Frequently Asked Questions

Validation means that our system has been directly compared to a gold standard measurement system.

In our main validation study below, the average difference between RealHorse and the gold standard 3D multicamera reference system was only 1 mm for the head, withers, and pelvis. This level of accuracy is considered highest ever recorded in equine gait analysis and we are the only system validated for handheld use.

The validation has been carried out through multiple peer reviewed studies conducted in collaboration with the University of Copenhagen.

We currently have four scientific validation studies:

• Groundline estimation on a treadmill: https://doi.org/10.1002/vms3.70739
• Keypoint precision on soft surface including circles: https://doi.org/10.1002/evj.70149
• Main validation study on straight-line and circles: https://doi.org/10.1111/evj.70109
• Validation of the back ROM (submitted for peer review)

Across these studies, the system demonstrated high accuracy in measuring movement symmetry and detecting lameness using standard video recordings, including handheld use. To our knowledge, this is the only system that has been validated for handheld recordings.

The results show strong agreement with established reference methods, with only minor variations that are not clinically significant.

What makes this system different?

The system includes a novel groundline estimation method that makes it possible to analyze horses reliably using handheld video, even under varying conditions.

This allows the system to be used outside controlled laboratory environments, making it suitable for both clinical use and everyday situations for riders and horse owners.

How does it compare to other systems?

Markerless, video based gait analysis systems vary widely in both validation and performance.

Based on currently available published evidence, this system is among the most extensively validated and precise gait analysis solutions.

Only full 3D multi camera motion capture systems, typically used in research settings, provide higher levels of precision.

Is development ongoing?

Yes. Additional validation studies are ongoing to further refine the algorithm even further across different environments, horse types, and practical use cases.

Yes, absolutely.

Tap the icon in the top right corner of the Summary or Analysis screen to share your horse’s analysis using your preferred method (for example email, messaging, or AirDrop). You can also save the report on your phone and import it into any journal or record system.

The generated PDF report includes:

• All results from the current analysis
• Results from the selected baseline
• A history of analyses between the baseline and the current recording

This makes it easy to share meaningful insights with your veterinarian, trainer, or others involved in your horse’s care, and allows professionals to store and use the analysis outside the app.

Absolutely! Our patented sound generator is more than just a fun feature—it's a powerful tool designed to help you detect subtle irregularities in your horse's gait. This aligns with our mission to make equine care accessible to everyone, empowering all horse owners to spot signs of lameness early and take action before issues become serious.

Why Sound Matters

Humans often find it challenging to notice tiny differences in fast-moving visuals, like the legs of a trotting horse. Our eyes can miss small details when things move quickly. It's similar to how early animators like Walt Disney created the illusion of motion using just a few frames per second—our brains fill in the gaps to make sense of what we see.

However, our ears are excellent at picking up small irregularities in sound. Just like a music conductor can immediately notice an instrument that's slightly out of tune, you're naturally more sensitive to slight changes in rhythm and timing when you listen carefully. This is because our brains are especially good at processing sounds and noticing when something doesn't match the expected pattern. The Neuroscience behind this is called Predective Processing.

How the Sound Generator Helps

Our sound generator takes advantage of this by turning your horse's movement data into sound. We've used actual hoofbeats for the impact sounds and reversed hoofbeats to simulate the push-off phase. By listening to these sounds, you can "hear" any asymmetries or irregularities in your horse's gait that might indicate lameness.

Try It Yourself!

To make the most of this feature:

1. Play the Video at 50% Speed: Slowing down the video helps you match what you see with what you hear.
2. Turn Off AR Key Points and Graphs: This reduces visual distractions, allowing you to focus on the sounds.
3. Use the Sound Generator for Front or Hind Legs: This lets you concentrate on specific areas of concern.

Do you "see" your horse more clearly now?

Please follow the on-screen instructions when recording your horse.

See the instruction video at the bottom of this screen. 

Record at the approximate same height as the wither-height of your horse.

Ensure the app sees the entire side of your horse without equipment and make sure the eye and withers is not obscured by the forelock or mane. 

We recommend you start with only analyzing left and right circle and wait with analyzing straight line. Routine circle analysis works well in most cases.

Yes, we save your data when you pause or downgrade your subscription to ensure you don’t lose valuable historical records. If you reactivate your subscription, you’ll still have full access to your data. However, if you cancel your subscription and delete the app, your data will be automatically removed from our servers.

Yes, you can easily upgrade to Premium for just one month if you need expert advice or help getting started with this innovative technology. We’re here to assist you as you explore the full potential of our app!

