A Mortality Risk Assessment Approach on ICU Patients Clinical Medication Events Using Deep Learning

ICU patients are vulnerable to medications,especially infusion medications,and the rate and dosage of infusion drugs may worsen the condition.The mortality prediction model can monitor the real-time response of patients to drug treatment,evaluate doctors’treatment plans to avoid severe situations such as inverse Drug-Drug Interactions(DDI),and facilitate the timely intervention and adjustment of doctor’s treatment plan.The treatment process of patients usually has a time-sequence relation(which usually has the missing data problem)in patients’treatment history.The state-of-the-art method to model such time-sequence is to use Recurrent Neural Network(RNN).However,sometimes,patients’treatment can last for a long period of time,which RNN may not fit for modelling long time sequence data.Therefore,we propose to use the heterogeneous medication events driven LSTM to predict the outcome of the patient,and the Natural Language Processing and Gaussian Process(GP),which can handle noisy,incomplete,sparse,heterogeneous and unevenly sampled patients’medication records.In our work,we emphasize the semantic meaning of each medication event and the sequence of the medication events on patients,while also handling the missing value problem using kernel-based Gaussian process.We compare the performance of LSTM and Phased-LSTM on modelling the outcome of patients’treatment and data imputation using kernel-based Gaussian process and conduct an empirical study on different data imputation approaches.

Clinical characteristics and mortality risk prediction model in children with acute myocarditis

Background Acute myocarditis(AMC)can cause poor outcomes or even death in children.We aimed to identify AMC risk factors and create a mortality prediction model for AMC in children at hospital admission.Methods This was a single-center retrospective cohort study of AMC children hospitalized between January 2016 and January 2020.The demographics,clinical examinations,types of AMC,and laboratory results were collected at hospital admission.In-hospital survival or death was documented.Clinical characteristics associated with death were evaluated.Results Among 67 children,51 survived,and 16 died.The most common symptom was digestive disorder(67.2%).Based on the Bayesian model averaging and Hosmer–Lemeshow test,we created a final best mortality prediction model(acute myocarditis death risk score,AMCDRS)that included ten variables(male sex,fever,congestive heart failure,left-ventricular ejection fraction<50%,pulmonary edema,ventricular tachycardia,lactic acid value>4,fulminant myocarditis,abnormal creatine kinase-MB,and hypotension).Despite differences in the characteristics of the validation cohort,the model discrimination was only marginally lower,with an AUC of 0.781(95%confidence interval=0.675–0.852)compared with the derivation cohort.Model calibration likewise indicated acceptable fit(Hosmer‒Lemeshow goodness-of-fit,P¼=0.10).Conclusions Multiple factors were associated with increased mortality in children with AMC.The prediction model AMCDRS might be used at hospital admission to accurately identify AMC in children who are at an increased risk of death.

Investigation of the risk factors associated with early mortality of the rapid two-stage arterial switch operation

Objective To investigate the risk factors associated with early mortality of the rapid two-stage arerial switch operation,which has a significantly higher overall mortality than that of ASO procedure for D-TGA with an intact ventricular septum. Methods The data we reviewed involving patients who underwent rapid two-stage switch operations from September,2002 to September,2007 in our center,13 patients were male and 8

Development and Validation of a Prognostic Risk Score System for COVID-19 Inpatients:A Multi-Center Retrospective Study in China

Coronavirus disease 2019(COVID-19)has become a worldwide pandemic.Hospitalized patients of COVID-19 suffer from a high mortality rate,motivating the development of convenient and practical methods that allow clinicians to promptly identify high-risk patients.Here,we have developed a risk score using clinical data from 1479 inpatients admitted to Tongji Hospital,Wuhan,China(development cohort)and externally validated with data from two other centers:141 inpatients from Jinyintan Hospital,Wuhan,China(validation cohort 1)and 432 inpatients from The Third People’s Hospital of Shenzhen,Shenzhen,China(validation cohort 2).The risk score is based on three biomarkers that are readily available in routine blood samples and can easily be translated into a probability of death.The risk score can predict the mortality of individual patients more than 12 d in advance with more than 90%accuracy across all cohorts.Moreover,the Kaplan-Meier score shows that patients can be clearly differentiated upon admission as low,intermediate,or high risk,with an area under the curve(AUC)score of 0.9551.In summary,a simple risk score has been validated to predict death in patients infected with severe acute respiratory syndrome coronavirus 2(SARS-CoV-2);it has also been validated in independent cohorts.

