Background In the rapidly evolving landscape of veterinary healthcare, integrating machine learning (ML) clinical decision-making tools with electronic health records (EHRs) promises to improve diagnostic accuracy and patient care. However, the seamless integration of ML classifiers into existing EHR systems in veterinary medicine is often hindered by the inherent rigidity of these systems or by the limited availability of IT resources to implement the modifications necessary for ML compatibility. Results Anna is a standalone analytics platform that can host ML classifiers and interfaces with EHR systems to provide classifier predictions for laboratory data in real-time. Following a request from the EHR system, Anna retrieves patient-specific data from the EHR system, merges diagnostic test results based on user-defined temporal criteria and returns predictions for all available classifiers for display in real-time. Anna was developed in Python and is freely available. Because Anna is a stand-alone platform, it does not require substantial modifications to the existing EHR, allowing for easy integration into existing computing infrastructure. To demonstrate Anna’s versatility, we implemented three previously published ML classifiers to predict a diagnosis of hypoadrenocorticism, leptospirosis, or a portosystemic shunt in dogs. Conclusion Anna is an open-source tool designed to improve the accessibility of ML classifiers for the veterinary community. Its flexible architecture supports the integration of classifiers developed in various programming languages and with diverse environment requirements. Anna facilitates rapid prototyping, enabling researchers and developers to deploy ML classifiers quickly without modifications to the existing EHR system. Anna could drive broader adoption of ML in veterinary practices, ultimately enhancing diagnostic capabilities and patient outcomes.

Anna: an open-source platform for real-time integration of machine learning classifiers with veterinary electronic health records

期刊论文
出版模式：

开放获取
发表日期：

2025年10月2日

查看全文

Chun Yin Kong,
Picasso Vasquez,
Makan Farhoodimoghadam,
Chris Brandt,
Titus C. Brown,
Krystle L. Reagan,
Allison Zwingenberger,
Stefan M. Keller

摘要

Background

In the rapidly evolving landscape of veterinary healthcare, integrating machine learning (ML) clinical decision-making tools with electronic health records (EHRs) promises to improve diagnostic accuracy and patient care. However, the seamless integration of ML classifiers into existing EHR systems in veterinary medicine is often hindered by the inherent rigidity of these systems or by the limited availability of IT resources to implement the modifications necessary for ML compatibility.

Results

Anna is a standalone analytics platform that can host ML classifiers and interfaces with EHR systems to provide classifier predictions for laboratory data in real-time. Following a request from the EHR system, Anna retrieves patient-specific data from the EHR system, merges diagnostic test results based on user-defined temporal criteria and returns predictions for all available classifiers for display in real-time. Anna was developed in Python and is freely available. Because Anna is a stand-alone platform, it does not require substantial modifications to the existing EHR, allowing for easy integration into existing computing infrastructure. To demonstrate Anna’s versatility, we implemented three previously published ML classifiers to predict a diagnosis of hypoadrenocorticism, leptospirosis, or a portosystemic shunt in dogs.

Conclusion

Anna is an open-source tool designed to improve the accessibility of ML classifiers for the veterinary community. Its flexible architecture supports the integration of classifiers developed in various programming languages and with diverse environment requirements. Anna facilitates rapid prototyping, enabling researchers and developers to deploy ML classifiers quickly without modifications to the existing EHR system. Anna could drive broader adoption of ML in veterinary practices, ultimately enhancing diagnostic capabilities and patient outcomes.