A study of Cardiac reference values and environmental factors using big data and deep learning methods

A study of Cardiac reference values and environmental factors using big data and deep learning methods | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article A study of Cardiac reference values and environmental factors using big data and deep learning methods Jing Jing, Chong Zhang, Miao Ge, Mark Rosenberg, Ziqi Yang, Peng Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2802057/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Aims The purpose of this study was to simulate the Left Ventricular Ejection Fraction (LVEF) reference values with heart rate and environmental data using LSTM deep learning methods and to derive the spatial distribution of LVEF reference values in China. Methods Heart rate and environmental factors were used as independent variables, and LVEF indicator values were used as the dependent variable. After the sample data were randomly sampled, the block acquisition data were converted into sample sequence data. Once the sequence data were processed, the sample data were input into the long- and short-term memory networks for deep learning parameter training. After repeated weighting parameter adjustment training and optimization, the optimal prediction model for adult LVEF reference values were derived. Results The LVEF reference values of normal adults showed a downward trend from moving from the south to north in China. LVEF is negatively correlated with heart rate and annual air temperature range; while positively correlated with annual mean air temperature, annual mean relative humidity, annual precipitation. Conclusions The LVEF reference values are related to heart rate and environmental factors. According to the predicted LSTM model, if the environmental factors of a region is known, combined with the heart rate data from big data, the model can be used to obtain a more accurate LVEF reference value prediction model. A predicted LSTM model is more capable of taking geographical and individual differences into account. LVEF reference values health big data deep learning methods LSTM Figures Figure 1 Figure 2 Figure 3 Introduction This paper reports on a study of deep learning methods for analysing and simulating normal adults Left Ventricular Ejection Fraction (LVEF) reference values in relation to environmental factors in China. LVEF is an important indicator of cardiac function. It means the ratio of stroke volume to ventricular end-diastolic volume. LVEF evaluates the ventricular ejection function from a volume perspective. Usually, when myocardial contraction ability is strong, then the stroke volume and the LVEF are high 1 . Heart failure can be judged by the LVEF 2 . The LVEF reference values are often used in the examination of heart disease. It provides an important reference for drug observation and surgical efficacy. According to the results of our previous studies, the LVEF reference values are closely related to the environment 7 – 10 . There is a negative correlation between heart rate and LVEF reference values 11 , 12 . Many environmental factors affect the growth and health of the human body. Specifically, many factors such as temperature, air humidity, atmospheric precipitation, solar radiation, sunshine index, negative ion content in the air, and oxygen partial pressure affect the physiological function of the human body through physiological activities such as the cardiovascular, circulatory, and endocrine systems 30 . Temperature is one of the important reasons that causes many heart diseases. The effect of temperature on the disease is generally divided into the effects of high temperature and low temperature on the disease. According to some studies, the incidence of cardiovascular disease increases with the rise of temperature when the temperature is higher than a certain range 31 . A study in South Korea showed that cardiovascular deaths caused by high temperature heat waves account for more than half of deaths 32 – 34 . Many studies have consistently shown that high temperatures can cause some adverse health effects and increase mortality 35 – 37 . In a US study, 15 of 50 cities surveyed, reported a significant relationship between summer mortality and temperature 40 . The mortality rate is significantly increased when the maximum temperature reaches 32°C or above. In addition, Canadian research was carried out in 10 cities. The results of the research also showed that the high temperatures above 29°C in summer led to an increase in mortality. Studies in China have also shown that the critical temperature for population mortality in Shanghai and Guangzhou in summer is a daily maximum temperature of 34°C 41 . A study in Nanjing found that the maximum daily temperature threshold for cardiovascular disease deaths in the summer is 32°C 42 . The mechanism of temperature effects on cardiac function can be explained by the flow of blood to the surface of the skin due to high temperature, resulting in an increased heavy burden on the heart, lungs and other body organs and the reduction in cardiac blood flow. High temperatures also increase viscosity of blood flow in the human body which increases the cholesterol level. In addition, people in hot weather are prone to irritating emotions which may lead to loss of appetite and poor sleep. High temperature can easily cause cardiovascular diseases due to the combination of various reasons. In contrast to the research on high temperatures and heart disease, a survey on the effects of hypothermia and heart disease shows that the incidence of heart disease is negatively correlated with the decrease in temperature. The lower the temperature, the higher the incidence of heart failure which reduces the LVEF. The skin increases systemic vascular resistance and heart rate increases when the outside conditions are cold. Thereby plasma norepinephrine concentration is increases leading to more circulating vasoconstrictor secretion and high blood pressure 43 , 44 . The sympathetic nerves are excited when the temperature drops to 1.5°C which causes an increase in norepinephrine and adrenaline secretion that accelerates the heart rate. The blood vessels of human skin are mainly microcirculatory vasoconstriction when the temperature is lower than 1.5°C. The peripheral vascular resistance increases 45 . Cold stimulation can cause peripheral vasoconstriction and increase systemic blood volume. At the same time, it causes an increase in circulating resistance which increases blood pressure. Sympathetic nerve excitability enhances catecholamine levels during the cold season 45 – 48 . This can promote the increase of adrenaline secreted by the adrenal medulla and accelerate the metabolism of the human body. Then heart rate and cardiac output increase. Ultimately blood pressure is elevated. Increased blood pressure, abnormal cardiovascular and cerebrovascular reactions increase stroke 49 . This also leads to the increasing of heart rate and the myocardial oxygen consumption. Peripheral vascular resistance increases when the temperature is low. Left ventricular load increases due to the increasing blood viscosity and slow blood flow. These combined effects can lead to a decrease in cardiac contractility and a decrease in LVEF. In summary, the heart rate increases and the LVEF decreases as the temperature decreases. Some studies have shown that hydrothermal conditions including humidity and temperature also have an impact on health. One study found that most diseases show high levels of distribution in high temperature and high humidity environments. Humidity is significantly positively correlated with incidence of disease when atmospheric temperature reaches an optimal range (12°C or higher) 50 . The same research results were also obtained by Qiao Liang and Feng Dexun. Relative humidity has a positive correlation with incidence of disease. The incidence of cardiovascular disease increases with the increase of humidity when the relative humidity is high 51 . Some scholars have explored the regional differences between hydrothermal conditions and the physiological phenomena of living organisms found that the heart rate is generally higher with a decrease in relative humidity 52 . The results of an analytical model on the effects of temperature and humidity on the human body indicated that heart rate is higher when relative humidity of the living environment is smaller 53 . In a normal range, an increase in normal heart rate can result in a slight increase in cardiac output due to the corresponding shortening of the systolic phase. At the same time, the heart rate is shortened, the volume of blood back to the heart is also reduced. In this situation, Stroke volume(SV) is reduced in the short-term Left ventricular end diastolic(LVEDV) changes little, so LVEF will be reduced. Relative humidity changes are also significantly associated with the incidence of heart failure 54 . Studies have also shown that high temperature and high humidity conditions can easily lead to myocardial infarction 55 , 56 . Analysis of the impact mechanism can be interpreted in that the negative ion content in the air is higher when the humidity of the air increases. Air negative ions can cause blood vessels to dilate and reduce arterial spasm. At the same time, increasing blood oxygen content can improve heart function and myocardial nutritional status 57 . The heart rate and the LVEF reference values will decrease when the relative humidity is low. The relative humidity and the LVEF reference values show a positive correlation. In this study, we explore the relationship between LVEF reference values, heart rate, and environmental data. It is argued that research results can be used to predict, observe, and even alert individuals about their health status in real time. A prediction model is developed using heart rate and environmental data to obtain LVEF reference values. The starting point of this study is to estimate difficult to obtain indicators based on the indicators that are easy to measure and obtainto simulate a simple and accurate method for obtaining LVEF reference values. Data selection Some research has reported expected cardio-vascular disease (CVD) incidence of nearly 8% in men and 3–5% in the women population, defined as fatal or nonfatal myocardial infarction, angina pectoris or stroke over a 5-year follow up period 21 . In China, a recent study reported that the rates of CVD mortality in Beijing increased by > 50% in men and > 27% in women from 1984 to 1999 22 . Using the China National Knowledge Infrastructure (CNKI) database, we had access to nearly 10 years of data from 2010 to 2020 from more than 44 cities, 184 regional units in China which included 6360 individual cases of adults (age range18-83) with LVEF and heart rate measurements (3502 are males and 2858 are females). The distribution of sampling points are seen in Fig. 1 .There was less data from Western cities than the eastern regions. The distribution of data geographically is 107 cities from eastern regions, 