Application of Improved LSTM Algorithm in Macroeconomic Forecasting.

From a macro perspective, futures index of agricultural products can reflect the trend of macroeconomy and can also have an early warning effect on the possible crisis and provide a reference for the government's economic forecast and macro control. Therefore, it is necessary to strengthen the research on early warning and prediction of agricultural futures price. For the prediction of futures price, there are two kinds of common models: one is the traditional classic time series model, and the other is the neural network model under the wave of artificial intelligence. This paper selects the 1976 closing data of agricultural futures index from January 10, 2012, to February 27, 2020, and uses the time series differential autoregressive integrated moving average model (ARIMA model) and long short-term memory model (LSTM model) to study this work, respectively, and compares the predicted effects of the two models in some metrics. Based on the predicted results of the two models, a simple trading strategy is established, and the trading effects of the two models are compared. The results show that the LSTM model has obvious advantage over ARIMA time series model in the price index prediction of agricultural futures market.

Head-To-Head Comparison of Treatment Failure and Costs among COPD Patients Who Used Noninvasive Ventilation in the Ward versus in the ICU: A Propensity-Matched Cohort Study.

Background: Head-to-head comparison of treatment failure and costs among chronic obstruct pulmonary disease (COPD) patients who used noninvasive ventilation (NIV) in the ward versus in the ICU is lacking. Methods: This retrospective study was performed in a department of respiratory and critical care medicine in a teaching hospital. COPD patients who used NIV in the respiratory ward or respiratory ICU were screened. We enrolled patients with PaCO2 more than 45 mmHg and pH less than 7.35 before the use of NIV. Results: We enrolled 83 patients who initiated NIV in the ward and 319 patients in the ICU. Only 5 (6%) patients in the ward were required to transfer to ICU for intensive care. The vital signs were worse but improved faster within 24 h of NIV among patients in the ICU than those in the ward. The NIV failure, hospital mortality, and the length of stay in hospital did not differ between the two groups. However, the duration of NIV was shorter (median 4.0 vs. 6.1 days, p < 0.01) and hospital costs were higher (median 4638 vs. 3093 $USD, p < 0.01) among patients in the ICU than those in the ward. After propensity matching, 42 patients were left in each group, and the baseline data were comparable between the two groups. The findings in the overall cohort were confirmed again in the propensity-matched cohort. Conclusions: Among COPD patients, the use of NIV in the ward leads to longer duration of NIV, but lower hospital costs, and similar NIV failure and mortality compared with those in the ICU.

Assessment of heart rate, acidosis, consciousness, oxygenation, and respiratory rate to predict noninvasive ventilation failure in hypoxemic patients.

PURPOSE: To develop and validate a scale using variables easily obtained at the bedside for prediction of failure of noninvasive ventilation (NIV) in hypoxemic patients. METHODS: The test cohort comprised 449 patients with hypoxemia who were receiving NIV. This cohort was used to develop a scale that considers heart rate, acidosis, consciousness, oxygenation, and respiratory rate (referred to as the HACOR scale) to predict NIV failure, defined as need for intubation after NIV intervention. The highest possible score was 25 points. To validate the scale, a separate group of 358 hypoxemic patients were enrolled in the validation cohort. RESULTS: The failure rate of NIV was 47.8 and 39.4% in the test and validation cohorts, respectively. In the test cohort, patients with NIV failure had higher HACOR scores at initiation and after 1, 12, 24, and 48 h of NIV than those with successful NIV. At 1 h of NIV the area under the receiver operating characteristic curve was 0.88, showing good predictive power for NIV failure. Using 5 points as the cutoff value, the sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy for NIV failure were 72.6, 90.2, 87.2, 78.1, and 81.8%, respectively. These results were confirmed in the validation cohort. Moreover, the diagnostic accuracy for NIV failure exceeded 80% in subgroups classified by diagnosis, age, or disease severity and also at 1, 12, 24, and 48 h of NIV. Among patients with NIV failure with a HACOR score of >5 at 1 h of NIV, hospital mortality was lower in those who received intubation at ≤12 h of NIV than in those intubated later [58/88 (66%) vs. 138/175 (79%); p = 0.03). CONCLUSIONS: The HACOR scale variables are easily obtained at the bedside. The scale appears to be an effective way of predicting NIV failure in hypoxemic patients. Early intubation in high-risk patients may reduce hospital mortality.