Flame Burn Injury in Yichang of China:the Trends,Complications,and Risk Factor Analysis

Background A flame burn is an injury of body tissues,including respiratory tract damage,due to exposure to a flame or its dense smoke.Flame burns cause some of the most physically and psychologically devastating forms of trauma.Compared to scald burns,flame burn patients have a higher mortality rate and a higher frequency of multiorgan failure.The purpose of this research was to investigate the trends,complications,and mortality risk factors of flame burns at the Department of Plastic and Burn Surgery(DPBS)of the People’s Hospital of China Three Gorges University(PHCTGU).Methods A retrospective analysis of 48 flame burn patients—accounting for 8.3%of the 576 burn victims admitted for burns at the PHCTGU from February 1,2010,to September 30,2019—was performed after collecting information from the Burns Registry of the said hospital.Results The proportion of patients with flame burns was 8.3%(n=48).The mean total body surface area(TBSA)affected was 27.6%.The mean duration of hospitalization was 32.5 days.The etiologies of the flame burns were as follows:gas explosions(21,43.8%),ethanol(8,16.7%),charcoal fire(7,14.6%),petrol explosions(4,8.3%),wooden houses(4,8.3%),and others,including dust,cigarette lighter,and burning incense,accounting for 8.3%of cases(4).Finally,42(87.5%)patients were treated and discharged,and 6(12.5%)patients died.Complications included scarring in 38(90.5%)patients,severe scar contractures on different parts of the body in 25(60.0%)patients,scar ulcer in 6(14.3%)patients,keloids in 3(7.1%)patients,and scar cancer in 1(2.4%)patient.Multiple complications occurred in the same patient.The only risk factor for mortality that was identified was TBSA(P=0.043).Conclusions Our study revealed that a small population(8.3%)was injured by flame burns,but 6 deaths were recorded.Society must continually enhance safeguard procedures to flames and strengthen education to protect life and avoid severe complications.

Bloodstream Infections Caused by Enterococcus spp：A 10-year Retrospective Analysis at a Tertiary Hospital in China

In order to discover the risk factors for 30-day mortality in bloodstream infections（BSI） caused by Enterococcus spp.strains,we explored the clinical and therapeutic profile of patients with Enterococcus spp.BSI and the characteristics of this condition.A total of 64 patients with BSI caused by Enterococcus spp.who were treated in our hospital between 2006 and 2015 were included in the study.The clinical features of patients,microbiology,and 30-day mortality were collected from the electronic medical records database and analyzed.The results showed that there were 38 patients infected by Enterococcus faecalis（E.faecalis）,24 by Enterococcus faecium（E.faecium）,1 by Enterococcus casseliflavus（E.casseliflavus）,and 1 by Enterococcus gallinarum（E.gallinarum）.A Charlson comorbidity score ≥5,corticosteroid treatment,placement of catheters or other prosthetic devices and history of antibiotic use were found more frequently in E.faecium BSI patients than in E.faecalis patients（P=0.017,P=0.027,P=0.008 and P=0.027,respectively）.Furthermore,the univariate and multivariate analysis showed that corticosteroid treatment（OR=17.385,P=0.008）,hospital acquisition（OR=16.328,P=0.038）,and vascular catheter infection（OR=14.788,P=0.025） were all independently associated with 30-day mortality.Our results indicate that E.faecalis and E.faecium are two different pathogens with unique microbiologic characteristics,which cause different clinical features in BSI,and the empiric antimicrobial treatments are paramount for patients with enterococcal BSI.

