I started my career as an engineer at Microsoft directly out of high school. I later went back to school and became a veterinarian where I learned about physiology, pathology, medicine, and surgery. Afterwards, I combined these experiences to complete a joint PhD in the fields of Natural Language Processing and Veterinary Epidemiology. My research interests fall within the fields of Natural Language Processing, Clinical Informatics and Machine Learning. I am more specifically interested in exploiting structured and unstructured data to help machines understand the treatments given, the reasons behind them and using this data to help clinicians, as done in my thesis focused on using ML/AI to inform Antimicrobial Stewardship Programs in Australia to combat Antibiotic Resistance.

News

• Our study Evaluating the dose, indication and agreement with guidelines of antimicrobial use in companion animal practice with natural language processing was published. In this study we used the data generated from the methods described in the paper presented at BioNLP to describe why antimicrobials are given, their dosages, and how they agree with the prescribing guidelines.
• Our Traitement Automatique des Langues (TAL) paper describes the methods we used for the National NLP Clinical Challenge shared task 3 on clinical concept normalization. In this study, we link entity mentions of clinical concepts in clinical documents to their corresponding standardized medical terminology. We were able to create the highest performing rules based method for the shared task and contrast its performance to using ClinicalBERT for the same task.
• Grant funding from Australian Research Data Commons for expansion of VetCompass Australia to develop the world’s first platform to gather data from veterinary hospitals and veterinary pathology labs on national scale. A major component of this project is building an infrastructure to enable the NLP models we created to be applied to help researchers around the world.
• Our Veterinary Record Paper describes the usage of Cefovecin in veterinary practices accross Australia. Cefovecin is a 3rd generation cephlasporin and crtically important antibiotic in terms of antibiotic resistance. We used our previous algorithms to generate the labels for this study and used this study to generate training data for our BioNLP paper.
• Antimicrobial Prescribing Guidelines made available online for veterinarians in Companion Animal Practice.
• Our paper for BioNLP @ ACL 2020 paper was published. In this paper we use instance selection and developed VetBERT to minimize the amount of labels required to train a model to classify the reason for an antimicrobial administration.

Selected Papers

• Wang, Yuxia, Brian Hur, Karin Verspoor and Timothy Baldwin (2021) A Multi-pass Sieve for Clinical Concept Normalization, Traitement Automatique des Langues 2020 Volume 61 Numéro 2.
• Hur, Brian, Timothy Baldwin, Karin Verspoor, Laura Hardefeldt and James Gilkerson (2020) Domain Adaptation and Instance Selection for Disease Syndrome Classification over Veterinary Clinical Notes, In Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing (BioNLP 2020), pp. 156—166.
• Hardefeldt, Laura Y, Brian Hur, Karin Verspoor, Timothy Baldwin, Kirsten E Bailey, Riata Scarborough, Suzanna Richards, Helen Bilman-Jacobe, Glenn F Browning and James R Gilkerson (2020) Use of cefovecin in dogs and cats attending first-opinion veterinary practices in Australia, Veterinary Record.
• Hur, Brian A., Laura Y. Hardefeldt, Karin M. Verspoor, Timothy Baldwin, and James R Gilkerson (2020) Describing the Antimicrobial Usage Patterns of Companion Animal Veterinary Practices; Free Text Analysis of more than 4.4 Million Consultation Records, PLoS ONE 15(3): e0230049.
• Brian Hur, Laura Y. Hardefeldt, Karin Verspoor, Timothy Baldwin and James R Gilkerson (2019) Using Natural Language Processing and VetCompass to understand antimicrobial usage patterns in Australia, Australian Veterinary Journal 97(8), pp. 298—300.