Subtle changes on electrocardiogram in severe patients with COVID-19 may be predictors of treatment outcome

Subtle changes on electrocardiogram in severe patients with COVID-19 may be predictors of treatment outcome | 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 Article Subtle changes on electrocardiogram in severe patients with COVID-19 may be predictors of treatment outcome Illya Chaikovsky, Dmytro Dziuba, Olga Kryvova, Katerina Marushko, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4384411/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 Background Two years after the COVID-19 pandemic, it became known that one of the complications of this disease is myocardial injury. Electrocardiography (ECG) and cardiac biomarkers play a vital role in the early detection of cardiovascular complications and risk stratification. The study aimed to investigate the value of a new electrocardiographic metric for detecting subtle myocardial injury in patients during COVID-19 treatment. Methods The study was conducted in 2021. A group of 26 patients with verified COVID-19 diagnosis admitted to the intensive care unit for infectious diseases was examined. The severity of a patient's condition was calculated using the NEWS score. The digital ECGs were repeatedly recorded (at the beginning and 2 to 4 times during the treatment). 240 primary and composite ECG parameters were analyzed for each electrocardiogram. Among these patients, 6 patients died during treatment. Cluster analysis was used to identify subgroups of patients that differed significantly in terms of disease severity (NEWS), SрО 2 and integral ECG index (an indicator of the state of the cardiovascular system). Results Using analysis of variance (ANOVA repeated measures), a statistical assessment of changes of indicators in subgroups at the end of treatment was given. These subgroup differences persisted at the end of the treatment. To identify potential predictors of mortality, critical clinical and ECG parameters of surviving(S) and non-surviving patients (D) were compared using parametric and non-parametric statistical tests. A decision tree model to classify survival in patients with COVID-19 was constructed based on partial ECG parameters and NEWS score. Conclusions A comparison of potential mortality predictors showed no significant differences in vital signs between survivors and non-survivors at the beginning of treatment. A set of ECG parameters was identified that were significantly associated with treatment outcomes and may be predictors of COVID-19 mortality: T-wave morphology (SVD), Q-wave amplitude, and R-wave amplitude (lead I). Health sciences/Cardiology Health sciences/Diseases/Infectious diseases Health sciences/Diseases/Infectious diseases/Viral infection electrocardiography myocardial injury severity mortality COVID-19 Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 1. Introduction Experience with the pandemic has shown that the disease can pose a severe threat to the lives of patients. The main danger of the disease is acute respiratory syndrome and lung injury. However, patients may experience damage to other organs and systems: the cardiovascular system, the immune system, the liver and the kidneys. Myocardial injury occurred in at least 10% of unselected COVID-19 cases and up to 41% in critically ill patients or those with comorbidities [1]. In the survivors, the majority showed long-term symptoms, now often referred to as long COVID-19 [2, 3]. One of the critical long-term clinical consequences of COVID-19 seems to be myocardial injury [4–6]. Signs and symptoms of possible myocardial injury after COVID-19 may include severe fatigue, palpitations, chest pain, shortness of breath, postural orthostatic tachycardia syndrome (POTS) due to neurologic disturbances, post-exertional fatigue, and higher troponin levels [7–10]. In addition, COVID-19 appears to cause severe myocarditis. It can affect the myocardium and pericardium, causing severe fatigue without other apparent symptoms [7]. Diagnosis of myocarditis is relatively inaccurate because both tests and diagnostic protocols lack accuracy. Some reports showed that symptoms persisted for an average of 47 days before being diagnosed by cardiac magnetic resonance (CMR) imaging [11]. Therefore, it is critical to identify critical factors for assessing COVID-19 severity, predicting treatment outcomes, and optimizing individual treatment strategies [12, 13]. It is known that 49 variables can provide valuable prognostic information about mortality and disease severity in patients with COVID-19 [12]. Numerous studies have confirmed that cardiac [14] and other biomarkers may reflect cardiovascular injury and inflammation in COVID-19 and are strongly associated with poor prognosis and mortality [15, 16]. In addition, some electrocardiographic [17] and echocardiographic alterations [18] appear to have prognostic implications for patients with COVID-19. Several prognostic models have been developed to assess disease severity in patients with COVID-19 and predict mortality [19–24]. Such classification models have usually been developed using various machine learning (ML) algorithms. For example, one neural network model has demonstrated 93% accuracy in predicting mortality based on patients' physiological status, symptoms, and demographic information [20]. A multivariable logistic regression model and an online risk calculator based on 10 clinical indicators were proposed to predict critical illness development among hospitalized patients with COVID-19 [21]. A support vector machine (SVM) model based on 11 routine clinical parameters was developed to assess the severity of COVID-19 patients [22]. An interpretable mortality prediction model for COVID-19 patients was proposed by Yan et al., where the XGBoost ML algorithm was used to select predictors. The interpretable decision tree and the decision rule for 3 biomarkers that predict the survival of individual patients with more than 90% accuracy were obtained [23]. It should be noted that in one of the ML models for predicting the severity of COVID disease, among the 33 analyzed signs and indicators, there was the cardiac functional grading (according to New York Heart Association functional classification) [24]. However, this cardiac indicator was excluded from the model because of its weak positive correlation with the severity of COVID-19. In this context, the advanced analysis of ECG is highly demanded.This is especially true for patients with a normal or slightly changed electrocardiogram, i.e. if the analysis did not reveal any“major” category according to the, for example, Minnesota coding system. The only way to increase the diagnostic value of ECG examination is to develop proper information technology (IT) — a combination of up-to-date methods and equipment bound into a chain that provides collection, storage, pre-processing, interpretation, conclusion and dissemination of information [25]. At the same time, the advancement of diagnostic methods, especially instrumental ones (i.e., methods of functional diagnostics), primarily entails a constant increase of their "distributive capacity" — the ability to detect subtler and subtler changes in the function examined by one method or another. Such opportunities emerge due to progress in technical measurement tools of a specific function and even more due to the development of informational technologies. In other words, due to the creation of new metrics — numerical parameters using which one can assess the aspects of the functioning of various human organs and systems that were inaccessible before. As a result, new ways of improving the diagnostic accuracy of a particular method within its traditional application scenarios are discovered. Additionally, familiar methods find unconventional uses in new areas. Everything mentioned above fully applies to the new informational technologies for cardiac electrical activity assessment developed at V.M. Glushkov Institute of Cybernetics of the National Academy of Sciences of Ukraine. The main goal set by the developers in this context was to make any electrocardiography informative. Routine ECG analysis is based on specific ECG syndromes or phenomena defined within one of the existing visual ECG analysis algorithms. However, in most cases, no ECG syndrome can be identified during the analysis of an individual electrocardiogram, at least not one that reflects cardiac pathology, i.e., belongs to the "major" category according to the Minnesota coding system, for example. During the routine analysis, one is forced to assign a single class to all these electrocardiograms — electrocardiograms with no primary ECG syndrome identified. However, the question arises: are all these electrocardiograms the same in terms of their relative "distance" to the "ideal" electrocardiogram of a healthy human? They are not. Depending on the myocardial condition, this "distance" can be further or closer. Moreover, there is a reasonable hypothesis that this "distance" reflects the likelihood of serious cardiovascular events. This is where routine analysis of an electrocardiogram is uninformative. That is why the Universal Scoring system method and software for ECG scaling that can provide the quantitative evaluation of the slightest changes in ECG signal were developed [25, 26]. This approach is based on, first of all, measuring the maximum number of ECG parameters and heart rate variability and, secondly, on positioning each parameter value on a scale between the absolute norm and extreme pathology. The suggested approach follows a popular Z-scoring ideology, where quantitative, usually point-based assessment of test results is determined using a unique scale containing data about intra-group test results variation. To calculate the Z-score mean, the test value of the group and its standard deviation are needed [27]. This study aimed to investigate the value of a new electrocardiographic metric for detecting subtle myocardial injury in patients during COVID-19 treatment. And also to test the hypothesis about the prognostic value of myocardial injury on the treatment outcome. 2. Materials And Methods 2.1 Study Design and Patient Characteristics The study was conducted in 2021. 26 patients with confirmed COVID-19 were monitored while on treatment in the intensive care unit (ICU) of the Kyiv Clinical Hospital #4. The hospitalization duration ranged from 5 to 27 days. All the patients were initially in a severe condition. The vital signs were documented to evaluate the course of the illness: heart rate, blood oxygen saturation, blood pressure, body temperature and respiration rate. Based on them, the severity of a patient's condition was calculated using a widely accepted NEWS score [16].Severe COVID-19condition was defined as meeting NEWS aggregate score of 7 or over. The process of patients enrollment is presented on Fig. 1 . Thus, only patients with no signs of instability in relation to heart disease and no gross changes in theelectrocardiogram in accordance with Minnesota coding were included in the study. In 26 patients, an ECG in 12 leads by serial digital ECG device (Solvaig Ltd, Ukraine) was repeatedly recorded (at the beginning and several times during the treatment — from 2 to 4 times). Among these patients, 6 patients died during the treatment. The main characteristics of the patient's condition were recorded several times. The integral indicators were used to calculate the patient's severity according to the NEWS scale (National Early Warning Score) [28] and SAPS II (The Simplified Acute Physiology II Scale) [29]. А demographic and anthropometric values, clinical parameters and ICU characteristics are presented in Table 1 . Table 1 Patient characteristics at ICU admission. Parameter Value Age (years) 63 ± 14.1 Sex (female) 10 (38.47%) Sex (male) 16 (61.53%) Weight (kg) 80.4 ± 16.65 Length (cm) 166.5 ± 9.09 BMI (kg m²) 28.48 ± 6.5 Hypertension 22 (84%) Diabetes Mellitus 9 (34%) Ischemic heart disease 18 (69%) Heart failure 11 (42%) Pulmonary embolism 11 (42%) Pulmonary hypertension 26 (100%) Malignant disease 3 (11.5%) Liver failure 2 (7.6%) Vascular disease 4 (15.3%) Days with symptoms at ICU admission 11.5 (5–27) SAPS II 25 (9–35) NEWS 7.34 (3–10) Data are presented as (mean ± standard deviation), median (interquartile range) and numbers (percentages). ICU: Intensive care unit. BMI – body mass index; SAPS II – Simplified Acute Physiology Score II; NEWS – National Early Warning Score. 2.2 Statistical analysis Data are presented as means ± standard deviation (SD) or median (interquartile range, IQR) for continuous variables, based on normality and as percentages for categorical variables. A two-sample t-test compared the baseline characteristics of subjects within each group with unequal variances for continuous variables. Mann–Whitney U test was performed for variables that were not normally distributed. Two-tailed p < .05 was considered statistically significant. The expectation–maximization (EM) clustering algorithm with 10-fold cross-validation was used to identify homogeneous groups. Homogenous groups were formed based on disease severity and integral index of patients at the beginning of treatment. As a result, two subgroups were identified that were significantly different in the severity of the disease and the integral indicator of the state of the cardiovascular system of patients at the start of treatment. Repeated measures ANOVA was used to evaluate statistical differences in the main clinical parameters in these subgroups at the beginning and the end of treatment. We used machine learning algorithms (CART) such as Decision Trees to construct a model for classifying patient mortality. Statistical analysis was performed using Statistica 12.0 software. 