Explainable Augmented Intelligence and Deep Transfer Learning for Pediatric Pulmonary Health Evaluation

Biomedical Instrumentation is one of the fastest health emerging innovative technologies with proven contribution towards interdisciplinary medicine, it helps physicians to diagnose complex medical problems and provide treatment to patients precisely and safely. With this technological trend, explainable artificial intelligence, biomedical image processing and augmented intelligence can provide a tool that can help pediatricians, pulmonology and otolaryngology physicians, epidemiologists and pediatric practitioners to interpretably and reliably diagnose chronic and acute respiratory disorders in children, adolescents and infants. Unfortunately, the reliability of digital image processing for pulmonary disease diagnosis often depends on availability of large chest X-ray image datasets. This work presents a reliable interpretable deep transfer learning approach for pediatric pulmonary health evaluation regardless of the scarcity and limited annotated pediatric chest X-ray Image dataset sizes. This approach leverages a combination of computer vision tools and techniques to reduce child morbidity and mortality through predictive and preventive medicine with reduced surveillance risks and affordability in low resource settings. With open datasets, the deep neural networks classified the generated augmented images into 4 classes namely;Normal, Covid-19, Tuberculosis and Pneumonia at an accuracy of 97%, 97%, 70%, and 73% respectively with recall of 100% for Pneumonia and overall accuracy of 79% at only 10 epochs for both regular and transferred learning. © 2022 IEEE.

Cardiotocogram Biomedical Signal Classification and Interpretation for Fetal Health Evaluation

Maternal and Neonatal health has been greatly constrained by the in-access to essential maternal health care services due to the preventive measures implemented against the spread of covid-19 hence making maternal and fetal monitoring so hard for physicians. Besides maternal toxic stress caused by fear of catching covid-19, affordable mobility of pregnant mothers to skilled health practitioners in limited resource settings is another contributor to maternal and neonatal mortality and morbidity. In this work, we leveraged existing health data to build interpretable Machine Learning (ML) models that allow physicians to offer precision maternal and fetal medicine based on biomedical signal classification results of fetal cardiotocograms (CTGs).We obtained 99%, 100% and 97% accuracy, precision and recall respectively for the LightGBM classification model without any GPU Learning resources. Then we explainably evaluated all built models with ELI5 and comprehensive feature extraction.

COVID-19 Fake News Prediction On Social Media Data

It is, to tell the truth, that the COVID-19 pandemic has put the whole world in a tough time, and sensitive information concerning COVID-19 has grown tremendously online. Most importantly, the gradual spread of fake news and misleading information during these hard times can have dire consequences, causing widespread panic and exacerbating the apparent threat of a pandemic that we cannot ignore. Because of the time-consuming nature of evidence gathering and careful truth-checking, people get confused between fallacious and trustworthy statement. So, we need a way to keep track of misinformation on social media. Most people think that all social media information is real information though, at the same time, it is a shame that some people misuse this social media platform for their own benefit by spreading misinformation. Many individuals take advantage by playing with the weaknesses of others. As a result, people around the world not only are facing COVID-19, they are also facing infodemics. To get rid of this kind of fake news, we have proposed a research model that can predict fake news related to the COVID-19 issue on social media data using classical classification methods such as multinomial naive bayes classifier, logistic regression classifier, and support vector machine classifier. Moreover, we have applied a deep learning based algorithm named distil BERT to accurately predict fake COVID-19 news. These approaches have been used in this paper to compare which technique is much more convenient for accurately predicting fake news about COVID-19 on social media posts. In addition, we have used a data-set that included 6424 social media posts.

COVID-19 impact on students' Mental Health: Explainable AI and Classifiers

COVID-19, lockdown, and isolation have included an enormous impact on the students around the world like others. As isolation strategy with quarantine is useful to prevent transmission, students remaining at home gained nothing but illness perception, anxiety, and depression in spite of sharpening their knowledge and reflecting the thoughts. The detachment from routine life has affected the pillars of the mental health balance and isolated and suffocating lives have created toxic feelings in lives. Therefore the purpose of our paper is to predict the mental health of students in such situations. To accomplish our work, we have collected the students' mental health survey dataset from the Kaggle website later trained the data with suitable classifiers to predict mental health. In this paper, we demonstrated five different classifiers models to predict optimal accuracy, including two different Explainable AI (XAI) techniques (LIME, SHAP) as it enhances the trust in an AI system.

Demystifying Black-box Learning Models of Rumor Detection from Social Media Posts

Social media and its users are vulnerable to the spread of rumors, therefore, protecting users from the spread of rumors is extremely important. For this reason, we propose a novel approach for rumor detection in social media that consists of multiple robust models: XGBoost Classifier, Support Vector Machine, Random Forest Classifier, Extra Tree Classifier, Decision Tree Classifier, a hybrid model, deep learning models-LSTM and BERT. For evaluation, two datasets are used. These artificial intelligence algorithms are often referred to as "Black-box" where data go in the box and predictions come out of the box but what is happening inside the box frequently remains cloudy. Although, there have been several works on detecting fake news, the number of works regarding rumor detection is still limited and the models used in the existing works do not explain their decision-making process. We take models with higher accuracy to illustrate which feature of the data contributes the most for a post to have been predicted as a rumor or a non-rumor by the models to explain the opaque process happening inside the black-box models. Our hybrid model achieves an accuracy of 93.22% and 82.49%, while LSTM provides 99.81%, 98.41% and BERT provides 99.62%, 94.80% accuracy scores on the COVID-19 Fake News and the concatenation of Twitter15 and Twitter16 datasets respectively.

