Survival Analysis and Risk Factors in COVID-19 Patients

Tab-Cox: An Interpretable Deep Survival Analysis Model for Patients With Nasopharyngeal Carcinoma Based on TabNet

The nutritional status of cancer patients is closely associated with the clinical progression of the disease. A survival analysis model combined with a neural network can predict future disease trends in patients, facilitating early prevention and assisting physicians in making diagnoses. However, the complexity of neural networks and their incompatibility with medical tabular data can reduce the interpretability of the model. To address this issue, thr paper propose a novel survival analysis model called Tab-Cox, which combines TabNet and Cox models. This model is specifically designed to predict the survival outcomes of patients with nasopharyngeal carcinoma. The model utilizes TabNet's sequential attention mechanism to extract more interpretable features, providing an interpretable method for identifying disease risk factors. Consequently, the model ensures accurate survival prediction while also making the results more comprehensible for both patients and doctors. The paper tested the efficacy of the model by conducting experiments on various diverse datasets in comparison with other commonly used survival models. The results showed that the proposed model delivered the highest or second-highest accuracy across all datasets. Furthermore, the paper conducted a comparative interpretability analysis against the classical Cox model. In addition and compare the interpretability of the Tab-Cox model with the classical Cox model and discuss the advantages and disadvantages of its interpretability. This demonstrates that Tab-Cox can assist doctors in identifying risk factors that are challenging to capture using artificial methods.

Application of Mixture and Non-mixture Cure Models in Survival Analysis of Patients With COVID-19

Background Due to the emergence of new COVID-19 mutations and an increase in re-infection rates, it has become an important priority for the medical community to identify the factors affecting the short- and long-term survival of patients. This study aimed to determine the risk factors of short- and long-term survival in patients with COVID-19 based on mixture and non-mixture cure models. Methodology In this study, the data of 880 patients with COVID-19 confirmed with polymerase chain reaction in Fereydunshahr city (Isfahan, Iran) from February 20, 2020, to December 21, 2021, were gathered, and the vital status of these patients was followed for at least one year. Due to the high rate of censoring, mixture and non-mixture cure models were applied to estimate the survival. Akaike information criterion values were used to evaluate the fit of the models. Results In this study, the mean age of the patients was 48.9 ± 21.23 years, and the estimated survival rates on the first day, the fourth day, the first week, the first month, and at one year were 0.997, 0.982, 0.973, 0.936, and 0.928, respectively. Among the parametric models, the log-logistic mixed cure model with the logit link, which showed the lowest Akaike information criterion value, demonstrated the best fit. The variables of age and prescribed medication type were significant predictors of long-term survival, while occupation was influential in the short-term survival of patients. Conclusions According to the results of this study, it can be concluded that elderly patients should observe health protocols more strictly and consider receiving booster vaccine doses. The log-logistic cure model with a logit link can be used for survival analysis in COVID-19 patients, a fraction of whom have long-term survival.

Characterization and trajectories of hematological parameters prior to severe COVID-19 based on a large-scale prospective health checkup cohort in western China: a longitudinal study of 13-year follow-up

BACKGROUND

The relaxation of the "zero-COVID" policy on Dec. 7, 2022, in China posed a major public health threat recently. Complete blood count test was discovered to have complicated relationships with COVID-19 after the infection, while very few studies could track long-term monitoring of the health status and identify the characterization of hematological parameters prior to COVID-19.

METHODS

Based on a 13-year longitudinal prospective health checkup cohort of ~ 480,000 participants in West China Hospital, the largest medical center in western China, we documented 998 participants with a laboratory-confirmed diagnosis of COVID-19 during the 1 month after the policy. We performed a time-to-event analysis to explore the associations of severe COVID-19 patients diagnosed, with 34 different hematological parameters at the baseline level prior to COVID-19, including the whole and the subtypes of white and red blood cells.