While our RealHorse experts are here to help you interpret your horse's data and provide guidance on using the app effectively, they cannot provide a complete diagnosis of your horse's condition, even with a Premium or Unlimited subscription.

Diagnosing a horse requires a thorough, hands-on examination by a qualified veterinarian.

Our experts can:

• Assist you in understanding the analysis results.
• Explain what the symmetry measurements might indicate.
• Suggest possible next steps.

For a comprehensive assessment and accurate diagnosis, we recommend consulting your local veterinarian. RealHorse makes it easy to share your horse's analysis by generating a detailed PDF summary that you can email directly to your vet, helping them gain insights from the data you've collected.

1.

Evaluating the Accuracy of a Vision-Based Algorithm for Groundline Estimation in Trotting Horses Using Multiple Camera Angles

https://doi.org/10.1002/vms3.70739

ABSTRACT

Background
Equine lameness diagnosis largely relies on subjective visual assessments, which can be biased. Although marker-based methods, force plates and inertial measurement units (IMUs) provide objective measurements, they require specialized setups. Vision-based algorithms offer a portable, markerless alternative, but their accuracy needs thorough testing.

Objectives
To evaluate a custom vision-based algorithm for estimating the groundline across multiple camera angles, including handheld use in horses trotting on a treadmill.

Study design
Experimental comparative study.

Methods
Eight Standardbred trotter mares were recorded trotting on a high-speed treadmill using seven iPhones positioned at various heights and angles, including a handheld device. A trained deep neural network algorithm placed 2D keypoints on each video frame. Vertical Displacement Signals (VDS) for the eye, withers and croup (tuber sacrale) were computed relative to either an algorithm-estimated or a fixed treadmill groundline. Maximum (Maxdiff) and minimum (Mindiff) stride values were compared using Bland–Altman analysis, scatter plots and histograms. The effect of handheld use on variability and accuracy was assessed by comparing results from a handheld camera to those from a static camera.

Results
Groundline estimation closely matched the fixed reference, exhibiting near-zero mean angle error and low mean average error (MAE = 0.45°; n = 242.192). Maxdiff and Mindiff stride-level (n = 36.981) MAE were 0.5 mm, with clinically acceptable additional variability introduced by handheld use at the trial level (Maxdiff and Mindiff MAE < 1.8 mm; n = 357).

Main limitations
Treadmill-based data and a single breed/coat colour may limit generalizability to other settings.

Conclusions
The vision-based algorithm accurately estimates the groundline and stride VDS parameters from various camera setups, including handheld. Further validation in diverse environments and against other objective gait analysis systems is recommended.

2.

Reliability, agreement and variability of a markerless computer vision algorithm for equine gait analysis under field conditions

https://doi.org/10.1111/evj.70109

Abstract

Background
Computer vision-based algorithms offer accessible alternatives for equine gait analysis but require thorough assessment under diverse conditions.

Objectives
To evaluate a proprietary vision-based algorithm's reliability in measuring vertical displacement signals (VDS) at the eye, withers and croup, alongside groundline estimation, for horses trotting on straight lines and circles under field conditions.

Study Design
Cross-sectional comparative study evaluating agreement, variability and reliability of a markerless computer vision algorithm.

Methods
We obtained 67 handheld iPhone recordings from 37 horses. A vision-based algorithm and independent manual annotation produced 2D anatomical keypoints on all frames of the recordings, which were processed to estimate a groundline and compute VDS and stride-based maxima (Maxdiff) and minima (Mindiff) vertical differences. Mean signed error (MSE), mean absolute error (MAE) and Bland–Altman plots were used to compare detected and annotated data.

Results
The frame level vertical keypoint accuracy was 4.5 mm (eye), 5.5 mm (croup) and 11.8 mm (withers), and the manual annotation error was averaged at 2.7 mm. At the stride level (n = 1556), the overall mean absolute errors (MAEs) for both Maxdiff and Mindiff were 4.3 mm. The eye keypoint exhibited the lowest errors (2.9 mm Maxdiff, 3.0 mm Mindiff), while the withers error was 5.5 mm for both Maxdiff and Mindiff, and the croup showed 4.3 mm (Maxdiff) and 4.4 mm (Mindiff). Trial-level (n = 67) analysis, with below optimal number of strides per trial in this study, revealed lower overall absolute differences (Eye: 2.3 mm, Withers: 3.7 mm, Croup: 2.7 mm), indicating consistent performance across multiple strides. Subjective lameness scoring aligned with objective measures with some variation.

