Article
Computer Science, Artificial Intelligence
Elias P. Medeiros, Marcos R. Machado, Emannuel Diego G. de Freitas, Daniel S. da Silva, Renato William R. de Souza
Summary: This study applies machine learning algorithms with texture descriptors to X-rays of COVID-19 patients' lungs, aiming to accurately evaluate the patients' condition. Experiments show that combining texture descriptors with other features improves the predictive power and accuracy of the algorithms.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Information Systems
Doaa Sami Khafaga, Faten Khalid Karim, Mohamed M. Dessouky, Mohamed A. El-Rashidy
Summary: This paper presents an intelligent model based on machine learning approaches to analyze data collected from countries affected by the COVID-19 virus. The experimental results show that the proposed model is accurate in predicting the number of cases, and the wrapper technique is a superior feature extraction method.
Article
Engineering, Multidisciplinary
Emre Avuclu
Summary: The COVID-19 pandemic has had significant global impact and poses a major threat to public health. This study focuses on the development of a machine learning-based early diagnosis system to alleviate the burden on healthcare professionals. The experimental results demonstrate high accuracy rates in both training and testing using RGB values to classify images.
Article
Public, Environmental & Occupational Health
Suleman Khan, Saqib Hakak, N. Deepa, B. Prabadevi, Kapal Dev, Silvia Trelova
Summary: Since December 2019, there has been an abundance of posts and news about the COVID-19 pandemic on social media, traditional print, and electronic media, which may lead to anxiety and unnecessary exposure to medical remedies. In response to this issue, the author used a dataset fused from multiple sources and trained several machine learning algorithms for classifying COVID-19 related news after preprocessing, tokenization, and feature selection steps. The results showed that the random forest classifier performed the best with an accuracy of 88.50%.
FRONTIERS IN PUBLIC HEALTH
(2022)
Article
Neurosciences
Huaiqiang Sun, Guoting Luo, Su Lui, Xiaoqi Huang, John Sweeney, Qiyong Gong
Summary: This study proposes a specially designed autoencoder to investigate structural brain changes in schizophrenia. The classifier trained with autoencoded features outperforms the classifier trained with conventional morphological features in identifying schizophrenia patients from healthy controls.
HUMAN BRAIN MAPPING
(2023)
Article
Medicine, General & Internal
Ulzhalgas Zhunissova, Roza Dzierzak, Zbigniew Omiotek, Volodymyr Lytvynenko
Summary: The aim of this study was to develop a computerized method to distinguish COVID-19-affected cases from pneumonia cases. A comprehensive set of diagnostic information, including medical history, demographic data, signs and symptoms, and laboratory results, was used to build predictive models. The most effective model achieved high accuracy, sensitivity, and specificity. These findings provide an opportunity to develop a computer system to assist in the diagnosis of COVID-19.
JOURNAL OF CLINICAL MEDICINE
(2023)
Article
Engineering, Multidisciplinary
Ahmet Cagdas Seckin, Mine Seckin
Summary: A new feature extraction method for fabric defect detection is proposed, which is faster and more accurate compared to traditional texture feature extraction methods. This method can be used on low-level devices.
ALEXANDRIA ENGINEERING JOURNAL
(2022)
Article
Computer Science, Artificial Intelligence
Daniel Gibert, Jordi Planes, Carles Mateu, Quan Le
Summary: This paper presents a hybrid approach that combines deep learning and hand-crafted features for malware classification, achieving state-of-the-art performance in experiments.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Engineering, Biomedical
Santwana S. Gudadhe, Anuradha D. Thakare, Diego Oliva
Summary: Blood vessels in brain tissue can leak or burst, leading to potentially fatal intracranial hemorrhage. This study aims to classify intracranial hemorrhage computed tomography images using texture-based approaches and machine learning classifiers. The results show that the Weber local descriptor performs well for texture code classification.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Auwalu Saleh Mubarak, Sertan Serte, Fadi Al-Turjman, Zubaida Sa'id Ameen, Mehmet Ozsoz
Summary: The COVID-19 pandemic was confirmed by the World Health Organization in December 2019, emphasizing the importance of early identification of suspected patients to control the spread of the virus and improve medical treatment efficacy. Machine learning and deep learning have been efficient methods in detecting respiratory diseases, but require manual feature extraction and are affected by architecture and data limitations. Combining handcrafted LBP and deep learning features has shown to improve classifier performance in detecting COVID-19.
