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.

COVID-19 Diagnosis from Routine Blood Tests using Artificial Intelligence Techniques.

Coronavirus disease (COVID-19) is a unique worldwide pandemic. With new mutations of the virus with higher transmission rates, it is imperative to diagnose positive cases as quickly and accurately as possible. Therefore, a fast, accurate, and automatic system for COVID-19 diagnosis can be very useful for clinicians. In this study, seven machine learning and four deep learning models were presented to diagnose positive cases of COVID-19 from three routine laboratory blood tests datasets. Three correlation coefficient methods, i.e., Pearson, Spearman, and Kendall, were used to demonstrate the relevance among samples. A four-fold cross-validation method was used to train, validate, and test the proposed models. In all three datasets, the proposed deep neural network (DNN) model achieved the highest values of accuracy, precision, recall or sensitivity, specificity, F1-Score, AUC, and MCC. On average, accuracy 92.11%, specificity 84.56%, and AUC 92.20% values have been obtained in the first dataset. In the second dataset, on average, accuracy 93.16%, specificity 93.02%, and AUC 93.20% values have been obtained. Finally, in the third dataset, on average, the values of accuracy 92.5%, specificity 85%, and AUC 92.20% have been obtained. In this study, we used a statistical t-test to validate the results. Finally, using artificial intelligence interpretation methods, important and impactful features in the developed model were presented. The proposed DNN model can be used as a supplementary tool for diagnosing COVID-19, which can quickly provide clinicians with highly accurate diagnoses of positive cases in a timely manner.

Predictors of coronavirus disease 19 (COVID-19) pneumonitis outcome based on computed tomography (CT) imaging obtained prior to hospitalization: a retrospective study.

PURPOSE: Computed tomography (CT) has been utilized as a diagnostic modality in the coronavirus disease 19 (COVID-19), while some studies have also suggested a prognostic role for it. This study aimed to assess the diagnostic and prognostic value of computed tomography (CT) imaging in COVID-19 patients. METHODS: This was a retrospective study of fifty patients with COVID-19 pneumonia. Twenty-seven patients survived, while 23 passed away. CT imaging was performed in all of the patients on the day of admission. Imaging findings were interpreted based on current guidelines by two expert radiologists. Imaging findings were compared between surviving and deceased patients. Lung scores were assigned to patients based on CT chest findings. Then, the receiver operating characteristic curve was used to determine cutoff values for lung scores. RESULTS: The common radiologic findings were ground-glass opacities (82%) and airspace consolidation (42%), respectively. Air bronchogram was more commonly seen in deceased patients (p = 0.04). Bilateral and multilobar involvement was more frequently found in deceased patients (p = 0.049 and 0.014, respectively). The mean number of involved lobes was 3.46 ± 1.80 lobes in surviving patients and 4.57 ± 0.60 lobes in the deceased patients (p = 0.009). The difference was statistically significant. The area under the curve for a lung score cutoff of 12 was 0.790. CONCLUSION: Air bronchogram and bilateral and multilobar involvement were more frequently seen in deceased patients and may suggest a poor outcome for COVID-19 pneumonia.

Clinical and radiological characteristics of pediatric patients with COVID-19: focus on imaging findings.

PURPOSE: CT imaging has been a detrimental tool in the diagnosis of COVID-19, but it has not been studied thoroughly in pediatric patients and its role in diagnosing COVID-19. METHODS: 27 pediatric patients with COVID-19 pneumonia were included. CT examination and molecular assay tests were performed from all participants. A standard checklist was utilized to extract information, and two radiologists separately reviewed the CT images. RESULTS: The mean age of patients was 4.7 ± 4.16 (mean ± SD) years. Seventeen patients were female, and ten were male. The most common imaging finding was ground-glass opacities followed by consolidations. Seven patients had a single area of involvement, five patients had multiple areas of involvement, and four patients had diffuse involvement. The sensitivity of CT imaging in diagnosing infections was 66.67%. Also, some uncommon imaging findings were seen, such as a tree-in-bud and lung collapse. CONCLUSION: CT imaging shows less involvement in pediatric compared to adult patients, due to pediatric patients having a milder form of the disease. CT imaging also has a lower sensitivity in detecting abnormal lungs compared to adult patients. The most common imaging findings are ground-glass opacities and consolidations, but other non-common imaging findings also exist.