Background: This study intends to identify the best model for predicting the incidence of hand, foot and mouth disease (HFMD) in Ningbo by comparing Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory Neural Network (LSTM) models combined and uncombined with exogenous meteorological variables. Methods: The data of daily HFMD incidence in Ningbo from January 2014 to November 2017 were set as the training set, and the data of December 2017 were set as the test set. ARIMA and LSTM models combined and uncombined with exogenous meteorological variables were adopted to fit the daily incidence of HFMD by using the data of the training set. The forecasting performances of the four fitted models were verified by using the data of the test set. Root mean square error (RMSE) was selected as the main measure to evaluate the performance of the models. Results: The RMSE for multivariate LSTM, univariate LSTM, ARIMA and ARIMAX (Autoregressive Integrated Moving Average Model with Exogenous Input Variables) was 10.78, 11.20, 12.43 and 14.73, respectively. The LSTM model with exogenous meteorological variables has the best performance among the four models and meteorological variables can increase the prediction accuracy of LSTM model. For the ARIMA model, exogenous meteorological variables did not increase the prediction accuracy but became the interference factor of the model. Conclusions: Multivariate LSTM is the best among the four models to fit the daily incidence of HFMD in Ningbo. It can provide a scientific method to build the HFMD early warning system and the methodology can also be applied to other communicable diseases.

Little is known about the association between spicy food intake, dietary approaches to stop hypertension (DASH) score, and incident stroke. This study aimed to explore the association of eating spicy food, DASH score, and their interaction with stroke incidence. We included 22,160 Han residents aged 30–79 in southwest China from the China Multi-Ethnic Cohort. Three hundred and twelve cases were newly diagnosed with stroke by October 8, 2022, during a mean of 45.5 months of follow-up. Cox regression analyses showed that eating spicy food reduced stroke risk by 34% among people with low DASH scores (HR 0.66, 95%CI 0.45–0.97), while individuals with high DASH scores versus low DASH scores had a 46% lower stroke incidence among spicy food nonconsumers (HR 0.54, 95%CI 0.36–0.82). The HR of the multiplicative interactive term was 2.02 (95%CI 1.24–3.30) and the overall estimates of relative excess risk due to interaction (RERI), attributable proportion due to interaction (AP), and the synergy index (S) were 0.54 (95%CI 0.24–0.83), 0.68 (95%CI 0.23–1.14), and 0.29 (95%CI 0.12–0.70), respectively. Consuming spicy food seems to be associated with lower stroke risk only in people who have a lower DASH score, while the beneficial effect of higher DASH scores seems to be found only among nonconsumers of spicy food, and a negative interaction may exist between them in southwestern Chinese aged 30–79. This study could provide scientific evidence for dietary guidance to reduce stroke risk.

China has the largest number of dementia patients in the world, posing a significant health and economic burden. Alzheimer's disease (AD) and other dementia patients face a higher risk of mortality during heatwaves, but relevant studies on this topic have been limited so far. The study extracted data from the China Cause of Death Reporting System (CDRS) on deaths of AD and other dementia patients aged 60 years and above between 2013 and 2020. Using an individual-level, time-stratified, and case-crossover study design, the effects of heatwaves across nine scenarios on dementia mortality were quantified by conditional logistic regression combined with distributed lag non-linear model (DLNM). Additionally, the attributable fractions (AFs) of deaths due to heatwaves were calculated. A total of 399,036 death cases were reported caused by AD and other dementias during the study period. It was found that heatwaves significantly increased the risk of death among people with AD and other dementias. As the intensities and durations of the heatwaves increased, the lag0-7 cumulative odds ratios (CORs) of mortality increased progressively from 1.140 (95% CI: 1.118, 1.163) under the mildest heatwave to 1.459 (95% CI: 1.403, 1.518) under the most severe one, across nine heatwave scenarios examined. Additionally, under specific heatwave scenarios, sex and regions modified the mortality risk, but no significant age differences were observed. The AFs of AD and other dementia mortality due to milder heatwaves were lower compared to more severe heatwaves, ranging from 12.281% (95% CI: 10.555%, 14.015%) to 31.460% (95% CI: 28.724%, 34.124%). The study provided critical insights into the substantial increase in heatwave-related mortality among AD and other dementia patients during and after heatwave events. The results from our quantitative analyses will provide needed scientific evidence for policymakers and practitioners to develop relevant policies and guidelines to protect the health and well-beings of vulnerable populations in future in the context of both seasonal changes and long-term climate change. This work was supported by the Project of Prevention and Intervention on Major Diseases for Elderly in China, NCNCD [00240201307], the 10.13039/501100012166 National Key Research and Development Program of China [2022YFC2602301, 2023YFC2308703] and the Science and Technology Fundamental Resources Investigation Program of China [2017FY101201].

Parkinson's disease (PD) is a prevalent neurodegenerative disorder with significant negative health and economic implications for individuals, families and society. This study utilized an individual‐level time‐stratified case‐crossover study design to investigate the relationship between ambient temperatures and PD mortality among the elderly in China. A combination of conditional logistic regression and distributed lag non‐linear model was employed to analyze the data, and the mortality burden attributed to ambient temperatures was quantified. The study included a total of 59,397 deceased PD patients aged 60 years and above who died between 2013 and 2020. Findings revealed that the effects of extremely low temperature (−1°C) could persist for up to 14 days, while the impacts of extremely high temperature (30°C) were acute and last for 4 days and showing a significant harvest effect. For the overall population, the high temperatures significantly increased the risk of death, where low temperature did not. A lag0‐14 cumulative odds ratios (COR) of extremely low temperature compared to the reference temperature (15°C) was 1.024 (95% CI: 0.971, 1.080). The lag0‐14 COR of extremely high temperature was 1.206 (95% CI: 1.116, 1.304). Additionally, high temperatures attributed greater AF of 4.013 (95% eCI: 1.990, 5.894) comparing to low temperatures did of 0.762 (95% eCI: −0.624, 2.017). Significant differences were found across regions. No statistically significant differences were found between the sex and age. This nationwide study provides evidence for tailored interventions in specific regions and populations to reduce temperature‐related PD mortality among the elderly in China.