Domain Adaptation and Instance Selection for Disease Syndrome Classification over Veterinary Clinical Notes

Hur, Brian; Baldwin, Timothy; Verspoor, Karin; Hardefeldt, Laura Y.; Gilkerson, James R.

doi:10.18653/v1/2020.bionlp-1.17

Cited by 8 publications

(15 citation statements)

References 33 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Increased use of bacterial cultures and susceptibility testing is likely to improve the clinical outcomes while reducing the importance ratings of the antimicrobials used. While there were labels with culture and sensitivity annotated in the original corpus used to train the disease syndrome classifier, 17 , 47 there were not enough of these labels to train the model. Evaluation of the antimicrobial susceptibility of isolates obtained from canine urine cultures in Australia demonstrated that antimicrobial agents of lower critical importance could be selected without compromising efficacy, 48 but further work is required to incorporate clinical pathology data into VetCompass and evaluate this in a large scale dataset.…”

Section: Discussionmentioning

confidence: 99%

“…A model referred to as VetBERT was used to classify the indication for disease. 17 VetBERT was created using a model known as ClinicalBERT 28 as a base and then using additional pretraining steps as described by Devlin et al . 24 using the entire corpus of 15 million clinical notes from VetCompass Australia to provide a good representation of the veterinary clinical text.…”

Section: Methodsmentioning

confidence: 99%

“…Previous studies have evaluated frequency and types of antimicrobial usage patterns in the UK 14 , 15 and Australia. 16 , 17 Studies describing the reason for antimicrobial administration have relied on the indication recorded when an appointment was booked, 18 or on the reason submitted in a claim to the pet insurance company. 19 However, neither of these studies examined the reason for the antimicrobial use directly from the veterinarian’s clinical notes.…”

Section: Introductionmentioning

confidence: 99%

“…Recent work in this area has integrated representations based on generalized texts, such as Wikipedia, with specialized texts, such as clinical notes, in order to more effectively analyse medical records. 28 One such model, ‘VetBERT’, 17 has been developed specifically for the veterinary domain was pre-trained using data from VetCompass Australia and further trained to classify the indication for which an antimicrobial was given out of free-text clinical notes.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Evaluating the dose, indication and agreement with guidelines of antimicrobial use in companion animal practice with natural language processing

Hur

Hardefeldt

Verspoor

et al. 2022

JAC-Antimicrobial Resistance

Self Cite

View full text Add to dashboard Cite

Background As antimicrobial prescribers, veterinarians contribute to the emergence of MDR pathogens. Antimicrobial stewardship programmes are an effective means of reducing the rate of development of antimicrobial resistance. A key component of antimicrobial stewardship programmes is selecting an appropriate antimicrobial agent for the presenting complaint and using an appropriate dose rate for an appropriate duration. Objectives To describe antimicrobial usage, including dose, for common indications for antimicrobial use in companion animal practice. Methods Natural language processing (NLP) techniques were applied to extract and analyse clinical records. Results A total of 343 668 records for dogs and 109 719 records for cats administered systemic antimicrobials from 1 January 2013 to 31 December 2017 were extracted from the database. The NLP algorithms extracted dose, duration of therapy and diagnosis completely for 133 046 (39%) of the records for dogs and 40 841 records for cats (37%). The remaining records were missing one or more of these elements in the clinical data. The most common reason for antimicrobial administration was skin disorders (n = 66 198, 25%) and traumatic injuries (n = 15 932, 19%) in dogs and cats, respectively. Dose was consistent with guideline recommendations in 73% of cases where complete clinical data were available. Conclusions Automated extraction using NLP methods is a powerful tool to evaluate large datasets and to enable veterinarians to describe the reasons that antimicrobials are administered. However, this can only be determined when the data presented in the clinical record are complete, which was not the case in most instances in this dataset. Most importantly, the dose administered varied and was often not consistent with guideline recommendations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evaluating the dose, indication and agreement with guidelines of antimicrobial use in companion animal practice with natural language processing

Hur

Hardefeldt

Verspoor

et al. 2022

JAC-Antimicrobial Resistance

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ma et al (2019) used BERT for domain-discriminative data selection. Hur et al (2020) used BERT for domain adaptation and instance selection for disease classification. Our selection method is similar to these methods but focuses on selecting conversational-style sentences.…”

Section: Related Workmentioning

confidence: 99%

Accelerating Text Communication via Abbreviated Sentence Input

Adhikary¹,

Berger²,

Vertanen³

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Typing every character in a text message may require more time or effort than strictly necessary. Skipping spaces or other characters may be able to speed input and reduce a user's physical input effort. This can be particularly important for people with motor impairments. In a large crowdsourced study, we found workers frequently abbreviated text by omitting midword vowels. We designed a recognizer optimized for expanding noisy abbreviated input where users often omit spaces and mid-word vowels. We show using neural language models for selecting conversational-style training text and for rescoring the recognizer's n-best sentences improved accuracy. On noisy touchscreen data collected from hundreds of users, we found accurate abbreviated input was possible even if a third of characters was omitted. Finally, in a study where users had to dwell for a second on each key, sentence abbreviated input was competitive with a conventional keyboard with word predictions.

show abstract

PetBERT: automated ICD-11 syndromic disease coding for outbreak detection in first opinion veterinary electronic health records

Farrell,

Appleton,

Noble

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Effective public health surveillance requires consistent monitoring of disease signals such that researchers and decision-makers can react dynamically to changes in disease occurrence. However, whilst surveillance initiatives exist in production animal veterinary medicine, comparable frameworks for companion animals are lacking. First-opinion veterinary electronic health records (EHRs) have the potential to reveal disease signals and often represent the initial reporting of clinical syndromes in animals presenting for medical attention, highlighting their possible significance in early disease detection. Yet despite their availability, there are limitations surrounding their free text-based nature, inhibiting the ability for national-level mortality and morbidity statistics to occur. This paper presents PetBERT, a large language model trained on over 500 million words from 5.1 million EHRs across the UK. PetBERT-ICD is the additional training of PetBERT as a multi-label classifier for the automated coding of veterinary clinical EHRs with the International Classification of Disease 11 framework, achieving F1 scores exceeding 83% across 20 disease codings with minimal annotations. PetBERT-ICD effectively identifies disease outbreaks, outperforming current clinician-assigned point-of-care labelling strategies up to 3 weeks earlier. The potential for PetBERT-ICD to enhance disease surveillance in veterinary medicine represents a promising avenue for advancing animal health and improving public health outcomes.

show abstract

Domain Adaptation and Instance Selection for Disease Syndrome Classification over Veterinary Clinical Notes

Cited by 8 publications

References 33 publications

Evaluating the dose, indication and agreement with guidelines of antimicrobial use in companion animal practice with natural language processing

Evaluating the dose, indication and agreement with guidelines of antimicrobial use in companion animal practice with natural language processing

Accelerating Text Communication via Abbreviated Sentence Input

PetBERT: automated ICD-11 syndromic disease coding for outbreak detection in first opinion veterinary electronic health records

Contact Info

Product

Resources

About