Ambient Assisted Living for Elderly Care and Monitoring in CQVID-19 Pandemic

In late 2019, a novel Coronavirus broke out from China, which has dispersed all over the globe and has taken away countless lives. Despite the fact that every person is at risk of getting infected with the virus, older people are more likely to fall victim to the virus due to their declining immune systems. Although there has been significant development of vaccines, it is seen that the mutation of the COVID-19 has made it tough to control with the medication available. Due to an uncountable number of Coronavirus strains, many countries are now facing several waves of the pandemic. Assisted living technologies are evolving with time to give people a better life. This technology can be used for older people in Coronavirus pandemic situations as most of the older people have physical and cognitive impairments. In this paper, we have proposed an Internet of Things(loT)-architectured system incorporated with Artificial intelligence and deep learning that can help diagnose COVID-19 in older people. The proposed architecture will collect all the data from different medical loT sensors and relay them to the cloud, where the system will process and help us monitor the health of older people. This information could be seen from a dedicated dashboard where the user would be able to get diagnosis status of COVID-19 by our system. In order to be prepared for any future pandemic, this type of system will be beneficial. © 2021 IEEE

COVID-19 Confirmed Cases and Deaths Prediction in Bangladesh Using Hidden Markov Model

The number of people affected by Coronavirus is quite concerning in Bangladesh. It has become a necessity to forecast the future cases since it involves ensuring adequate resources to help people and imposing strict guidelines to deal with this epidemic. This research is about predicting upcoming COVID-19 confirmed cases and deaths from a time series dataset using Hidden Markov Model. The optimal number of hidden states were determined using AIC and BIC. The proposed models are implemented to forecast the daily confirmed cases and daily deaths of Bangladesh for next 90 days. © 2021 IEEE.

Demystify the Black-box of Deep Learning Models for COVID-19 Detection from Chest CT Radiographs

Covid 19 continues to have a catastrpoic effect on the world, causing terrible spots to appear all over the place. Due to global epidemics and doctor and healthcare personel shortages, developing an AI-based system to detect COVID in a timely and cost-effective method has become a requirement. It is also essential to detect covid from chest X-ray and CT radiographs due to their accuracy in detecting lung infection and as well as to understand the severity. Moreover, though the number of infected people around the globe is enormous, the amount of covid data set to build an AI system is scarce and scattered. In this letter, we presented a Chest CT scan data (HRCT) set for Covid and healthy patients considering a varying range of severity of COVID, which we published on kaggle, that can assist other researchers to contribute to healthcare AI. We also developed three deep learning approaches for detecting covid quickly and cheaply. Our three transfer learning-based approaches, Inception v3, Resnet 50, and VGG16, achieve accuracy of 99.8%, 91.3%, and 99.3%, respectively on unseen data. We delve deeper into the black boxes of those models to demonstrate how our model comes to a certain conclusion, and we found that, despite the low accuracy of the model based on VGG16, it detects the covid spot of images well, which we believe may further assist doctors in visualizing which regions are affected. © 2021 IEEE.

A Federated Learning Approach to Pneumonia Detection

Pneumonia Detection has been a real problem for the last few centuries. Detecting Pneumonia has been a job for the skilled, such as doctors and medical practitioners. Visiting doctors in this time in many countries is very tough with Covid-19 on the rise and stricter lockdown regulations. Deep Learning has helped build many systems and algorithms over the years to detect pneumonia using X-ray images. Such Deep Learning models are first trained on many X-ray images that would be collected from multiple hospitals and diagnostic centers and then can be deployed centrally for people to use them. However, building such models is impeded by the problem of garnering mass data from hospitals due to data confidentiality between patients and hospitals. For that, we propose a system where detecting Pneumonia would be done using a Deep Learning model with a Federated Learning approach and achieve an accuracy of around 90%. This will build a central model by training local models in different hospitals with their own data, maintaining all patient data privacy. © 2021 IEEE.

Covid-19 Confirmed-Cases Prediction in SAARC Countries through Machine Learning

In December 2019, a new variant of the SARS virus named Severe Acute Respiratory Syndrome Coronavirus 2(SARS-CoV-2), began its outspread in Wuhan, China, and has since expanded throughout the whole planet. In this novel research, we predicted the number of confirmed cases of SARS-CoV-2 in the South Asian Association for Regional Cooperation (SAARC) Countries through the use of the numerous machine learning (ML) techniques and time series model. Furthermore, we made a comparative study on which technique performed better. The hugely popular Support Vector Machine(SVM) and Bayesian Ridge regression was taken into consideration for the predictions made. The time series analysis model, i.e. Seasonal Autoregressive Integrated Moving Average(SARIMA) model was further used to get even better predictions on the forecasts for the confirmed cases of SARS-CoV-2. Along with this, comparisons were conducted on the confirmed cases, followed by the deaths resulted from these cases, as well as on the number of recoveries made, the number of active cases, and mortality rate across these countries, from which nations were limited down to a handful that should take extreme steps to stop the virus from spreading. © 2021 IEEE.