35 cities from middle regions and 42 cities from western regions. T-tests were employed to test the disparities of LVEF reference values among different regions, and the results had a p-value = 0.001, indicating a significant difference of LVEF reference values among regions (Table 1 ) Table 1 LVEF and heart rate data & T-test Group Total Male Female Age BMI LVEF HR P Healthy people 3502 3502 2858 18–81 18.5–25.0 50.45-75 60–88 0.001 The subjects were apparently healthy. The inclusion criteria were normal weight and height (body mass index > 18.5 but < 25.0, in Kg/m2), normal blood pressure, normal blood glucose and 8 hours fasting before testing blood. The primary exclusion criteria were hepatobiliary and kidney diseases (fatty liver, liver cirrhosis, hepatitis, nephritis, kidney stone, ect.), blood diseases (hemangioma, disturbance of blood circulation, other blood abnormities and so on) and hepatobiliary ultrasound abnormalities. The cardiac normal adults were selected according to the following standards 23 : (1) Confirmed normal size of the left ventricular cavity and no myocardial dysmotility;(2) Ventricular arrhythmia and non-pacing rhythm, no tachycardia and bradycardia;(3) Left ventricular myocardium without myocardial infarction or segmental ischemia;(4) Left ventricular outflow tract without abnormal structure;(5) Left heart valve no obvious morphological and functional abnormalities (no obvious stenosis and regurgitation); and (6) No heart shunt. China National Knowledge Infrastructure (CKNI) data were collected in adherence to ethical review of human and biomedical research in China. LVEF data were acquired through image acquisition using GE Vivid 7 ultrasonic diagnostic apparatus, M5S probe, probe frequency of 1.7 ~ 3.4 MHz, frame rate (45 ± 10) frames/s. LVEF was then obtained by the Simpson method from the apical four-chamber view 24 , 25 . For environmental factors, we selected five factors which affect heart health of people including: annual duration of sunshine, annual mean air temperature, annual mean relative humidity, annual precipitation amount, and annual air temperature range. The five indexes come from the database of The Annual Surface Climate Normals of China (1971–2000), offered by the China Meteorological Data Sharing Service System ( http://old-cdc.cma.gov.cn/ ). Methods Preprocessing of raw data We established a comprehensive database of integrated attribute data and spatial data for heart rates and five environmental data sets based on 2322 administrative units of China. Interpolation using the empirical Bayesian Kriging method was employed to create TIFF images for each indicator band after subsequent modeling processing. The 500m Surface Reflectance Band 1 ~ 7 of MOD09A1 (Surf_Ref_8Days_500m) remote sensing images downloaded from MODIS were processed separately. First, we converted the TIFF images of the original remote sensing image into a H5 sequence which was then ready for cloud processing. Then we inputted the previous stage TIFF to H5 file, mask images matching and the processed layers. After that, we re-transferred the H5 files and the matching mask image to the TIFF images. The processed remote sensing images were then ready for the subsequent modeling processing Long-term and short-term memory (LSTM) network of deep learning Deep learning can simulate the way human brain learns. It completes the expression of information by simulating the human brain mechanisms, including images and sounds, etc. It is the result of LSTM exploration and accumulation of artificial neural networks. The structure of deep learning is mainly to build multi-layered “perceptrons” with multiple hidden layers. As the number of layers increases, the error rate drops. The most critical feature of deep learning is the elimination of some defects in the artificial neural network, such as over/under fitting, which can greatly improve the accuracy and effectiveness of the results 25 .The LSTM network is based on a cyclic neural network, which was established in 1997 by Sepp Hochreiter and Jürgen Schmidhuber 26 . A LSTM network model overcomes the long-term dependence of training results and greatly enhances the efficiency and practicability of cyclic neural networks. It can remember longer time information 27 . The LSTM model structure includes a forget gate, an input gate, an output gate and a memory cell. The activation function used by the three gates is the sigmoid function. The input functions and memory cells are usually converted using tanh 28 . To train deep neural networks, we must specify the neural network architecture and the options for the training algorithm. Selecting and adjusting these parameters can be difficult and takes time to adjust. Bayesian optimization is an algorithm that is very suitable for optimizing the internal parameters of classification and regression models. This research uses Bayesian optimization to optimize non-differential, discontinuous, and time-consuming functions. The algorithm internally maintains the Gaussian process model of the objective function and uses the objective function calculation to train the model. A target detection method based on deep learning To analyze a large number of high-resolution remote sensing image data, a hierarchical deep learning model was established (Fig. 2 ). The first part was to use deep learning to clarify the target characteristics. From the image pixel as a starting point, a deep learning network was constructed. The image representation was defined on the basis of hierarchical learning. In order to accurately and reasonably represent the goal, it was necessary to set the corresponding meaning for each layer of the deep network. The second part was to change the deep network through context information. In the case of determining the image characteristics, the network weight was reasonably adjusted based on the target mark, the context and the context of the scene. Strengthening network prediction ability based on context interaction made target feature prediction more accurate 29 . Matlab software was used to develop the LSTM network modeling work in this research. Remote sensing data was processed through self-developed APP 30 . The training modeling processes mainly included sample collection, model training and remote sensing inversion. Sample collection Inputting 13-band independent variables in the sampling operation interface, including heart rate indicator, 5 climate indicators and 7 remote sensing band data, samples were extracted in sequence order. During the acquisition process the samples were converted into sample sequence data by block acquisition for subsequent data sequence processing. Mask data used LVEF data as the dependent variable. The sampling window size was set to 64×64. The total number of samples was 50,000. The response image was from LVEF prediction data. The parameters that needed to be set included the remote sensing image, mask data, sample window size, sampling interval, sample size, total sample setting, label image, output sample. LSTM Model training The training processes were divided into two stages: network construction and model training. The first stage was network construction. The random sampled data was input into the LSTM network for network parameter training by the sample data collecting results. We then entered the network build code, set the number of hidden neurons to 100, set the dimension reference argument band to 12, and outputted the dimension to 1. Then the network was built. In the second stage we entered the network construction model obtained in the previous stage. We set the parameters according to the characteristics of the learning samples, adjusted, and tried weights and offsets. Several important variables that needed to be optimized during training included the Initial learning rate, Stochastic Gradient Descent and L2 Regularization. The initial learning rate depends on the sample data and the network being trained. Stochastic Gradient Descent Momentum includes a contribution proportional to the update in the previous iteration in the current parameter update, thereby increasing inertia in the update. This makes parameter updates smoother and reduces the noise inherent in random gradient drops. Using regularization is to prevent overfitting. Searching for regularized intensity space is to find good values. Data enhancement and batch normalization also help to regularize the network. After multiple trainings and comparison of results, the final selection is the best predictive model parameters according to the characteristics of the sampled data. The maximum number of generations was set to 10, the initial learning rate was set to 0.001, the L2 regularization was set to 0.0001, the mini batch was set to 16, the Stochastic Gradient Descent with Momentum selected sgdm(SGD with momentum), the Option for data shuffling selected each generation shuffle, and the gradient threshold method selected the L2 norm. The gradient threshold was set to 0.05, the learning rate schedule was selected to be segmented, the learning rate drop period was reduced to 5, and the learning rate drop factor was set to 0.1. The model of the first stage network construction output was inputted into the network of the second stage, then the second stage model training started. Remote Sensing Inversion Results Based on LSTM Model A total of 13 bands of remote sensing image data were input including heart rate, annual duration of sunshine, annual mean air temperature, annual mean relative humidity, annual precipitation amount and annual air temperature range and MODIS 500m Surface Reflectance Band 1 ~ 7. The processing range of the mask image was the boundary of China. The size of the remote sensing classification window was set to64×64 size consistent with the sampling time. Correlation analysis The correlations between LVEF and heart rate of Chinese subjects and environmental factors are shown in Table 2 . It can be seen that the LVEF and heart rate are significantly correlated with five environmental factors in China. LVEF has a negative correlation with heart rate(X 1 ), annual duration of sunshine (X 2 ) and annual air temperature range (X 6 ), but has a positive correlation with annual mean air temperature (X 3 ), annual mean relative humidity (X 4 ) and annual precipitation amount (X 5 ). Table 2 Correlation between Chinese LVEF and heart rate and environmental factors X n Independent variable R value P value X 1 heart rate -0.149* 0.043 X 2 annual duration of sunshine − .137 .065 X 3 annual mean air temperature .154* .037 X 4 annual mean relative humidity .164* .026 X 5 annual precipitation amount .208** .005 X 6 annual air temperature range − .190** .010 LSTM prediction model results We used the best-predicted LSTM prediction model trained in the second stage and the LVEF prediction value as the response image to start processing. Then we converted the previous sequence data into an image to obtain a predicted image of the final Chinese normal adults’ LVEF reference values(Fig. 3 ). It can be seen from Fig. 3 that