AUTHOR=Hirashima Junya , Saito Miyoko , Hasegawa Daisuke , Asada Rikako , Kitagawa Masato , Ito Daisuke , Kanazono Shinichi , Fujiwara Koichi TITLE=In-hospital evaluation of an app-based seizure detection system in dogs: timely detection of generalized tonic–clonic seizures JOURNAL=Frontiers in Veterinary Science VOLUME=Volume 12 - 2025 YEAR=2025 URL=https://www.frontiersin.org/journals/veterinary-science/articles/10.3389/fvets.2025.1558274 DOI=10.3389/fvets.2025.1558274 ISSN=2297-1769 ABSTRACT=The seizure detection system (SDS) is a wearable device developed by us to detect generalized tonic–clonic seizures (GTCSs) in dogs with epilepsy. In our previous study, a feasibility test was conducted for the SDS, which demonstrated its ability to correctly identify three GTCSs in one dog. To enhance user accessibility and facilitate real-time monitoring of epileptic seizures in dogs, we integrated the system into a smartphone application. This study aimed to evaluate the performance of the app-based SDS in a clinical setting involving a larger number of dogs. Initially, the app-based SDS was tested on a laboratory dog with no history of seizures, and a drug-induced GTCS was accurately detected. Subsequently, an in-hospital evaluation was conducted. A total of 12 dogs were included, comprising 10 dogs with epilepsy, either hospitalized or temporarily housed at participating veterinary hospitals, and two laboratory dogs with epilepsy. In total, 34 GTCSs occurred in four of the 12 dogs, and the app-based SDS correctly detected 25 of the 34 GTCSs. Including the preliminary test results, the overall sensitivity of the app-based SDS was 74.3% (26 out of 35 GTCSs). Two false positives were observed in both in one dog. The false-positive rate and positive predictive value of the app-based SDS for detection of GTCS were 0.018 events/day and 92.6%, respectively. The median detection latency from the onset of a GTCS was 11 s. This study demonstrates that the app-based SDS is effective for detecting GTCSs in hospitalized dogs in clinical settings.