3. Results 3.1 Correlation and cluster analysis, changes of integral parameters in the course of treatment Previous studies have shown heterogeneity in clinical manifestations, severity and outcomes in COVID-19 patients. Our task was to study the heterogeneity of patients, taking into account the vital signs, the severity of the disease, and the state of the cardiovascular system (CVS). In addition, it was necessary to determine the influence of these factors on the treatment outcome. We calculated correlation coefficients for all monitoring data to study the relationship between the CVS state's integral index and patients' vital signs during treatment. Mean values and Spearman correlation coefficients for the vital signs and the integral index of ECG U-score are shown in Table 2 . Table 2 Mean values and Spearman's correlation coefficients for vital signs and U-score integral ECG index. Variables Mean ± SD HR SрО 2 t NEWS SAPS II U-score HR (heart rate) 80.05 ± 11.98 1.00 – 0.24* – 0.10 0.10 0.06 – 0.11 SрО 2 (blood oxygen saturation) 86.46 ± 4.76 – 0.24* 1.00 – 0.24* – 0.64* – 0.12 0.28* Body temperature (tºC) 37.17 ± 0.66 – 0.10 – 0.24* 1.00 0.46* – 0.52 – 0.22* NEWS score 6.14 ± 2.24 0.10 – 0.64* 0.46* 1.00 – 0.25 – 0.25* SAPS II 23.5 ± 6.14 0.06 – 0.12 – 0.52* – 0.25 1.00 – 0.17 U-score 59.49 ± 10.66 – 0.11 0.28* – 0.22* – 0.25* – 0.17 1.00 SD - standard deviation, * p < 0.05 As one can see, a weak but statistically significant correlation exists between U-score integral ECG index and blood oxygen saturation, body temperature and NEWS score (in the last two cases - negative correlation). Table 3 shows the distribution of patients according to the NEWS score, indicating the heterogeneity group of patients at the beginning of treatment. To identify homogeneous subgroups (clusters), the sample of 26 patients was analyzed using EM cluster analysis with 10-fold cross-validation. The NEWS score (as a categorial variable), SрО 2 and U-score integral ECG index at the beginning of treatment have been taken for clusterization. NEWS and U-score were taken for clustering as the most integral indexes, and SpO 2 - since this is the vital sign for patients in the ISU for COVID-19. As a result, two subgroups significantly differing from each other in SpO 2 , NEWS score and U-score values were identified among these patients: Cluster 1 included 19 patients with mean NEWS = 7.1, SрО 2 = 84.3, U-score = 60.5. Cluster 2 included 7 patients with mean NEWS = 8.3, SрО 2 = 78.0, U-score = 49.8. Table 3 The distribution of patient severity score at the beginning of treatment. NEWS score Number of cases % 3 2 6.25 5 2 6.25 6 2 6.25 7 8 25.00 8 13 40.63 9 3 9.38 10 2 6.25 A diagram of standardized values of SpO 2 and U-score is shown in Fig. 2 . As we can see, at the beginning of treatment, patients from cluster 1 have higher levels of oxygen and an integral ECG index compared to cluster 2. Сluster 2 (subgroup 2) is characterized by a combination of greater severity with low oxygen level and lower U-score (integral ECG index level). The average values of vital signs in the identified subgroups are shown in Table 4 . Table 4 Comparison of vital signs in cluster 1 and cluster 2 (t-test). Vital signs Cluster 1 (n = 19) Mean ± SD Cluster 2 (n = 7) Mean ± SD p -value Age 59.63 ± 10.23 71.43 ± 18.48 0.047 BR (breathing rate) 23.84 ± 3.20 24.86 ± 2.91 0.470 HR 82.05 ± 15.06 88.29 ± 11.35 0.331 SpO 2 84.37 ± 2.48 78.00 ± 4.47 0.0001 Body temperature 37.46 ± 0.81 37.79 ± 0.73 0.358 NEWS 7.16 ± 1.77 8.29 ± 1.25 0.136 SAPS II 23.19 ± 5.75 25.67 ± 7.37 0.413 U-score 60.05 ± 11.87 49.86 ± 7.90 0.046 SD - standard deviation, n - number of patients. In addition, the subgroup with a more severe course of the disease (cluster 2) significantly differs in the age of patients. In subgroup 2, patients are older but do not differ in physiological severity. They do not have a significant difference in the indicator of physiological severity SAPS II. We studied the dynamics of the abovementioned main parameters (SpO 2 , NEWS, U-score) in two clusters throughout treatment using a repeated measures analysis of variance (RepANOVA). The changes of these parameters at the beginning (1) and by the end (2) of treatment are shown in Fig. 3 – 5 . As shown from the figures above, both subgroups show a decrease in NEWS severity score and an increase in SpO 2 as a result of treatment, and these changes are statistically significant. The impact of therapy on main parameters in subgroups can be assessed by partial effect sizes (partial eta-squared, ɳ p 2 ). The effect of increasing oxygen in each cluster is significant: cluster 1 R1 SpO 2 ɳ p 2 = 0.73, p = 0.00001; cluster 2 ɳ p 2 = 0.72, p = 0.007. In addition, the dynamics of severity reduction in the 1st subgroup is more pronounced. Sub NEWS partial eta-squared = ɳ p 2 = 0.7, p = 0.0001. Note that a decrease in the mean NEWS is not statistically significant in subgroup 2 (cluster 2 with severe baseline). The U-score integral functional state index has a positive tendency to increase. However, the wide dispersion observed indicates a heterogeneity of U-score changes. Note that in subgroup 2, with low initial levels of integral indicator and oxygen, the part of unfavorable outcomes (ratio deceased / survivors) is 3 out of 7, greaterthan 3 out of 19 in subgroup 1. 3.2 Comparison of vital signs and ECG indicators in two groups by the outcome of treatment Next, we studied the differences between patient groups formed according to treatment outcomes. The study group of 26 patients consisted of two classes according to the treatment outcome: 20 survivors and 6 non-survivors. Clinical data and ECG parameters at the beginning and end of treatment were compared between survivors (S) and non-survivors (D). At the beginning of treatment, there were no significant differences between groups S and D in the vital signs (SAPS II, SpO 2 , NEWS score and U-score), except for the patient's age and body temperature (Table 5 ). Table 5 Comparison of mean vital signs between survivors and non-survivors (t-test). ECG indicators Survivors (n = 20) Mean ± SD Non-survivors (n = 6) Mean ± SD p -value SAPS II 23.61 ± 5.91 25.00 ± 0.693 Age 59.30 ± 11.06 74.50 ± 0.013 SpO 2 82.95 ± 4.16 81.67 ± 0.521 Body temperature 37.47 ± 0.83 37.80 ± 0.63 0.023 NEWS 7.30 ± 1.89 8.00 ± 0.63 0.388 HR 77.25 ± 20.67 78.50 ± 13.91 0.891 U-score 58.10 ± 10.83 54.67 ± 15.23 0.541 Then, an analysis was performed to identify any statistically significant differences among all partial ECG indicators constituting the U-score. The results of comparisons of ECG indicators in these groups at the beginning of treatment according to the t-test are shown in Table 6 and according to the Mann-Whitney U test in Table 7 . Table 6 Mean ECG indicators for survivors and non-survivors at the beginning of treatment (t-test). ECG indicators Survivors (n = 20) Mean ± SD Non-survivors (n = 6) Mean ± SD p -value Т-wave morphology (SVD) 28.95 ± 49.16 98.67 ± 84.44 0.017 Signs of heart failure according to ECG data (12 leads) 0.151 ± 0.09 0.062 ± 0.05 0.039 Square QRS complex (I) 0.023 ± 0.01 0.037 ± 0.02 0.025 Complex serious cardiovascular events risk assessment 60.4 ± 21.30 38.3 ± 22.40 0.037 R-wave amplitude (µV) (lead I) 593.1 ± 231.00 861.8 ± 356.08 0.036 Q-wave amplitude (µV) (lead I) -18.40 ± 29.19 -32.67 ± 43.83 0.358 R-wave amplitude (µV) (lead II) 412.85 ± 210.75 313.00 ± 263.49 0.345 n - number of patients. Table 7 ECG indicators – survivors and non-survivors at the beginning of treatment (Mann-Whitney U test). ECG indicators Survivors (n = 20) Median (IQR) Non-survivors (n = 6) Median (IQR) p -value Shift of the ST segment after 0.08s after point J (mV, lead II) 0.0105 (-0.03; 0.03) -0.00005(− 0.06; 0.01) 0.007 T-wave symmetry through maximum derivatives ratio (lead I) 0.855 (0.76; 0.93) 1.165 (0.92; 2.68) 0.052 IQR - interquartile range, n - number of patients At the beginning of the treatment, statistically significant differences were observed among the following parameter values: 1. T-wave morphology (SVD); 2. Signs of heart failure according to ECG data (12 leads); 3. Complex serious cardiovascular events risk assessment; 4. R-wave amplitude (µV) (lead I); 5. Square QRS complex (lead I); 6. T-wave symmetry through maximum derivatives ratio (lead I). By the end of the treatment, statistically significant differences were observed, in addition to the severity of the disease, among the same ECG parameters and in one of the fundamental heart rate variability indicators, RMSSD, which represents parasympathetic nervous system activity. 3.3 Vital signs and ECG indicators as treatment outcome predictors In the last step of statistical treatment, we explored which parameters had the highest correlation with treatment outcomes using vital signs and the entire ECG and HRV dataset. We used univariate feature selection for classification based on the Chi-square statistical test (Table 8 , Table 9 ). Variables with higher Chi-square statistical values are then selected as predictors for classification. Table 8 Chi-square statistics: outcomes – vital signs. Vital signs (at the beginning of treatment) Chi-square p -value Age 13.09 0.109 SAPS II 11.02 0.201 Body temperature 5.95 0.428 HR 5.15 0.741 BR 2.90 0.714 SpO 2 5.11 0.647 NEWS 3.211 0.782 As follows from Table 8 , vital signs at the beginning of treatment cannot be selected as treatment outcome predictors. ECG indicators that significantly correlate with the treatment outcome class attribute and previously identified features (independent-group t-test) listed in Table 9 ranged p -value. After testing the features with several statistics, we applied the wrapping method to the extracted features. With this approach, we evaluate the effectiveness of a subset of features, considering the final result of the applied learning algorithm (increase in accuracy when solving the classification problem). Table 9 ECG indicators – treatment outcome predictors. Treatment outcome predictors (at the beginning of treatment ) Chi-square p -value R-wave amplitude (mV) (lead II) 18.01 0.011 Т-wave morphology (SVD) 9.56 0.043 Q-wave amplitude (µV) (lead I) 12.26 0.052 Shift of the ST segment after 0.08 sec after point J (mV) (lead I) 13.23 0.104 R-wave amplitude (µV) (lead I) 11.17 0.135 Composite indicator of cardiovascular severe events risk assessment 8.29 0.141 Signs of heart failure according to ECG data (12 leads) 2.87 0.59 We used the CART machine learning algorithm (decision tree method) with 10-fold cross-validation to divide patients into two classes (S, D) according to the tested feature sets. As a result, a set of features with the highest classification accuracy (one classification error) was obtained. Figure 6 shows the optimal classification tree built based on three features. Contribution of 3 ECG parameters to the resulting rules listed in Table 10 . Classification accuracy – 96%. One of the recovered patients was erroneously classified as deceased. Table 10 The contribution (rank) of parameters to the survival classification model. Parameters Variable rank Importance Т-wave morphology (SVD) 100 1.000 R-wave amplitude (µV) (lead II) 98 0.977 Q-wave amplitude (µV) (lead I) 28 0.278 If one builds a tree using both parameters above and an additional attribute, NEWS score value, the result will be as shown in Fig. 7 . This tree has the same structure as the previous one. Still, its right branch has an additional split determined by the NEWS score condition. Contribution of 4 parameters to the resulting rules listed in Table 11 . Table 11 The contribution of parameters to the survival classification model. Parameters Variable rank Importance Т-wave morphology (SVD) 100 1.000 R-wave amplitude (µV) (lead II) 97 0.966 NEWS score 75 0.751 Q-wave amplitude (µV) (lead I) 43 0.428 The classification accuracy on the training set was 100%. Discussion This study and our previous works showed that the combination of ECG and HRV parameters has the best diagnostic value [30–35]. Changes in individual ECG and HRV parameters demonstrate only certain aspects of the examined phenomenon. Moreover, they can occur in opposite directions. Therefore, to reach a particular conclusion, in our case concerning the degree of subtle myocardial injury, a specific summarizing index that would synthesize the effects of individual components is necessary. The calculation method of such an index can be implemented in different ways. However, it must always include such sequential steps as theoretical justification of the composite index for the particular task selection of data adequate to the problem at hand analysis of this data, including its normalization, using methods of multivariate statistics selection of the informative private indicators (including the exclusion of correlated parameters) and finally an actual construction of the composite index through the aggregation of private indicators. As was shown above, we have fulfilled all those steps. At the same time, it is crucial to consider that in addition to the composite index, various partial indicators are the most informative for detecting subtle changes in various clinical scenarios. Usually, those are modern electrocardiographic indexes with a common pathophysiological basis. All of them assess the electrical homogeneity of the myocardium through different means, as the more heterogeneous the myocardium is from an electrical point of view (the higher the dispersion of the generated transmembrane action potentials in amplitude and length), the higher the likelihood