Research progress of epileptic seizure predictions based on electroencephalogram signals / 生物医学工程学杂志

As a common disease in nervous system, epilepsy is possessed of characteristics of high incidence, suddenness and recurrent seizures. Timely prediction with corresponding rescues and treatments can be regarded as effective countermeasure to epilepsy emergencies, while most accidental injuries can thus be avoided. Currently, how to use electroencephalogram (EEG) signals to predict seizure is becoming a highlight topic in epilepsy researches. In spite of significant progress that made, more efforts are still to be made before clinical applications. This paper reviews past epilepsy studies, including research records and critical technologies. Contributions of machine learning (ML) and deep learning (DL) on seizure predictions have been emphasized. Since feature selection and model generalization limit prediction ratings of conventional ML measures, DL based seizure predictions predominate future epilepsy studies. Consequently, more exploration may be vitally important for promoting clinical applications of epileptic seizure prediction.

Design of ECG signal acquisition system based on MSP430 microcontroller / 医疗卫生装备

Objective To design a high performance and low power consumption ECG signal acquisition system which can meet the demand for long time monitoring of the physiological status of patients.Methods The prototype system utilized low power ECG analog front end ADAS1000 and MSP430F5529 microcontroller to achieve configuration of AFE and back-reading of ECG data by SPI bus. Results This system implemented 24-hour dynamic ECG monitoring of patients in active state, and the data acquired were accurate and reliable.Conclusion The system realizes PCB integration, low power consumption, and can be used for battery powered portable application such as wearable devices.

Study of gene data mining based on informatics theory / 中国医疗器械杂志

By combining with informatics theory, ta system model consisting of feature selection which is based on redundancy and correlation is presented to develop disease classification research with five gene data set (NCI, Lymphoma, Lung, Leukemia, Colon). The result indicates that this modeling method can not only reduce data management computation amount, but also help confirming amount of features, further more improve classification accuracy, and the application of this model has a bright foreground in fields of disease analysis and individual treatment project establishment.