Sadiq Hussain

Dibrugarh University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Roohallah Alizadehsani

Deakin University

Saeid Nahavandi

Swinburne University of Technology

Afshin Shoeibi

Universidad de Granada

Abbas Khosravi

Deakin University

U. Rajendra Acharya

University of Southern Queensland

Zahra Alizadeh Sani

Shaheed Rajaei Cardiovascular Medical and Research Center

Javad Hassannataj Joloudari

University of Birjand

Fahime Khozeimeh

Deakin University

Mohamad Roshanzamir

Fasa University of Medical Sciences

Jane B. Lian

Massachusetts Institute of Technology

Cooperative Institutions

University of Massachusetts Chan Medical School

Dibrugarh University

Deakin University

Ferdowsi University of Mashhad

Islamic Azad University, Tehran

University of Vermont

Iran University of Medical Sciences

Mayo Clinic

UNSW Sydney

Universidad de Granada

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Combining a convolutional neural network with autoencoders to predict the survival chance of COVID-19 patients

Scientific Reports (2021)

Fahime Khozeimeh Danial Sharifrazi Navid Hoseini Izadi Javad Hassannataj Joloudari Afshin Shoeibi

Abstract COVID-19 has caused many deaths worldwide. The automation of the diagnosis of this virus is highly desired. Convolutional neural networks (CNNs) have shown outstanding classification performance on image datasets. To date, it appears that COVID computer-aided diagnosis systems based on CNNs and clinical information have not yet been analysed or explored. We propose a novel method, named the CNN-AE, to predict the survival chance of COVID-19 patients using a CNN trained with clinical information. Notably, the required resources to prepare CT images are expensive and limited compared to those required to collect clinical data, such as blood pressure, liver disease, etc. We evaluated our method using a publicly available clinical dataset that we collected. The dataset properties were carefully analysed to extract important features and compute the correlations of features. A data augmentation procedure based on autoencoders (AEs) was proposed to balance the dataset. The experimental results revealed that the average accuracy of the CNN-AE (96.05%) was higher than that of the CNN (92.49%). To demonstrate the generality of our augmentation method, we trained some existing mortality risk prediction methods on our dataset (with and without data augmentation) and compared their performances. We also evaluated our method using another dataset for further generality verification. To show that clinical data can be used for COVID-19 survival chance prediction, the CNN-AE was compared with multiple pre-trained deep models that were tuned based on CT images.

Generality

10.1038/s41598-021-93543-8

Cite

Citations (102)

CNN-KCL: Automatic Myocarditis Diagnosis using Convolutional Neural Network Combined with K-means Clustering

Danial Sharifrazi Roohallah Alizadehsani Javad Hassannataj Joloudari Shahab S. Band Sadiq Hussain

Myocarditis is the form of an inflammation of the middle layer of the heart wall which is caused by a viral infection and can affect the heart muscle and its electrical system. It has remained as one of the most challenging diagnoses in cardiology. Myocardial is the prime cause of unexpected death in approximately 20% of adults less than 40 years of age. Cardiac MRI (CMR) has been considered as a noninvasive and golden standard diagnostic tool for suspected myocarditis and plays an indispensable role in diagnosing various cardiac diseases. However, the performance of CMR is heavily dependent on the clinical presentation and non-specific features such as chest pain, arrhythmia, and heart failure. Besides, other imaging factors like artifacts, technical errors, pulse sequence, acquisition parameters, contrast agent dose, and more importantly qualitatively visual interpretation can affect the result of the diagnosis. This paper introduces a new deep learning-based model called Convolutional Neural Network-Clustering (CNN-KCL) to diagnose the Myocarditis. The hybrid CNN-KCL method performs the early and accurate diagnosis of Myocarditis. To the best-of-our-knowledge, a Convolutional neural network has never been used before for the diagnosis of Myocarditis. In this study, we used 47 subjects to diagnose myocarditis patients from Tehran's Omid Hospital. The total number of data examined is 10425. Our results demonstrate that CNN-KCL achieves 92.3% in terms of diagnosis myocarditis prediction accuracy which is significantly better than those reported in previous studies.