of serious cardiovascular events. In our study, such a highly informative modern electrocardiographic index was the T-wave SVD. The SVD of T-wave represents the complexity of ventricular repolarization. One major spatial component (eigenvector) can be identified when repolarization is uniform, as in normal individuals. Conversely, when the repolarization pattern becomes fragmented, the relative value of the smaller vectors increases proportionally. Such an approach allows a comparison between the morphology of the T-wave across the 12 leads and the quantification of T-wave abnormalities in an observer-independent way [35]. This work is the first study to assess minor electrocardiogram changes using the original scaling method in patients with COVID-19. Limitations of the study are the following: Firstly, the number of patients is relatively small. Secondly, no comparison of minor ECG changes with the levels of biomarkers of myocardial damage and inflammation was performed. Finally, the prognostic value of detected ECG changes regarding long-term COVID complications has yet to be analyzed. Further larger-scale studies are planned to confirm and clarify the results. Conclusion The suggested ECG and HRV scaling method allows for registering and analyzing minor electrocardiogram changes during treatment. Modern ECG parameters used for advanced ECG analysis were the most informative. Contrary to this outline, the ECG analysis must be more informative for this task. Two subgroups were identified that differed significantly in the severity of COVID-19 and the integral indicator of the cardiovascular system at the beginning of treatment. At the end of treatment, differences between subgroups remained. In the severe subgroup, there were 50 percent of deaths. A comparison of potential predictors of mortality showed that at the beginning of treatment, there were no significant differences in vital signs between those who survived and those who died. In our study, the average age in the group of deceased patients was slightly higher, and the SAPS II score was not associated with the treatment outcome. A set of ECG parameters significantly associated with treatment outcome and may be predictors of treatment outcome were identified. In addition to the composite index, partial indicators are the most informative for detecting subtle changes in various clinical scenarios, such as treatment outcome prediction. A decision tree for the survival classification of patients with COVID-19 was built based on the partial ECG parameters and NEWS score. Declarations Availability of Data and Materials The authors are committed to providing raw data supporting the conclusions of this study. The detailed data related to the findings of this study are available from the corresponding author upon reasonable request. Author Contributions Conceptualization: Chaikovsky І.А., Dziuba D.О., Loskutov О.А.; methodology: Chaikovsky І.А., Dziuba D.О.; Loskutov О.А. software: Kryvova O.A., Malanin V.O.; validation: Dziuba D.О., Loskutov О.А. and Vakulenko U.G.; formal analysis: Chaikovsky І.А.; investigation: Marushko K.R. and Dziuba D.О.; resources: VakulenkoU.G.. Loskutov O.A.; data curation: Dziuba D.О. and Loskutov О.А.; writing original draft preparation: Chaikovsky І.А. and Dziuba D.О.; review and editing: Chaikovsky І.А and Dziuba D.О.; visualization: Kryvova O.A.; supervision: Loskutov О.А.; project administration: Chaikovsky І.А., Dziuba D.О. All authors have read and agreed to the published version of the manuscript. Ethics Approval and Consent to Participate The study was conducted according to the guidelines of the Declaration of Helsinki and approved by the Ethics Committee of Shupik National Healthcare University of Ukraine, Kyiv (protocol code №5 and date of approval is April 4, 2021). Informed consent was obtained from all subjects involved in the study. Acknowledgment The authors are sincerely grateful to Mrs. Anna Starynska (Cardiolyse Oy, Finland) for her long-term support concerning data management. Funding This work was performed following the main areas of research interest of the Department of Anesthesiology and Intensive Care of the Shupik National Healthcare University of Ukraine under the granting of the Ministry of Health of Ukraine. Conflict of Interest The authors declare no conflict of interest References Cameli M, Pastore MC, Aboumarie SH, Mandoli GE, D'Ascenzi F, Cameli P, et al . Usefulness of echocardiography to detect cardiac involvement in COVID‐19 patients. Echocardiography, 2020; 37(8): 1278–1286. Garg M, Maralakunte M, Garg S, Dhooria S, Sehgal I, Bhalla AS, et al . The conundrum of 'long-COVID-19: a narrative review. International journal of general medicine, 2021; 14: 2491–2506. Crook H, Raza, S, Nowell J, Young M, Edison P. Long covid—mechanisms, risk factors, and management. bmj, 2021; 374: 1–18. Guzik TJ, Mohiddin SA, Dimarco A, Patel V, Savvatis K, Marelli-Berg FM, et al . COVID-19 and the cardiovascular system: implications for risk assessment, diagnosis, and treatment options. Cardiovascular research, 2020; 116: 1666–1687. Italia L, Tomasoni D, Bisegna S, Pancaldi E, Stretti L, Adamo M, et al . COVID-19 and heart failure: from epidemiology during the pandemic to myocardial injury, myocarditis, and heart failure sequelae. Frontiers in cardiovascular medicine, 2021; 8: 713560. Akhmerov A, Marbán E. COVID-19 and the heart.Circulation research, 2020: 126 (10): 1443–1455. Lovell JP, Čiháková D, Gilotra N. A. COVID-19 and myocarditis: review of clinical presentations, pathogenesis and management. Heart International, 2022; 16(1): 20–27. Bandyopadhyay D, Akhtar T, Hajra A, Gupta M, Das A, Chakraborty S, et al . COVID-19 pandemic: cardiovascular complications and future implications. American Journal of Cardiovascular Drugs, 2020; 20: 311–324. Xie Y, Xu E, Bowe B. Long-term cardiovascular outcomes of COVID-19. Nature medicine, 2022; 28(3): 583–590. Matsumori A, Auda ME, Bruno KA, Shapiro KA, KatoT, Nakamura T, et al . Cardiovascular factors associated with COVID-19 from an international registry of primarily Japanese patients. Diagnostics, 2022; 12(10), 2350–2369. OjhaV, Verma M, Pandey NN, Mani A, Malhi AS, Kumar S, et al. Cardiac magnetic resonance imaging in coronavirus disease 2019 (COVID-19): a systematic review of cardiac magnetic resonance imaging findings in 199 patients. Journal of Thoracic Imaging, 2021; 36(2): 73–83. Izcovich A, Ragusa MA, Tortosa F, Lavena Marzio MA, Agnoletti C, Bengolea A, et al . Prognostic factors for severity and mortality in patients infected with COVID-19: A systematic review. PloS one, 2020; 15(11): e0241955. Fathi M, Vakili K, Sayehmiri F, Mohamadkhani A, Hajiesmaeili M, Rezaei-Tavirani M, et al . The prognostic value of comorbidity for the severity of COVID-19: A systematic review and meta-analysis study. PloS one, 2021; 16(2): e0246190. Mueller C, Giannitsis E, Jaffe AS, Huber K, Mair J, Cullen L, et al. Cardiovascular biomarkers in patients with COVID-19. European Heart Journal Acute Cardiovascular Care Association, 2021; 10(3): 310–319. Battaglini D, Lopes-Pacheco M, Castro-Faria-Neto HC., Pelosi P., Rocco PR. Laboratory biomarkers for diagnosis and prognosis in COVID-19. Frontiers in immunology, 2022;13: 857573. Wang K, Zuo P, Liu Y, Zhang M, Zhao X, Xie S, et al. Clinical and laboratory predictors of in-hospital mortality in patients with coronavirus disease-2019: a cohort study in Wuhan, China. Clinical infectious diseases, 2020 ;71(16): 2079–2088. Bergamaschi L, D’Angelo EC, Paolisso P, Toniolo S, Fabrizio M, Angeli F, et al. The value of ECG changes in risk stratification of COVID‐19 patients. Annals of Noninvasive Electrocardiology, 2021; 26(3): e12815. LongB, Brady WJ, Bridwell RE, RamzyM, MontriefT, Singh M, et al. Electrocardiographic manifestations of COVID-19. The American journal of emergency medicine, 2021; 41: 96–103. Bertsimas D, Lukin G,MingardiL, Nohadani O, Orfanoudaki A, Stellato B, et al. COVID-19 mortality risk assessment: An international multi-center study. PLoS ONE, 2020: 15(12), e0243262. Pourhomayoun M, Shakibi M. Predicting mortality risk in patients with COVID-19 using machine learning to help medical decision-making. Smart Health, 2021; 20: 100178. Liang W, Liang H, Ou L, Chen B, Chen A, Li C, et al Development and validation of a clinical risk score to predict the occurrence of critical illness in hospitalized patients with COVID-19. JAMA internal medicine, 2020; 180(8): 1081–1089. Zhou K, Sun Y, Li L, Zang Z, Wang J, Li J, et al Eleven routine clinical features predict COVID-19 severity uncovered by machine learning of longitudinal measurements. Computational and structural biotechnology journal, 2021; 19: 3640–3649. Yan L, Zhang HT, Goncalves J, XiaoY, Wang M, Guo Y, et al An interpretable mortality prediction model for COVID-19 patients. Nature machine intelligence, 2020; 2(5):283–288. Kang J, Chen T, Luo H, Luo Y, Du G, Jiming-Yang M. Machine learning predictive model for severe COVID-19. Infection, Genetics and Evolution, 2021; 90: 104737. Chaikovsky I. Electrocardiogram scoring beyond the routine analysis: subtle changes matters. Expert Review of Medical Devices, 2020; 17(5): 379–382. Chaykovskyy IA, Budnyk MM, Starynska GA. Method of ECG evaluation based on universal scoring system.USA: United States patent US 10,512,412. 24 December 2019. Colan SD. Thy Way and How of Z-Scores. JASE. 2013; 26(1): 38–40. Baker K F, Hanrath AT, van der Loeff IS, Kay LJ, Back J, Duncan CJ. National Early Warning Score 2 (NEWS2) to identify inpatient COVID-19 deterioration: a retrospective analysis. Clinical Medicine, 2021; 21(2): 84–89. Allyn J, Ferdynus C, Bohrer M, Dalban C, Valance D, Allou N. Simplified Acute Physiology Score II as Predictor of Mortality in Intensive Care Units: A Decision Curve Analysis. PLoS ONE, 2016; 11(10): e0164828. Chaikovsky I, Kryvova, O, Kazmirchyk A, Mjasnikov G, Sofienko S, Bugay,A. et al. Assessment of the Post-Traumatic Damage of Myocardium in Patients with Combat Trauma Using a Data Mining Analysis of an Electrocardiogram, In 2019 Signal Processing Symposium (SPSympo). IEEE. Krakow. Poland. 2019; 34–38. Chaikovsky I, Oshlianska O, Artsymovych A, Kryvova O, Kovalenko O, Stadniuk L. Using of Data Mining methods to evaluate the myocardial damage in children with juvenile idiopathic arthritis. 2020 IEEE 40th International Conference on Electronics and Nanotechnology (ELNANO). Kyiv. Ukraine. 2020; 391–395. Apykhtin K, Chaikovsky I, Yaroslavska S, Starynska A, Stadnyk L. Adaptation of cardiovascular system to work in the night shifts of doctors and nurses. Journal of the American College of Cardiology. 2018; 72(16S): 243–243. Neary JP, Baker TP, Jamnik V, Gledhill N, Chaikovsky I, Frolov YA, et al. Multimodal Approach to Cardiac Screening of Elite Ice Hockey Players During the NHL Scouting Combine. Medicine & Science in Sports & Exercise. 2014; 46(5S):742.· Chaikovsky I, Lebedev E, Ponomarev V, Necheporuk A. The relationship between ECG/HRV variables and socio-economic factors: results of mass screening in the rural region of Ukraine. European Journal of Preventive Cardiology, 2020; 27(1): 92. Clarke R, Chaikovsky I, Wright N, Du H, Chen Y, Guo Y, et al. Independent relevance of left ventricular hypertrophy for risk of ischaemic heart disease in 25,000 Chinese adults. European Heart Journal, 2020; 41(Supplement_2): ehaa946-2938. 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-4384411","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":304925557,"identity":"1755e18a-8174-48ee-9ae4-cb3f56c48110","order_by":0,"name":"Illya Chaikovsky","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABE0lEQVRIiWNgGAWjYBACNnbmBhCdwMDMBqH5wVQBHi3MjGhaJEH8BAM81sC1MEC1GBwA0Xi08DEztkn8YLDL429nS3zM8yctcfP51YkfHhgwyPOLHcDlsDbJHobkYonDbIeNedtyErfdeLtZAugww5mzE3BqkeBhOJDYcJi9TXJmQwVQy9kNIC0JBrdxa5H8A9QyH6Rlxp+KxM0zzm7+QUiLNMiWDYfZjkl8YMtJ3MDfu42QLc3WMgbJiRsPsyUbfGxLM55xg3ebRYKBBE6/yLc3H7z5psIucd75Y4YPEv4ky/b3n91880eFjTy/NHYtQMAigRwLjg0SYJUSuJSDAPMHZJ49A/8BfKpHwSgYBaNgBAIAeS5enEkGqewAAAAASUVORK5CYII=","orcid":"","institution":"V.M. Glushkov Institute of Cybernetics","correspondingAuthor":true,"prefix":"","firstName":"Illya","middleName":"","lastName":"Chaikovsky","suffix":""},{"id":304925558,"identity":"f9908480-f401-488a-824f-ba916a295be2","order_by":1,"name":"Dmytro Dziuba","email":"","orcid":"","institution":"Department of Anaesthesiology an Intensive Care, Shupyk National Healthcare University","correspondingAuthor":false,"prefix":"","firstName":"Dmytro","middleName":"","lastName":"Dziuba","suffix":""},{"id":304925559,"identity":"65579357-8b37-4412-b930-eee8e9040bd2","order_by":2,"name":"Olga Kryvova","email":"","orcid":"","institution":"International Research and Training Center of the National Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Olga","middleName":"","lastName":"Kryvova","suffix":""},{"id":304925560,"identity":"5b69f188-fac1-4c30-af9d-fcd146e1511c","order_by":3,"name":"Katerina Marushko","email":"","orcid":"","institution":"Kyiv City Clinical Hospital № 4","correspondingAuthor":false,"prefix":"","firstName":"Katerina","middleName":"","lastName":"Marushko","suffix":""},{"id":304925561,"identity":"e6738c51-a8b4-4f3b-bb49-0d7873ce04e7","order_by":4,"name":"Julia Vakulenko","email":"","orcid":"","institution":"Kyiv City Clinical Hospital № 4","correspondingAuthor":false,"prefix":"","firstName":"Julia","middleName":"","lastName":"Vakulenko","suffix":""},{"id":304925562,"identity":"92a3d3e1-d66e-47b9-ac86-14526069ba3a","order_by":5,"name":"Vladislav Malanin","email":"","orcid":"","institution":"V.M. Glushkov Institute of Cybernetics","correspondingAuthor":false,"prefix":"","firstName":"Vladislav","middleName":"","lastName":"Malanin","suffix":""},{"id":304925563,"identity":"124bc0ba-9e59-4069-872e-7448427a718d","order_by":6,"name":"Oleg Loskutov","email":"","orcid":"","institution":"Shupyk National Healthcare University","correspondingAuthor":false,"prefix":"","firstName":"Oleg","middleName":"","lastName":"Loskutov","suffix":""}],"badges":[],"createdAt":"2024-05-07 16:49:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4384411/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4384411/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":57037047,"identity":"f021a86c-376d-41e5-bc25-6944cd22e14c","added_by":"auto","created_at":"2024-05-23 18:41:57","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":105773,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFlow-chart of the enrollment of COVID-19 patients with serial ECG evaluations.