Explore the vast range of titles available.

Unstructured clinical narratives are continuously being recorded as part of delivery of care in electronic health records, and dedicated tagging staff spend considerable effort manually assigning clinical codes for billing purposes. Despite these efforts, however, label availability and accuracy are both suboptimal. In this retrospective study, we aimed to automate the assignment of top-level International Classification of Diseases version 9 (ICD-9) codes to clinical records from human and veterinary data stores using minimal manual labor and feature curation. Automating top-level annotations could in turn enable rapid cohort identification, especially in a veterinary setting. To this end, we trained long short-term memory (LSTM) recurrent neural networks (RNNs) on 52,722 human and 89,591 veterinary records. We investigated the accuracy of both separate-domain and combined-domain models and probed model portability. We established relevant baseline classification performances by training Decision Trees (DT) and Random Forests (RF). We also investigated whether transforming the data using MetaMap Lite, a clinical natural language processing tool, affected classification performance. We showed that the LSTM-RNNs accurately classify veterinary and human text narratives into top-level categories with an average weighted macro F1 score of 0.74 and 0.68 respectively. In the \"neoplasia\" category, the model trained on veterinary data had a high validation accuracy in veterinary data and moderate accuracy in human data, with F1 scores of 0.91 and 0.70 respectively. Our LSTM method scored slightly higher than that of the DT and RF models. The use of LSTM-RNN models represents a scalable structure that could prove useful in cohort identification for comparative oncology studies. Digitization of human and veterinary health information will continue to be a reality, particularly in the form of unstructured narratives. Our approach is a step forward for these two domains to learn from and inform one another.

Inbreeding depression has been demonstrated to impact vital rates, productivity, and performance in human populations, wild and endangered species, and in recent years, the domestic species. In all cases, standardized, high-quality phenotype data on all individuals are invaluable for longitudinal analyses such as those required to evaluate vital rates of a study cohort. Further, many investigators agree upon the preference for and utility of genomic measures of inbreeding in lieu of pedigree-based estimates of inbreeding. We evaluated the association of measures of reproductive fitness in 93 Golden Retrievers enrolled in the Golden Retriever Lifetime Study with a genomic measurement of inbreeding, FROH. We demonstrate a statistically significant negative correlation between fecundity and FROH. This work sets the stage for larger scale analyses to investigate genomic regions associated with fecundity and other measures of fitness.

Unlike human medical records, most of the veterinary records are free text without standard diagnosis coding. The lack of systematic coding is a major barrier to the growing interest in leveraging veterinary records for public health and translational research. Recent machine learning effort is limited to predicting 42 top-level diagnosis categories from veterinary notes. Here we develop a large-scale algorithm to automatically predict all 4577 standard veterinary diagnosis codes from free text. We train our algorithm on a curated dataset of over 100 K expert labeled veterinary notes and over one million unlabeled notes. Our algorithm is based on the adapted Transformer architecture and we demonstrate that large-scale language modeling on the unlabeled notes via pretraining and as an auxiliary objective during supervised learning greatly improves performance. We systematically evaluate the performance of the model and several baselines in challenging settings where algorithms trained on one hospital are evaluated in a different hospital with substantial domain shift. In addition, we show that hierarchical training can address severe data imbalances for fine-grained diagnosis with a few training cases, and we provide interpretation for what is learned by the deep network. Our algorithm addresses an important challenge in veterinary medicine, and our model and experiments add insights into the power of unsupervised learning for clinical natural language processing.

The Golden Retriever Lifetime Study (GRLS) is the first prospective longitudinal study attempted in veterinary medicine to identify the major dietary, genetic and environmental risk factors for cancer and other important diseases in dogs. The GRLS is an observational study that will follow a cohort of 3000 purebred Golden Retrievers throughout their lives via annual online questionnaires from the dog owner and annual physical examinations and collection of biological samples by the primary care veterinarian. The field of comparative medicine investigating naturally occurring disorders in pets is specifically relevant to the many diseases that have a genetic basis for disease in both animals and humans, including cancer, blindness, metabolic and behavioural disorders and some neurodegenerative disorders. The opportunity for the GRLS to provide high-quality data for translational comparative medical initiatives in several disease categories is great. In particular, the opportunity to develop a lifetime dataset of lifestyle and activity, environmental exposure and diet history combined with simultaneous annual biological sample sets and detailed health outcomes will provide disease incidence data for this cohort of geographically dispersed dogs and associations with a wide variety of potential risk factors. The GRLS will provide a lifetime historical context, repeated biological sample sets and outcomes necessary to interrogate complex associations between genes and environmental influences and cancer.

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.

