Detecting false-positive disease references in veterinary clinical notes without manual annotations

Kennedy, Noel; Brodbelt, David; Church, David; O’Neill, Dan G.

doi:10.1038/s41746-019-0108-y

Cited by 6 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to the 3,998 dogs in the earlier report, the larger sample size of 22,333 dogs in the current study offers greater current precision. In addition, the methods used to extract disorder data from the clinical records have also advanced considerably during the intervening years [ 47 ], meaning that the current study was more highly powered and technologically enabled than the previous study. The ranking of the most common disorders in the current study that relied on veterinary clinical records differs substantially to results based on other data resources.…”

Section: Discussionmentioning

confidence: 99%

Prevalence of commonly diagnosed disorders in UK dogs under primary veterinary care: results and applications

et al. 2021

Self Cite

View full text Add to dashboard Cite

Background Although dogs are a commonly owned companion animal in the UK, the species experiences many health problems that are predictable from demographic information. This study aimed to use anonymised veterinary clinical data from the VetCompass™ Programme to report the frequency of common disorders of dogs under primary veterinary care in the UK during 2016 and to explore effects associated with age, sex and neuter status. Results From an available population of 905,543 dogs under veterinary care at 886 veterinary clinics during 2016, the current study included a random sample of 22,333 (2.47 %) dogs from 784 clinics. Prevalence for each disorder was calculated at the most refined level of diagnostic certainty (precise-level precision) and after grouping to a more general level of diagnostic precision (grouped-level precision). The most prevalent precise-level precision disorders recorded were periodontal disease (prevalence 12.52 %, 95 % CI: 12.09–12.97), otitis externa (7.30 %, 95 % CI: 6.97–7.65) and obesity (7.07 %, 95 % CI: 6.74–7.42). The most prevalent grouped-level disorders were dental disorder (14.10 %, 95 % CI: 13.64–14.56), skin disorder (12.58 %, 95 % CI: 12.15–13.02) and enteropathy (10.43 %, 95 % CI: 10.04–10.84). Associations were identified for many common disorders with age, sex and neuter. Conclusions The overall findings can assist veterinarians and owners to prioritise preventive care and to understand demographic risk factors in order to facilitate earlier diagnosis of common disorders in dogs. The information on associations with age, sex and neuter status provides additional contextual background to the complexity of disorder occurrence and supports targeted health controls for demographic subsets of dogs.

show abstract

Section: Discussionmentioning

confidence: 99%

Prevalence of commonly diagnosed disorders in UK dogs under primary veterinary care: results and applications

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…As discussed previously, presenting signs where more than one was listed were reported as the first given, which might have affected the data due to linguistic biases. Novel methods of diagnosis coding based on natural language processing recently developed by VetCompass might provide a solution to these problems in the future 93 .…”

Section: Limitationsmentioning

confidence: 99%

Disorder predispositions and protections of Labrador Retrievers in the UK

Pegram

Woolley

Brodbelt

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

The Labrador Retriever is one of the most popular dog breeds worldwide, therefore it is important to have reliable evidence on the general health issues of the breed. Using anonymised veterinary clinical data from the VetCompass Programme, this study aimed to explore the relative risk to common disorders in the Labrador Retriever. The clinical records of a random sample of dogs were reviewed to extract the most definitive diagnoses for all disorders recorded during 2016. A list of disorders was generated, including the 30 most common disorders in Labrador Retrievers and the 30 most common disorders in non-Labrador Retrievers. Multivariable logistic regression was used to report the odds of each of these disorders in 1462 (6.6%) Labrador Retrievers compared with 20,786 (93.4%) non-Labrador Retrievers. At a specific-level of diagnostic precision, after accounting for confounding, Labrador Retrievers had significantly increased odds of 12/35 (34.3%) disorders compared to non-Labrador Retrievers; osteoarthritis (OR 2.83) had the highest odds. Conversely, Labrador Retrievers had reduced odds of 7/35 (20.0%) disorders; patellar luxation (OR 0.18) had the lowest odds. This study provides useful information about breed-specific disorder predispositions and protections, which future research could evaluate further to produce definitive guidance for Labrador Retriever breeders and owners.

show abstract

“…Clinical features in this study were extracted through manual revision of the clinical notes, restricting the sample size. Future work for feature extraction using natural language processing methods or classification of clinical features could be beneficial for the clinical application of such predictive algorithms to optimise the analysis of large datasets, like VetCompass 39 . Due to the retrospective collection of the data, there is a possibility of feature misclassification and an introduction of noise, which could have diluted some predictive effects.…”

Section: Discussionmentioning

confidence: 99%

Machine-learning based prediction of Cushing’s syndrome in dogs attending UK primary-care veterinary practice

Schofield

Brodbelt

Kennedy

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

Cushing’s syndrome is an endocrine disease in dogs that negatively impacts upon the quality-of-life of affected animals. Cushing’s syndrome can be a challenging diagnosis to confirm, therefore new methods to aid diagnosis are warranted. Four machine-learning algorithms were applied to predict a future diagnosis of Cushing's syndrome, using structured clinical data from the VetCompass programme in the UK. Dogs suspected of having Cushing's syndrome were included in the analysis and classified based on their final reported diagnosis within their clinical records. Demographic and clinical features available at the point of first suspicion by the attending veterinarian were included within the models. The machine-learning methods were able to classify the recorded Cushing’s syndrome diagnoses, with good predictive performance. The LASSO penalised regression model indicated the best overall performance when applied to the test set with an AUROC = 0.85 (95% CI 0.80–0.89), sensitivity = 0.71, specificity = 0.82, PPV = 0.75 and NPV = 0.78. The findings of our study indicate that machine-learning methods could predict the future diagnosis of a practicing veterinarian. New approaches using these methods could support clinical decision-making and contribute to improved diagnosis of Cushing’s syndrome in dogs.

show abstract

Detecting false-positive disease references in veterinary clinical notes without manual annotations

Cited by 6 publications

References 21 publications

Prevalence of commonly diagnosed disorders in UK dogs under primary veterinary care: results and applications

Prevalence of commonly diagnosed disorders in UK dogs under primary veterinary care: results and applications

Disorder predispositions and protections of Labrador Retrievers in the UK

Machine-learning based prediction of Cushing’s syndrome in dogs attending UK primary-care veterinary practice

Contact Info

Product

Resources

About