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-4384411/v1/84b26a285d5095857c26f963.png"},{"id":57037053,"identity":"fd1d04ed-2a4f-431c-bef5-4ba947f8eca4","added_by":"auto","created_at":"2024-05-23 18:41:58","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":20683,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNormalized means SpO\u003c/strong\u003e\u003csub\u003e\u003cstrong\u003e2\u003c/strong\u003e\u003c/sub\u003e\u003cstrong\u003e and U-score in cluster 1 and cluster 2.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-4384411/v1/ad4f65d8375c0af4a74ede05.png"},{"id":57037055,"identity":"77d6e669-e5d9-4953-818a-32ad027ed4b4","added_by":"auto","created_at":"2024-05-23 18:41:58","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":16870,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNEWS severity score changes due to treatment in clusters 1 and 2.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-4384411/v1/a92ec1726d320f29485d607f.png"},{"id":57037054,"identity":"4de72135-8803-4e5f-a671-e5026bd7f1f1","added_by":"auto","created_at":"2024-05-23 18:41:58","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":18391,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSpO\u003c/strong\u003e\u003csub\u003e\u003cstrong\u003e2\u003c/strong\u003e\u003c/sub\u003e\u003cstrong\u003e changes due to treatment in clusters 1 and 2.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-4384411/v1/cd80ab1bfffaed8490365447.png"},{"id":57037050,"identity":"45b1ea02-c40e-4f80-9f3a-b01a600dfdf4","added_by":"auto","created_at":"2024-05-23 18:41:57","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":15226,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eU-score integral ECG index changes due to treatment in clusters 1 and 2\u003c/strong\u003e.\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-4384411/v1/a19a98da2f8bb4abab675794.png"},{"id":57037052,"identity":"7b01e77a-856e-4591-9fa4-70aa09ae04b3","added_by":"auto","created_at":"2024-05-23 18:41:57","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":98057,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eThe optimal decision tree for the treatment outcome prognosis.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-4384411/v1/b16c9fe47ecfecd4aa76c424.png"},{"id":57037049,"identity":"3027bb37-2c80-4e7c-8fdd-edfd946eea6d","added_by":"auto","created_at":"2024-05-23 18:41:57","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":114628,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFull tree for the survival classification according to ECG parameters and NEWS score.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"7.png","url":"https://assets-eu.researchsquare.com/files/rs-4384411/v1/25b2bb36eb6ccba307da7d2f.png"},{"id":71970287,"identity":"1707eb72-54ca-477d-ada2-e8ea5c1bf2ff","added_by":"auto","created_at":"2024-12-20 08:09:22","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1283025,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4384411/v1/1ff154fd-5e1e-4dc5-8f68-117ebd776f39.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Subtle changes on electrocardiogram in severe patients with COVID-19 may be predictors of treatment outcome","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eExperience with the pandemic has shown that the disease can pose a severe threat to the lives of patients. The main danger of the disease is acute respiratory syndrome and lung injury. However, patients may experience damage to other organs and systems: the cardiovascular system, the immune system, the liver and the kidneys. Myocardial injury occurred in at least 10% of unselected COVID-19 cases and up to 41% in critically ill patients or those with comorbidities [1].\u003c/p\u003e \u003cp\u003eIn the survivors, the majority showed long-term symptoms, now often referred to as long COVID-19 [2, 3]. One of the critical long-term clinical consequences of COVID-19 seems to be myocardial injury [4\u0026ndash;6].\u003c/p\u003e \u003cp\u003eSigns and symptoms of possible myocardial injury after COVID-19 may include severe fatigue, palpitations, chest pain, shortness of breath, postural orthostatic tachycardia syndrome (POTS) due to neurologic disturbances, post-exertional fatigue, and higher troponin levels [7\u0026ndash;10].\u003c/p\u003e \u003cp\u003eIn addition, COVID-19 appears to cause severe myocarditis. It can affect the myocardium and pericardium, causing severe fatigue without other apparent symptoms [7]. Diagnosis of myocarditis is relatively inaccurate because both tests and diagnostic protocols lack accuracy. Some reports showed that symptoms persisted for an average of 47 days before being diagnosed by cardiac magnetic resonance (CMR) imaging [11].\u003c/p\u003e \u003cp\u003eTherefore, it is critical to identify critical factors for assessing COVID-19 severity, predicting treatment outcomes, and optimizing individual treatment strategies [12, 13]. It is known that 49 variables can provide valuable prognostic information about mortality and disease severity in patients with COVID-19 [12].\u003c/p\u003e \u003cp\u003eNumerous studies have confirmed that cardiac [14] and other biomarkers may reflect cardiovascular injury and inflammation in COVID-19 and are strongly associated with poor prognosis and mortality [15, 16]. In addition, some electrocardiographic [17] and echocardiographic alterations [18] appear to have prognostic implications for patients with COVID-19.\u003c/p\u003e \u003cp\u003eSeveral prognostic models have been developed to assess disease severity in patients with COVID-19 and predict mortality [19\u0026ndash;24].\u003c/p\u003e \u003cp\u003eSuch classification models have usually been developed using various machine learning (ML) algorithms. For example, one neural network model has demonstrated 93% accuracy in predicting mortality based on patients' physiological status, symptoms, and demographic information [20].\u003c/p\u003e \u003cp\u003eA multivariable logistic regression model and an online risk calculator based on 10 clinical indicators were proposed to predict critical illness development among hospitalized patients with COVID-19 [21]. A support vector machine (SVM) model based on 11 routine clinical parameters was developed to assess the severity of COVID-19 patients [22].\u003c/p\u003e \u003cp\u003eAn interpretable mortality prediction model for COVID-19 patients was proposed by Yan et al., where the XGBoost ML algorithm was used to select predictors. The interpretable decision tree and the decision rule for 3 biomarkers that predict the survival of individual patients with more than 90% accuracy were obtained [23].\u003c/p\u003e \u003cp\u003eIt should be noted that in one of the ML models for predicting the severity of COVID disease, among the 33 analyzed signs and indicators, there was the cardiac functional grading (according to New York Heart Association functional classification) [24]. However, this cardiac indicator was excluded from the model because of its weak positive correlation with the severity of COVID-19.\u003c/p\u003e \u003cp\u003eIn this context, the advanced analysis of ECG is highly demanded.This is especially true for patients with a normal or slightly changed electrocardiogram, i.e. if the analysis did not reveal any\u0026ldquo;major\u0026rdquo; category according to the, for example, Minnesota coding system. The only way to increase the diagnostic value of ECG examination is to develop proper information technology (IT) \u0026mdash; a combination of up-to-date methods and equipment bound into a chain that provides collection, storage, pre-processing, interpretation, conclusion and dissemination of information [25].\u003c/p\u003e \u003cp\u003eAt the same time, the advancement of diagnostic methods, especially instrumental ones (i.e., methods of functional diagnostics), primarily entails a constant increase of their \"distributive capacity\" \u0026mdash; the ability to detect subtler and subtler changes in the function examined by one method or another. Such opportunities emerge due to progress in technical measurement tools of a specific function and even more due to the development of informational technologies. In other words, due to the creation of new metrics \u0026mdash; numerical parameters using which one can assess the aspects of the functioning of various human organs and systems that were inaccessible before.\u003c/p\u003e \u003cp\u003eAs a result, new ways of improving the diagnostic accuracy of a particular method within its traditional application scenarios are discovered. Additionally, familiar methods find unconventional uses in new areas.\u003c/p\u003e \u003cp\u003eEverything mentioned above fully applies to the new informational technologies for cardiac electrical activity assessment developed at V.M. Glushkov Institute of Cybernetics of the National Academy of Sciences of Ukraine.\u003c/p\u003e \u003cp\u003eThe main goal set by the developers in this context was to make any electrocardiography informative. Routine ECG analysis is based on specific ECG syndromes or phenomena defined within one of the existing visual ECG analysis algorithms. However, in most cases, no ECG syndrome can be identified during the analysis of an individual electrocardiogram, at least not one that reflects cardiac pathology, i.e., belongs to the \"major\" category according to the Minnesota coding system, for example. During the routine analysis, one is forced to assign a single class to all these electrocardiograms \u0026mdash; electrocardiograms with no primary ECG syndrome identified. However, the question arises: are all these electrocardiograms the same in terms of their relative \"distance\" to the \"ideal\" electrocardiogram of a healthy human? They are not. Depending on the myocardial condition, this \"distance\" can be further or closer. Moreover, there is a reasonable hypothesis that this \"distance\" reflects the likelihood of serious cardiovascular events. This is where routine analysis of an electrocardiogram is uninformative.\u003c/p\u003e \u003cp\u003eThat is why the Universal Scoring system method and software for ECG scaling that can provide the quantitative evaluation of the slightest changes in ECG signal were developed [25, 26]. This approach is based on, first of all, measuring the maximum number of ECG parameters and heart rate variability and, secondly, on positioning each parameter value on a scale between the absolute norm and extreme pathology. The suggested approach follows a popular Z-scoring ideology, where quantitative, usually point-based assessment of test results is determined using a unique scale containing data about intra-group test results variation. To calculate the Z-score mean, the test value of the group and its standard deviation are needed [27].\u003c/p\u003e \u003cp\u003eThis study aimed to investigate the value of a new electrocardiographic metric for detecting subtle myocardial injury in patients during COVID-19 treatment. And also to test the hypothesis about the prognostic value of myocardial injury on the treatment outcome.\u003c/p\u003e"},{"header":"2. Materials And Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Study Design and Patient Characteristics\u003c/h2\u003e \u003cp\u003eThe study was conducted in 2021. 26 patients with confirmed COVID-19 were monitored while on treatment in the intensive care unit (ICU) of the Kyiv Clinical Hospital #4. The hospitalization duration ranged from 5 to 27 days. All the patients were initially in a severe condition.\u003c/p\u003e \u003cp\u003eThe vital signs were documented to evaluate the course of the illness: heart rate, blood oxygen saturation, blood pressure, body temperature and respiration rate. Based on them, the severity of a patient's condition was calculated using a widely accepted NEWS score [16].Severe COVID-19condition was defined as meeting NEWS aggregate score of 7 or over.\u003c/p\u003e \u003cp\u003eThe process of patients enrollment is presented on Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThus, only patients with no signs of instability in relation to heart disease and no gross changes in theelectrocardiogram in accordance with Minnesota coding were included in the study.\u003c/p\u003e \u003cp\u003eIn 26 patients, an ECG in 12 leads by serial digital ECG device (Solvaig Ltd, Ukraine) was repeatedly recorded (at the beginning and several times during the treatment \u0026mdash; from 2 to 4 times). Among these patients, 6 patients died during the treatment. The main characteristics of the patient's condition were recorded several times. The integral indicators were used to calculate the patient's severity according to the NEWS scale (National Early Warning Score) [28] and SAPS II (The Simplified Acute Physiology II Scale) [29]. А demographic and anthropometric values, clinical parameters and ICU characteristics are presented in 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\u003ePatient characteristics at ICU admission.