Epilepsy is the neurological disorder affecting around 50 million people worldwide. It is characterized by recurrent and unpredictable seizures. Correctly counting seizure occurrences is crucial for diagnosis and treatment of epilepsy, which will lower the risk of SUDEP (sudden unexpected deaths in epilepsy). Many previous researches on patient-specific seizure detection have obtained a good performance but with limited practicability in clinical setting. On the other hand, patient non-specific detection is clinically practicable but with limited performance. This study aims to improve the performance of patient non-specific seizure detection by comparing performances among one modality based models and multi-modal based model. The study was based on clinical data from the open source Siena Scalp EEG Database, which consist of simultaneous EEG (Electroenchephalography) and ECG (electrocardiography) recording from 14 patients with focal epilepsy. The seizures were annotated by an epilepsy expert after a careful review of the clinical and EEG data of each patient. First, relevant signal pre-processing were performed, followed by features extraction. Then, machine learning approach based on random forest was employed for seizure detection with leave-one-patient-out cross validation scheme. EEG detector and ECG detector were separately trained with each signal. Multi-modal detector was based on combining EEG detector and ECG detector by the late integration approach with the Boolean operation “OR” strategy. The performances were compared among those three detectors and with the state of the art. The result has shown that the multi-modal detector achieved a sensitivity of 87.62% and outperformed the ECG detector (41.55%), the EEG detector (81.43%), and the state-of-the-art non-specific detectors. Notably, the ECG detector detected some seizures which EEG detector failed to detect. This indicated that the ECG signal was beneficial for increasing sensitivity. However, due to the “OR” fusion strategy, the multi-modal detector also inherited the false detections resulted from either EEG detector or ECG detector. The findings of the study demonstrate the potential of improving performance of patient non-specific seizure detection by multimodal data. It shows that the proposed method should be further validated on large database and further development should focus on lowering false detections before clinical application.