CN114468986A

CN114468986A - Wearable device based on artificial intelligence multimode epileptic seizure monitoring

Info

Publication number: CN114468986A
Application number: CN202011267802.0A
Authority: CN
Inventors: 刘军; 徐鑫
Original assignee: Research Institute of Zhejiang University Taizhou
Current assignee: Research Institute of Zhejiang University Taizhou
Priority date: 2020-11-13
Filing date: 2020-11-13
Publication date: 2022-05-13

Abstract

The invention discloses a wearable device based on artificial intelligence multi-modal seizure monitoring. The wearable device comprises a muscle sound signal acquisition module, a signal processing and data analysis module, a power management module and a data transceiving module. The signal output end of the muscle sound signal acquisition module is connected with the signal input end of the signal processing and data analysis module, and the signal end of the signal processing and data analysis module is bidirectionally connected with the signal end of the data transceiver module. The power management module supplies power for the muscle sound signal acquisition module and the signal processing and data analysis module. The muscle sound signal acquisition module acquires muscle sound signals of the upper arm, the forearm and the wrist. The invention solves the problem that the epileptic seizure monitoring system has lower accuracy rate for monitoring epileptic seizures.

Description

Wearable device based on artificial intelligence multimode epileptic seizure monitoring

Technical Field

The invention relates to a wearable device based on artificial intelligence multi-modal seizure monitoring.

Background

Epilepsy (epilesys) is an ancient disease. Transient cerebral dysfunction can be caused during epileptic seizure, and symptoms such as limb stiffness, abnormal tetany of limbs, absence and the like are generated. It is known that seizures are dangerous, especially grand mal, and are the subject of considerable investigation for the monitoring of seizures, which are mainly characterized by persistent muscle contractions, symmetric or asymmetric twitching, and each time involving the same muscle group, accompanied by movements such as the fist making, the wrist bending, etc. In the case of epileptic seizures, patients are often accidentally injured due to loss of mind, uncontrolled body, respiratory arrest, etc., and many patients may easily bite the tongue and lose their lives when they have seizures. And the nervous system injury may be aggravated by brain inflammatory reaction if the treatment is not timely obtained during the attack, and more serious consequences are caused. The epileptic seizure is paroxysmal, influences the normal work and life of the patient and causes the patient to generate anxiety. The epileptic seizure is accompanied by transient absence which can hardly be detected or severe clonus for a long time, and the conditions are complex and various and have no obvious rule. If the patient is not in public places or cared by no person during the attack, the patient is difficult to be found, and the attack history of the patient is difficult to be recalled afterwards.

At present, domestic and foreign enterprises develop epileptic seizure monitoring and alarming devices, which are foreign Embrace, smartwatch and domestic self-developed caring bracelets, and can send help-seeking information to family members when epileptic seizure occurs, so that the family members can arrive in time to prevent accidental injury. Such devices are largely able to reduce accidental injury from epileptic seizures. But judging seizures based on wrist movements has its own limitations. Such as running, brushing teeth, etc. in life, many actions are very similar to seizures. In terms of accuracy, there can be false positives for this type of device.

Disclosure of Invention

The invention aims to overcome the defects of the prior art and provides a wearable device based on artificial intelligence multi-modal seizure detection.

Wearable device based on artificial intelligence multimode epileptic seizure detects includes: wearable device, intelligent mobile device or PC end.

The wearable device comprises a muscle sound signal acquisition module, a signal processing and data analysis module, a power management module and a data transceiver module. The signal output end of the muscle sound signal acquisition module is connected with the signal input end of the signal processing and data analysis module, and the signal end of the signal processing and data analysis module is bidirectionally connected with the signal end of the data transceiver module. The power management module supplies power for the muscle sound signal acquisition module and the signal processing and data analysis module.

The muscle sound signal acquisition module acquires muscle sound signals of the upper arm, the forearm and the wrist.

The signal processing and data analysis module processes the muscle sound signal data by using a wavelet theory, and performs frequency domain analysis on the VMG by using a frequency spectrum to obtain rich information such as muscle states, motion modes, motion intentions and the like.

The intelligent mobile equipment comprises a mobile phone, a tablet and the like.

The PC end comprises a data receiving and transmitting host module and a computer. The wearable device worn by the patient is in data communication with the upper computer and used for displaying and analyzing signals.

The muscle tone (MMG) is a sound signal generated by a muscle due to mechanical vibration, and is generated by minute vibration on the skin surface at a corresponding position caused by lateral expansion and deformation of muscle fibers during contraction, and contains abundant information such as muscle state, motion pattern, and motion intention.

The invention solves the problem that the epileptic seizure monitoring system in the related technology has lower accuracy in monitoring epileptic seizures.

Drawings

Fig. 1 is a block diagram of the overall design of the device.

Detailed Description

The present invention is further analyzed with reference to the following specific examples.

The wearable device comprises a muscle sound signal acquisition module, a signal processing and data analysis module, a power management module and a data transceiver module. As shown in fig. 1, the signal output end of the muscle sound signal collecting module is connected with the signal input end of the signal processing and data analyzing module, and the signal end of the signal processing and data analyzing module is bidirectionally connected with the signal end of the data transceiver module. The power management module supplies power for the muscle sound signal acquisition module and the signal processing and data analysis module.

The PC end comprises a data receiving and transmitting host module and a computer. The wearable device is worn by the patient to carry out data communication with the upper computer, and the data communication is used for displaying and analyzing signals.

The above embodiments are not intended to limit the present invention, and the present invention is not limited to the above embodiments, and all embodiments are within the scope of the present invention as long as the requirements of the present invention are met.

Claims

1. Wearable equipment based on artificial intelligence multimode epileptic seizure monitoring, its characterized in that includes: a wearable device, an intelligent mobile device or a PC terminal;

the wearable device comprises a muscle sound signal acquisition module, a signal processing and data analysis module, a power management module and a data transceiving module; the signal output end of the muscle sound signal acquisition module is connected with the signal input end of the signal processing and data analysis module, and the signal end of the signal processing and data analysis module is bidirectionally connected with the signal end of the data transceiver module; the power management module supplies power to the muscle sound signal acquisition module and the signal processing and data analysis module;