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eParameter\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eValue\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge (years)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e63\u0026thinsp;\u0026plusmn;\u0026thinsp;14.1\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSex (female)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10 (38.47%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSex (male)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16 (61.53%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWeight (kg)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e80.4\u0026thinsp;\u0026plusmn;\u0026thinsp;16.65\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLength (cm)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e166.5\u0026thinsp;\u0026plusmn;\u0026thinsp;9.09\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBMI (kg m\u0026sup2;)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e28.48\u0026thinsp;\u0026plusmn;\u0026thinsp;6.5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHypertension\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e22 (84%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiabetes Mellitus\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9 (34%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIschemic heart disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e18 (69%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHeart failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e11 (42%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePulmonary embolism\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e11 (42%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePulmonary hypertension\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e26 (100%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMalignant disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3 (11.5%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLiver failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (7.6%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVascular disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4 (15.3%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDays with symptoms at ICU admission\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e11.5 (5\u0026ndash;27)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSAPS II\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e25 (9\u0026ndash;35)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNEWS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7.34 (3\u0026ndash;10)\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\u003eData are presented as (mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation), median (interquartile range) and numbers (percentages). ICU: Intensive care unit. BMI \u0026ndash; body mass index; SAPS II \u0026ndash; Simplified Acute Physiology Score II; NEWS \u0026ndash; National Early Warning Score.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Statistical analysis\u003c/h2\u003e \u003cp\u003eData are presented as means\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation (SD) or median (interquartile range, IQR) for continuous variables, based on normality and as percentages for categorical variables. A two-sample t-test compared the baseline characteristics of subjects within each group with unequal variances for continuous variables. Mann\u0026ndash;Whitney U test was performed for variables that were not normally distributed. Two-tailed p\u0026thinsp;\u0026lt;\u0026thinsp;.05 was considered statistically significant.\u003c/p\u003e \u003cp\u003eThe expectation\u0026ndash;maximization (EM) clustering algorithm with 10-fold cross-validation was used to identify homogeneous groups. Homogenous groups were formed based on disease severity and integral index of patients at the beginning of treatment. As a result, two subgroups were identified that were significantly different in the severity of the disease and the integral indicator of the state of the cardiovascular system of patients at the start of treatment. Repeated measures ANOVA was used to evaluate statistical differences in the main clinical parameters in these subgroups at the beginning and the end of treatment.\u003c/p\u003e \u003cp\u003eWe used machine learning algorithms (CART) such as Decision Trees to construct a model for classifying patient mortality. Statistical analysis was performed using Statistica 12.0 software.\u003c/p\u003e \u003c/div\u003e"},{"header":"3. Results","content":"\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e3.1 Correlation and cluster analysis, changes of integral parameters in the course of treatment\u003c/h2\u003e \u003cp\u003ePrevious studies have shown heterogeneity in clinical manifestations, severity and outcomes in COVID-19 patients. Our task was to study the heterogeneity of patients, taking into account the vital signs, the severity of the disease, and the state of the cardiovascular system (CVS). In addition, it was necessary to determine the influence of these factors on the treatment outcome.\u003c/p\u003e \u003cp\u003eWe calculated correlation coefficients for all monitoring data to study the relationship between the CVS state's integral index and patients' vital signs during treatment. Mean values and Spearman correlation coefficients for the vital signs and the integral index of ECG U-score are shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\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\u003eMean values and Spearman's correlation coefficients for vital signs and U-score integral ECG index.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"8\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariables\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eHR\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSрО\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003et\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNEWS\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eSAPS II\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eU-score\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHR (heart rate)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e80.05\u0026thinsp;\u0026plusmn;\u0026thinsp;11.98\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026ndash; 0.24*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u0026ndash; 0.10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.06\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e\u0026ndash; 0.11\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSрО\u003csub\u003e2\u003c/sub\u003e (blood oxygen saturation)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e86.46\u0026thinsp;\u0026plusmn;\u0026thinsp;4.76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e\u0026ndash; 0.24*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u0026ndash; 0.24*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026ndash; 0.64*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026ndash; 0.12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.28*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBody temperature (t\u0026ordm;C)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e37.17\u0026thinsp;\u0026plusmn;\u0026thinsp;0.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e\u0026ndash; 0.10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026ndash; 0.24*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.46*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026ndash; 0.52\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e\u0026ndash; 0.22*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNEWS score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e6.14\u0026thinsp;\u0026plusmn;\u0026thinsp;2.24\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026ndash; 0.64*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.46*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026ndash; 0.25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e\u0026ndash; 0.25*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSAPS II\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e23.5\u0026thinsp;\u0026plusmn;\u0026thinsp;6.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.06\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026ndash; 0.12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u0026ndash; 0.52*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026ndash; 0.25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e\u0026ndash; 0.17\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eU-score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e59.49\u0026thinsp;\u0026plusmn;\u0026thinsp;10.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e\u0026ndash; 0.11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.28*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u0026ndash; 0.22*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026ndash; 0.25*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u0026ndash; 0.17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"8\"\u003eSD - standard deviation, *\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eAs one can see, a weak but statistically significant correlation exists between U-score integral ECG index and blood oxygen saturation, body temperature and NEWS score (in the last two cases - negative correlation).\u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e shows the distribution of patients according to the NEWS score, indicating the heterogeneity group of patients at the beginning of treatment.\u003c/p\u003e \u003cp\u003eTo identify homogeneous subgroups (clusters), the sample of 26 patients was analyzed using EM cluster analysis with 10-fold cross-validation. The NEWS score (as a categorial variable), SрО\u003csub\u003e2\u003c/sub\u003e and U-score integral ECG index at the beginning of treatment have been taken for clusterization. NEWS and U-score were taken for clustering as the most integral indexes, and SpO\u003csub\u003e2\u003c/sub\u003e - since this is the vital sign for patients in the ISU for COVID-19.\u003c/p\u003e \u003cp\u003eAs a result, two subgroups significantly differing from each other in SpO\u003csub\u003e2\u003c/sub\u003e, NEWS score and U-score values were identified among these patients:\u003c/p\u003e \u003cp\u003eCluster 1 included 19 patients with mean NEWS\u0026thinsp;=\u0026thinsp;7.1, SрО\u003csub\u003e2\u003c/sub\u003e = 84.3, U-score\u0026thinsp;=\u0026thinsp;60.5.\u003c/p\u003e \u003cp\u003eCluster 2 included 7 patients with mean NEWS\u0026thinsp;=\u0026thinsp;8.3, SрО\u003csub\u003e2\u003c/sub\u003e = 78.0, U-score\u0026thinsp;=\u0026thinsp;49.8.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eThe distribution of patient severity score at the beginning of treatment.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNEWS score\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNumber of cases\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003e%\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e6.25\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e6.25\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e6.25\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e25.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e40.63\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9.38\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e6.25\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\u003eA diagram of standardized values of SpO\u003csub\u003e2\u003c/sub\u003e and U-score is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. As we can see, at the beginning of treatment, patients from cluster 1 have higher levels of oxygen and an integral ECG index compared to cluster 2. Сluster 2 (subgroup 2) is characterized by a combination of greater severity with low oxygen level and lower U-score (integral ECG index level).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe average values of vital signs in the identified subgroups are shown in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eComparison of vital signs in cluster 1 and cluster 2 (t-test).\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVital signs\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCluster 1 (n\u0026thinsp;=\u0026thinsp;19)\u003c/p\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eCluster 2 (n\u0026thinsp;=\u0026thinsp;7)\u003c/p\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e-value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e59.63\u0026thinsp;\u0026plusmn;\u0026thinsp;10.23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e71.43\u0026thinsp;\u0026plusmn;\u0026thinsp;18.48\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.047\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBR (breathing rate)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e23.84\u0026thinsp;\u0026plusmn;\u0026thinsp;3.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e24.86\u0026thinsp;\u0026plusmn;\u0026thinsp;2.91\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.470\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e82.05\u0026thinsp;\u0026plusmn;\u0026thinsp;15.06\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e88.29\u0026thinsp;\u0026plusmn;\u0026thinsp;11.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.331\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSpO\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e84.37\u0026thinsp;\u0026plusmn;\u0026thinsp;2.48\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e78.00\u0026thinsp;\u0026plusmn;\u0026thinsp;4.47\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBody temperature\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e37.46\u0026thinsp;\u0026plusmn;\u0026thinsp;0.