RESULTS

A total of 998 participants with a positive SARS-CoV-2 test were documented in the cohort, 42 of which were severe cases. For white blood cell-related parameters, a higher level of basophil percentage (HR = 6.164, 95% CI = 2.066-18.393, P = 0.001) and monocyte percentage (HR = 1.283, 95% CI = 1.046-1.573, P = 0.017) were found associated with the severe COVID-19. For lymphocyte-related parameters, a lower level of lymphocyte count (HR = 0.571, 95% CI = 0.341-0.955, P = 0.033), and a higher CD4/CD8 ratio (HR = 2.473, 95% CI = 1.009-6.059, P = 0.048) were found related to the risk of severe COVID-19. We also observed that abnormality of red cell distribution width (RDW), mean corpuscular hemoglobin concentration (MCHC), and hemoglobin might also be involved in the development of severe COVID-19. The different trajectory patterns of RDW-SD and white blood cell count, including lymphocyte and neutrophil, prior to the infection were also discovered to have significant associations with the risk of severe COVID-19 (all P < 0.05).

CONCLUSIONS

Our findings might help decision-makers and clinicians to classify different risk groups of population due to outbreaks including COVID-19. They could not only optimize the allocation of medical resources, but also help them be more proactive instead of reactive to long COVID-19 or even other outbreaks in the future.

Searching for New Biomarkers to Assess COVID-19 Patients: A Pilot Study

During the initial diagnosis of urgent medical conditions, which include acute infectious diseases, it is important to assess the severity of the patient's clinical state as quickly as possible. Unlike individual biochemical or physiological indicators, derived indices make it possible to better characterize a complex syndrome as a set of symptoms, and therefore quickly take a set of adequate measures. Recently, we reported on novel diagnostic indices containing butyrylcholinesterase (BChE) activity, which is decreased in COVID-19 patients. Also, in these patients, the secretion of von Willebrand factor (vWF) increases, which leads to thrombosis in the microvascular bed. The objective of this study was the determination of the concentration and activity of vWF in patients with COVID-19, and the search for new diagnostic indices. One of the main objectives was to compare the prognostic values of some individual and newly derived indices. Patients with COVID-19 were retrospectively divided into two groups: survivors (n = 77) and deceased (n = 24). According to clinical symptoms and computed tomography (CT) results, the course of disease was predominantly moderate in severity. The first blood sample (first point) was taken upon admission to the hospital, the second sample (second point)-within 4-6 days after admission. Along with the standard spectrum of biochemical indicators, BChE activity (BChEa or BChEb for acetylthiocholin or butyrylthiocholin, respectively), malondialdehyde (MDA), and vWF analysis (its antigen level, AGFW, and its activity, ActWF) were determined and new diagnostic indices were derived. The pooled sensitivity, specificity, and area under the receiver operating curve (AUC), as well as Likelihood ratio (LR) and Odds ratio (OR) were calculated. The level of vWF antigen in the deceased group was 1.5-fold higher than the level in the group of survivors. Indices that include vWF antigen levels are superior to indices using vWF activity. It was found that the index [Urea] × [AGWF] × 1000/(BChEb × [ALB]) had the best discriminatory power to predict COVID-19 mortality (AUC = 0.91 [0.83, 1.00], p < 0.0001; OR = 72.0 [7.5, 689], p = 0.0002). In addition, [Urea] × 1000/(BChEb × [ALB]) was a good predictor of mortality (AUC = 0.95 [0.89, 1.00], p < 0.0001; OR = 31.5 [3.4, 293], p = 0.0024). The index [Urea] × [AGWF] × 1000/(BChEb × [ALB]) was the best predictor of mortality associated with COVID-19 infection, followed by [Urea] × 1000/(BChEb × [ALB]). After validation in a subsequent cohort, these two indices could be recommended for diagnostic laboratories.

The Role of Procalcitonin/Albumin Ratio and CRP/Albumin Ratio in Predicting In-hospital Mortality in COVID-19 Patients

Background

Hospitalized coronavirus disease 2019 (COVID-19) patients have higher mortality rates. Parameters to predict mortality are needed. Therefore, we investigated the power of procalcitonin/albumin ratio (PAR) and C-reactive protein/albumin ratio (CAR) to predict in-hospital mortality in hospitalized COVID-19 patients.

Methods

In this study, 855 patients were included. Patients' PAR and CAR values were recorded from the hospital information management system. The patients were evaluated in two groups according to their in-hospital mortality status.

Results

In-hospital mortality was observed in 163 patients (19.1%). The median PAR and CAR values of patients in the non-survivor group were statistically significantly higher than those of patients in the survivor group, PAR (median: 0.07, interquartile range [IQR]: 0.03-0.33 vs. median: 0.02, IQR: 0.01-0.04, respectively; p < 0.001); CAR (median: 27.60, IQR: 12.49-44.91 vs. median: 7.47, IQR: 2.66-18.93, respectively; p < 0.001). The area under the curve (AUC) and odds ratio (OR) values obtained by PAR to predict in-hospital mortality were higher than the values obtained by procalcitonin, CAR, albumin, and CRP (AUCs of PAR, procalcitonin, CAR, albumin, and CRP: 0.804, 0.792, 0.762, 0.755, and 0.748, respectively; OR: PAR > 0.04, procalcitonin > 0.14, CAR > 20.59, albumin < 4.02, and CRP > 63; 8.215, 7.134, 5.842, 6.073, and 5.07, respectively). Patients with concurrent PAR > 0.04 and CAR > 20.59 had an OR of 15.681 compared to patients with concurrent PAR < 0.04 and CAR < 20.59.

Conclusions

In this study, PAR was found to be more valuable for predicting in-hospital COVID-19 mortality than all other parameters. In addition, concurrent high levels of PAR and CAR were found to be more valuable than a high level of PAR or CAR alone.

Survival Analysis of Hospital Length of Stay of COVID-19 Patients in Ilam Province, Iran: A Retrospective Cross-Sectional Study

Knowledge of the length of hospitalization of patients infected with coronavirus disease 2019 (COVID-19), its characteristics, and its related factors creates a better understanding of the impact of medical interventions and hospital capacities. Iran is one of the countries with the most deaths in the world (146,321 total deaths; 5 September 2023) and ranks first among the countries of the Middle East and the EMRO. Analysis of confirmed COVID-19 patients' hospital length of stay in Ilam Province can be informative for decision making in other provinces of Iran. This study was conducted to analyze the survival of COVID-19 patients and the factors associated with COVID-19 deaths in the hospitals of Ilam Province. This is a retrospective cross-sectional study. Data from confirmed COVID-19 cases in Ilam Province were obtained from the SIB system in 2019. The sample size was 774 COVID-19-positive patients from Ilam Province. Measuring survival and risk probabilities in one-week intervals was performed using Cox regression. Most patients were male (55.4%) and 55.3% were over 45 years old. Of the 774 patients, 87 (11.2%) died during the study period. The mean hospital length of stay was 5.14 days. The median survival time with a 95% confidence interval was four days. The probability of survival of patients was 80%, 70%, and 38% for 10, 20, and 30 days of hospital stay, respectively. There was a significant relationship between the survival time of patients with age, history of chronic lung diseases, history of diabetes, history of heart diseases, and hospitalization in ICU (p < 0.05). The risk of dying due to COVID-19 disease was higher among men, older age groups, and patients with a history of chronic lung diseases, diabetes, and heart disease. According to the results, taking preventive measures for elderly patients and those with underlying conditions to prevent the infection of COVID-19 patients is of potential interest. Efficiency in the management of hospital beds should also be considered.

Albumin Is a Component of the Esterase Status of Human Blood Plasma

The esterase status of blood plasma can claim to be one of the universal markers of various diseases; therefore, it deserves attention when searching for markers of the severity of COVID-19 and other infectious and non-infectious pathologies. When analyzing the esterase status of blood plasma, the esterase activity of serum albumin, which is the major protein in the blood of mammals, should not be ignored. The purpose of this study is to expand understanding of the esterase status of blood plasma and to evaluate the relationship of the esterase status, which includes information on the amount and enzymatic activity of human serum albumin (HSA), with other biochemical parameters of human blood, using the example of surviving and deceased patients with confirmed COVID-19. In experiments in vitro and in silico, the activity of human plasma and pure HSA towards various substrates was studied, and the effect of various inhibitors on this activity was tested. Then, a comparative analysis of the esterase status and a number of basic biochemical parameters of the blood plasma of healthy subjects and patients with confirmed COVID-19 was performed. Statistically significant differences have been found in esterase status and biochemical indices (including albumin levels) between healthy subjects and patients with COVID-19, as well as between surviving and deceased patients. Additional evidence has been obtained for the importance of albumin as a diagnostic marker. Of particular interest is a new index, [Urea] × [MDA] × 1000/(BChEb × [ALB]), which in the group of deceased patients was 10 times higher than in the group of survivors and 26 times higher than the value in the group of apparently healthy elderly subjects.

Weibull Regression and Machine Learning Survival Models: Methodology, Comparison, and Application to Biomedical Data Related to Cardiac Surgery

In this article, we propose a comparative study between two models that can be used by researchers for the analysis of survival data: (i) the Weibull regression model and (ii) the random survival forest (RSF) model. The models are compared considering the error rate, the performance of the model through the Harrell C-index, and the identification of the relevant variables for survival prediction. A statistical analysis of a data set from the Heart Institute of the University of São Paulo, Brazil, has been carried out. In the study, the length of stay of patients undergoing cardiac surgery, within the operating room, was used as the response variable. The obtained results show that the RSF model has less error rate for the training and testing data sets, at 23.55% and 20.31%, respectively, than the Weibull model, which has an error rate of 23.82%. Regarding the Harrell C-index, we obtain the values 0.76, 0.79, and 0.76, for the RSF and Weibull models, respectively. After the selection procedure, the Weibull model contains variables associated with the type of protocol and type of patient being statistically significant at 5%. The RSF model chooses age, type of patient, and type of protocol as relevant variables for prediction. We employ the randomForestSRC package of the R software to perform our data analysis and computational experiments. The proposal that we present has many applications in biology and medicine, which are discussed in the conclusions of this work.

COVID-19 mortality surveillance in Lebanon

Since the beginning of the COVID-19 pandemic, the Epidemiological surveillance program of the Lebanese Ministry of Public Health has launched a rapid surveillance system for collecting COVID-19-related mortality data. In this study, we document the Lebanese experience of COVID-19 mortality surveillance and provide an analysis of the epidemiological characteristics of confirmed deaths. The implementation of the rapid COVID-19 mortality surveillance system, data sources, and data collection were described. A retrospective descriptive analysis of the epidemiological characteristics of confirmed cases occurring in Lebanon between February 20, 2020, and September 15, 2021, was performed. Epidemiological curves of Covid-19 confirmed cases and deaths as well as the geographic distribution map of mortality rates were generated. Between February 21, 2020, and September 15, 2021, a total of 8163 COVID-19-related deaths were reported with a predominance of males (60.4%). More than 60% were aged 70 years or above. Of all deaths, 84% occurred at hospitals and 16% at home. The overall cumulative mortality rate was 119.6 per 100,000. The overall case fatality ratio (CRF) was 1.3%. Of the total deaths, 82.2% had at least one underlying medical condition. The top reported COVID-19 comorbidities associated with COVID-19-related deaths are cardiovascular diseases including hypertension (59.1%), diabetes (37.2%), kidney diseases including dialysis (11%), cancer (6.7%), and lung diseases (6.3%). The CFR was 30.9% for kidney diseases, 20.2% for cancer, 20.2% for lung diseases, 18.1% for liver diseases, 14% for diabetes, and 12.2% for cardiovascular diseases. Considering the limited human and financial resources in Lebanon due to the economic and political crisis, the rapid mortality surveillance system can be considered successful. Improving this system is important and would contribute to better detection of deaths from emerging and re-emerging diseases during health crises.

Analysis of Survival of Patients Hospitalized with COVID-19 in Espírito Santo, Brazil

Objective: To analyze the survival of patients hospitalized with COVID-19 and its associated factors. Methods: Retrospective study of survival analysis in individuals notified and hospitalized with COVID-19 in the state of Espírito Santo, Brazil. As data source, the reports of hospitalized patients in the period from 1 March 2020, to 31 July 2021 were used. The Cox regression analysis plus the proportional risk assessment (assumption) were used to compare hospitalization time until the occurrence of the event (death from COVID-19) associated with possible risk factors. Results: The sample comprised 9806 notifications of cases, with the occurrence of 1885 deaths from the disease (19.22%). The mean age of the group was 58 years (SD ± 18.3) and the mean hospital length of stay was 10.5 days (SD ± 11.8). The factors that presented a higher risk of death from COVID-19, associated with a lower survival rate, were non-work-related infection (HR = 4.33; p < 0.001), age group 60−79 years (HR: 1.62; p < 0.001) and 80 years or older (HR = 2.56; p < 0.001), presence of chronic cardiovascular disease (HR = 1.18; p = 0.028), chronic kidney disease (HR = 1.5; p = 0.004), smoking (HR = 1.41; p < 0.001), obesity (HR = 2.28; p < 0.001), neoplasms (HR = 1.81; p < 0.001) and chronic neurological disease (HR = 1.68; p < 0.001). Conclusion: It was concluded that non-work-related infection, age group above or equal to 60 years, presence of chronic cardiovascular disease, chronic kidney disease, chronic neurological disease, smoking, obesity and neoplasms were associated with a higher risk of death, and, therefore, a lower survival in Brazilian patients hospitalized with COVID-19. The identification of priority groups is crucial for Health Surveillance and can guide prevention, control, monitoring, and intervention strategies against the new coronavirus.

COVID Mortality Prediction with Machine Learning Methods: A Systematic Review and Critical Appraisal

More than a year has passed since the report of the first case of coronavirus disease 2019 (COVID), and increasing deaths continue to occur. Minimizing the time required for resource allocation and clinical decision making, such as triage, choice of ventilation modes and admission to the intensive care unit is important. Machine learning techniques are acquiring an increasingly sought-after role in predicting the outcome of COVID patients. Particularly, the use of baseline machine learning techniques is rapidly developing in COVID mortality prediction, since a mortality prediction model could rapidly and effectively help clinical decision-making for COVID patients at imminent risk of death. Recent studies reviewed predictive models for SARS-CoV-2 diagnosis, severity, length of hospital stay, intensive care unit admission or mechanical ventilation modes outcomes; however, systematic reviews focused on prediction of COVID mortality outcome with machine learning methods are lacking in the literature. The present review looked into the studies that implemented machine learning, including deep learning, methods in COVID mortality prediction thus trying to present the existing published literature and to provide possible explanations of the best results that the studies obtained. The study also discussed challenging aspects of current studies, providing suggestions for future developments.

Clinical characteristics and risk factors for mortality in COVID-19 inpatients in Birjand, Iran: a single-center retrospective study

Background

The coronavirus disease 2019(COVID-19) has affected mortality worldwide. The Cox proportional hazard (CPH) model is becoming more popular in time-to-event data analysis. This study aimed to evaluate the clinical characteristics in COVID-19 inpatients including (survivor and non-survivor); thus helping clinicians give the right treatment and assess prognosis and guide the treatment.

Methods

This single-center study was conducted at Hospital for COVID-19 patients in Birjand. Inpatients with confirmed COVID-19 were included. Patients were classified as the discharged or survivor group and the death or non-survivor group based on their outcome (improvement or death). Clinical, epidemiological characteristics, as well as laboratory parameters, were extracted from electronic medical records. Independent sample T test and the Chi-square test or Fisher’s exact test were used to evaluate the association of interested variables. The CPH model was used for survival analysis in the COVID-19 death patients. Significant level was set as 0.05 in all analyses.

Results

The results showed that the mortality rate was about (17.4%). So that, 62(17%) patients had died due to COVID-19, and 298 (83.6%) patients had recovered and discharged. Clinical parameters and comorbidities such as oxygen saturation, lymphocyte and platelet counts, hemoglobin levels, C-reactive protein, and liver and kidney function, were statistically significant between both studied groups. The results of the CPH model showed that comorbidities, hypertension, lymphocyte counts, platelet count, and C-reactive protein level, may increase the risk of death due to the COVID-19 as risk factors in inpatients cases.

Conclusions

Patients with, lower lymphocyte counts in hemogram, platelet count and serum albumin, and high C-reactive protein level, and also patients with comorbidities may have more risk for death. So, it should be given more attention to risk management in the progression of COVID-19 disease.