the LVEF reference values of normal adults in China shows the lowest values in the north and the highest values in the south. LVEF is negatively correlated with heart rate and annual air temperature range; while positively correlated with annual mean air temperature, annual mean relative humidity, annual precipitation amount. It can also be seen from the results of this study that environmental factors are closely related to the LVEF reference values of normal adults in China. Affected by geographic location and climate, normal adults have higher LVEF reference values in areas with high annual average temperatures. The normal adults LVEF is higher in areas with lower annual air temperature range. Normal adults have higher LVEF reference values in areas with higher annual average relative humidity. Normal adults have higher LVEF reference values in areas with more annual precipitation. In contrast, normal adults have lower LVEF reference values in areas with low annual average temperatures. Normal adults LVEF reference values are lower in areas with higher annual air temperature range. Normal adults have lower LVEF reference values in areas with low annual average relative humidity. Normal adults have lower LVEF reference values in areas with less annual precipitation. Conclusions Summarizing the spatial distribution, it is concluded that the LVEF reference values of normal adults in China decline across geographic areas and scales as one moves from south to north. On this basis, a prediction model of LVEF reference values is obtained by combining heart rate and environmental factors, and the results from network training can be obtained. Summarizing the spatial distribution of LVEF reference values of normal adults in China, a trend of high values in the south and low values in the north was observed. The LVEF reference values were positively correlated with annual average temperature and annual average relative humidity across geographic areas and scales. In the future, combined with heart rate data from wearable devices (e.g., smart watches), a prediction model might be widely used to obtain more accurate LVEF reference values at finer geographic scales and individual differences taken into account. If this study can be extended to individuals, where they live and their everyday behavious, heart rate data could be linked by wearable devices to “Big Data”. Big data could effectively monitor people's physical conditions, judgment on disease prevention and human health trends through the processing of massive data 13 . Such steps forward might also contribute to better planning of health promotion to reduce heart disease and better plan health care services in anticipation of changes in LVEF levels with changing environmental measures. Declarations Acknowledgments: The authors would like to thank all of the volunteers that took part in this study and the people for their assistance in technical and laboratory support. Funding: This study was supported by the Fundamental Research Funds For the Central Universities 2016TS055, Youth Project of Shaanxi Province Natural Science Basic Research Plan 2021JQ-804 and Shaanxi Provincial Social Science Fund Project 2020F009. Ethics approval and consent to participate: The study was approved by Medical Ethics Committee of Second Affiliated Hospital of Xi'an Jiaotong University medical school(2010-LS-009). All methods were performed in accordance with the relevant guidelines and regulations by including a statement in the methods section to this effect. Competing interests: None of the authors have any financial or other potential conflict of interest for this study. Consent for publication: All authors consent for publication this study. Authors’ Contribution statement: Jing Jing and Ge Miao wrote the main manuscript text. Zhang Chong processed data and modeling. Yang Ziqi collected the data. Li Peng prepared figures. Mark Rosenberg revised the paper. Availability of supporting data The five geographic indexes come from The Annual Surface Climate Normals of China (1971–2000), offered by the China Meteorological Data Sharing Service System( http://old-cdc.cma.gov.cn/ ). The remote sensing data are selected from the remote sensing image acquired by the medium resolution imaging spectrometer MODIS（moderate-resolution imaging spectroradiometer） sensing（http://cdc.cma.gov.cn/home.do） References John JV, McMurray S, Adamopoulos SD, Anker (2012) ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure. Eur Heart J 33:1787–1847 Bax JJ, Visser FC, Poldermans D et al Relationship Between Preoperative Viability and Postoperative Improvement in LVEF and Heart Failure Symptoms.Journal of Nuclear Medicine Official Publication Society of Nuclear Medicine,2001, 42(1):79–86 Ota T, Kisslo J, von Ramm OT et al Realtime, volumetric echocardiography: usefulness of volumetric scanning for the assessment of cardiac Volume and function. Cardiol,2001, 37(s1):93–101 Chou HY Heart rate and cardiovascular risk.Chin J Cardio Diseases,2005, 33(4):388–390 Donald R, Ricci FRCP(C) (1979) Arthur E., Influence of heart rate on left ventricular ejection fraction in human beings.The American J of Cardiology, (44):447–451 Nosir YF, Vletter WB, Kasprzak JD et al (2000) Optimal rotational interval for 3-dimensional echocardiography data acquisition for rapid and accurate Measurement of left ventricular function. Am Soc Echocardiogr 13(8):715–722 Jing J (2012) Relationship between five reference values of cardiac function and geographical environment.Master’s degree of SNNU. :101–120 Pan L, Li SZ (2012) Change of cardiac function in healthy young males following rapid travel to highlands. J Third Mil Med Uni 34(11):1104–1106 Rimoldi SF, Sartori C, Seiler C et al High-altitude exposure in patients with cardiovascular disease: risk assessment and practical recommendations.Prog Cardiovasc Dis,2010, 52(6):512–524 Jing J, Ge M, Yang ZQ et al A New Method to get the LVEF Reference Values of the Healthy Adult Male by Heart Rate and Geographical Environment Factors.International Journal of Gerontology,2018, 12(4):319–325 Ricci DR, Orlick AE, Alderman EL et al Influence of heart rate on left ventricular ejection fraction in human beings.The American Journal of Cardiology,1979, 44(3):447–451 Jing J, Ge M, Yang ZQ et al (2018) Correlation of Heart ï¼²ate and Geographical Environmental Factors with ï¼²eference Values of Left Ventricular Ejection Fraction in Healthy Adult Males, vol 40. ACTA ACADEMIAE MEDICINAE SINICAE, pp 55–60. 04 Zhu Y, Xu J, Zhu L et al Policies of healthcare big data in major developed countries.Chin J Med Libr Inf Sci,2015, 24(10):13–17 Lim YH, Kim H, Kim JH et al Effect of diurnal temperature range on cardiovascular markers in the elderly in Seoul, Korea.International Journal of Biometeorology,2013, 57(4):597–603 Lv SQ, Yu LT Advances in research on heart failure in the middle range of ejection fraction.Chinese Journal of Cardiology,2018, 46(3):236–236 Chen YY, Yu XP, Chen SH Clinical Value of Heart Failure Ultrasound Index in Evaluating Ejection Fraction Middle Range Heart Failure.Chinese Journal of Gerontology,2018, 38(10):43–45 Wang H, Huang DJ Advances in research on ejection fraction normal heart failure.Huaxi Medicine,2005, 20(2):415–416 Chinese Medical Association Cardiovascular Disease Branch. China Heart Failure Diagnosis and Treatment Guide 2014.Chinese Journal of Cardiology,2014, 42(2):3–10 Ponikowski P, Voors AA, Anker SD et al 2016 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure: The Task Force for the diagnosis and treatment of acute and chronic heart failure of the European Society of Cardiology (ESC). Developed with the special contribution of the Heart Failure Association (HFA) of the ESC.European journal of heart failure,2016, 18(8):891–975 Ginsberg J Detecting influenza epidemics using search engine query data.Nature,2009, 457(7232):1012 Hung CL, Wu YJ, Liu CC et al (2012) Rationale and Design of MAGNET (Mitochondria-AGing in NorthErn Taiwan) Study: A Community-based Cohort Investigating Mitochondria-related Aging and Cardiovascular Diseases in Suburban Areas of Northern Taiwan. Int J Gerontology 6:122–126 Huang YT, Wang CH, Wu YF (2011) Adhering to a TaiChiChuan Exercise Program Improves Vascular Resistance and Cardiac Function. Int J Gerontology 5:150–154 Wang CZ, Xu ZZ (1999) Ultrasound diagnosis. People's Health Publishing House, Beijing, pp 1179–1183 Wang XY, Wang D, Liu NF et al (2015) Left atrial function evaluated by 2D speckle tracking imaging in patients with hypertension and preserved left ventricular ejection fraction. ACTA Uni Medi Nanjing(Natural Science) 35(10):1474–14781490 Vincent P, Larochelle H, Bengio Y et al Extracting and Composing Robust Features with Denoising Autoencoders. International Conference on Machine Learning,ACM,2008 Hochreiter S, Schmidhuber J (1997) Long Short-Term Memory. Neural Comput 9(8):1735–1780 Sofiyanti N, Fitmawati D, Roza A Understanding LSTM Networks. GITHUB colah blog,2015,22(2):137–141 Yao L, Torabi A, Cho K et al (2015) Describing Videos by Exploiting Temporal Structure. IEEE International Conference on Computer Vision (ICCV), :4507–4515 Sang N Cascade of hierarchical context and appearance for object detection.Optical Engineering,2010, 49(3):30–37 Zhang ZH Meteorology and heart.Journal of Cardiovascular Disease Prevention Knowledge,2005,(1):51–51 Cui WW, Yu LM, Zhang JJ et al Study on the relationship between the onset of acute cardiovascular disease and meteorological factors.Chinese Journal of Emergency Medicine,2014, 23(4):465–469 Kim CT, Youn-Hee L, Alistair W et al (2015) Heat-Attributable Deaths between 1992 and 2009 in Seoul, South Korea, vol 10. US National Library of Medicine National Institutes of Health, p 0118577. 2 Bobb JF, Peng RD, Bell ML et al Heat-Related Mortality and Adaptation to Heat in the United States.Environmental Health Perspectives,2014, 122(8):811–816 Huang C, Barnett AG, Wang X et al Effects of Extreme Temperatures on Years of Life Lost for Cardiovascular Deaths: A Time Series Study in Brisbane, Australia. Circulation: Cardiovascular Quality and Outcomes,2012,5(5): 609–614 Gasparrini A, Guo Y, Hashizume M et al Mortality risk attributable to high and low ambient temperature: a multicountry observational study.The Lancet,2015, 386(9991):369–375 Bobb JF, Obermeyer Z, Wang Y et al (2014) Cause-Specific Risk of Hospital Admission Related to Extreme Heat in Older Adults. JAMA 312(24):2659–2667 Guo YM, Antonio G, Ben A et al Global variation in the effects of ambient temperature on mortality: a systematic evaluation.Epidemiology,2014, 25(6):781–789 Sun XM, Sun Q, Zhou X et al Heat wave impact on mortality in Pudong New Area, China in 2013.Science of The Total Environment,2014, 493(5):789–794 Ma W, Zeng W, Zhou M et al (2015) The short-term effect of heat waves on mortality and its modifiers in China: An analysis from 66 communities. Environ Int 75:103–109 Kalkstein LS, Davis RE Weather and Human Mortality: An Evaluation of Demographic and Interregional Responses in the United States.Annals of the Association of American Geographers,2015, 79(1):44–64 Wang LR, Lei LH The impact of weather changes on population mortality. Ecological science,1997,(2):81–86 Liang YQ, Hong X, Xu F Influence of meteorological factors in Nanjing on cardiovascular death in residents.Chinese Journal of Disease Control,2015, 19(1):24–27 Westheim A, Os I, Thaulow E et al Haemodynamic and neurohumoral effects of cold pressor test in severe heart failure.Clin Physiol,1992,(12):95–106 Rodríguez-García JL, Paule A, Domínguez J et al (1999) Effects of the angiotensin II antagonist losartan on endothelin-1 and norepinephrine plasma levels during cold pressor test in patients with chronic heart failure.Int Cardiol,(70):293–301 Feng YM, Cheng GQ (1997) Chinese Medicine Meteorology and Geopathology]. Shanghai Science Popularization Press, 上海, p 210214 Barnett AG, Sans S, Salomaa V et al (2007) The effect of temperature on systolic blood pressure. Blood Press Monit 12(3):195–203 Modesti PA, Morabito M, Bertolozzi I et al (2006) Weather-Related Changes in 24-Hour Blood Pressure Profile: Effects of Age and Implications for Hypertension Management, vol 47. Hypertension, pp 155–161. 