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e37.79\u0026thinsp;\u0026plusmn;\u0026thinsp;0.73\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.358\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNEWS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e7.16\u0026thinsp;\u0026plusmn;\u0026thinsp;1.77\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e8.29\u0026thinsp;\u0026plusmn;\u0026thinsp;1.25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.136\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSAPS II\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e23.19\u0026thinsp;\u0026plusmn;\u0026thinsp;5.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e25.67\u0026thinsp;\u0026plusmn;\u0026thinsp;7.37\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.413\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eU-score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e60.05\u0026thinsp;\u0026plusmn;\u0026thinsp;11.87\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e49.86\u0026thinsp;\u0026plusmn;\u0026thinsp;7.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.046\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\u003eSD - standard deviation, n - number of patients.\u003c/p\u003e \u003cp\u003eIn addition, the subgroup with a more severe course of the disease (cluster 2) significantly differs in the age of patients. In subgroup 2, patients are older but do not differ in physiological severity. They do not have a significant difference in the indicator of physiological severity SAPS II.\u003c/p\u003e \u003cp\u003eWe studied the dynamics of the abovementioned main parameters (SpO\u003csub\u003e2\u003c/sub\u003e, NEWS, U-score) in two clusters throughout treatment using a repeated measures analysis of variance (RepANOVA). The changes of these parameters at the beginning (1) and by the end (2) of treatment are shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e\u0026ndash;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eAs shown from the figures above, both subgroups show a decrease in NEWS severity score and an increase in SpO\u003csub\u003e2\u003c/sub\u003e as a result of treatment, and these changes are statistically significant. The impact of therapy on main parameters in subgroups can be assessed by partial effect sizes (partial eta-squared, ɳ\u003csub\u003ep\u003c/sub\u003e\u003csup\u003e2\u003c/sup\u003e). The effect of increasing oxygen in each cluster is significant: cluster 1 R1 SpO\u003csub\u003e2\u003c/sub\u003eɳ\u003csub\u003ep\u003c/sub\u003e\u003csup\u003e2\u003c/sup\u003e = 0.73, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.00001; cluster 2 ɳ\u003csub\u003ep\u003c/sub\u003e\u003csup\u003e2\u003c/sup\u003e = 0.72, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.007.\u003c/p\u003e \u003cp\u003eIn addition, the dynamics of severity reduction in the 1st subgroup is more pronounced. Sub NEWS partial eta-squared = ɳ\u003csub\u003ep\u003c/sub\u003e\u003csup\u003e2\u003c/sup\u003e = 0.7, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.0001. Note that a decrease in the mean NEWS is not statistically significant in subgroup 2 (cluster 2 with severe baseline).\u003c/p\u003e \u003cp\u003eThe U-score integral functional state index has a positive tendency to increase. However, the wide dispersion observed indicates a heterogeneity of U-score changes. Note that in subgroup 2, with low initial levels of integral indicator and oxygen, the part of unfavorable outcomes (ratio deceased / survivors) is 3 out of 7, greaterthan 3 out of 19 in subgroup 1.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e3.2 Comparison of vital signs and ECG indicators in two groups by the outcome of treatment\u003c/h2\u003e \u003cp\u003eNext, we studied the differences between patient groups formed according to treatment outcomes. The study group of 26 patients consisted of two classes according to the treatment outcome: 20 survivors and 6 non-survivors. Clinical data and ECG parameters at the beginning and end of treatment were compared between survivors (S) and non-survivors (D).\u003c/p\u003e \u003cp\u003eAt the beginning of treatment, there were no significant differences between groups S and D in the vital signs (SAPS II, SpO\u003csub\u003e2\u003c/sub\u003e, NEWS score and U-score), except for the patient's age and body temperature (Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eComparison of mean vital signs between survivors and non-survivors (t-test).\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eECG indicators\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSurvivors\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;20)\u003c/p\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNon-survivors\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;6)\u003c/p\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e-value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSAPS II\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e23.61\u0026thinsp;\u0026plusmn;\u0026thinsp;5.91\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e25.00 \u0026plusmn;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.693\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e59.30\u0026thinsp;\u0026plusmn;\u0026thinsp;11.06\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e74.50 \u0026plusmn;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.013\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSpO\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e82.95\u0026thinsp;\u0026plusmn;\u0026thinsp;4.16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e81.67 \u0026plusmn;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.521\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBody temperature\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e37.47\u0026thinsp;\u0026plusmn;\u0026thinsp;0.83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e37.80\u0026thinsp;\u0026plusmn;\u0026thinsp;0.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.023\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNEWS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e7.30\u0026thinsp;\u0026plusmn;\u0026thinsp;1.89\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e8.00\u0026thinsp;\u0026plusmn;\u0026thinsp;0.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.388\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e77.25\u0026thinsp;\u0026plusmn;\u0026thinsp;20.67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e78.50\u0026thinsp;\u0026plusmn;\u0026thinsp;13.91\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.891\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eU-score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e58.10\u0026thinsp;\u0026plusmn;\u0026thinsp;10.83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e54.67\u0026thinsp;\u0026plusmn;\u0026thinsp;15.23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.541\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\u003eThen, an analysis was performed to identify any statistically significant differences among all partial ECG indicators constituting the U-score. The results of comparisons of ECG indicators in these groups at the beginning of treatment according to the t-test are shown in Table\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e and according to the Mann-Whitney U test in Table\u0026nbsp;\u003cspan refid=\"Tab7\" class=\"InternalRef\"\u003e7\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab6\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 6\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eMean ECG indicators for survivors and non-survivors at the beginning of treatment (t-test).\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eECG indicators\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSurvivors\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;20)\u003c/p\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNon-survivors\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;6)\u003c/p\u003e \u003cp\u003eMean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e-value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eТ-wave morphology (SVD)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e28.95\u0026thinsp;\u0026plusmn;\u0026thinsp;49.16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e98.67\u0026thinsp;\u0026plusmn;\u0026thinsp;84.44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.017\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSigns of heart failure according to ECG data (12 leads)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e0.151\u0026thinsp;\u0026plusmn;\u0026thinsp;0.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e0.062\u0026thinsp;\u0026plusmn;\u0026thinsp;0.05\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.039\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSquare QRS complex (I)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e0.023\u0026thinsp;\u0026plusmn;\u0026thinsp;0.01\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e0.037\u0026thinsp;\u0026plusmn;\u0026thinsp;0.02\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.025\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eComplex serious cardiovascular events risk assessment\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e60.4\u0026thinsp;\u0026plusmn;\u0026thinsp;21.30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e38.3\u0026thinsp;\u0026plusmn;\u0026thinsp;22.40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.037\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eR-wave amplitude (\u0026micro;V) (lead I)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e593.1\u0026thinsp;\u0026plusmn;\u0026thinsp;231.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e861.8\u0026thinsp;\u0026plusmn;\u0026thinsp;356.08\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.036\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eQ-wave amplitude (\u0026micro;V) (lead I)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e-18.40\u0026thinsp;\u0026plusmn;\u0026thinsp;29.19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e-32.67\u0026thinsp;\u0026plusmn;\u0026thinsp;43.83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.358\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eR-wave amplitude (\u0026micro;V) (lead II)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e412.85\u0026thinsp;\u0026plusmn;\u0026thinsp;210.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e313.00\u0026thinsp;\u0026plusmn;\u0026thinsp;263.49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.345\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\u003en - number of patients.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab7\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 7\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eECG indicators \u0026ndash; survivors and non-survivors at the beginning of treatment (Mann-Whitney U test).\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\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=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eECG indicators\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSurvivors\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;20)\u003c/p\u003e \u003cp\u003eMedian (IQR)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNon-survivors\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;6)\u003c/p\u003e \u003cp\u003eMedian (IQR)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e-value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eShift of the ST segment after 0.08s after point J (mV, lead II)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.0105 (-0.03; 0.03)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e-0.00005(\u0026minus;\u0026thinsp;0.06; 0.01)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.007\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eT-wave symmetry through maximum derivatives ratio (lead I)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.855 (0.76; 0.93)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.165 (0.92; 2.68)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.052\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\u003eIQR - interquartile range, n - number of patients\u003c/p\u003e \u003cp\u003eAt the beginning of the treatment, statistically significant differences were observed among the following parameter values:\u003c/p\u003e\u003cp\u003e1. T-wave morphology (SVD);\u003c/p\u003e \u003cp\u003e2. Signs of heart failure according to ECG data (12 leads);\u003c/p\u003e \u003cp\u003e3. Complex serious cardiovascular events risk assessment;\u003c/p\u003e \u003cp\u003e4. R-wave amplitude (\u0026micro;V) (lead I);\u003c/p\u003e\u003cp\u003e5. Square QRS complex (lead I);\u003c/p\u003e \u003cp\u003e6. T-wave symmetry through maximum derivatives ratio (lead I).\u003c/p\u003e \u003cp\u003eBy the end of the treatment, statistically significant differences were observed, in addition to the severity of the disease, among the same ECG parameters and in one of the fundamental heart rate variability indicators, RMSSD, which represents parasympathetic nervous system activity.