A Novel Innovative Sleeping Mattress Could Possibly Save Lives and the National Economy: Small but Solid Evidence from a Medical Perspective

The RAND Corporation reported that insufficient sleep causes an economic loss of $138 billion (2.92% of GDP) in Japan every year. In this study, we investigated the sleep improvement effect of a novel innovative sleeping mattress called “AiR SI” (Nishikawa Co., Ltd.) to find a simple method to solve the problem of sleep deprivation. We conducted a 2-week randomized, open-label, crossover, self-controlled study in 14 healthy adults in their 30s to 50s (control: 1 week, AiR SI: 1 week), with sleep quality as the primary endpoint as well as salivary components (cortisol, melatonin) and autonomic nervous function (sympathetic nerve, parasympathetic nerve) as secondary endpoints. Trends toward improvement in sleep were suggested for all the endpoints, regardless of differences in the subject background. The results suggested that the use of AiR SI for 1 week not only improved sleep but normalized both the endocrine and autonomic functions as well. We conclude that, by using a sleeping mattress with a high sleep improvement effect, the user may easily achieve higher labor productivity and have a lower mortality risk. Eliminating sleep deprivation with a sleeping mattress may lead to a reduction in national economic losses and ultimately produce significant economic effects.

直接和间接消费所引起的中国城乡空气污染相关过早死亡不平等性

Household consumption in China is associated with substantial PM_(2.5)pollution,through activities directly(i.e.,fuel use)and/or indirectly(i.e.,consumption of goods and services)causing pollutant emissions.Urban and rural households exhibit different consumption preferences and living areas,thus their contributions to and suffering from air pollution could differ.Assessing this contrast is crucial for comprehending the environmental impacts of the nation’s ongoing urbanization process.Here we quantify Chinese urban and rural households’contributions to ambient PM_(2.5)pollution and the health risks they suffer from,by integrating economic,atmospheric,and health models and/or datasets.The national premature deaths related to long-term exposure to PM_(2.5)pollution contributed by total household consumption are estimated to be 1.1 million cases in 2015,among which 56%are urban households and 44%are rural households.For pollution contributed indirectly,urban households,especially in developed provinces,tend to bear lower mortality risks compared with the portions of deaths or pollution they contribute.The opposite results are true for direct pollution.With China’s rapid urbanization process,without adequate reduction in emission intensity,the increased indirect pollution-associated premature deaths could largely offset that avoided by reduced direct pollution,and the indirect pollution-associated urban–rural inequalities might become severer.Developing pollution mitigation strategies from both production and consumption sides could help with reducing pollution-related mortality and associated urban-rural inequality.

Subjective well-being and mortality among the older people in China

The present study investigates the effects of subjective well-being(SWB)on mortality risk using a large sample from the Chinese Longitudinal Healthy Longevity Study conducted in 1998,2000,2002,2005,2008,2011 and 2014.SWB is measured by life satisfaction,positive affect and negative affect.We found that positive affect,negative affect,life satisfaction and the change of life satisfaction significantly have predicted mortality risks of the older people with control of social demographic characteristics,physical health,social support,cognitive ability,and social participation.The higher the positive affect,the lower the negative affect,the improvement the life satisfaction,the lower the mortality risk.Marital status plays a decisive role in the influence of life satisfaction on the mortality risk.The married persons have lower mortality risk even if they rate their life bad.In further analyses,we found that the effects of SWB on mortality risk were underestimated in short-term study compared with those in long-term study.SWB is essentially a time-dependent variable and changes with age,so treating SWB as time-independent variable underestimated its impact on mortality risk.