2 Elwood PC, Beswick A, O'Brien JR et al Temperature and risk factors for ischaemic heart disease in the Caerphilly prospective study.British Heart Journal,1993, 70(6):520–520 Rufca GF, Zaffani E, Zerbini R et al Influence of circadian and temperature variations on the ischemic stroke.Revista Da Associação Médica Brasileira,2009, 55(1):60–63 Choi SH, Lee SW, Hong YS et al (2010) Effects of atmospheric temperature and humidity on outbreak of diseases. Emerg Med Australasia 19(6):501–508 Qiao L, Feng DX (2000) Relationship between the onset of acute myocardial infarction and seasonal climate and diurnal changes. J Hubei Coll Traditional Chin Med 2(1):24–25 Kampmann B, Bride P, Fiala D Physiological responses to temperature and humidity compared to the assessment by UTCI, WGBT and PHS.International Journal of Biometeorology,2012, 56(3):505–513 Bernhard K, Peter B, Dusan F Physiological responses to temperature and humidity compared to the assessment by UTCI, WGBT and PHS.International Journal of Biometeorol,2012, 56(3):505–513 Li YW, Tan JG, Jiang JQ The influence of meteorological factors on heart failure.Progress in modern biomedicine,2015, 15(7):1275–1280 Guangzhou Cardiovascular Research Collaboration Group. Analysis of the incidence and meteorological factors of acute myocardial infarction in Guangzhou.Chinese Journal of Internal Medicine,1984, 23(9):548–548 Wu YY, Ge QF (1990) Discussion on the relationship between coronary heart disease, stroke and meteorology in Beijing.Chinese Journal of Epidemiology, (2):88–91 Zhang CX Air negative ions and health.Yunnan Chemical Technology,2017, 10(44),92–93 Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-2802057","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":191403208,"identity":"b3fc7942-f058-47c7-8d04-7f7a4a43768b","order_by":0,"name":"Jing Jing","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwElEQVRIiWNgGAWjYBACNvbGxgcfeGyY+dkbiNTCx3O42XCGTBq7ZM8BIrXISaS3CfPYHOY3uJFArMN4DrYx8+SkSRvcfLzxBkONTTRhLeyNbQ/nnLExlrydVmzBcCwtt4EIW9oN3vakJfPdzjGTYGw4TIQWicQ2Cd5/h+sbbp4hQYskD89hZoEbPMRq4TkIDGSeNGbJHqBfEojxi3x7+0NoVB7eeONDjQ1hLcjAQCKBFOUQLaTqGAWjYBSMgpEBAI9+QEenuMmYAAAAAElFTkSuQmCC","orcid":"","institution":"Modeling，Baoji University of Arts and Sciences","correspondingAuthor":true,"prefix":"","firstName":"Jing","middleName":"","lastName":"Jing","suffix":""},{"id":191403209,"identity":"eec40446-7ec2-41f6-94ec-2c1602af2a0d","order_by":1,"name":"Chong Zhang","email":"","orcid":"","institution":"Modeling，Baoji University of Arts and Sciences","correspondingAuthor":false,"prefix":"","firstName":"Chong","middleName":"","lastName":"Zhang","suffix":""},{"id":191403210,"identity":"5b685153-e8c9-49b4-83f5-0118a4b4cda7","order_by":2,"name":"Miao Ge","email":"","orcid":"","institution":"Shaanxi Normal University","correspondingAuthor":false,"prefix":"","firstName":"Miao","middleName":"","lastName":"Ge","suffix":""},{"id":191403211,"identity":"fcc928da-0355-4ff6-9fe7-4bf688f5e7f9","order_by":3,"name":"Mark Rosenberg","email":"","orcid":"","institution":"Queen’s University","correspondingAuthor":false,"prefix":"","firstName":"Mark","middleName":"","lastName":"Rosenberg","suffix":""},{"id":191403213,"identity":"9f68dbd2-7970-4802-84ab-97e5c4ca3c8b","order_by":4,"name":"Ziqi Yang","email":"","orcid":"","institution":"Modeling，Baoji University of Arts and Sciences","correspondingAuthor":false,"prefix":"","firstName":"Ziqi","middleName":"","lastName":"Yang","suffix":""},{"id":191403216,"identity":"1f44e898-c648-4efc-83c2-6408c6654841","order_by":5,"name":"Peng Li","email":"","orcid":"","institution":"The First Affiliated Hospital of Xian Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Peng","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2023-04-11 16:59:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2802057/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2802057/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":35789489,"identity":"37e8732e-0f0f-4302-910e-0b4903c7e9ff","added_by":"auto","created_at":"2023-04-14 22:08:51","extension":"jpeg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":68399,"visible":true,"origin":"","legend":"\u003cp\u003eThe distribution of sampling points\u003c/p\u003e","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-2802057/v1/2a0b22e0dbcd83c95ad530f4.jpeg"},{"id":35789490,"identity":"ce04b0ff-40e4-4022-bbaa-0a27f418c630","added_by":"auto","created_at":"2023-04-14 22:08:51","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":362882,"visible":true,"origin":"","legend":"\u003cp\u003eRemote sensing image feature prediction framework based on deep learning\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-2802057/v1/2b7fb7154a00427610f585c0.png"},{"id":35789491,"identity":"b4c6c20b-b0e6-433a-aabb-fea8c52bee74","added_by":"auto","created_at":"2023-04-14 22:08:51","extension":"jpeg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":190422,"visible":true,"origin":"","legend":"\u003cp\u003eSpatial tendency chart of the LVEF reference values for normal adults in China\u003c/p\u003e","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-2802057/v1/ef1bcb310aed03c7a7192311.jpeg"},{"id":35954054,"identity":"84ea81ba-a6df-4323-926c-4b850ad8faaf","added_by":"auto","created_at":"2023-04-18 17:59:37","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":716619,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2802057/v1/5d370e5e-7756-4de1-8922-b440fbaa284c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A study of Cardiac reference values and environmental factors using big data and deep learning methods","fulltext":[{"header":"Introduction","content":"\u003cp\u003eThis paper reports on a study of deep learning methods for analysing and simulating normal adults Left Ventricular Ejection Fraction (LVEF) reference values in relation to environmental factors in China. LVEF is an important indicator of cardiac function. It means the ratio of stroke volume to ventricular end-diastolic volume. LVEF evaluates the ventricular ejection function from a volume perspective. Usually, when myocardial contraction ability is strong, then the stroke volume and the LVEF are high\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003e. Heart failure can be judged by the LVEF\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e. The LVEF reference values are often used in the examination of heart disease. It provides an important reference for drug observation and surgical efficacy.\u003c/p\u003e \u003cp\u003eAccording to the results of our previous studies, the LVEF reference values are closely related to the environment\u003csup\u003e\u003cspan additionalcitationids=\"CR8 CR9\" citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u003c/sup\u003e. There is a negative correlation between heart rate and LVEF reference values\u003csup\u003e\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e,\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u003c/sup\u003e. Many environmental factors affect the growth and health of the human body. Specifically, many factors such as temperature, air humidity, atmospheric precipitation, solar radiation, sunshine index, negative ion content in the air, and oxygen partial pressure affect the physiological function of the human body through physiological activities such as the cardiovascular, circulatory, and endocrine systems\u003csup\u003e\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eTemperature is one of the important reasons that causes many heart diseases. The effect of temperature on the disease is generally divided into the effects of high temperature and low temperature on the disease. According to some studies, the incidence of cardiovascular disease increases with the rise of temperature when the temperature is higher than a certain range\u003csup\u003e\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e\u003c/sup\u003e. A study in South Korea showed that cardiovascular deaths caused by high temperature heat waves account for more than half of deaths\u003csup\u003e\u003cspan additionalcitationids=\"CR33\" citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e\u003c/sup\u003e. Many studies have consistently shown that high temperatures can cause some adverse health effects and increase mortality\u003csup\u003e\u003cspan additionalcitationids=\"CR36\" citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e\u003c/sup\u003e. In a US study, 15 of 50 cities surveyed, reported a significant relationship between summer mortality and temperature\u003csup\u003e\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e\u003c/sup\u003e. The mortality rate is significantly increased when the maximum temperature reaches 32\u0026deg;C or above. In addition, Canadian research was carried out in 10 cities. The results of the research also showed that the high temperatures above 29\u0026deg;C in summer led to an increase in mortality. Studies in China have also shown that the critical temperature for population mortality in Shanghai and Guangzhou in summer is a daily maximum temperature of 34\u0026deg;C\u003csup\u003e\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e\u003c/sup\u003e. A study in Nanjing found that the maximum daily temperature threshold for cardiovascular disease deaths in the summer is 32\u0026deg;C\u003csup\u003e\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eThe mechanism of temperature effects on cardiac function can be explained by the flow of blood to the surface of the skin due to high temperature, resulting in an increased heavy burden on the heart, lungs and other body organs and the reduction in cardiac blood flow. High temperatures also increase viscosity of blood flow in the human body which increases the cholesterol level. In addition, people in hot weather are prone to irritating emotions which may lead to loss of appetite and poor sleep. High temperature can easily cause cardiovascular diseases due to the combination of various reasons.