Viral Myocarditis

Acute myocarditis

10.20944/preprints202007.0650.v1

Cite

Citations (42)

Deep Learning for Personalized Health Monitoring and Prediction: A Review

Authorea (Authorea) (2023)

Kandala N. V. P. S. Rajesh Robertas Damaševicˇius Senthil Kumar Jagatheesaperumal Sadiq Hussain Roohallah Alizadehsani

Personalized health monitoring and prediction have become essential for improving health- care delivery, especially with the growing prevalence of chronic diseases and an aging population. Deep learning (DL) has emerged as a promising approach for developing personalized health mon- itoring systems that can predict health outcomes accurately and efficiently. With the increasing availability of personal health data, DL-based methods have emerged as a promising approach to improve healthcare delivery by providing accurate and timely predictions of health outcomes. This article provides a comprehensive review of the recent developments in the application of DL for personalized health monitoring and prediction. It summarizes various DL architectures and their applications for personalized health monitoring, including wearable devices, electronic health records, and social media data. Furthermore, the article also explores the challenges and future directions for the application of DL in personalized health monitoring. valuable insights into the potential of DL for personalized health monitoring and prediction.

Personalized Medicine

Wearable Technology

Population Health

10.22541/au.168723724.45330026/v1

Cite

Citations (2)

Identification of clinical features associated with mortality in COVID-19 patients

medRxiv (Cold Spring Harbor Laboratory) (2021)

Rahimeh Eskandarian Zahra Alizadeh Sani Mohaddeseh Behjati Mehrdad Zahmatkesh Azadeh Haddadi

Summary Background To prevent infectious diseases, it is necessary to understand how they are spread and their clinical features. Early identification of risk factors and clinical features is needed to identify critically ill patients, provide suitable treatments, and prevent mortality. Methods We conducted a prospective study on COVID-19 patients referred to a tertiary hospital in Iran between March and November 2020. Of the 3008 patients (mean age 59.3±18.7 years, range 1 to 100 years), 1324 were women. We investigated COVID-19 related mortality and its association with clinical features including headache, chest pain, symptoms on CT, hospitalization, time to infection, history of neurological disorders, having a single or multiple risk factors, fever, myalgia, dizziness, seizure, abdominal pain, nausea, vomiting, diarrhoea and anorexia. Findings There was a significant association between COVID-19 mortality and old age, headache, chest pain, respiratory distress, low respiratory rate, oxygen saturation less than 93%, need for a mechanical ventilator, having symptoms on CT, hospitalization, time to infection, history of hypertension, neurological disorders, cardiovascular diseases and having a risk factor or multiple risk factors. In contrast, there was no significant association between mortality and gender, fever, myalgia, dizziness, seizure, abdominal pain, nausea, vomiting, diarrhoea and anorexia. Interpretation Our results might help identify early symptoms related to COVID-19 and better manage patients clinically.

myalgia

Anorexia

Chills

10.1101/2021.04.19.21255715

Cite

Citations (14)

Classification of Road Traffic Accident Data Using Machine Learning Algorithms

Bulbula Kumeda Fengli Zhang Fan Zhou Sadiq Hussain Ammar Almasri

The dramatic increase in road traffic accidents in the world is causing serious problems in every aspect of human lives. The most important and meaningful nature of traffic characteristics, causation analysis, and associations between different causal factors have been ignored. Moreover, the traffic accident data is only used to conduct a rudimentary statistical analysis and data mining efforts which results only in patterns and statistics. The main targets of this road accident data classification are to identify the major and key factors that cause the road traffic accident and form policies and preventive actions that would reduce the accident severity level. Machine learning algorithms are used to analyze the data, extract hidden patterns, predict the severity level of the accidents and summarize the information in a useful format. In this work, we have applied different machine learning classification algorithms and discussed here the six algorithms with high accuracy and best classification performances such as Fuzzy-FARCHD, Random Forest, Hierarchal LVQ, RBF Network (Radial Basis Function Network), Multilayer Perceptron, and Naïve Bayes on road traffic accident data set obtained from UK road traffic accident of the year 2016. The data set contains information on all road accident casualties across Calderdale. The results from our analysis show that Fuzzy-FARCHD algorithm is effective to classify the dataset and achieves an accuracy of 85.94%. In this work, we have revealed that Lighting Conditions, 1st Road Class & No., Number of vehicles are the key features in selecting the attributes.

Road accident

Statistical classification

Traffic accident

Data set

Accident (philosophy)

10.1109/iccsn.2019.8905362

Cite

Citations (41)

Optical-Flow Based Symmetric Feature Extraction for Facial Expression Recognition

SSRN Electronic Journal (2023)

Mohammad Ali Zeraatkar Javad Hassannataj Joloudari Kandala N. V. P. S. Rajesh Silvia Gaftandzhıeva Sadiq Hussain

