Objective: To construct a deep learning model based on convolutional neural network(CNN)-long short term memory network(LSTM)-Attention to explore the correlation between meteorological and clinical factors and the incidence of ischemic stroke. Methods: A fusion model CNN-LSTM-Attention based on CNN, LSTM, and Attention was constructed by incorporating clinical data and meteorological data of ischemic stroke inpatients. The predictive performance of the model was evaluated by maximum prediction error and root mean square error(RMSE). The impact of different lag days on prediction performance was investigated by selecting lag periods ranging from 1 to 7 days. Results: In both short-term and long-term predictions, the CNN-LSTM-Attention fusion model(short-term: 1.5 and 0.6; long-term: 8.3 and 2.5) showed superior maximum prediction bias and RMSE compared to the LSTM model(short-term: 2.8 and 1.2; long-term: 19.5 and 5.5) and the CNN-LSTM model(short-term: 2.0 and 0.8; long-term: 11.2 and 3.3). After incorporating lag days, the maximum prediction deviation and RMSE for lags of 3 days(short-term: 0.7 and 0.4; long-term: 5.5 and 1.9) and 5 days(short-term: 0.8 and 0.3; long-term: 6.5 and 2.0) in both short-term and long-term forecasts were smaller than lags of 0 days(short-term: 1.5 and 0.6; long-term: 8.3 and 2.5). The maximum prediction deviation and RMSE in the short-term forecast were greater than lag 0 days for both lag 1 days(1.5 and 0.8) and lag 7 days(1.9 and 0.9). In the long-term forecast, the two indicators for lag 1 days(6.8 and 2.4) were lower than those for lag 0 days but higher than those for lag 3 days and 5 days. The maximum prediction deviation for lag 7 days(7.5) was lower than that for lag 0 days, but the RMSE(2.7) is higher than that for lag 0 days. Conclusion The established CNN-LSTM-Attention model demonstrates significant predictive value for the onset of ischemic stroke and can provide reference for the rational allocation of medical resources.

Objective To investigate the effect of drug dependence severity on the relationship between impulsivity and craving.Methods 36 abstiuent drug-dependent individuals were recruited in the study.The participants were divided into the heavy depeudence group (HDG) or the low dependence group (LDG) according to the scores of Addiction Severity Index (ASI).The Barratt Impulsiveness Scale (BIS-11) and classical Stroop task were used to measure the trait impulsivity and state impulsivity.Block designed cue-induced craving paradigm was presented to measure cue-elicited craving.Results For the HDG,a significant positive correlation was found between trait impulsivity (the mean value of BIS-11-CI scale was (39.03± 16.50)) or state impulsivity (the difference of reaction time between congruent and incongruent situation was (87.77±36.95)ms)and cue-elicited craving (0.83± 1.91)(r=0.487,0.500,P＜0.05).However,for the LDG subjects,the impulsivity was not found significantly correlated with the cue-elicited craving(r=-0.261,0.081,P＞0.05).Conclusion The addiction severity influences the relationship between impulsivity and craving,and impulsivity can only be used as a predictor of relapse in HDG.The findings suggest that the drug may influence the shared brain mechanism between impulsivity and craving.