综合气象致灾因子影响人口、死亡人口与GDP损失风险的制图与排名（英文）

Coping with extreme climate events and its related climatic disasters caused by climate change has become a global issue and drew wide attention from scientists, policy-makers and public. This paper calculated the expected annual multiple climatic hazards intensity index based on the results of nine climatic hazards including tropical cyclone, flood, landslide, storm surge, sand-dust storm, drought, heat wave, cold wave and wildfire. Then a vulnerability model involving the coping capacity indicator with mortality rate, affected population rate and GDP loss rate, was developed to estimate the expected annual affected population, mortality and GDP loss risks. The results showed that： countries with the highest risks are also the countries with large population or GDP. To substantially reduce the global total climatic hazards risks, these countries should reduce the exposure and improving the governance of integrated climatic risk; Without considering the total exposure, countries with the high mortality rate, affected population rate or GDP loss rate, which also have higher or lower coping capacity, such as the Philippines, Bangladesh and Vietnam, are the hotspots of the planning and strategy making for the climatic disaster risk reduction and should focus on promoting the coping capacity.

Magnitude and Determinants of Mortalities Related to COVID-19:Evidence from 94 Countries Using Regression Techniques

This study attempts to investigate the factors determining COVID-19 deaths during the pandemic across countries by employing a rich dataset sourced from 94 countries updated till 6 February,2022.For empirical analysis,the study makes use of cross-sectional linear regression technique in the first part and after required diagnostic tests use 2SLS regression technique for correcting possible endogeneity bias in the second part.Findings from the study indicate that factors like total reported cases,population size,population over 70 years of age,extreme poverty,and human development index play significant role in determining COVID-19-related death.Further,to check the robustness of the findings the present study employed LASSO regression.Findings from the study highlight the possibility of government intervention to devise appropriate policies to control COVID-related incidence and death.

Important scoring systems for assessing the severity of COVID-19 based on COVID-19-related deaths in Wuhan,China

Background:This study aimed to investigate the clinical characteristics of 21 deaths and evaluate potential factors affecting disease severity and mortality risk in patients with coronavirus disease(COVID-19).Methods:This retrospective analysis assessed clinical data of 21 patients who died owing to COVID-19.Disease severity and mortality risk were assessed using Acute Physiology and Chronic Health Evaluation Ⅱ(APACHE Ⅱ);Sepsis-related Organ Failure Assessment(SOFA);multilobular infiltration,hypo-lymphocytosis,bacterial coinfection,smoking history,hypertension and age(MuLBSTA);and pneumonia severity index(PSI)scores.Results:The mean age of the patients was 66±14 years and 15(71.4%)patients were men.Sixteen(76.2%)patients had chronic medical illnesses.Twelve(57.1%)patients were overweight.Decreased lymphocyte proportions were observed in 17(81.0%)patients on admission.Elevated D-dimer levels were observed in 11(52.4%)patients,and the levels significantly increased when pneumonia deteriorated.The initial APACHE II and SOFA scores demonstrated that 18(85.7%)and 13(61.9%)patients,respectively,were in the middle-risk level.MuLBSTA and PSI scores after admission were associated with higher risks of mortality in 13(61.9%)patients.Most patients developed organ failure and subsequently died.Conclusions:Older,overweight,male patients with a history of chronic illnesses and continuously decreased lymphocyte proportions and increased D-dimer levels might have higher risks of death owing to COVID-19.The combination of general scoring(SOFA)and pneumonia-specific scoring(MuLBSTA and PSI)systems after admission might be sensitive in assessing the mortality risk of patients with COVID-19 who are in critical condition.

Analysis of Factors Associated with Death in Maintenance Hemodialysis Patients： A Multicenter Study in China

Background： Patients on hemodialysis have a high-mortality risk. Tiffs study analyzed factors associated with death in patients on maintenance hemodialysis （MHD）. While some studies used baseline data of MHD patients, this study used the most recent data obtained from patients just prior to either a primary endpoint or the end of the study period to iliad the characteristics of patients preceding death.Methods： Participants were selected from 16 blood purification centers in China from January 2012 to December 2014, Patients＇ data were collected retrospectively. Based on survival status, the participants were divided into two groups： survival group and the death group. Logistic regression analysis was performed to determine/＇actors associated with all-cause mortality.