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e3.3 Vital signs and ECG indicators as treatment outcome predictors\u003c/h2\u003e \u003cp\u003eIn the last step of statistical treatment, we explored which parameters had the highest correlation with treatment outcomes using vital signs and the entire ECG and HRV dataset. We used univariate feature selection for classification based on the Chi-square statistical test (Table\u0026nbsp;\u003cspan refid=\"Tab8\" class=\"InternalRef\"\u003e8\u003c/span\u003e, Table\u0026nbsp;\u003cspan refid=\"Tab9\" class=\"InternalRef\"\u003e9\u003c/span\u003e). Variables with higher Chi-square statistical values are then selected as predictors for classification.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab8\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 8\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eChi-square statistics: outcomes \u0026ndash; vital signs.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVital signs (at the beginning of treatment)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eChi-square\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e-value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e13.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.109\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSAPS II\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e11.02\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.201\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBody temperature\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.428\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5.15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.741\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.714\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSpO\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5.11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.647\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNEWS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3.211\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.782\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\u003eAs follows from Table\u0026nbsp;\u003cspan refid=\"Tab8\" class=\"InternalRef\"\u003e8\u003c/span\u003e, vital signs at the beginning of treatment cannot be selected as treatment outcome predictors.\u003c/p\u003e \u003cp\u003eECG indicators that significantly correlate with the treatment outcome class attribute and previously identified features (independent-group t-test) listed in Table\u0026nbsp;\u003cspan refid=\"Tab9\" class=\"InternalRef\"\u003e9\u003c/span\u003e ranged \u003cem\u003ep\u003c/em\u003e-value.\u003c/p\u003e \u003cp\u003eAfter testing the features with several statistics, we applied the wrapping method to the extracted features. With this approach, we evaluate the effectiveness of a subset of features, considering the final result of the applied learning algorithm (increase in accuracy when solving the classification problem).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab9\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 9\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eECG indicators \u0026ndash; treatment outcome predictors.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTreatment outcome predictors (at the beginning of treatment )\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eChi-square\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e-value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eR-wave amplitude (mV) (lead II)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e18.01\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.011\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eТ-wave morphology (SVD)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e9.56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.043\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eQ-wave amplitude (\u0026micro;V) (lead I)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e12.26\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.052\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eShift of the ST segment after 0.08 sec after point J (mV) (lead I)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e13.23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.104\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eR-wave amplitude (\u0026micro;V) (lead I)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e11.17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.135\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eComposite indicator of cardiovascular severe events risk assessment\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e8.29\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.141\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSigns of heart failure according to ECG data (12 leads)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2.87\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.59\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\u003eWe used the CART machine learning algorithm (decision tree method) with 10-fold cross-validation to divide patients into two classes (S, D) according to the tested feature sets. As a result, a set of features with the highest classification accuracy (one classification error) was obtained. Figure\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e shows the optimal classification tree built based on three features.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eContribution of 3 ECG parameters to the resulting rules listed in Table\u0026nbsp;\u003cspan refid=\"Tab10\" class=\"InternalRef\"\u003e10\u003c/span\u003e. Classification accuracy \u0026ndash; 96%. One of the recovered patients was erroneously classified as deceased.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab10\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 10\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eThe contribution (rank) of parameters to the survival classification model.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eParameters\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eVariable rank\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eImportance\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eТ-wave morphology (SVD)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eR-wave amplitude (\u0026micro;V) (lead II)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e98\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.977\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eQ-wave amplitude (\u0026micro;V) (lead I)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e28\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.278\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\u003eIf one builds a tree using both parameters above and an additional attribute, NEWS score value, the result will be as shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e7\u003c/span\u003e. This tree has the same structure as the previous one. Still, its right branch has an additional split determined by the NEWS score condition.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eContribution of 4 parameters to the resulting rules listed in Table\u0026nbsp;\u003cspan refid=\"Tab11\" class=\"InternalRef\"\u003e11\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab11\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 11\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eThe contribution of parameters to the survival classification model.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eParameters\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eVariable rank\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eImportance\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eТ-wave morphology (SVD)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eR-wave amplitude (\u0026micro;V) (lead II)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e97\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.966\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNEWS score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.751\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eQ-wave amplitude (\u0026micro;V) (lead I)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.428\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 classification accuracy on the training set was 100%.\u003c/p\u003e \u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eThis study and our previous works showed that the combination of ECG and HRV parameters has the best diagnostic value [30\u0026ndash;35].\u003c/p\u003e \u003cp\u003eChanges in individual ECG and HRV parameters demonstrate only certain aspects of the examined phenomenon. Moreover, they can occur in opposite directions. Therefore, to reach a particular conclusion, in our case concerning the degree of subtle myocardial injury, a specific summarizing index that would synthesize the effects of individual components is necessary. The calculation method of such an index can be implemented in different ways. However, it must always include such sequential steps as theoretical justification of the composite index for the particular task selection of data adequate to the problem at hand analysis of this data, including its normalization, using methods of multivariate statistics selection of the informative private indicators (including the exclusion of correlated parameters) and finally an actual construction of the composite index through the aggregation of private indicators. As was shown above, we have fulfilled all those steps. At the same time, it is crucial to consider that in addition to the composite index, various partial indicators are the most informative for detecting subtle changes in various clinical scenarios.\u003c/p\u003e \u003cp\u003eUsually, those are modern electrocardiographic indexes with a common pathophysiological basis. All of them assess the electrical homogeneity of the myocardium through different means, as the more heterogeneous the myocardium is from an electrical point of view (the higher the dispersion of the generated transmembrane action potentials in amplitude and length), the higher the likelihood of serious cardiovascular events. In our study, such a highly informative modern electrocardiographic index was the T-wave SVD.\u003c/p\u003e \u003cp\u003eThe SVD of T-wave represents the complexity of ventricular repolarization. One major spatial component (eigenvector) can be identified when repolarization is uniform, as in normal individuals. Conversely, when the repolarization pattern becomes fragmented, the relative value of the smaller vectors increases proportionally. Such an approach allows a comparison between the morphology of the T-wave across the 12 leads and the quantification of T-wave abnormalities in an observer-independent way [35].\u003c/p\u003e \u003cp\u003eThis work is the first study to assess minor electrocardiogram changes using the original scaling method in patients with COVID-19.\u003c/p\u003e \u003cp\u003eLimitations of the study are the following: Firstly, the number of patients is relatively small. Secondly, no comparison of minor ECG changes with the levels of biomarkers of myocardial damage and inflammation was performed. Finally, the prognostic value of detected ECG changes regarding long-term COVID complications has yet to be analyzed.\u003c/p\u003e \u003cp\u003eFurther larger-scale studies are planned to confirm and clarify the results.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThe suggested ECG and HRV scaling method allows for registering and analyzing minor electrocardiogram changes during treatment. Modern ECG parameters used for advanced ECG analysis were the most informative. Contrary to this outline, the ECG analysis must be more informative for this task.\u003c/p\u003e \u003cp\u003eTwo subgroups were identified that differed significantly in the severity of COVID-19 and the integral indicator of the cardiovascular system at the beginning of treatment. At the end of treatment, differences between subgroups remained. In the severe subgroup, there were 50 percent of deaths.\u003c/p\u003e \u003cp\u003eA comparison of potential predictors of mortality showed that at the beginning of treatment, there were no significant differences in vital signs between those who survived and those who died. In our study, the average age in the group of deceased patients was slightly higher, and the SAPS II score was not associated with the treatment outcome. A set of ECG parameters significantly associated with treatment outcome and may be predictors of treatment outcome were identified.\u003c/p\u003e \u003cp\u003eIn addition to the composite index, partial indicators are the most informative for detecting subtle changes in various clinical scenarios, such as treatment outcome prediction. A decision tree for the survival classification of patients with COVID-19 was built based on the partial ECG parameters and NEWS score.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAvailability of Data and Materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors are committed to providing raw data supporting the conclusions of this study. The detailed data related to the findings of this study are available from the corresponding author upon reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor Contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eConceptualization: Chaikovsky І.А., Dziuba D.О., Loskutov О.А.; methodology: Chaikovsky І.А., Dziuba D.О.; Loskutov О.А. software: Kryvova O.A., Malanin V.O.; validation: Dziuba D.О., Loskutov О.А. and Vakulenko U.G.; formal analysis: Chaikovsky І.А.; investigation: Marushko K.R. and Dziuba D.О.; resources: VakulenkoU.G.. Loskutov O.A.; data curation: Dziuba D.О. and Loskutov О.А.; writing original draft preparation: Chaikovsky І.А. and Dziuba D.О.; review and editing: Chaikovsky І.А and Dziuba D.О.; visualization: Kryvova O.A.; supervision: Loskutov О.А.; project administration: Chaikovsky І.А., Dziuba D.О. All authors have read and agreed to the published version of the manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics Approval and Consent to Participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study was conducted according to the guidelines of the Declaration of Helsinki and approved by the Ethics Committee of Shupik National Healthcare University of Ukraine, Kyiv (protocol code №5 and date of approval is\u0026nbsp;April 4, 2021). Informed consent was obtained from all subjects involved in the study.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgment\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors are sincerely grateful to Mrs. Anna Starynska (Cardiolyse Oy, Finland) for her long-term support concerning data management.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis work was performed following the main areas of research interest of the Department of Anesthesiology and Intensive Care of the Shupik National Healthcare University of Ukraine under the granting of the Ministry of Health of Ukraine.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflict of Interest\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare no conflict of interest\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eCameli M, Pastore MC, Aboumarie SH, Mandoli GE, D\u0026apos;Ascenzi F, Cameli P, \u003cem\u003eet al\u003c/em\u003e. Usefulness of echocardiography to detect cardiac involvement in COVID‐19 patients. Echocardiography, 2020; 37(8): 1278\u0026ndash;1286. \u003c/li\u003e\n\u003cli\u003eGarg M, Maralakunte M, Garg S, Dhooria S, Sehgal I, Bhalla AS, \u003cem\u003eet al\u003c/em\u003e. The conundrum of \u0026apos;long-COVID-19: a narrative review. International journal of general medicine, 2021; 14: 2491\u0026ndash;2506.\u003c/li\u003e\n\u003cli\u003eCrook H, Raza, S, Nowell J, Young M, Edison P. Long covid\u0026mdash;mechanisms, risk factors, and management. bmj, 2021; 374: 1\u0026ndash;18.\u003c/li\u003e\n\u003cli\u003eGuzik TJ, Mohiddin SA, Dimarco A, Patel V, Savvatis K, Marelli-Berg FM, \u003cem\u003eet al\u003c/em\u003e. COVID-19 and the cardiovascular system: implications for risk assessment, diagnosis, and treatment options. Cardiovascular research, 2020; 116: 1666\u0026ndash;1687.\u003c/li\u003e\n\u003cli\u003eItalia L, Tomasoni D, Bisegna S, Pancaldi E, Stretti L, Adamo M, \u003cem\u003eet al\u003c/em\u003e. COVID-19 and heart failure: from epidemiology during the pandemic to myocardial injury, myocarditis, and heart failure sequelae. Frontiers in cardiovascular medicine, 2021; 8: 713560.\u003c/li\u003e\n\u003cli\u003eAkhmerov A, Marb\u0026aacute;n E. COVID-19 and the heart.Circulation research, 2020: 126 (10): 1443\u0026ndash;1455. \u003c/li\u003e\n\u003cli\u003eLovell JP, Čih\u0026aacute;kov\u0026aacute; D, Gilotra N. A. COVID-19 and myocarditis: review of clinical presentations, pathogenesis and management. Heart International, 2022; 16(1): 20\u0026ndash;27.\u003c/li\u003e\n\u003cli\u003eBandyopadhyay D, Akhtar T, Hajra A, Gupta M, Das A, Chakraborty S, \u003cem\u003eet al\u003c/em\u003e. COVID-19 pandemic: cardiovascular complications and future implications. American Journal of Cardiovascular Drugs, 2020; 20: 311\u0026ndash;324.\u003c/li\u003e\n\u003cli\u003eXie Y, Xu E, Bowe B. Long-term cardiovascular outcomes of COVID-19. Nature medicine, 2022; 28(3): 583\u0026ndash;590. \u003c/li\u003e\n\u003cli\u003eMatsumori A, Auda ME, Bruno KA, Shapiro KA, KatoT, Nakamura T, \u003cem\u003eet al\u003c/em\u003e. Cardiovascular factors associated with COVID-19 from an international registry of primarily Japanese patients. Diagnostics, 2022; 12(10), 2350\u0026ndash;2369.\u003c/li\u003e\n\u003cli\u003eOjhaV, Verma M, Pandey NN, Mani A, Malhi AS, Kumar S, \u003cem\u003eet al.\u003c/em\u003e Cardiac magnetic resonance imaging in coronavirus disease 2019 (COVID-19): a systematic review of cardiac magnetic resonance imaging findings in 199 patients. Journal of Thoracic Imaging, 2021; 36(2): 73\u0026ndash;83.\u003c/li\u003e\n\u003cli\u003eIzcovich A, Ragusa MA, Tortosa F, Lavena Marzio MA, Agnoletti C, Bengolea A, \u003cem\u003eet al\u003c/em\u003e. Prognostic factors for severity and mortality in patients infected with COVID-19: A systematic review. PloS one, 2020; 15(11): e0241955.\u003c/li\u003e\n\u003cli\u003eFathi M, Vakili K, Sayehmiri F, Mohamadkhani A, Hajiesmaeili M, Rezaei-Tavirani M, \u003cem\u003eet al\u003c/em\u003e. The prognostic value of comorbidity for the severity of COVID-19: A systematic review and meta-analysis study. PloS one, 2021; 16(2): e0246190.\u003c/li\u003e\n\u003cli\u003eMueller C, Giannitsis E, Jaffe AS, Huber K, Mair J, Cullen L, \u003cem\u003eet al.\u003c/em\u003eCardiovascular biomarkers in patients with COVID-19. European Heart Journal Acute Cardiovascular Care Association, 2021; 10(3): 310\u0026ndash;319.\u003c/li\u003e\n\u003cli\u003eBattaglini D, Lopes-Pacheco M, Castro-Faria-Neto HC., Pelosi P., Rocco PR. Laboratory biomarkers for diagnosis and prognosis in COVID-19. Frontiers in immunology, 2022;13: 857573.\u003c/li\u003e\n\u003cli\u003eWang K, Zuo P, Liu Y, Zhang M, Zhao X, Xie S, \u003cem\u003eet al.\u003c/em\u003eClinical and laboratory predictors of in-hospital mortality in patients with coronavirus disease-2019: a cohort study in Wuhan, China. Clinical infectious diseases, 2020 ;71(16): 2079\u0026ndash;2088.\u003c/li\u003e\n\u003cli\u003eBergamaschi L, D\u0026rsquo;Angelo EC, Paolisso P, Toniolo S, Fabrizio M, Angeli F, \u003cem\u003eet al.\u003c/em\u003eThe value of ECG changes in risk stratification of COVID‐19 patients. Annals of Noninvasive Electrocardiology, 2021; 26(3): e12815.\u003c/li\u003e\n\u003cli\u003eLongB, Brady WJ, Bridwell RE, RamzyM, MontriefT, Singh M, \u003cem\u003eet al.\u003c/em\u003eElectrocardiographic manifestations of COVID-19. The American journal of emergency medicine, 2021; 41: 96\u0026ndash;103.\u003c/li\u003e\n\u003cli\u003eBertsimas D, Lukin G,MingardiL, Nohadani O, Orfanoudaki A, Stellato B,\u003cem\u003eet al.\u003c/em\u003eCOVID-19 mortality risk assessment: An international multi-center study. PLoS ONE, 2020: 15(12), e0243262. \u003c/li\u003e\n\u003cli\u003ePourhomayoun M, Shakibi M. Predicting mortality risk in patients with COVID-19 using machine learning to help medical decision-making. Smart Health, 2021; 20: 100178.\u003c/li\u003e\n\u003cli\u003eLiang W, Liang H, Ou L, Chen B, Chen A, Li C, \u003cem\u003eet al \u003c/em\u003eDevelopment and validation of a clinical risk score to predict the occurrence of critical illness in hospitalized patients with COVID-19. JAMA internal medicine, 2020; 180(8): 1081\u0026ndash;1089. \u003c/li\u003e\n\u003cli\u003eZhou K, Sun Y, Li L, Zang Z, Wang J, Li J, \u003cem\u003eet al \u003c/em\u003eEleven routine clinical features predict COVID-19 severity uncovered by machine learning of longitudinal measurements. Computational and structural biotechnology journal, 2021; 19: 3640\u0026ndash;3649.\u003c/li\u003e\n\u003cli\u003eYan L, Zhang HT, Goncalves J, XiaoY, Wang M, Guo Y, \u003cem\u003eet al \u003c/em\u003eAn interpretable mortality prediction model for COVID-19 patients. Nature machine intelligence, 2020; 2(5):283\u0026ndash;288.\u003c/li\u003e\n\u003cli\u003eKang J, Chen T, Luo H, Luo Y, Du G, Jiming-Yang M. Machine learning predictive model for severe COVID-19. Infection, Genetics and Evolution, 2021; 90: 104737.\u003c/li\u003e\n\u003cli\u003eChaikovsky I. Electrocardiogram scoring beyond the routine analysis: subtle changes matters. Expert Review of Medical Devices, 2020; 17(5): 379\u0026ndash;382. \u003c/li\u003e\n\u003cli\u003eChaykovskyy IA, Budnyk MM, Starynska GA. Method of ECG evaluation based on universal scoring system.USA: United States patent US 10,512,412. 24 December 2019.\u003c/li\u003e\n\u003cli\u003eColan SD. Thy Way and How of Z-Scores. JASE. 2013; 26(1): 38\u0026ndash;40.\u003c/li\u003e\n\u003cli\u003eBaker K F, Hanrath AT, van der Loeff IS, Kay LJ, Back J, Duncan CJ. National Early Warning Score 2 (NEWS2) to identify inpatient COVID-19 deterioration: a retrospective analysis. Clinical Medicine, 2021; 21(2): 84\u0026ndash;89.\u003c/li\u003e\n\u003cli\u003eAllyn J, Ferdynus C, Bohrer M, Dalban C, Valance D, Allou N. Simplified Acute Physiology Score II as Predictor of Mortality in Intensive Care Units: A Decision Curve Analysis. PLoS ONE, 2016; 11(10): e0164828.\u003c/li\u003e\n\u003cli\u003eChaikovsky I, Kryvova, O, Kazmirchyk A, Mjasnikov G, Sofienko S, Bugay,A.\u003cem\u003eet al.\u003c/em\u003e Assessment of the Post-Traumatic Damage of Myocardium in Patients with Combat Trauma Using a Data Mining Analysis of an Electrocardiogram, In 2019 Signal Processing Symposium (SPSympo). IEEE. Krakow. Poland. 2019; 34\u0026ndash;38.\u003c/li\u003e\n\u003cli\u003eChaikovsky I, Oshlianska O, Artsymovych A, Kryvova O, Kovalenko O, Stadniuk L. Using of Data Mining methods to evaluate the myocardial damage in children with juvenile idiopathic arthritis. 2020 IEEE 40th International Conference on Electronics and Nanotechnology (ELNANO). Kyiv. Ukraine. 2020; 391\u0026ndash;395.\u003c/li\u003e\n\u003cli\u003eApykhtin K, Chaikovsky I, Yaroslavska S, Starynska A, Stadnyk L. Adaptation of cardiovascular system to work in the night shifts of doctors and nurses. Journal of the American College of Cardiology. 2018; 72(16S): 243\u0026ndash;243.\u003c/li\u003e\n\u003cli\u003eNeary JP, Baker TP, Jamnik V, Gledhill N, Chaikovsky I, Frolov YA, \u003cem\u003eet al.\u003c/em\u003e Multimodal Approach to Cardiac Screening of Elite Ice Hockey Players During the NHL Scouting Combine. Medicine \u0026amp; Science in Sports \u0026amp; Exercise. 2014; 46(5S):742.\u0026middot;\u003c/li\u003e\n\u003cli\u003eChaikovsky I, Lebedev E, Ponomarev V, Necheporuk A. The relationship between ECG/HRV variables and socio-economic factors: results of mass screening in the rural region of Ukraine. European Journal of Preventive Cardiology, 2020; 27(1): 92.\u003c/li\u003e\n\u003cli\u003eClarke R, Chaikovsky I, Wright N, Du H, Chen Y, Guo Y, \u003cem\u003eet al.\u003c/em\u003eIndependent relevance of left ventricular hypertrophy for risk of ischaemic heart disease in 25,000 Chinese adults. European Heart Journal, 2020; 41(Supplement_2): ehaa946-2938.\u003c/li\u003e\n\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":"electrocardiography, myocardial injury, severity, mortality, COVID-19","lastPublishedDoi":"10.21203/rs.3.rs-4384411/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4384411/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eTwo years after the COVID-19 pandemic, it became known that one of the complications of this disease is myocardial injury. Electrocardiography (ECG) and cardiac biomarkers play a vital role in the early detection of cardiovascular complications and risk stratification. The study aimed to investigate the value of a new electrocardiographic metric for detecting subtle myocardial injury in patients during COVID-19 treatment.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThe study was conducted in 2021. A group of 26 patients with verified COVID-19 diagnosis admitted to the intensive care unit for infectious diseases was examined. The severity of a patient's condition was calculated using the NEWS score. The digital ECGs were repeatedly recorded (at the beginning and 2 to 4 times during the treatment). 240 primary and composite ECG parameters were analyzed for each electrocardiogram. Among these patients, 6 patients died during treatment. Cluster analysis was used to identify subgroups of patients that differed significantly in terms of disease severity (NEWS), SрО\u003csub\u003e2\u003c/sub\u003eand integral ECG index (an indicator of the state of the cardiovascular system).\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eUsing analysis of variance (ANOVA repeated measures), a statistical assessment of changes of indicators in subgroups at the end of treatment was given. These subgroup differences persisted at the end of the treatment. To identify potential predictors of mortality, critical clinical and ECG parameters of surviving(S) and non-surviving patients (D) were compared using parametric and non-parametric statistical tests. A decision tree model to classify survival in patients with COVID-19 was constructed based on partial ECG parameters and NEWS score.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eA comparison of potential mortality predictors showed no significant differences in vital signs between survivors and non-survivors at the beginning of treatment. A set of ECG parameters was identified that were significantly associated with treatment outcomes and may be predictors of COVID-19 mortality: T-wave morphology (SVD), Q-wave amplitude, and R-wave amplitude (lead I).\u003c/p\u003e","manuscriptTitle":"Subtle changes on electrocardiogram in severe patients with COVID-19 may be predictors of treatment outcome","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-23 18:41:52","doi":"10.21203/rs.3.rs-4384411/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":"e8e2d16c-0581-4313-98b1-11de7fb197a0","owner":[],"postedDate":"May 23rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":32192991,"name":"Health sciences/Cardiology"},{"id":32192992,"name":"Health sciences/Diseases/Infectious diseases"},{"id":32192993,"name":"Health sciences/Diseases/Infectious diseases/Viral infection"}],"tags":[],"updatedAt":"2024-12-20T08:08:50+00:00","versionOfRecord":[],"versionCreatedAt":"2024-05-23 18:41:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4384411","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4384411","identity":"rs-4384411","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}