Detecting aberrant behaviors in dogs or observing emotional interactions between a dog and its owner may serve as indicators of potential canine diseases. However, dog owners typically struggle to assess or predict the health status of their pets independently. Consequently, there is a demand for a methodology enabling owners to evaluate their dogs’ health based on everyday behavioral data. To address this need, we gathered individual canine data, including three months of standard daily activities (such as scratching, licking, swallowing, and sleeping), to train an AI model. This model identifies abnormal behaviors and quantifies each behavior as a numerical score, termed the “Health Score”. This score is categorized into ten levels, where a higher score indicates a healthier state. Scores below 5 warrant medical consultation, while those above 5 are deemed healthy. We validated the baseline value of the Health Score against veterinarian diagnoses, achieving an 87.5% concordance rate. This validation confirms the reliability of the Health Score, which assesses canine health through daily activity monitoring, and is expected to significantly benefit dog owners who face challenges in determining the health status of their pets.