Artificial intelligence will change everyday veterinary practice. This technology can be used positively and be an aid for veterinarians. By analyzing complex medical data, examinations can be made more objective and therapies optimized. Our goal is to use this technology and make it accessible for the benefit of pet owners, veterinarians and patients.
Evidence for the benefit of patients can be achieved through the standardized collection of clinical data in text and images in a digital patient file and a high degree of automation in evaluation and communication (saving time, personnel and costs).
Standardized digital patient record
networking of clinical data
training of artificial intelligence
Standardized digital patient record
Networking of clinical data
Training of artificial intelligence
Our primary goal is to enable the standardized recording of clinical data in everyday life. This leads to improved communication with both animal owners and colleagues. It also creates the basis for long-term studies and the systematic review of the effectiveness of treatment measures. The secure collection of meaningful statistics on one's own patient collective promotes transparency and provides a good basis for decisions on clinical patients.
Our app
for veterinarians
and soon pet owners
Our app offers a comprehensive tool for recording and documenting standardized findings and also serves as a digital patient file. It has an integrated photo and video function that enables visual documentation. In addition, it supports the efficient management of animal data and functions as an interactive information tool that ensures better overview and organization in everyday practice.
Version 1.1.11
November 2024
The app is currently in the testing phase.
Apple App Store and Google Play Store
integration are in progress .
connecting care
May A., Gesell-May S., Müller T., Ertel W.
DOI: 10.1111/evj.13528
Abstract
Background
Due to recent developments in artificial intelligence, deep learning, and smart-device-technology, diagnostic software may be developed which can be executed offline as an app on smartphones using their high-resolution cameras and increasing processing power to directly analyze photos taken on the device.
Objectives
A software tool was developed to aid in the diagnosis
of equine ophthalmic diseases, especially uveitis.
Study design
Prospective comparison of software and clinical diagnoses.
Methods
A deep learning approach for image classification was used to train software by analyzing photographs of equine eyes to make a statement on whether the horse was displaying signs of uveitis or other ophthalmic diseases. Four base networks of different sizes (MobileNetV2, InceptionV3, VGG16, VGG19) with modified top layers were evaluated. Convolutional Neural Networks (CNN) were trained on 2346 images of equine eyes, which were augmented to 9384 images. 261 separate unmodified images were used to evaluate the performance of the trained network.
Results
Cross validation showed accuracy of 99.82% on training data and 96.66% on validation data when distinguishing between three categories (uveitis, other ophthalmic diseases, healthy).
Main limitations
One source of selection bias for the artificial intelligence presumably was the increased pupil size, which was mainly present in horses with ophthalmic diseases due to the use of mydriatics, and was not homogeneously dispersed in all categories of the dataset.
Conclusion
Our system for detection of equine uveitis is unique and novel and can differentiate between uveitis and other equine ophthalmic diseases. Its development also serves as a proof-of-concept for image-based detection of ophthalmic diseases in general and as a basis for its further use and expansion.
Research
We are in research cooperation with the Faculty of Veterinary Medicine at the Ludwig Maximilian University of Munich and the Institute for Artificial Intelligence at the Ravensburg-Weingarten University of Applied Sciences.
Standardized
digital patient record
Documentation is not easy in everyday veterinary practice. This is also why there is a lack of clinical data and therefore no evidence in veterinary medicine. As a rule, one has to rely on experience and basic knowledge.
We standardize documentation and facilitate communication. The digital patient file enables us to network clinical data. This creates transparency. However, we pay explicit attention to data security, both internally and externally. At most, only anonymized overall statistics are passed on to veterinarians within anirec. This also applies to managing veterinarians.
Through the digital patient record and the networking of images with clinical data, we create a basis for the factual assessment of clinical cases and their evaluations.
Networking
clinical data
Evidence and the training of artificial intelligence is only possible on the basis of a "good" data basis.
We see it as our task to link scientific data from everyday veterinary practice, university and non-university research and long-term observation in follow-up care. The interests of medicine are at the forefront. We want to advance clinical research by releasing anonymized scientific data.