Article
Engineering, Biomedical
Daniel I. Moris, Joaquim de Moura, Pedro J. Marcos, Enrique Miguez Rey, Jorge Novo, Marcos Ortega
Summary: COVID-19 poses a global threat to healthcare systems due to its rapid spread. In this situation, clinicians face the challenge of making important decisions with potentially limited medical resources. Computer-aided diagnosis systems can provide support and analysis to help clinicians better understand the disease and identify high-risk patients.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Mariana Daniel, Rui Guerra, Antonio Brazio, Daniela Rodrigues, Ana Margarida Cavaco, Maria Dulce Antunes, Jose Valente de Oliveira
Summary: This study explores the use of feature engineering for preprocessing in fruit classification, as well as the division and selection of wavelength domain spectra. These methods can improve classification accuracy and reduce over-training. Experimental results show that the proposed method outperforms traditional approaches in accuracy and can identify features with physical chemistry significance.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Engineering, Biomedical
Ridhi Arora, Vipul Bansal, Himanshu Buckchash, Rahul Kumar, Vinodh J. Sahayasheela, Narayanan Narayanan, Ganesh N. Pandian, Balasubramanian Raman
Summary: The study proposes a stochastic deep learning model for rapid COVID-19 diagnosis and comprehensively evaluates X-ray based disease diagnosis methods. By learning the latent space of X-ray image distribution, the model improves its understanding of X-ray images, making it more generic for future use in other domains of medical image analysis.
PHYSICAL AND ENGINEERING SCIENCES IN MEDICINE
(2021)
Article
Computer Science, Artificial Intelligence
Elena Hernandez-Pereira, Oscar Fontenla-Romero, Veronica Bolon-Canedo, Brais Cancela-Barizo, Bertha Guijarro-Berdinas, Amparo Alonso-Betanzos
Summary: This study analyzed the capability of various machine learning methods to predict the need for hospital care in patients diagnosed with CoVid-19, using only demographic and clinical data. Results showed that models based on oversampling achieved the best accuracies, with age and gender being the most relevant variables for classification.
APPLIED INTELLIGENCE
(2022)
Article
Engineering, Electrical & Electronic
Durga Prasad Mannepalli, Varsha Namdeo
Summary: This work presents an innovative deep learning methodology for predicting COVID-19 patients using chest x-ray images. The approach combines an adaptive dual-stage horse herd bidirectional LSTM model with preprocessing, feature extraction, and feature dimensionality reduction techniques to enhance performance.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2022)
Review
Hematology
Wouter S. Hoogenboom, Tharun T. Alamuri, Daniel M. McMahon, Nino Balanchivadze, Vrushali Dabak, William B. Mitchell, Kerry B. Morrone, Deepa Manwani, Tim Q. Duong
Summary: Individuals with sickle cell disease (SCD) and sickle cell trait (SCT) are more susceptible to severe COVID-19 illness and death compared to the general population. Studies have shown that adults with SCD have a milder disease course but an increased risk of hospitalization and death compared to those without SCD. There is also evidence of increased risk of hospitalization and death for individuals with SCT. Children with SCD generally have a mild COVID-19 course, but those with SCD-related comorbidities may require more care. SCD-directed therapies may be associated with better COVID-19 outcomes, but further research is needed for confirmation.
Article
Medicine, General & Internal
Benjamin Musheyev, Montek S. Boparai, Reona Kimura, Rebeca Janowicz, Stacey Pamlanye, Wei Hou, Tim Q. Duong
Summary: The medical specialty usage of COVID-19 survivors after hospital discharge was investigated in this study. The findings showed that a high incidence of persistent symptoms and medical specialty care needs were present in hospitalized COVID-19 survivors 1-24 months post-discharge. Some specialty care needs were COVID-19 related while others were associated with pre-existing medical conditions.
