General short-term load forecasting based on multi-task temporal convolutional network in COVID-19

The spread of the global COVID-19 epidemic has resulted in significant shifts in electricity consumption compared to regular days. It is unknown if standard single-task, single-indicator load forecasting algorithms can accurately reflect COVID-19 load patterns. Power practitioners urgently want a simple, efficient, and accurate solution for anticipating reliable load. In this paper, we first propose a unique collaborative TCN-LSTM-MTL short-term load forecasting model based on mobility data, temporal convolutional networks, and multi-task learning. The addition of the parameter sharing layers and the structure with residual convolution improves the data input diversity of the forecasting model and enables the model to obtain a wider time series receptive field. Then, to demonstrate the usefulness of the mobility optimized TCN-LSTM-MTL, tests were conducted in three levels and twelve base regions using 19 different benchmark models. It is capable of controlling predicting mistakes to within 1 % in the majority of tasks. Finally, to rigorously explain the model, the Shapley additive explanations (SHAP) visual model interpretation technology based on game theory is introduced. It examines the TCN-LSTM-MTL model's internal mechanism at various time periods and establishes the validity of the mobility indicators as well as the asynchronous relationship between indicator significance and real contribution.

Risk Factors of In-hospital Death in COVID-19 Patients：a Meta-analysis

Background The worldwide COVID-19 pandemic has turned into a global catastrophic public health crisis，and the conclusion about the risk factors of hospital death in COVID-19 patients is not uniform. Objective To explore risk factors of in-hospital death in patients with COVID-19 by a meta-analysis. Methods Case-control studies about risk factors of in-hospital death in COVID-19 patients were searched from databases of the Cochrane Library，ScienceDirect，PubMed，Medline，Wanfang Data，CNKI and CQVIP from inception to October 1，2021. Literature screening，data extraction and methodological quality assessment were conducted. Meta-analysis was performed using Stata 15.1. Meta-regression was used to explore the potential sources of heterogeneity. Results Eighty studies were included which involving 405 157 cases〔349 923 were survivors（86.37%），and 55 234 deaths（13.63%）〕，that were rated as being of high quality by the Newcastle-Ottawa Scale. Meta-analysis showed that being male〔OR=1.49，95%CI（1.41，1.57），P<0.001），older age〔WMD=10.44，95%CI（9.79，11.09），P<0.001〕，dyspnoea〔OR=2.09，95%CI（1.80，2.43），P<0.001〕，fatigue〔OR=1.49，95%CI（1.31，1.69），P<0.001〕，obesity〔OR=1.46，95%CI（1.43，1.50），P<0.001〕，smoking〔OR=1.18，95%CI （1.14，1.23），P<0.001〕，stroke〔OR=2.26，95%CI（1.41，3.62），P<0.001〕，kidney disease〔OR=3.62，95%CI （3.26，4.03），P<0.001〕，cardiovascular disease〔OR=2.34，95%CI（2.21，2.47），P<0.001〕，hypertension〔OR=2.23，95%CI（2.10，2.37），P<0.001〕，diabetes〔OR=1.84，95%CI（1.74，1.94），P<0.001〕，cancer〔OR=1.86，95%CI （1.69，2.05），P<0.001〕，pulmonary disease〔OR=2.38，95%CI（2.19，2.58），P<0.001〕，liver disease〔OR=1.65，95%CI（1.36，2.01），P<0.001〕，elevated levels of white blood cell count〔WMD=2.03，95%CI（1.74，2.32），P<0.001〕，neutrophil count〔WMD=1.77，95%CI（1.49，2.05），P<0.001〕，total bilirubin〔WMD=3.19，95%CI（1.96，4.42），P<0.001〕，aspartate transaminase〔WMD=13.02，95%CI（11.70，14.34），P<0.001〕，alanine transaminase 〔WMD=2.76，95%CI（1.68，3.85），P<0.001〕，lactate dehydrogenase〔WMD=166.91，95%CI（150.17，183.64），P<0.001〕，blood urea nitrogen〔WMD=3.11，95%CI（2.61，3.60），P<0.001〕，serum creatinine〔WMD=22.06，95%CI （19.41，24.72），P<0.001〕，C-reactive protein〔WMD=76.45，95%CI （71.33，81.56），P<0.001〕，interleukin-6 〔WMD=28.21，95%CI（14.98，41.44），P<0.001〕，and erythrocyte sedimentation rate〔WMD=8.48，95%CI（5.79，11.17），P<0.001〕were associated with increased risk of in-hospital death for patients with COVID-19，while myalgia〔OR=0.73，95%CI（0.62，0.85），P<0.001〕，cough〔OR=0.87，95%CI（0.78，0.97），P=0.013〕，vomiting〔OR=0.73，95%CI （0.54，0.98），P=0.030〕，diarrhoea〔OR=0.79，95%CI（0.69，0.92），P=0.001〕，headache〔OR=0.55，95%CI（0.45，0.68），P<0.001〕，asthma〔OR=0.73，95%CI（0.69，0.78），P<0.001〕，low body mass index〔WMD=-0.58，95%CI （-1.10，-0.06），P=0.029〕，decreased lymphocyte count〔WMD=-0.36，95%CI（-0.39，-0.32），P<0.001〕，decreased platelet count 〔WMD=-38.26，95%CI（-44.37，-32.15），P<0.001〕，increased D-dimer〔WMD=0.79，95%CI（0.63，0.95），P<0.001〕，longer prothrombin time〔WMD=0.78，95%CI（0.61，0.94），P<0.001〕，lower albumin〔WMD =-1.88，95%CI（-2.35，-1.40），P<0.001〕，increased procalcitonin〔WMD=0.27，95%CI（0.24，0.31），P<0.001〕，and increased cardiac troponin〔WMD=0.04，95%CI（0.03，0.04），P<0.001〕were associated with decreased risk of in-hospital death due to COVID-19. According to the meta-regression result，the heterogeneity in gender，renal disease，cardiovascular diseases，asthma，white blood cell count，neutrophil count，platelet count，hemoglobin，and urea nitrogen differed siangificnatly by country（P<0.05）. Conclusion The risk of in-hospital death due to COVID-19 may be increased by 25 factors（including being male，older age，dyspnoea，fatigue，obesity，smoking，stroke，kidney disease，cardiovascular disease，hypertension，diabetes，cancer，pulmonary disease，liver disease，elevated levels of white blood cells，neutrophil count，total bilirubin，aspartate transaminase，alanine transaminase，lactate dehydrogenase，blood urea nitrogen，serum creatinine，C-reactive protein，interleukin-6，and erythrocyte sedimentation rate），and may be decreased by 13 factors（including myalgia，cough，vomiting，diarrhoea，headache，asthma，low body mass index，decreased lymphocyte count and platelet count，increased D-dimer，longer prothrombin time，lower albumin，increased procalcitonin and cardiac troponin）. The conclusion drawn from this study needs to be further confirmed by high-quality，multicenter，large-sample，real-world studies. © 2023 Chinese General Practice. All rights reserved.

