Craig, J. J. | bioRxiv Science

bioRxiv2025

Validation of deep learning enabled software MetronMind to measure vertebral heart size and vertebral left atrial size in dogs

Vertebral heart size (VHS) and vertebral left atrial size (VLAS) are objective radiographic measurements of heart and left atrial size respectively and are associated with inter and intraobserver variability when measured by humans. Artificial intelligence (AI) tools to determine VHS and VLAS have been developed which may reduce variability and save time. Two manual methods for measuring VHS and VLAS on right and left lateral canine thoracic radiographs were compared. Measurements of VHS and VLAS made by deep learning enabled program, MetronMind, were compared to a trained observer on right and left lateral radiographs from 1058 client-owned dogs including 80 breeds with a variety of heart sizes, thoracic conformations and radiographic quality. This was a retrospective, single center, method comparison study. Pearsons correlation, Bland-Altman plots and Passing-Bablok regression were used to assess agreement. Correlation between traditional and modified manual measurements for VHS and VLAS were strong (r=0.994 and r=0.974 respectively), with minimal bias (-0.10 and 0.04 vertebrae respectively) indicating that the modified methods closely approximate traditional measurements obtained from right lateral views. MetronMind measurements of VHS and VLAS from right lateral radiographs correlated well with the human observers modified measurements (r=0.947 and r=0.811 respectively), showing small mean biases (0.08 and 0.07 vertebrae respectively). Correlation between left and right lateral radiographic measurements of VHS (0.87 and 0.91) was higher than for VLAS (0.73 and 0.64) and bias was larger for VHS (0.26 and 0.31 vertebrae) than VLAS (-0.13 and -0.10 vertebrae) for humans and MetronMind respectively. MetronMind can therefore assist veterinarians with measuring VHS and VLAS in dogs and right lateral radiographs are preferred. Future studies are needed to compare artificial intelligence derived radiographic measures with echocardiographic measures of cardiac size.

physiology↗

bioRxiv2025

Predicting Drug Response with Multi-Task Gradient-Boosted Trees in Epilepsy

MotivationDespite the availability of numerous anti-seizure medications (ASMs), drug resistance remains a major issue for people with epilepsy. The probability of achieving seizure freedom diminishes with each unsuccessful drug trial, and the impact of genetic and clinical markers on ASM response remains unclear. To address this issue, we used state-of-the-art machine learning (ML) methods to predict the response of people with epilepsy to individual ASMs based on their clinical and genomic information. ResultsTo overcome data sparsity for less common drugs, we implement a multi-task (MT) learning approach for gradient-boosted trees (GBTs), assuming that predicting responses to different ASMs involves similar tasks. This strategy allows models for less prevalent drugs to leverage the more abundant data available for other drugs during training. The proposed model outperforms individual and combined drug-response predictions for most drugs. Our findings identify key genomic and clinical features influencing drug response, enhancing understanding of individual drug responses in people with epilepsy, and aiding clinicians in making informed treatment decisions. Availability and ImplementationDue to privacy reasons data is not publically available. The code will be made available upon acceptance under https://github.com/pfeiferAI/MT-GBT

bioinformatics↗