INTERNAL AND EMERGENCY MEDICINE
(2023)
Article
Multidisciplinary Sciences
Aaquib Q. Syed, Richard Adam, Thomas Ren, Jinyu Lu, Takouhie Maldjian, Tim Duong
Summary: Using extreme gradient boosting (XGBoost) with MRI and non-imaging data, it is possible to predict pathological complete response (pCR) after neoadjuvant chemotherapy. By analyzing texture features of DWI and DCE images, along with patient demographics and tumor data, pCR can be accurately predicted. The combination of MRI and non-MRI data from multiple treatment timepoints as inputs achieves the highest prediction accuracy.
Article
Multidisciplinary Sciences
Hongyi Dammu, Thomas Ren, Tim Q. Duong
Summary: The goal of this study was to use a novel deep-learning convolutional-neural-network (CNN) to predict pathological complete response (PCR), residual cancer burden (RCB), and progression-free survival (PFS) in breast cancer patients treated with neoadjuvant chemotherapy using longitudinal multiparametric MRI, demographics, and molecular subtypes as inputs. The results showed that the Integrated approach of CNN outperformed the Stack or Concatenation CNN, and the combination of MRI and non-MRI data performed better than either alone. The best model achieved an accuracy of 0.81 for PCR prediction, 0.80 for RCB prediction, and a mean absolute error of 24.6 months for PFS prediction.
Article
Medicine, General & Internal
Anna Eligulashvili, Megan Darrell, Carolyn Miller, Jeylin Lee, Seth Congdon, Jimmy S. Lee, Kevin Hsu, Judy Yee, Wei Hou, Marjan Islam, Tim Q. Duong
Summary: This study reports the symptoms and assessments of COVID-19 survivors up to five months post-acute infection. The results showed that many survivors experienced issues in pulmonary function, physical, emotional, and cognitive health. Furthermore, lung imaging abnormalities were more common than brain imaging abnormalities.
Review
Endocrinology & Metabolism
Tharun T. Alamuri, Sandhya Mahesh, Kevin Dell'Aquila, Taylor Jan Leong, Rebecca Jennings, Tim Q. Duong
Summary: SARS-CoV-2 infection may lead to endocrine dysfunction and dysregulation of blood sugar levels, causing diabetes mellitus. The relationship between COVID-19 and endocrine dysfunctions is still not completely understood. This review analyzed 27 publications on COVID-19 associated ketosis or diabetic ketoacidosis, suggesting that DKA in the setting of COVID-19 could increase the risk of death, especially in patients with new-onset diabetes. Larger studies with more specific variables are needed for better conclusions.
DIABETES OBESITY & METABOLISM
(2023)
Correction
Multidisciplinary Sciences
Shahzad Ahmad Qureshi, Lal Hussain, Usama Ibrar, Eatedal Alabdulkreem, Mohamed K. Nour, Mohammed S. Alqahtani, Faisal Mohammed Nafie, Abdullah Mohamed, Gouse Pasha Mohammed, Tim Q. Duong
SCIENTIFIC REPORTS
(2023)
Article
Multidisciplinary Sciences
Shahzad Ahmad Qureshi, Lal Hussain, Usama Ibrar, Eatedal Alabdulkreem, Mohamed K. Nour, Mohammed S. Alqahtani, Faisal Mohammed Nafie, Abdullah Mohamed, Gouse Pasha Mohammed, Tim Q. Duong
Summary: Accurate radiogenomic classification of brain tumors is essential for improving diagnosis, prognosis, and treatment planning for glioblastoma patients. This study proposes a novel MGMT-PMP system that combines latent and radiomic features to predict the genetic subtype of glioblastoma, achieving high classification performance.