Main Limitations
Groundline estimation accuracy was stress-tested on treadmill data in another study. Further clinical comparison with established gait analysis systems is recommended.

Conclusions
The algorithm robustly measured vertical displacements under varied conditions.

3.

Validation of a handheld smartphone markerless gait-analysis tool using an estimated groundline in horses

https://doi.org/10.1002/evj.70149

Abstract

Background
A handheld smartphone-based computer vision algorithm (RealHorse® [RH]) offers accessible alternatives for equine gait analysis but requires validation against a gold-standard three-dimensional multicamera optical motion capture system (Qualisys® [QS]).

Objectives
To evaluate the accuracy and precision of RH in measuring vertical displacement signals (VDS) at the eye, withers, back and croup in horses trotting on a straight line and on a circle.

Study Design
Cross-sectional comparative validation study of a markerless computer vision algorithm.

Methods
Fifty-nine horses were recorded while trotting on a straight line and 24 were lunged on a circle. RH detected two-dimensional anatomical keypoints on each frame, which were used to estimate a dynamic groundline and compute ground relative VDS with stride-based difference in maxima (Maxdiff) and minima (Mindiff). QS provided synchronous ground-relative VDS reference values. Agreement was evaluated using mean signed error, mean absolute error and Bland–Altman analysis.

Results
On the straight line (n = 2620 strides), the pooled stride-level MAE for Maxdiff and Mindiff was 3.8 mm. Keypoint-specific errors were 5.1 mm (eye), 4.3 mm (withers) and 3.0 mm (croup). On the circle (n = 2419 strides), pooled stride-level error increased to 5.5 mm. Trial-level analysis (n = 58 trials) showed much lower errors: 1.4 mm for both eye and withers and 1.1 mm for croup. On the circle (n = 24 trials), trial-level errors were higher, with 2.8 mm for the eye, 1.8 mm for the withers and 3.3 mm for the croup. The back keypoint consistently showed the lowest errors across both stride and trial levels.

Main Limitations
RH measurements of the croup Mindiff during circling resulted in higher values and showed the largest error.

Conclusions
RH measured vertical displacement of all keypoints with high accuracy and precision (trial-level MAE 1.1–1.4 mm straight, 1.8–3.3 mm circle), supporting its use for equine gait analysis.

4.

Validation of a handheld smartphone markerless method for quantifying thoracolumbar flexion–extension range of motion in horses at trot

(under review)

ABSTRACT

Background
Back pain and poor performance in horses are difficult to assess objectively and thoracolumbar flexion-extension range of motion (FEROM) is not reliably evaluated by subjective observation alone. A handheld, smartphone-based markerless computer vision system (RealHorse®; RH) may enable objective field-based assessment but requires validation against an established optical motion capture reference system (Qualisys®; QS).

Objectives
To compare the accuracy and precision of RH relative to QS for measuring FEROM in horses trotting on a straight-line and on a circle.

Study Design
Cross-sectional comparative validation study of a markerless computer vision algorithm.

Methods
Fifty-nine horses were recorded trotting on a straight-line; 23 of these were also recorded on a circle. Data were collected simultaneously using RH and QS, with a marker light used for manual frame-level temporal synchronisation. The validation videos or horses were not used to train the RH algorithm. Agreement between RH and QS was analysed separately for straight-line and circular trot at stride- and trial-levels using mean signed error (MSE), mean absolute error (MAE), and Bland-Altman limits of agreement (LoA).

Results
On the straight-line, stride-level MSE was −0.08°, MAE 0.96°, and LoA −2.49° to 2.32°. Trial-level agreement was better, with MSE −0.13°, MAE 0.44°, and LoA −1.22° to 0.94°. On the circle, stride-level MSE was −0.71°, MAE 1.14°, and LoA −3.17° to 1.74°. At the trial-level, variability was better (MSE −0.62°, MAE 0.78°, LoA −2.18° to 0.93°). Overall agreement was lower on the circle than on the straight-line and higher at trial-level than at stride-level.

Conclusions
Stride-level agreement between RH and QS was influenced by expected stride-to-stride variability, particularly during circular exercise, whereas averaging across strides improved agreement at the trial-level. RH may support objective field-based monitoring of thoracolumbar flexion-extension range of motion, especially for repeated within-horse assessments, but clinical decision thresholds remain to be established.

With your Premium or Unlimited subscription, you can have one consultation per week with our in-app experts. This includes your initial inquiry and necessary follow-up messages related to that specific issue. Our experts aim to respond within 24-48 hours during normal office hours.

To make the most of your consultation:

• Be Thorough in Your Initial Message: Include all relevant details and questions about your concern. This helps our experts provide comprehensive assistance more efficiently.
• Check In-App Resources First: Explore the Analysis section of the app, where expandable drawers offer detailed information and answers to common questions. You might find immediate answers there.

Please note that while we're here to help interpret your horse's data and provide guidance, we cannot offer a complete diagnosis remotely. For a thorough assessment, we recommend consulting your local veterinarian. You can easily share a detailed summary PDF of your horse's analysis with your vet directly from the app.

Absolutely! RealHorse is designed for everyone who loves and cares for horses—whether you're a horse owner, trainer, veterinarian, or equine enthusiast. Our mission is to democratize access to advanced equine health monitoring, empowering all horse lovers to proactively take care of their horses and detect signs of lameness before it's too late.

We understand that early detection of lameness is crucial in preventing long-term health issues. By providing a user-friendly app that harnesses cutting-edge technology, we make it possible for anyone to assess their horse's movement symmetry with just a smartphone. This means you don't need specialized equipment or extensive training to monitor your horse's well-being.

For horse owners and trainers, RealHorse offers quick and accurate results that help you make informed decisions about your horse's care. You can easily track changes over time, allowing you to spot potential issues early and consult a professional if needed.

For veterinarians and equine professionals seeking deeper insights, the app includes advanced features and detailed analytics. This allows you to supplement your expertise with precise data, enhancing your ability to diagnose and treat your patients effectively.

By bridging the gap between professional diagnostics and everyday horse care, RealHorse aims to improve the overall health and happiness of horses everywhere. We're committed to making advanced equine health assessment accessible to all who love horses, ensuring that every horse has the opportunity for timely care and attention.

Yes, we have validated the app's use with handheld cameras. In fact we are the only system validated with handheld camera use.

During our treadmill study, we tested the app using both stationary and handheld camera footage, and the results showed only minor differences in accuracy. This means you can use the app on your smartphone while holding the camera, and still get reliable results.

https://doi.org/10.1002/vms3.70739

Our two other validation study was also done with handheld use:

https://doi.org/10.1002/evj.70149

https://doi.org/10.1111/evj.70109

Yes, absolutely! The app saves your analysis history so you can monitor changes in your horse's movement over time. The first analysis you perform is automatically set as a baseline, and all subsequent analyses are compared to this baseline in your horse's profile.

You have the flexibility to set any analysis as a new baseline or remove existing baselines whenever you like. Improvements and regressions are shown as percentage point (%pt) changes in the lameness categories, giving you clear insights into your horse's condition.

This feature is particularly useful for tracking progress during rehabilitation or spotting any developing issues early on. By regularly monitoring your horse's movement, you can stay proactive about their health and well-being.

Yes, RealHorse can help assess your horse's trotting symmetry using just your iPhone, trotting symmetry is a crucial aspect of detecting lameness in horses. While the app can identify asymmetries in your horse's movement—which may indicate lameness—it does not diagnose the underlying cause of any asymmetry or lameness.

Our goal is to assist you in monitoring your horse's movement patterns, and we are continually working to improve the algorithm to provide even more detailed insights in the future. Sometimes, our algorithm will offer predictions or suggestions of a specific diagnosis based on asymmetry pattern recognition, in the "What to Make of It" section in the analysis summary.

RealHorse utilizes advanced Vision Analysis technology, a form of artificial intelligence, to assess your horse's movement symmetry using your iPhone. We've trained our algorithm on thousands of horse images and videos, enabling it to precisely identify key points—like joints and limbs—in every frame of your videos.

This sophisticated algorithm runs directly on your iPhone without needing an internet connection. By analyzing these key points, we calculate the symmetry of your horse's movements.

In the world of equine health, symmetrical movement often indicates soundness, while asymmetry can be a sign of lameness—though minor asymmetry can sometimes be normal. By measuring movement symmetry, RealHorse helps you assess your horse's well-being conveniently and accurately.

With RealHorse, you have a powerful professional-grade tool right in your pocket, making it easier than ever to monitor your horse's gait and detect potential issues early on.

Please note that while RealHorse provides valuable insights into your horse's movement, it does not replace a professional veterinary diagnosis. If you have concerns about your horse's health, we recommend consulting a qualified veterinarian.

We're here to help!