Facial expression analysis is one of the most important tools for behavior interpretation and emotion modeling in Intelligent Human-Computer Interaction (HCI). Although humans can easily interpret facial emotions, computers have great difficulty doing so. Analyzing changes and deformations in the face is one of the methods through which machines can interpret facial expressions. However, maintaining great precision while being accurate, stable, and quick is still a challenge in this field. To address this issue this research presents an innovative and novel method to extract key features from a face during a facial expression fully automatically. These features can be used by various machine learning models to analyze emotions. We used the optical flow algorithm to extract motion vectors, which were then divided into sections on the subjectâ€™s face. Finally, each section and its symmetric section were used to calculate a new vector. The final features produce a state-of-the-art accuracy of over 98% in emotion classification in the Extended Cohen-Kanade (CK+) facial expression dataset. Furthermore, we proposed an algorithm to filter the most important features, and with an SVM classifier, we were able to keep the accuracy over 98 % by only looking at 10% of the face area.

Optical Flow

Expression (computer science)

Three-dimensional face recognition

10.2139/ssrn.4477013

Cite

Citations (0)

Single-Point Crossover and Jellyfish Optimization for Handling Imbalanced Data Classification Problem

IEEE Access (2022)

Abeer S. Desuky Yomna M. Elbarawy Samina Kausar Asmaa Hekal Omar Sadiq Hussain

The imbalanced datasets and their classification has pulled in as a hot research topic over the years. It is used in different fields, for example, security, finance, health, and many others. The imbalanced datasets are balanced by applying resampling and various solutions are designed to tackle such datasets that mainly focus on class distribution issues. The imbalanced data is rebalanced using these methods. This paper introduces a technique for balancing data through two stages: first, oversampling methods are utilized in the process of rebalancing such imbalanced dataset using the single-point crossover to generate the new data of minority classes, second, it searches for an optimal subset of the imbalanced and balanced datasets by Jellyfish Search (JS) which is an optimization method. Experiments are performed on 18 real imbalanced datasets, and results are compared with famous oversampling methods and the recently published ACOR (Ant Colony Optimization Resampling) method in terms of different appraisal measurements. Higher performance is recorded by the proposed method and comparability with well-known and recent techniques.

Oversampling

Resampling

Comparability

10.1109/access.2022.3146424

Cite

Citations (13)

Functional coupling of transcription factor HiNF-P and histone H4 gene expression during pre- and post-natal mouse development

Gene (2011)

Lijun Liu Ronglin Xie Sadiq Hussain Jane B. Lian Jaime A. Rivera‐Pérez

10.1016/j.gene.2011.05.002

Cite

Citations (9)

Secreted frizzled related protein 1 is a target to improve fracture healing

Journal of Cellular Physiology (2009)

Tripti Gaur John J. Wixted Sadiq Hussain Shannon L. O’Connell Elise F. Morgan

Abstract Genetic studies have identified a high bone mass of phenotype in both human and mouse when canonical Wnt signaling is increased. Secreted frizzled related protein 1 (sFRP1) is one of several Wnt antagonists and among the loss‐of‐function mouse models in which 32‐week‐old mice exhibit a high bone mass phenotype. Here we show that impact fracture healing is enhanced in this mouse model of increased Wnt signaling at a physiologic level in young (8 weeks) sFRP1 −/− mice which do not yet exhibit significant increases in BMD. In vivo deletion of sFRP1 function improves fracture repair by promoting early bone union without adverse effects on the quality of bone tissue reflected by increased mechanical strength. We observe a dramatic reduction of the cartilage callous, increased intramembranous bone formation with bone bridging by 14 days, and early bone remodeling during the 28‐day fracture repair process in the sFRP1 −/− mice. Our molecular analyses of gene markers indicate that the effect of sFRP1 loss‐of‐function during fracture repair is to accelerate bone healing after formation of the initial hematoma by directing mesenchymal stem cells into the osteoblast lineage via the canonical pathway. Further evidence to support this conclusion is the observation of maximal sFRP1 levels in the cartilaginous callus of a WT mouse. Hence sFRP1 −/− mouse progenitor cells are shifted directly into the osteoblast lineage. Thus, developing an antagonist to specifically inhibit sFRP1 represents a safe target for stimulating fracture repair and bone formation in metabolic bone disorders, osteoporosis and aging. J. Cell. Physiol. 220: 174–181, 2009. © 2009 Wiley‐Liss, Inc.

LRP5

Bone remodeling

Bone fracture

10.1002/jcp.21747

Cite

Citations (67)

IAPSO-AIRS: A novel improved machine learning-based system for wart disease treatment

Journal of Medical Systems (2019)

Moloud Abdar Vivi Nur Wijayaningrum Sadiq Hussain Roohallah Alizadehsani Paweł Pławiak

Cryotherapy

10.1007/s10916-019-1343-0

Cite

Citations (64)