\u003c/p\u003e \u003cp\u003eIn contrast to the research on high temperatures and heart disease, a survey on the effects of hypothermia and heart disease shows that the incidence of heart disease is negatively correlated with the decrease in temperature. The lower the temperature, the higher the incidence of heart failure which reduces the LVEF. The skin increases systemic vascular resistance and heart rate increases when the outside conditions are cold. Thereby plasma norepinephrine concentration is increases leading to more circulating vasoconstrictor secretion and high blood pressure\u003csup\u003e\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e,\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e\u003c/sup\u003e. The sympathetic nerves are excited when the temperature drops to 1.5\u0026deg;C which causes an increase in norepinephrine and adrenaline secretion that accelerates the heart rate. The blood vessels of human skin are mainly microcirculatory vasoconstriction when the temperature is lower than 1.5\u0026deg;C. The peripheral vascular resistance increases\u003csup\u003e\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e\u003c/sup\u003e. Cold stimulation can cause peripheral vasoconstriction and increase systemic blood volume. At the same time, it causes an increase in circulating resistance which increases blood pressure. Sympathetic nerve excitability enhances catecholamine levels during the cold season\u003csup\u003e\u003cspan additionalcitationids=\"CR46 CR47\" citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e\u003c/sup\u003e. This can promote the increase of adrenaline secreted by the adrenal medulla and accelerate the metabolism of the human body. Then heart rate and cardiac output increase. Ultimately blood pressure is elevated. Increased blood pressure, abnormal cardiovascular and cerebrovascular reactions increase stroke\u003csup\u003e\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e\u003c/sup\u003e. This also leads to the increasing of heart rate and the myocardial oxygen consumption. Peripheral vascular resistance increases when the temperature is low. Left ventricular load increases due to the increasing blood viscosity and slow blood flow. These combined effects can lead to a decrease in cardiac contractility and a decrease in LVEF. In summary, the heart rate increases and the LVEF decreases as the temperature decreases.\u003c/p\u003e \u003cp\u003eSome studies have shown that hydrothermal conditions including humidity and temperature also have an impact on health. One study found that most diseases show high levels of distribution in high temperature and high humidity environments. Humidity is significantly positively correlated with incidence of disease when atmospheric temperature reaches an optimal range (12\u0026deg;C or higher)\u003csup\u003e\u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e\u003c/sup\u003e. The same research results were also obtained by Qiao Liang and Feng Dexun. Relative humidity has a positive correlation with incidence of disease. The incidence of cardiovascular disease increases with the increase of humidity when the relative humidity is high\u003csup\u003e\u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e51\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eSome scholars have explored the regional differences between hydrothermal conditions and the physiological phenomena of living organisms found that the heart rate is generally higher with a decrease in relative humidity\u003csup\u003e\u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e\u003c/sup\u003e. The results of an analytical model on the effects of temperature and humidity on the human body indicated that heart rate is higher when relative humidity of the living environment is smaller\u003csup\u003e\u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e\u003c/sup\u003e. In a normal range, an increase in normal heart rate can result in a slight increase in cardiac output due to the corresponding shortening of the systolic phase. At the same time, the heart rate is shortened, the volume of blood back to the heart is also reduced. In this situation, Stroke volume(SV) is reduced in the short-term Left ventricular end diastolic(LVEDV) changes little, so LVEF will be reduced. Relative humidity changes are also significantly associated with the incidence of heart failure\u003csup\u003e\u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e54\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eStudies have also shown that high temperature and high humidity conditions can easily lead to myocardial infarction\u003csup\u003e\u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e,\u003cspan citationid=\"CR56\" class=\"CitationRef\"\u003e56\u003c/span\u003e\u003c/sup\u003e. Analysis of the impact mechanism can be interpreted in that the negative ion content in the air is higher when the humidity of the air increases. Air negative ions can cause blood vessels to dilate and reduce arterial spasm. At the same time, increasing blood oxygen content can improve heart function and myocardial nutritional status\u003csup\u003e\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e\u003c/sup\u003e. The heart rate and the LVEF reference values will decrease when the relative humidity is low. The relative humidity and the LVEF reference values show a positive correlation.\u003c/p\u003e \u003cp\u003eIn this study, we explore the relationship between LVEF reference values, heart rate, and environmental data. It is argued that research results can be used to predict, observe, and even alert individuals about their health status in real time. A prediction model is developed using heart rate and environmental data to obtain LVEF reference values. The starting point of this study is to estimate difficult to obtain indicators based on the indicators that are easy to measure and obtainto simulate a simple and accurate method for obtaining LVEF reference values.\u003c/p\u003e \u003cp\u003eData selection\u003c/p\u003e \u003cp\u003eSome research has reported expected cardio-vascular disease (CVD) incidence of nearly 8% in men and 3\u0026ndash;5% in the women population, defined as fatal or nonfatal myocardial infarction, angina pectoris or stroke over a 5-year follow up period\u003csup\u003e\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e\u003c/sup\u003e. In China, a recent study reported that the rates of CVD mortality in Beijing increased by \u0026gt;\u0026thinsp;50% in men and \u0026gt;\u0026thinsp;27% in women from 1984 to 1999\u003csup\u003e22\u003c/sup\u003e. Using the China National Knowledge Infrastructure (CNKI) database, we had access to nearly 10 years of data from 2010 to 2020 from more than 44 cities, 184 regional units in China which included 6360 individual cases of adults (age range18-83) with LVEF and heart rate measurements (3502 are males and 2858 are females). The distribution of sampling points are seen in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.There was less data from Western cities than the eastern regions. The distribution of data geographically is 107 cities from eastern regions, 35 cities from middle regions and 42 cities from western regions.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eT-tests were employed to test the disparities of LVEF reference values among different regions, and the results had a p-value\u0026thinsp;=\u0026thinsp;0.001, indicating a significant difference of LVEF reference values among regions (Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e)\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eLVEF and heart rate data \u0026amp; T-test\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"9\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGroup\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTotal\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMale\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eFemale\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eAge\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eBMI\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eLVEF\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eHR\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHealthy people\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3502\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3502\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2858\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e18\u0026ndash;81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e18.5\u0026ndash;25.0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e50.45-75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e60\u0026ndash;88\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe subjects were apparently healthy. The inclusion criteria were normal weight and height (body mass index\u0026thinsp;\u0026gt;\u0026thinsp;18.5 but \u0026lt;\u0026thinsp;25.0, in Kg/m2), normal blood pressure, normal blood glucose and 8 hours fasting before testing blood. The primary exclusion criteria were hepatobiliary and kidney diseases (fatty liver, liver cirrhosis, hepatitis, nephritis, kidney stone, ect.), blood diseases (hemangioma, disturbance of blood circulation, other blood abnormities and so on) and hepatobiliary ultrasound abnormalities. The cardiac normal adults were selected according to the following standards\u003csup\u003e\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e\u003c/sup\u003e: (1) Confirmed normal size of the left ventricular cavity and no myocardial dysmotility;(2) Ventricular arrhythmia and non-pacing rhythm, no tachycardia and bradycardia;(3) Left ventricular myocardium without myocardial infarction or segmental ischemia;(4) Left ventricular outflow tract without abnormal structure;(5) Left heart valve no obvious morphological and functional abnormalities (no obvious stenosis and regurgitation); and (6) No heart shunt. China National Knowledge Infrastructure (CKNI) data were collected in adherence to ethical review of human and biomedical research in China.\u003c/p\u003e \u003cp\u003eLVEF data were acquired through image acquisition using GE Vivid 7 ultrasonic diagnostic apparatus, M5S probe, probe frequency of 1.7\u0026thinsp;~\u0026thinsp;3.4 MHz, frame rate (45\u0026thinsp;\u0026plusmn;\u0026thinsp;10) frames/s. LVEF was then obtained by the Simpson method from the apical four-chamber view\u003csup\u003e\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e,\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eFor environmental factors, we selected five factors which affect heart health of people including: annual duration of sunshine, annual mean air temperature, annual mean relative humidity, annual precipitation amount, and annual air temperature range. The five indexes come from the database of The Annual Surface Climate Normals of China (1971\u0026ndash;2000), offered by the China Meteorological Data Sharing Service System (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://old-cdc.cma.gov.cn/\u003c/span\u003e\u003cspan address=\"http://old-cdc.cma.gov.cn/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e).