SCIENTIFIC REPORTS
(2023)
Article
Medicine, General & Internal
Justin Y. Lu, Jack Wilson, Wei Hou, Roman Fleysher, Betsy C. Herold, Kevan C. Herold, Tim Q. Duong
Summary: This study compared the incidences and risk factors of new-onset persistent type-2 diabetes in COVID-19 patients to those in influenza patients. It was found that the incidence of type-2 diabetes was higher in COVID-19 patients compared to influenza patients. The risk of developing persistent type-2 diabetes was also higher in hospitalized COVID-19 patients compared to non-hospitalized COVID-19 patients and hospitalized influenza patients.
Article
Endocrinology & Metabolism
Alexander Y. Y. Xu, Stephen H. H. Wang, Tim Q. Q. Duong
Summary: This study aimed to investigate the incidence of new-onset diabetes in patients with prediabetes after COVID-19 and compared it with those not infected. The study found that hospitalized patients with prediabetes and COVID-19 had a higher incidence of in-hospital and post-infection diabetes compared to those without COVID-19. Critical illness, in-hospital steroid treatment, SARS-CoV-2 infection, and HbA1c were significant predictors of in-hospital diabetes.
BMJ OPEN DIABETES RESEARCH & CARE
(2023)
Article
Medicine, General & Internal
Beiyi Shen, Wei Hou, Zhao Jiang, Haifang Li, Adam J. J. Singer, Mahsa Hoshmand-Kochi, Almas Abbasi, Samantha Glass, Henry C. C. Thode, Jeffrey Levsky, Michael Lipton, Tim Q. Q. Duong
Summary: This study analyzed the temporal characteristics of lung chest X-ray (CXR) scores in COVID-19 patients during hospitalization and their correlation with other clinical variables and outcomes. The results showed that CXR scores have the potential to provide prognosis, guide treatment, and monitor disease progression in COVID-19 patients.
Article
Hematology
Avery Feit, Moshe Gordon, Tharun T. Alamuri, Wei Hou, William B. Mitchell, Deepa Manwani, Tim Q. Duong
Summary: This study examined whether patients with sickle cell disease (SCD) had increased risk of worse long-term outcomes and healthcare utilization 2.5 years after SARS-CoV-2 infection. The results showed that SCD patients with SARS-CoV-2 infection did not have additional risk of worse long-term outcomes compared to matched controls of SCD patients not infected by SARS-CoV-2.
EUROPEAN JOURNAL OF HAEMATOLOGY
(2023)
Article
Peripheral Vascular Disease
Vincent Zhang, Molly Fisher, Wei Hou, Lili Zhang, Tim Q. Duong
Summary: The incidence of new-onset persistent hypertension in patients with COVID-19 is higher than those with influenza, indicating a significant health burden associated with COVID-19.
Article
Rheumatology
Jai Mehrotra-Varma, Anand Kumthekar, Sonya Henry, Roman Fleysher, Wei Hou, Tim Q. Duong
Summary: This retrospective study examined the clinical outcomes of 361 patients with rheumatoid arthritis (RA) who were infected with COVID-19. The results showed that patients with RA and COVID-19 had higher rates of hospitalization, critical illness, and mortality compared to patients with RA without COVID-19. However, these adverse outcomes were not directly attributed to RA itself, but rather to age and preexisting medical conditions.
ACR OPEN RHEUMATOLOGY
(2023)
Article
Health Care Sciences & Services
Jing Yang, Por Lip Yee, Abdullah Ayub Khan, Hanen Karamti, Elsayed Tag Eldin, Amjad Aldweesh, Atef El Jery, Lal Hussain, Abdulfattah Omar
Summary: Lung cancer is the second leading cause of cancer-related deaths globally. Developing automated tools for prediction improvement remains a challenge. This study focuses on analyzing the posterior probabilities of gray-level co-occurrence matrix (GLCM) features to uncover network associations. Features were ranked based on t-test, with Cluster Prominence selected as the target node. Association and arc analysis were determined using mutual information. The selected cluster states' occurrence and reliability were computed, with a state <= 330.85 yielding perfect ROC and relative Gini indices. This proposed method provides a detailed analysis of computed GLCM features, shedding light on the hidden dynamics of lung cancer for accurate diagnosis and prognosis.