Ensembling of Efficient Deep Convolutional Networks and Machine Learning Algorithms for Resource Effective Detection of Tuberculosis using Thoracic (Chest) Radiography (June 2022)

Tuberculosis (TB) is a communicable pulmonary disorder and countries with low and middle-income share a higher TB burden as compared to others. The year 2020-2021 universally saw a brutal pandemic in the form of COVID-19, that crushed various lives, health infrastructures, programs, and economies worldwide at an unprecedented speed. The gravity of this estimation gets intensified in systems with limited technological advancements. To assist in the identification of tuberculosis, we propose the ensembling of efficient deep convolutional networks and machine learning algorithms that do not entail heavy computational resources. In this paper, the three of the most efficient deep convolutional networks and machine learning algorithms are employed for resource-effective (low computational and basic Imaging requirements) detection of Tuberculosis. The pivotal features extracted from the deep networks are ensembled and subsequently, the machine learning algorithms are used to identify the images based on the extracted features. The said model underwent k-fold cross-validation and achieved an accuracy of 87.90% and 99.10% with an AUC of 0.94 and 1 respectively in identifying TB infected images from Normal and COVID infected images. Also, the model’s error rate, F-score, and youden’s index values of 0.0093, 0.9901, and 0.9812 for TB versus COVID identification along with the model’s accuracy claim that its use can be beneficial in identifying TB infections amid this COVID-19 pandemic, predominantly in countries with limited resources. Author

IoT-Based Smart Diagnosis System for HealthCare

COVID-19 is a pandemic situation where isolation and social distancing are enforced to surge the pandemic. Pandemic Patient Health Management Platform is presently needed to retrieve health data without visiting healthcare centres. The Pandemic Patient Health Management Platform (PPHMP) uses Internet of things (IoT) and cloud computing technology and it is a remote patient health management platform. APPHMP model is proposed, which can help patients and elderly people to receive information about their health from their premises especially in consideration of COVID-19. In the present work, an algorithm is proposed to determine the patient’s current health status and send necessary information to the healthcare centre for subsequent decisions. The proposed work is implemented by utilizing a naïve Bayes machine learning algorithm for decision making, and the obtained accuracy is about 83%. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

IoT Based Intelligent Computer-Aided Diagnosis and Decision Making System for Health Care

Pandemic Patient Health Monitoring Platform (PPHMP) with the help of the internet of things (IoT) and cloud computing is proposed in this paper. As a result of a pandemic such as a coronavirus outbreak, healthcare task needs a system includes a continuous diagnosis for monitoring patients and supports decision making. The system should be also helpful for healthcare providers. Moreover, it should be accurate and robust based on machine learning. The proposed PPHMP would be helpful in terms of its efficiency for remote patients who are not supposed to visit the hospital where the health monitoring task could be continuous. In our work, we proposed an algorithm to predict the current health status of patients accompanied by continuous monitoring connected with their healthcare providers. Patient's health is considered with other parameters and algorithms such as K- nearest neighbor, logistic regression, support vector machine, random forest and Adaboost Classifiers. Thus, we were able to provide a tool for assisting patients, physicians and the health care system, where such a decision-making system has an accuracy of 93%. © 2021 IEEE.