\u003c/p\u003e "},{"header":"Methods","content":"\u003cdiv id=\"Sec2\" class=\"Section2\"\u003e \u003ch2\u003ePreprocessing of raw data\u003c/h2\u003e \u003cp\u003eWe established a comprehensive database of integrated attribute data and spatial data for heart rates and five environmental data sets based on 2322 administrative units of China. Interpolation using the empirical Bayesian Kriging method was employed to create TIFF images for each indicator band after subsequent modeling processing.\u003c/p\u003e \u003cp\u003eThe 500m Surface Reflectance Band 1\u0026thinsp;~\u0026thinsp;7 of MOD09A1 (Surf_Ref_8Days_500m) remote sensing images downloaded from MODIS were processed separately. First, we converted the TIFF images of the original remote sensing image into a H5 sequence which was then ready for cloud processing. Then we inputted the previous stage TIFF to H5 file, mask images matching and the processed layers. After that, we re-transferred the H5 files and the matching mask image to the TIFF images. The processed remote sensing images were then ready for the subsequent modeling processing\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eLong-term and short-term memory (LSTM) network of deep learning\u003c/h2\u003e \u003cp\u003eDeep learning can simulate the way human brain learns. It completes the expression of information by simulating the human brain mechanisms, including images and sounds, etc. It is the result of LSTM exploration and accumulation of artificial neural networks. The structure of deep learning is mainly to build multi-layered \u0026ldquo;perceptrons\u0026rdquo; with multiple hidden layers. As the number of layers increases, the error rate drops. The most critical feature of deep learning is the elimination of some defects in the artificial neural network, such as over/under fitting, which can greatly improve the accuracy and effectiveness of the results\u003csup\u003e\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e\u003c/sup\u003e.The LSTM network is based on a cyclic neural network, which was established in 1997 by Sepp Hochreiter and J\u0026uuml;rgen Schmidhuber \u003csup\u003e\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e\u003c/sup\u003e. A LSTM network model overcomes the long-term dependence of training results and greatly enhances the efficiency and practicability of cyclic neural networks. It can remember longer time information \u003csup\u003e\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e\u003c/sup\u003e. The LSTM model structure includes a forget gate, an input gate, an output gate and a memory cell. The activation function used by the three gates is the sigmoid function. The input functions and memory cells are usually converted using tanh\u003csup\u003e\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eTo train deep neural networks, we must specify the neural network architecture and the options for the training algorithm. Selecting and adjusting these parameters can be difficult and takes time to adjust. Bayesian optimization is an algorithm that is very suitable for optimizing the internal parameters of classification and regression models. This research uses Bayesian optimization to optimize non-differential, discontinuous, and time-consuming functions. The algorithm internally maintains the Gaussian process model of the objective function and uses the objective function calculation to train the model.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003eA target detection method based on deep learning\u003c/h2\u003e \u003cp\u003eTo analyze a large number of high-resolution remote sensing image data, a hierarchical deep learning model was established (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). The first part was to use deep learning to clarify the target characteristics. From the image pixel as a starting point, a deep learning network was constructed. The image representation was defined on the basis of hierarchical learning. In order to accurately and reasonably represent the goal, it was necessary to set the corresponding meaning for each layer of the deep network. The second part was to change the deep network through context information. In the case of determining the image characteristics, the network weight was reasonably adjusted based on the target mark, the context and the context of the scene. Strengthening network prediction ability based on context interaction made target feature prediction more accurate\u003csup\u003e\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eMatlab software was used to develop the LSTM network modeling work in this research. Remote sensing data was processed through self-developed APP\u003csup\u003e\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e\u003c/sup\u003e. The training modeling processes mainly included sample collection, model training and remote sensing inversion.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003eSample collection\u003c/h2\u003e \u003cp\u003eInputting 13-band independent variables in the sampling operation interface, including heart rate indicator, 5 climate indicators and 7 remote sensing band data, samples were extracted in sequence order. During the acquisition process the samples were converted into sample sequence data by block acquisition for subsequent data sequence processing. Mask data used LVEF data as the dependent variable. The sampling window size was set to 64\u0026times;64. The total number of samples was 50,000. The response image was from LVEF prediction data. The parameters that needed to be set included the remote sensing image, mask data, sample window size, sampling interval, sample size, total sample setting, label image, output sample.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003eLSTM Model training\u003c/h2\u003e \u003cp\u003eThe training processes were divided into two stages: network construction and model training. The first stage was network construction. The random sampled data was input into the LSTM network for network parameter training by the sample data collecting results. We then entered the network build code, set the number of hidden neurons to 100, set the dimension reference argument band to 12, and outputted the dimension to 1. Then the network was built. In the second stage we entered the network construction model obtained in the previous stage. We set the parameters according to the characteristics of the learning samples, adjusted, and tried weights and offsets. Several important variables that needed to be optimized during training included the Initial learning rate, Stochastic Gradient Descent and L2 Regularization.\u003c/p\u003e \u003cp\u003eThe initial learning rate depends on the sample data and the network being trained. Stochastic Gradient Descent Momentum includes a contribution proportional to the update in the previous iteration in the current parameter update, thereby increasing inertia in the update. This makes parameter updates smoother and reduces the noise inherent in random gradient drops. Using regularization is to prevent overfitting. Searching for regularized intensity space is to find good values. Data enhancement and batch normalization also help to regularize the network. After multiple trainings and comparison of results, the final selection is the best predictive model parameters according to the characteristics of the sampled data.\u003c/p\u003e \u003cp\u003eThe maximum number of generations was set to 10, the initial learning rate was set to 0.001, the L2 regularization was set to 0.0001, the mini batch was set to 16, the Stochastic Gradient Descent with Momentum selected sgdm(SGD with momentum), the Option for data shuffling selected each generation shuffle, and the gradient threshold method selected the L2 norm. The gradient threshold was set to 0.05, the learning rate schedule was selected to be segmented, the learning rate drop period was reduced to 5, and the learning rate drop factor was set to 0.1. The model of the first stage network construction output was inputted into the network of the second stage, then the second stage model training started.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eRemote Sensing Inversion Results Based on LSTM Model\u003c/h2\u003e \u003cp\u003eA total of 13 bands of remote sensing image data were input including heart rate, annual duration of sunshine, annual mean air temperature, annual mean relative humidity, annual precipitation amount and annual air temperature range and MODIS 500m Surface Reflectance Band 1\u0026thinsp;~\u0026thinsp;7. The processing range of the mask image was the boundary of China. The size of the remote sensing classification window was set to64\u0026times;64 size consistent with the sampling time.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eCorrelation analysis\u003c/h2\u003e \u003cp\u003eThe correlations between LVEF and heart rate of Chinese subjects and environmental factors are shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. It can be seen that the LVEF and heart rate are significantly correlated with five environmental factors in China. LVEF has a negative correlation with heart rate(X\u003csub\u003e1\u003c/sub\u003e), annual duration of sunshine (X\u003csub\u003e2\u003c/sub\u003e) and annual air temperature range (X\u003csub\u003e6\u003c/sub\u003e), but has a positive correlation with annual mean air temperature (X\u003csub\u003e3\u003c/sub\u003e), annual mean relative humidity (X\u003csub\u003e4\u003c/sub\u003e) and annual precipitation amount (X\u003csub\u003e5\u003c/sub\u003e).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eCorrelation between Chinese LVEF and heart rate and environmental factors\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eX\u003csub\u003en\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eIndependent variable\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eR value\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eP value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eX\u003csub\u003e1\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eheart rate\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e-0.149*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.043\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eX\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eannual duration of sunshine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026minus;\u0026thinsp;.137\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e.065\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eX\u003csub\u003e3\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eannual mean air temperature\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.154*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e.037\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eX\u003csub\u003e4\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eannual mean relative humidity\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.164*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e.026\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eX\u003csub\u003e5\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eannual precipitation amount\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.208**\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e.005\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eX\u003csub\u003e6\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eannual air temperature range\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026minus;\u0026thinsp;.190**\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e.010\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003eLSTM prediction model results\u003c/h2\u003e \u003cp\u003eWe used the best-predicted LSTM prediction model trained in the second stage and the LVEF prediction value as the response image to start processing. Then we converted the previous sequence data into an image to obtain a predicted image of the final Chinese normal adults\u0026rsquo; LVEF reference values(Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). It can be seen from Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e that the LVEF reference values of normal adults in China shows the lowest values in the north and the highest values in the south. LVEF is negatively correlated with heart rate and annual air temperature range; while positively correlated with annual mean air temperature, annual mean relative humidity, annual precipitation amount.