patients with lateral semicircular canal cupulopathy and recurrent vestibulopathy. Two patients (one with Meniere's disease and one with age-related dizziness) showed caloric inversion by cold water irrigation.ConclusionCaloric inversion can be observed in various diseases other than chronic otitis media with tympanic membrane perforation. Special care should be taken in the interpretation of caloric test results.Level of evidenceLevel 4.

Dataset Information

DeepTag: inferring diagnoses from veterinary clinical notes.

Publications

DeepTag: inferring diagnoses from veterinary clinical notes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets