Survival prediction of COVID-19 patients using multi-modal dataset

COVID-19 has proved to be a global emergency that has fractured the healthcare systems to the extent that its impact is too challenging to encompass. Though many Computer-Aided Diagnoses (CAD) systems have been developed for automatic detection of COVID-19 from Chest X-rays and chest CT images, very few works have been done on detecting COVID-19 from a clinical dataset. Resources needed for obtaining Clinical data like blood pressure, liver disease, past traveling history, etc., are inexpensive compared to collecting Chest CT images for COVID-19 infected patients. We propose a novel multi-model dataset for the survival prediction of patients infected with COVID-19. The dataset proposed is collected and created at Mahatma Gandhi Memorial Medical College, Indore. The dataset contains clinical data and chest X-ray images obtained from the same patient infected with COVID-19. For proper prognosis of the COVID19 positive patients from the clinical dataset, we have proposed a Bi-Stream Gated Attention-based CNN (BSGA-CNN) model. The BSGA-CNN model achieved an accuracy of 96.90% (± 3.05%). A CNN based on pre-trained VGG-Net is used to classify the corresponding Chest X-Ray images. It gave an accuracy of 87.76% (± 8.78%)%. © 2022 IEEE.

Prediction of Survival COVID-19 Patients by Using Backpropagation Neural Network Algorithm

COVID-19 is a disease caused by a virus and increasing in cases every day. This is because the large number of patients makes it difficult to be treated at the hospital. This is behind the need for survival prediction of COVID-19 patients within 48 days so that the medical team can prioritize patients who are predicted to not survive on that period. In this research, the firefly algorithm is used which aims to select attributes and will perform comparisons for data that is balance or imbalance and combined with data that do feature selection and does not feature selection. The data that will be used are age, asthma, diabetes, gender, COPD, pregnancy, hypertension, obesity, ICU, chronic kidney disease, smoking, heart disease, immune deficiency, pneumonia, and other medical history. In this research, the selected attributes were gender, type of patient, intubation, pneumonia, age, pregnancy, diabetes, COPD (Chronic Obstructive Pulmonary Disease), asthma, hypertension, other diseases, obesity, chronic kidney disease, smokers, contact with COVID patients, and ICU. The prediction model with the highest level of performance is a model with balanced data with a recall value of 0.79, then a precision value of 0.93, then an f score of 0.85, then an accuracy value of 0.86, then a specificity 0,93, then a NPV 0,82 and a geometric mean value of 0.87 © 2022 IEEE.

Application of machine learning techniques for predicting survival in ovarian cancer.

BACKGROUND: Ovarian cancer is the fifth leading cause of mortality among women in the United States. Ovarian cancer is also known as forgotten cancer or silent disease. The survival of ovarian cancer patients depends on several factors, including the treatment process and the prognosis. METHODS: The ovarian cancer patients' dataset is compiled from the Surveillance, Epidemiology, and End Results (SEER) database. With the help of a clinician, the dataset is curated, and the most relevant features are selected. Pearson's second coefficient of skewness test is used to evaluate the skewness of the dataset. Pearson correlation coefficient is also used to investigate the associations between features. Statistical test is utilized to evaluate the significance of the features. Six Machine Learning (ML) models, including K-Nearest Neighbors , Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Adaptive Boosting (AdaBoost), and Extreme Gradient Boosting (XGBoost), are implemented for survival prediction in both classification and regression approaches. An interpretable method, Shapley Additive Explanations (SHAP), is applied to clarify the decision-making process and determine the importance of each feature in prediction. Additionally, DTs of the RF model are displayed to show how the model predicts the survival intervals. RESULTS: Our results show that RF (Accuracy = 88.72%, AUC = 82.38%) and XGBoost (Root Mean Squad Error (RMSE)) = 20.61%, R2 = 0.4667) have the best performance for classification and regression approaches, respectively. Furthermore, using the SHAP method along with extracted DTs of the RF model, the most important features in the dataset are identified. Histologic type ICD-O-3, chemotherapy recode, year of diagnosis, age at diagnosis, tumor stage, and grade are the most important determinant factors in survival prediction. CONCLUSION: To the best of our knowledge, our study is the first study that develops various ML models to predict ovarian cancer patients' survival on the SEER database in both classification and regression approaches. These ML algorithms also achieve more accurate results and outperform statistical methods. Furthermore, our study is the first study to use the SHAP method to increase confidence and transparency of the proposed models' prediction for clinicians. Moreover, our developed models, as an automated auxiliary tool, can help clinicians to have a better understanding of the estimated survival as well as important features that affect survival.

Asthma and COVID-19 in the elderly: course, survival, predictors of mortality

Bronchial asthma occurs in 0.9 - 17% of patients hospitalized with COVID-19. However, it is not clear whether asthma is a risk factor for the development and severity of COVID-19. Studies have shown that patients with asthma appear to be more susceptible to COVID-19 infection, but severe disease progression is not related to medication use, including asthma biologics, but rather to older age and comorbidities. Aim. To evaluate the clinical course of SARS-CoV-2 infection in elderly patients with asthma, to examine the effect of asthma and comorbidities on COVID-19-related outcomes, and to determine predictors of mortality. Methods. Elderly patients [WHO, 2020] (> 60 years, n = 131, median age 74 (67;80) years;59 men, 72 women) with asthma hospitalized for COVID-19 were included in the study. COVID-19 was confirmed by laboratory tests (PCR smear) and/or clinical and radiological examinations. All patients had a history of a documented diagnosis of asthma (GINA, 2020). Results. Out of 131 patients, 30 (22.9%) died in the hospital, and 15 (14.9%) died after discharge from the hospital (within 90 days). The group of patients with lethal outcome showed the following differences from those who recovered: values of Charlson index, respiration rate, degree of lung damage on CT scan, absolute number of leukocytes, neutrophils and neutrophils-to-lymphocytes ratio, C-reactive protein on the 5th day of hospitalization, and LDH were statistically significantly higher, while absolute number of eosinophils, total protein content, SpO2 and SpO2/FiO2 levels were lower;steroid intake during the year and non-atopic asthma were more common. Multivariate and ROC analysis revealed the most significant predictors of hospital mortality and their thresholds: Charlson comorbidity index ≥ 6 points, neutrophil/lymphocyte ratio ≥ 4.5, total protein ≤ 60 g/l, eosinophil level ≤ 100 cells/μL. Conclusion. The most significant predictors of hospital mortality in elderly patients with severe COVID-19 against asthma are Charlson comorbidity, neutrophil/lymphocyte ratio;lower eosinophil and total protein levels. Survival time of patients has an inverse correlation with the number of mortality risk factors present.

Clinical applications of machine learning in the survival prediction and classification of sepsis: coagulation and heparin usage matter.

BACKGROUND: Sepsis is a life-threatening syndrome eliciting highly heterogeneous host responses. Current prognostic evaluation methods used in clinical practice are characterized by an inadequate effectiveness in predicting sepsis mortality. Rapid identification of patients with high mortality risk is urgently needed. The phenotyping of patients will assistant invaluably in tailoring treatments. METHODS: Machine learning and deep learning technology are used to characterize the patients' phenotype and determine the sepsis severity. The database used in this study is MIMIC-III and MIMIC-IV ('Medical information Mart for intensive care') which is a large, public, and freely available database. The K-means clustering is used to classify the sepsis phenotype. Convolutional neural network (CNN) was used to predict the 28-day survival rate based on 35 blood test variables of the sepsis patients, whereas a double coefficient quadratic multivariate fitting function (DCQMFF) is utilized to predict the 28-day survival rate with only 11 features of sepsis patients. RESULTS: The patients were grouped into four clusters with a clear survival nomogram. The first cluster (C_1) was characterized by low white blood cell count, low neutrophil, and the highest lymphocyte proportion. C_2 obtained the lowest Sequential Organ Failure Assessment (SOFA) score and the highest survival rate. C_3 was characterized by significantly prolonged PTT, high SIC, and a higher proportion of patients using heparin than the patients in other clusters. The early mortality rate of patients in C_3 was high but with a better long-term survival rate than that in C_4. C_4 contained septic coagulation patients with the worst prognosis, characterized by slightly prolonged partial thromboplastin time (PTT), significantly prolonged prothrombin time (PT), and high septic coagulation disease score (SIC). The survival rate prediction accuracy of CNN and DCQMFF models reached 92% and 82%, respectively. The models were tested on an external dataset (MIMIC-IV) and achieved good performance. A DCQMFF-based application platform was established for fast prediction of the 28-day survival rate. CONCLUSION: CNN and DCQMFF accurately predicted the sepsis patients' survival, while K-means successfully identified the phenotype groups. The distinct phenotypes associated with survival, and significant features correlated with mortality were identified. The findings suggest that sepsis patients with abnormal coagulation had poor outcomes, abnormal coagulation increase mortality during sepsis. The anticoagulation effects of appropriate heparin sodium treatment may improve extensive micro thrombosis-caused organ failure.