For Premium and Unlimited Subscribers:

If you're a Premium or Unlimited subscriber, you can consult your personal expert directly through the app for any relevant advice, including specific questions about your horse's health and analysis results. Simply access an expert from any summary view within the app.

For Basic and Basic Plus Subscribers:

If you're a Basic or Basic Plus subscriber, you're welcome to contact us with general inquiries about RealHorse, such as how to use certain features or troubleshoot issues. Please email us at support@realhorse.com, and we'll respond as soon as possible. Please note that we are unable to provide specific advice about your horse without a Premium or Unlimited subscription.

Interested in Personalized Expert Advice?

Consider upgrading to our Premium or Unlimited subscription to access one-on-one chat consultations with our expert veterinarians. This will allow our expert vets to access all the data you permit within the app, enabling you to receive personalized guidance tailored to your horse's needs.

Not necessarily. In fact, RealHorse is designed to empower horse owners and professionals by helping them monitor their horse's movement more effectively. This often leads to earlier detection of subtle asymmetries or potential issues, which means you can act sooner—whether that’s adjusting training or consultation by a veterinarian. By providing objective data, RealHorse enhances communication and supports more informed decisions. It’s a tool to complement professional care, not replace it.

RealHorse is a smartphone app (iPhone only, for now) that measures subtle asymmetries in a horse’s gait. Using a computer vision algorithm, the app tracks the ground-truth vertical displacement (VDS) of the head, withers, and pelvis. It then uses the withers as a reference point to determine whether a front or hind asymmetry is the likely primary issue—all in just a few minutes and without an internet connection.

We strongly advise against relying solely on any app or service, including RealHorse, for pre-purchase exams (PPEs). Clients who choose to forego a vet-conducted exam risk losing the legal protection, thoroughness, and professional expertise that only a qualified veterinarian can provide. RealHorse is designed to supplement, not replace, professional evaluations. Its goal is to enhance the standard of documentation in PPEs by introducing objective gait analysis, supporting both veterinarians and horse owners in making informed decisions.

Technology inevitably shapes how we do things. As tools like RealHorse become more common, PPE procedures and expectations around objective data may evolve. The key is to use these innovations to raise clinical standards. We strongly believe that having more data, rather than less, benefits veterinarians, buyers, and sellers alike—so long as a veterinarian remains central to the decision-making process.

We’ve partnered with the test clinic iKeyVet, where the RealHorse prototype has been used daily for over four years. The clinic’s orthopedic team of five veterinarians focuses almost exclusively on lameness and poor performance in sport horses. Four vets have completed extensive ISELP coursework, and one is both ISELP- and EGAS-certified, as well as serving as Team Vet for the Danish National Dressage Team. Their hands-on experience confirms that RealHorse is easy to use and clinically reliable in demanding equine sports settings. We believe RealHorse provides objective gait analysis on par with any other system available today.

Absolutely! We’re looking to bring together a group of dedicated experts who are passionate about equine lameness and objective gait analysis. Here’s what you need to know:

• Timely Responses & Expertise
  As a RealHorse expert, you’ll be expected to respond promptly to user queries and have in-depth knowledge of Equine Objective Gait Analysis.
• Direct Access to Clients
  You’ll have access to all the analyses performed by RealHorse users who connect with you - providing an invaluable source of potential new clients.
• Next Steps
  We encourage you to start by using RealHorse extensively in your practice so you’re comfortable interpreting and explaining the results. Once you’re ready, contact us at support@realhorse.com for more details on how to become an official RealHorse expert.

As a veterinarian, you’ll need our Unlimited subscription plan, which lets you add an unlimited number of horses to your account. You can install this subscription on two iPhones, and we don’t mind if you share these two phones among multiple vets at your clinic. You can also contact RealHorse experts directly in the app for advice on interpreting results - just remember to mention you’re a vet!

The Unlimited subscription costs $550 USD/year when billed annually.

Absolutely! With an Unlimited subscription RealHorse allows you to select from a list of diagnoses organized by anatomical region or to write a custom note. If you choose diagnostic block instead of a region on the leg, you can choose form our list of blocks. We encourage you to use this feature, as it helps us continually improve our algorithms ability to predict a diagnosis - but please only add a diagnosis if you’re reasonably confident in it.

• Check the In-App Info Videos
  Tap the small “i” icons in the apps analysis to watch our information videos, which explain the graphs and key measurements.
• Contact an Expert (Premium or Unlimited Subscription)
  If you have a Premium or Unlimited subscription, you can reach out to a RealHorse expert directly from the app. Once connected, they can see all your analyses and advise you on how to interpret your results.