The existing epilepsy seizure detection algorithms have problems such as overfitting and poor generalization ability due to high reliance on manual labeling of electroencephalogram's data and data imbalance between seizure and interictal periods. An unsupervised learning detection method for epileptic seizure that jointed graph attention network (GAT) and Transformer framework (GAT-T) was proposed. In this method, channel correlations were adaptively learned by GAT encoder. Temporal information was captured by one-dimensional convolution decoder. Combining outputs of the two mentioned above, predicted values for electroencephalogram were generated. The collective anomaly score was calculated and the detection threshold was determined. The results demonstrated that GAT-T achieved the average performance exceeding 90% (or 99%) with a 0.25 s (or 2 s) time segment length, which could effectively detect epileptic seizures. Moreover, the channel association probability matrix was expected to assist clinicians in the initial screening of the epileptogenic zone, and ablation experiments also reflected the significance of each module in GAT-T. This study may assist clinicians in making more accurate diagnostic and therapeutic decisions for epilepsy patients.
Humans ; Electroencephalography/methods* ; Epilepsy/physiopathology* ; Algorithms ; Seizures/physiopathology* ; Neural Networks, Computer ; Signal Processing, Computer-Assisted

OBJECTIVETo investigate the needlestick injuries in student nurses during nine months of in-ternship in our hospital, and reveal the high-risk periods, risk procedures, and influencing factors for needlestick injuries, and explore the prevention approaches.

METHODSThree hundred and fifty student nurses who interned at our hospital from April to December 2014 and from July 2014 to March 2015 were surveyed using self-de-signed questionnaires. Three hundred and forty questionnaires were recovered and 334 out of them were valid. Data were collected and questionnaires were analyzed.

RESULTSThe incidence of needlestick injuries was 60.8%; the incidence of needlestick injuries was substantially higher at the early stage than at the late stage of the internship, and higher in the day shift than in the night shift. Moreover, the incidence of needlestick injuries was the highest during the removal of a syringe or infusion needle, accounting for 24.3% of the total incidence. Some other significant factors for needlestick injuries in student nurses included education level, reports on oc-cupational exposure, constant update of nursing knowledge, regular hematological examination, and relevant training experiences. According to 61.7% of student nurses, clinical operations were affected due to underlying concern about needlestick injuries.

CONCLUSIONMore attention should be paid to high incidence of needlestick injuries in student nurses, especially at the early stage of their internship. To reduce the incidence of needlestick injuries, education on occupational protection should be given to student nurses in advance, and the pre-job training should be enhanced.

Accidents, Occupational ; statistics & numerical data ; Humans ; Incidence ; Internship and Residency ; Needles ; Needlestick Injuries ; epidemiology ; Nurses ; Risk ; Students ; Surveys and Questionnaires