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eIt can also be seen from the results of this study that environmental factors are closely related to the LVEF reference values of normal adults in China. Affected by geographic location and climate, normal adults have higher LVEF reference values in areas with high annual average temperatures. The normal adults LVEF is higher in areas with lower annual air temperature range. Normal adults have higher LVEF reference values in areas with higher annual average relative humidity. Normal adults have higher LVEF reference values in areas with more annual precipitation. In contrast, normal adults have lower LVEF reference values in areas with low annual average temperatures. Normal adults LVEF reference values are lower in areas with higher annual air temperature range. Normal adults have lower LVEF reference values in areas with low annual average relative humidity. Normal adults have lower LVEF reference values in areas with less annual precipitation.\u003c/p\u003e \u003c/div\u003e"},{"header":"Conclusions","content":"\u003cp\u003eSummarizing the spatial distribution, it is concluded that the LVEF reference values of normal adults in China decline across geographic areas and scales as one moves from south to north. On this basis, a prediction model of LVEF reference values is obtained by combining heart rate and environmental factors, and the results from network training can be obtained. Summarizing the spatial distribution of LVEF reference values of normal adults in China, a trend of high values in the south and low values in the north was observed. The LVEF reference values were positively correlated with annual average temperature and annual average relative humidity across geographic areas and scales.\u003c/p\u003e \u003cp\u003eIn the future, combined with heart rate data from wearable devices (e.g., smart watches), a prediction model might be widely used to obtain more accurate LVEF reference values at finer geographic scales and individual differences taken into account. If this study can be extended to individuals, where they live and their everyday behavious, heart rate data could be linked by wearable devices to \u0026ldquo;Big Data\u0026rdquo;. Big data could effectively monitor people's physical conditions, judgment on disease prevention and human health trends through the processing of massive data\u003csup\u003e\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u003c/sup\u003e. Such steps forward might also contribute to better planning of health promotion to reduce heart disease and better plan health care services in anticipation of changes in LVEF levels with changing environmental measures.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgments:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors would like to thank all of the volunteers that took part in this study and the people for their assistance in technical and laboratory support.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding: \u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was supported by the Fundamental Research Funds For the Central Universities 2016TS055, Youth Project of Shaanxi Province Natural Science Basic Research Plan 2021JQ-804 and Shaanxi Provincial Social Science Fund Project 2020F009.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study was approved by Medical Ethics Committee of Second Affiliated Hospital of Xi'an Jiaotong University medical school(2010-LS-009). All methods were performed in accordance with the relevant guidelines and regulations by including a statement in the methods section to this effect.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNone of the authors have any financial or other potential conflict of interest for this study.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll authors consent for publication this study.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors\u0026rsquo; Contribution statement:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eJing Jing and Ge Miao wrote the main manuscript text. Zhang Chong processed data and modeling. Yang Ziqi collected the data. Li Peng prepared figures. Mark Rosenberg revised the paper.\u003c/p\u003e\n\u003cp\u003eAvailability of supporting data\u003c/p\u003e\n\u003cp\u003eThe five geographic indexes come from The Annual Surface Climate Normals of China (1971\u0026ndash;2000), offered by the China Meteorological Data Sharing Service System(\u003ca href=\"http://old-cdc.cma.gov.cn/\"\u003ehttp://old-cdc.cma.gov.cn/\u003c/a\u003e). The remote sensing data are selected from the remote sensing image acquired by the medium resolution imaging spectrometer MODIS（moderate-resolution imaging spectroradiometer） sensing（http://cdc.cma.gov.cn/home.do）\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eJohn JV, McMurray S, Adamopoulos SD, Anker (2012) ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure. Eur Heart J 33:1787\u0026ndash;1847\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBax JJ, Visser FC, Poldermans D et al Relationship Between Preoperative Viability and Postoperative Improvement in LVEF and Heart Failure Symptoms.Journal of Nuclear Medicine Official Publication Society of Nuclear Medicine,2001, 42(1):79\u0026ndash;86\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOta T, Kisslo J, von Ramm OT et al Realtime, volumetric echocardiography: usefulness of volumetric scanning for the assessment of cardiac Volume and function. Cardiol,2001, 37(s1):93\u0026ndash;101\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChou HY Heart rate and cardiovascular risk.Chin J Cardio Diseases,2005, 33(4):388\u0026ndash;390\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDonald R, Ricci FRCP(C) (1979) Arthur E., Influence of heart rate on left ventricular ejection fraction in human beings.The American J of Cardiology, (44):447\u0026ndash;451\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNosir YF, Vletter WB, Kasprzak JD et al (2000) Optimal rotational interval for 3-dimensional echocardiography data acquisition for rapid and accurate Measurement of left ventricular function. Am Soc Echocardiogr 13(8):715\u0026ndash;722\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJing J (2012) Relationship between five reference values of cardiac function and geographical environment.Master\u0026rsquo;s degree of SNNU. :101\u0026ndash;120\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePan L, Li SZ (2012) Change of cardiac function in healthy young males following rapid travel to highlands. J Third Mil Med Uni 34(11):1104\u0026ndash;1106\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRimoldi SF, Sartori C, Seiler C et al High-altitude exposure in patients with cardiovascular disease: risk assessment and practical recommendations.Prog Cardiovasc Dis,2010, 52(6):512\u0026ndash;524\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJing J, Ge M, Yang ZQ et al A New Method to get the LVEF Reference Values of the Healthy Adult Male by Heart Rate and Geographical Environment Factors.International Journal of Gerontology,2018, 12(4):319\u0026ndash;325\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRicci DR, Orlick AE, Alderman EL et al Influence of heart rate on left ventricular ejection fraction in human beings.The American Journal of Cardiology,1979, 44(3):447\u0026ndash;451\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJing J, Ge M, Yang ZQ et al (2018) Correlation of Heart \u0026iuml;\u0026frac14;\u0026sup2;ate and Geographical Environmental Factors with \u0026iuml;\u0026frac14;\u0026sup2;eference Values of Left Ventricular Ejection Fraction in Healthy Adult Males, vol 40. ACTA ACADEMIAE MEDICINAE SINICAE, pp 55\u0026ndash;60. 04\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu Y, Xu J, Zhu L et al Policies of healthcare big data in major developed countries.Chin J Med Libr Inf Sci,2015, 24(10):13\u0026ndash;17\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLim YH, Kim H, Kim JH et al Effect of diurnal temperature range on cardiovascular markers in the elderly in Seoul, Korea.International Journal of Biometeorology,2013, 57(4):597\u0026ndash;603\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLv SQ, Yu LT Advances in research on heart failure in the middle range of ejection fraction.Chinese Journal of Cardiology,2018, 46(3):236\u0026ndash;236\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen YY, Yu XP, Chen SH Clinical Value of Heart Failure Ultrasound Index in Evaluating Ejection Fraction Middle Range Heart Failure.Chinese Journal of Gerontology,2018, 38(10):43\u0026ndash;45\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang H, Huang DJ Advances in research on ejection fraction normal heart failure.Huaxi Medicine,2005, 20(2):415\u0026ndash;416\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChinese Medical Association Cardiovascular Disease Branch. China Heart Failure Diagnosis and Treatment Guide 2014.Chinese Journal of Cardiology,2014, 42(2):3\u0026ndash;10\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePonikowski P, Voors AA, Anker SD et al 2016 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure: The Task Force for the diagnosis and treatment of acute and chronic heart failure of the European Society of Cardiology (ESC). Developed with the special contribution of the Heart Failure Association (HFA) of the ESC.European journal of heart failure,2016, 18(8):891\u0026ndash;975\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGinsberg J Detecting influenza epidemics using search engine query data.Nature,2009, 457(7232):1012\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHung CL, Wu YJ, Liu CC et al (2012) Rationale and Design of MAGNET (Mitochondria-AGing in NorthErn Taiwan) Study: A Community-based Cohort Investigating Mitochondria-related Aging and Cardiovascular Diseases in Suburban Areas of Northern Taiwan. Int J Gerontology 6:122\u0026ndash;126\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHuang YT, Wang CH, Wu YF (2011) Adhering to a TaiChiChuan Exercise Program Improves Vascular Resistance and Cardiac Function. Int J Gerontology 5:150\u0026ndash;154\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang CZ, Xu ZZ (1999) Ultrasound diagnosis. People's Health Publishing House, Beijing, pp 1179\u0026ndash;1183\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang XY, Wang D, Liu NF et al (2015) Left atrial function evaluated by 2D speckle tracking imaging in patients with hypertension and preserved left ventricular ejection fraction. ACTA Uni Medi Nanjing(Natural Science) 35(10):1474\u0026ndash;14781490\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVincent P, Larochelle H, Bengio Y et al Extracting and Composing Robust Features with Denoising Autoencoders. International Conference on Machine Learning,ACM,2008\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHochreiter S, Schmidhuber J (1997) Long Short-Term Memory. Neural Comput 9(8):1735\u0026ndash;1780\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSofiyanti N, Fitmawati D, Roza A Understanding LSTM Networks. GITHUB colah blog,2015,22(2):137\u0026ndash;141\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYao L, Torabi A, Cho K et al (2015) Describing Videos by Exploiting Temporal Structure. IEEE International Conference on Computer Vision (ICCV), :4507\u0026ndash;4515\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSang N Cascade of hierarchical context and appearance for object detection.Optical Engineering,2010, 49(3):30\u0026ndash;37\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang ZH Meteorology and heart.Journal of Cardiovascular Disease Prevention Knowledge,2005,(1):51\u0026ndash;51\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCui WW, Yu LM, Zhang JJ et al Study on the relationship between the onset of acute cardiovascular disease and meteorological factors.Chinese Journal of Emergency Medicine,2014, 23(4):465\u0026ndash;469\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKim CT, Youn-Hee L, Alistair W et al (2015) Heat-Attributable Deaths between 1992 and 2009 in Seoul, South Korea, vol 10. US National Library of Medicine National Institutes of Health, p 0118577. 2\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBobb JF, Peng RD, Bell ML et al Heat-Related Mortality and Adaptation to Heat in the United States.Environmental Health Perspectives,2014, 122(8):811\u0026ndash;816\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHuang C, Barnett AG, Wang X et al Effects of Extreme Temperatures on Years of Life Lost for Cardiovascular Deaths: A Time Series Study in Brisbane, Australia. Circulation: Cardiovascular Quality and Outcomes,2012,5(5): 609\u0026ndash;614\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGasparrini A, Guo Y, Hashizume M et al Mortality risk attributable to high and low ambient temperature: a multicountry observational study.The Lancet,2015, 386(9991):369\u0026ndash;375\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBobb JF, Obermeyer Z, Wang Y et al (2014) Cause-Specific Risk of Hospital Admission Related to Extreme Heat in Older Adults. JAMA 312(24):2659\u0026ndash;2667\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuo YM, Antonio G, Ben A et al Global variation in the effects of ambient temperature on mortality: a systematic evaluation.Epidemiology,2014, 25(6):781\u0026ndash;789\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSun XM, Sun Q, Zhou X et al Heat wave impact on mortality in Pudong New Area, China in 2013.Science of The Total Environment,2014, 493(5):789\u0026ndash;794\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMa W, Zeng W, Zhou M et al (2015) The short-term effect of heat waves on mortality and its modifiers in China: An analysis from 66 communities. Environ Int 75:103\u0026ndash;109\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKalkstein LS, Davis RE Weather and Human Mortality: An Evaluation of Demographic and Interregional Responses in the United States.Annals of the Association of American Geographers,2015, 79(1):44\u0026ndash;64\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang LR, Lei LH The impact of weather changes on population mortality. Ecological science,1997,(2):81\u0026ndash;86\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiang YQ, Hong X, Xu F Influence of meteorological factors in Nanjing on cardiovascular death in residents.Chinese Journal of Disease Control,2015, 19(1):24\u0026ndash;27\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWestheim A, Os I, Thaulow E et al Haemodynamic and neurohumoral effects of cold pressor test in severe heart failure.Clin Physiol,1992,(12):95\u0026ndash;106\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRodr\u0026iacute;guez-Garc\u0026iacute;a JL, Paule A, Dom\u0026iacute;nguez J et al (1999) Effects of the angiotensin II antagonist losartan on endothelin-1 and norepinephrine plasma levels during cold pressor test in patients with chronic heart failure.Int Cardiol,(70):293\u0026ndash;301\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFeng YM, Cheng GQ (1997) Chinese Medicine Meteorology and Geopathology]. Shanghai Science Popularization Press, \u0026auml;\u0026cedil;\u0026#138;\u0026aelig;\u0026micro;\u0026middot;, p 210214\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBarnett AG, Sans S, Salomaa V et al (2007) The effect of temperature on systolic blood pressure. Blood Press Monit 12(3):195\u0026ndash;203\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eModesti PA, Morabito M, Bertolozzi I et al (2006) Weather-Related Changes in 24-Hour Blood Pressure Profile: Effects of Age and Implications for Hypertension Management, vol 47. Hypertension, pp 155\u0026ndash;161. 2\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eElwood PC, Beswick A, O'Brien JR et al Temperature and risk factors for ischaemic heart disease in the Caerphilly prospective study.British Heart Journal,1993, 70(6):520\u0026ndash;520\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRufca GF, Zaffani E, Zerbini R et al Influence of circadian and temperature variations on the ischemic stroke.Revista Da Associa\u0026ccedil;\u0026atilde;o M\u0026eacute;dica Brasileira,2009, 55(1):60\u0026ndash;63\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChoi SH, Lee SW, Hong YS et al (2010) Effects of atmospheric temperature and humidity on outbreak of diseases. Emerg Med Australasia 19(6):501\u0026ndash;508\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eQiao L, Feng DX (2000) Relationship between the onset of acute myocardial infarction and seasonal climate and diurnal changes. J Hubei Coll Traditional Chin Med 2(1):24\u0026ndash;25\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKampmann B, Bride P, Fiala D Physiological responses to temperature and humidity compared to the assessment by UTCI, WGBT and PHS.International Journal of Biometeorology,2012, 56(3):505\u0026ndash;513\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBernhard K, Peter B, Dusan F Physiological responses to temperature and humidity compared to the assessment by UTCI, WGBT and PHS.International Journal of Biometeorol,2012, 56(3):505\u0026ndash;513\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi YW, Tan JG, Jiang JQ The influence of meteorological factors on heart failure.Progress in modern biomedicine,2015, 15(7):1275\u0026ndash;1280\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuangzhou Cardiovascular Research Collaboration Group. Analysis of the incidence and meteorological factors of acute myocardial infarction in Guangzhou.Chinese Journal of Internal Medicine,1984, 23(9):548\u0026ndash;548\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWu YY, Ge QF (1990) Discussion on the relationship between coronary heart disease, stroke and meteorology in Beijing.Chinese Journal of Epidemiology, (2):88\u0026ndash;91\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang CX Air negative ions and health.Yunnan Chemical Technology,2017, 10(44),92\u0026ndash;93\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"LVEF, reference values, health big data, deep learning methods, LSTM","lastPublishedDoi":"10.21203/rs.3.rs-2802057/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2802057/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cb\u003eAims\u003c/b\u003e\u003c/p\u003e \u003cp\u003eThe purpose of this study was to simulate the Left Ventricular Ejection Fraction (LVEF) reference values with heart rate and environmental data using LSTM deep learning methods and to derive the spatial distribution of LVEF reference values in China.\u003c/p\u003e\u003cp\u003e\u003cb\u003eMethods\u003c/b\u003e\u003c/p\u003e \u003cp\u003eHeart rate and environmental factors were used as independent variables, and LVEF indicator values were used as the dependent variable. After the sample data were randomly sampled, the block acquisition data were converted into sample sequence data. Once the sequence data were processed, the sample data were input into the long- and short-term memory networks for deep learning parameter training. After repeated weighting parameter adjustment training and optimization, the optimal prediction model for adult LVEF reference values were derived.\u003c/p\u003e\u003cp\u003e\u003cb\u003eResults\u003c/b\u003e\u003c/p\u003e \u003cp\u003eThe LVEF reference values of normal adults showed a downward trend from moving from the south to north in China. LVEF is negatively correlated with heart rate and annual air temperature range; while positively correlated with annual mean air temperature, annual mean relative humidity, annual precipitation.\u003c/p\u003e\u003cp\u003e\u003cb\u003eConclusions\u003c/b\u003e\u003c/p\u003e \u003cp\u003eThe LVEF reference values are related to heart rate and environmental factors. According to the predicted LSTM model, if the environmental factors of a region is known, combined with the heart rate data from big data, the model can be used to obtain a more accurate LVEF reference value prediction model. A predicted LSTM model is more capable of taking geographical and individual differences into account.\u003c/p\u003e","manuscriptTitle":"A study of Cardiac reference values and environmental factors using big data and deep learning methods","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-04-14 22:08:46","doi":"10.21203/rs.3.rs-2802057/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"ccbcda96-404e-423d-b7d2-06056d6c9a2b","owner":[],"postedDate":"April 14th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2023-04-18T17:59:30+00:00","versionOfRecord":[],"versionCreatedAt":"2023-04-14 22:08:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-2802057","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2802057","identity":"rs-2802057","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}