Training of artificial intelligence
We develop methods for pattern recognition. These become useful tools for diagnostics and prognosis.
We are confronted with complex systems in our environment every day and naturally use our human intelligence to navigate them. Using artificial intelligence means using programs to solve problems such as pattern recognition in such complex environments. Through machine learning, we train artificial intelligence with examples from which it can draw conclusions based on recurring patterns.
Artificial intelligence is already delivering impressive results, but this cannot hide the fact that it is still in its early stages. Artificial intelligence will become an important tool for veterinarians. No less, but also no more. The key to long-term integration will be not to use artificial intelligence to drive a wedge between veterinarians and owners.
Simplifying Long-Term Studies
- 2022
We are working to make it much easier for researchers to collect long-term data and use it to test the effectiveness of treatment methods.
Diagnosis of over 14 diseases of the horse's eye - 2023
We are already training an artificial intelligence that is able to diagnose over 20 diseases of the horse's eye.
Epidemiological data and preliminary reports fully available digitally - 2024
At the beginning of the examination, veterinarians can easily access epidemiological information and the preliminary report directly from the patient in the digital patient file.
Protocols according to lege artis - 2024
We want young veterinarians without years of experience to be able to follow examination protocols according to the rules of medical art, regardless of the quality of their training.
Easier Communication - 2025
With the diagnosis in the anirec app, photos and videos are saved directly in the digital patient file. This file can currently be sent as a PDF, for example to the owner or referring colleagues. This will soon be possible within the app by simply activating it.
Statistics of your own work - 2026
We are developing a tool with which every veterinarian and every clinic can statistically accurately measure the success rates of their own treatments and thus contribute to evidence-based medicine.
Lameness Detection and Pain Score - 2026
We are working on making our app indicate whether a horse is lame or in acute pain and how severe these expressions of pain are.
Fast documentation and creation of doctor's letters - 2027
Our goal is to significantly speed up documentation and the creation of the doctor's letter, thereby reducing the number of veterinarians involved. Patients and owners benefit from meaningful written information that can be accessed digitally anytime, anywhere.
Agenda
Scharre A., Scholler D., Gesell‐May S., Müller T., Zablotski Y., Ertel W., May A.
DOI: 10.1111/evj.14087
Abstract
Background
Lameness in horses is a long-known issue influencing the welfare, as well as the use, of a horse. Nevertheless, the detection and classification of lameness mainly occurs on a subjective basis by the owner and the veterinarian.
Objectives
The aim of this study was the development of a lameness detection system based on pose estimation, which permits non-invasive and easily applicable gait analysis. The use of 58 reference points on easily detectable anatomical landmarks offers various possibilities for gait evaluation using a simple setup.
Study design
For this study, three groups of horses were used: one training group, one analysis group of fore and hindlimb lame horses and a control group of sound horses. The first group was used to train the network; afterwards, horses with and without lameness were evaluated.
Results
The results show that forelimb lameness can be detected by visualizing the trajectories of the reference points on the head and both forelimbs. In hindlimb lameness, the stifle showed promising results as a reference point, whereas the tuber coxae were deemed unsuitable as a reference point.
Conclusion
The study presents a feasible application of pose estimation for lameness detection, but further development using a larger dataset is essential.
About us
Focus
Training artificial
intelligences
Tobias Müller
Management
Business development
Development of artificial intelligences
App development
IT specialist /
Software developer
Focus
Networking
clinical data
Dr. Stefan Gesell-May
Management
Business development
Veterinary medicine content
Equine ophthalmology
Practicing veterinarian
pferdeaugenheilkunde.de
Focus
Communicating
the brand
Elias Escotto
Business development
Brand management
Corporate design
Future UI / UX
Designer
elias-escotto.de
Artificial intelligence is a catalyst for the further development of veterinary medicine. In order to leverage the potential of artificial intelligence, we need to focus on three things.