Source: North Carolina State University
A new North Carolina State University study found that fourth-year Veterinary students matched, and experienced clinicians outperformed, an AI-enabled digital stethoscope when diagnosing heart murmurs and arrhythmias in dogs and cats. Researchers evaluated 105 animals, including 54 dogs and 51 cats.
In dogs, the AI correctly detected 33 of 38 heart murmurs, an 87% success rate comparable to Veterinary students. However, its arrhythmia performance was unreliable. Although it identified all six cases of atrial fibrillation, it falsely diagnosed 22 additional dogs and never classified a dog as arrhythmia-free. Performance was considerably worse in cats. The AI detected only two of 22 confirmed murmurs, while Veterinary students identified nearly two-thirds.
Researchers noted that the stethoscope’s diagnostic AI was trained using human rather than canine or feline data. They concluded that while features such as ECG recording can be useful, veterinarians should use the technology as an adjunct rather than a stand-alone diagnostic tool.
Read the full story HERE: https://news.ncsu.edu/2026/08/ai-enabled-stethoscope-can-miss-the-beat-in-pets/