Thyroid hormone concentrations in severely or critically ill patients with COVID-19.

OBJECTIVE: COVID-19 is a new coronavirus infectious disease. We aimed to study the characteristics of thyroid hormone levels in patients with COVID-19 and to explore whether thyroid hormone predicts all-cause mortality of severely or critically ill patients. METHODS: The clinical data of 100 patients with COVID-19, who were admitted to Wuhan Tongji Hospital from February 8 to March 8, 2020, were analyzed in this retrospective study. The patients were followed up for 6-41 days. Patients were grouped into non-severe illness and severe or critical illness, which included survivors and non-survivors. Multivariate Cox proportional hazards analysis was used to estimate hazard ratios (HRs) and 95% confidence intervals (CIs) for all-cause mortality in association with continuous and the lower two quartiles of thyroid hormone concentrations in severely or critically ill patients. RESULTS: The means of free T3 (FT3) were 4.40, 3.73 and 2.76 pmol/L in non-severely ill patients, survivors and non-survivors, respectively. The lower (versus upper) two quartiles of FT3 was associated with all-cause mortality HR (95% CI) of 9.23 (2.01, 42.28). The HR (95% CI) for all-cause mortality in association with continuous FT3 concentration was 0.41 (0.21, 0.81). In the multivariate-adjusted models, free T4 (FT4), TSH and FT3/FT4 were not significantly related to all-cause mortality. Patients with FT3 less than 3.10 pmol/L had increased all-cause mortality. CONCLUSION: FT3 concentration was significantly lower in patients with severe COVID-19 than in non-severely ill patients. Reduced FT3 independently predicted all-cause mortality of patients with severe COVID-19.