Deep-Learning Approach to Predict Survival Outcomes Using Wearable Actigraphy Device Among End-Stage Cancer Patients.

Survival prediction is highly valued in end-of-life care clinical practice, and patient performance status evaluation stands as a predominant component in survival prognostication. While current performance status evaluation tools are limited to their subjective nature, the advent of wearable technology enables continual recordings of patients' activity and has the potential to measure performance status objectively. We hypothesize that wristband actigraphy monitoring devices can predict in-hospital death of end-stage cancer patients during the time of their hospital admissions. The objective of this study was to train and validate a long short-term memory (LSTM) deep-learning prediction model based on activity data of wearable actigraphy devices. The study recruited 60 end-stage cancer patients in a hospice care unit, with 28 deaths and 32 discharged in stable condition at the end of their hospital stay. The standard Karnofsky Performance Status score had an overall prognostic accuracy of 0.83. The LSTM prediction model based on patients' continual actigraphy monitoring had an overall prognostic accuracy of 0.83. Furthermore, the model performance improved with longer input data length up to 48 h. In conclusion, our research suggests the potential feasibility of wristband actigraphy to predict end-of-life admission outcomes in palliative care for end-stage cancer patients. Clinical Trial Registration: The study protocol was registered on ClinicalTrials.gov (ID: NCT04883879).

Radiomics analysis of chest CT to predict the overall survival for the severe patients of COVID-19 pneumonia.

Personalized assessment and treatment of severe patients with COVID-19 pneumonia have greatly affected the prognosis and survival of these patients. This study aimed to develop the radiomics models as the potential biomarkers to estimate the overall survival (OS) for the COVID-19 severe patients. A total of 74 COVID-19 severe patients were enrolled in this study, and 30 of them died during the follow-up period. First, the clinical risk factors of the patients were analyzed. Then, two radiomics signatures were constructed based on two segmented volumes of interest of whole lung area and lesion area. Two combination models were built depend on whether the clinic risk factors were used and/or whether two radiomics signatures were combined. Kaplan-Meier analysis were performed for validating two radiomics signatures and C-index was used to evaluated the predictive performance of all radiomics signatures and combination models. Finally, a radiomics nomogram combining radiomics signatures with clinical risk factors was developed for predicting personalized OS, and then assessed with respect to the calibration curve. Three clinical risk factors were found, included age, malignancy and highest temperature that influence OS. Both two radiomics signatures could effectively stratify the risk of OS in COVID-19 severe patients. The predictive performance of the combination model with two radiomics signatures was better than that only one radiomics signature was used, and became better when three clinical risk factors were interpolated. Calibration curves showed good agreement in both 15 d survival and 30 d survival between the estimation with the constructed nomogram and actual observation. Both two constructed radiomics signatures can act as the potential biomarkers for risk stratification of OS in COVID-19 severe patients. The radiomics+clinical nomogram generated might serve as a potential tool to guide personalized treatment and care for these patients.

COVID-19 prediction using AI analytics for South Korea.

The severe spread of the COVID-19 pandemic has created a situation of public health emergency and global awareness. In our research, we analyzed the demographical factors affecting the global pandemic spread along with the features that lead to death due to the infection. Modeling results stipulate that the mortality rate increase as the age increase and it is found that most of the death cases belong to the age group 60-80. Cluster-based analysis of age groups is also conducted to analyze the maximum targeted age-groups. An association between positive COVID-19 cases and deceased cases are also presented, with the impact on male and female death cases due to corona. Additionally, we have also presented an artificial intelligence-based statistical approach to predict the survival chances of corona infected people in South Korea with the analysis of the impact on the exploratory factors, including age-groups, gender, temporal evolution, etc. To analyze the coronavirus cases, we applied machine learning with hyperparameters tuning and deep learning models with an autoencoder-based approach for estimating the influence of the disparate features on the spread of the disease and predict the survival possibilities of the quarantined patients in isolation. The model calibrated in the study is based on positive corona infection cases and presents the analysis over different aspects that proven to be impactful to analyze the temporal trends in the current situation along with the exploration of deceased cases due to coronavirus. Analysis delineates key points in the outbreak spreading, indicating that the models driven by machine intelligence and deep learning can be effective in providing a quantitative view of the epidemical outbreak.