Purpose Calcitriol potentiates cisplatin-mediated activity in a variety of tumor models. We examine here, the effect of calcitriol and cisplatin pre-clinically and clinically in canine spontaneous tumors through in vitro studies on tumor cells and through a phase I study of calcitriol and cisplatin to identify the maximum-tolerated dosage (MTD) of this combination in dogs with cancer and to characterize the pharmacokinetic disposition of calcitriol in dogs. Methods Canine tumor cells were investigated for calcitriol/cisplatin interactions on proliferation using an MTT assay in a median-dose effect analysis; data were used to derive a combination index (CI). Cisplatin was given at a fixed dosage of 60 mg/m 2 . Calcitriol was given i.v. and the dosage was escalated in cohorts of three dogs until the MTD was defined. Serum calcitriol concentrations were quantified by radioimmunoassay. Results In vitro, CIs < 1.0 were obtained for all combinations of calcitriol/cisplatin examined. The MTD was 3.75 μg/kg calcitriol in combination with cisplatin, and hypercalcemia was the dose-limiting toxicosis. The relationship between calcitriol dosage and either C max or AUC was linear. Calcitriol dosages >1.5 μg/kg achieved C max  ≥ 9.8 ng/mL and dosages >1.0 μg/kg achieved AUC ≥ 45 h ng/mL. Conclusions Calcitriol and cisplatin have synergistic antiproliferative effects on multiple canine tumor cells and high-dosages of i.v. calcitriol in combination with cisplatin can be safely administered to dogs. C max and AUC at the MTD 3.75 μg/kg calcitriol exceed concentrations associated with antitumor activity in a murine model, indicating this combination might have significant clinical utility in dogs.

The Golden Retriever Lifetime Study (GRLS) is the first prospective longitudinal study attempted in veterinary medicine to identify the major dietary, genetic and environmental risk factors for cancer and other important diseases in dogs. The GRLS is an observational study that will follow a cohort of 3000 purebred Golden Retrievers throughout their lives via annual online questionnaires from the dog owner and annual physical examinations and collection of biological samples by the primary care veterinarian. The field of comparative medicine investigating naturally occurring disorders in pets is specifically relevant to the many diseases that have a genetic basis for disease in both animals and humans, including cancer, blindness, metabolic and behavioural disorders and some neurodegenerative disorders. The opportunity for the GRLS to provide high-quality data for translational comparative medical initiatives in several disease categories is great. In particular, the opportunity to develop a lifetime dataset of lifestyle and activity, environmental exposure and diet history combined with simultaneous annual biological sample sets and detailed health outcomes will provide disease incidence data for this cohort of geographically dispersed dogs and associations with a wide variety of potential risk factors. The GRLS will provide a lifetime historical context, repeated biological sample sets and outcomes necessary to interrogate complex associations between genes and environmental influences and cancer.

Objective: Unstructured clinical narratives are continuously being recorded as part of delivery of care in electronic health records, and dedicated tagging staff spend considerable effort manually assigning clinical codes for billing purposes; despite these efforts, label availability and accuracy are both suboptimal. Materials and Methods: In this retrospective study, we trained long short-term memory (LSTM) recurrent neural networks (RNNs) on 52,722 human and 89,591 veterinary records. We investigated the accuracy of both separate-domain and combined-domain models and probed model portability. We established relevant baselines by training Decision Trees (DT) and Random Forests (RF), and using MetaMap Lite, a clinical natural language processing tool. Results: We show that the LSTM-RNNs accurately classify veterinary and human text narratives into top-level categories with an average weighted macro F1 score of 0.74 and 0.68 respectively. In the \"neoplasia\" category, the model built with veterinary data has a high accuracy in veterinary data, and moderate accuracy in human data, with F1 scores of 0.91 and 0.70 respectively. Our LSTM method scored slightly higher than that of the DT and RF models. Discussion: The use of LSTM-RNN models represents a scalable structure that could prove useful in cohort identification for comparative oncology studies. Conclusion: Digitization of human and veterinary health information will continue to be a reality, particularly in the form of unstructured narratives. Our approach is a step forward for these two domains to learn from, and inform, one another. Footnotes * This revised version has updated descriptions and focuses on comparative oncology.

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 multi-task 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 pre-processing. The technical framework in this work can be applied in other medical domains that currently lack medical coding resources.

Inbreeding depression has been demonstrated to impact vital rates, productivity, and performance in many domestic species. Many in the field have demonstrated the value of genomic measures of inbreeding compared to pedigree-based estimates of inbreeding; further, standardized, high-quality phenotype data on all individuals is invaluable for longitudinal analyses of a study cohort. We compared measures of reproductive fitness in a small cohort of Golden Retrievers enrolled in the Golden Retriever Lifetime Study (GRLS) to a genomic measurement of inbreeding, FROH. We demonstrate a statistically significant negative correlation between fecundity and FROH. This work sets the stage for larger scale analyses to investigate genomic regions associated with fecundity and other measures of fitness.