Machine Learning Prediction of Hospitalization due to COVID-19 based on Self-Reported Symptoms: A Study for Brazil

Miranda, Igor; Cardoso, Gildeberto; Pahar, Madhurananda; Oliveira, Gabriel Gomes de; Niesler, Thomas

doi:10.1109/bhi50953.2021.9508548

Cited by 4 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model can also be used to track the spread of malaria and to identify areas where there is an increased risk of infection. Miranda, I., et al [5] have used 3 different algorithms which are NN, decision tree and SVM. Here nested validation is used for every dataset & algorithm pair.…”

Section: Literature Surveymentioning

confidence: 99%

A Framework on Combining the Symptoms With Dissimilar Features to Predict Multiple Diseases Using Machine Learning Algorithms

Gantayat,

Suru

2023

Preprint

View full text Add to dashboard Cite

Health plays a vital role in the well-being of individuals. However, due to busy schedules, people often neglect regular health checkups. Engaging in weekly or monthly health checkups is crucial for leading a longer and healthier life. Contemporary food habits, lifestyle choices, pollution, and other factors contribute to various health issues. Unfortunately, many individuals remain unaware of numerous diseases, unknowingly spreading them due to their negligence. A striking example is the COVID-19 pandemic, where people struggle to differentiate between COVID-19 symptoms and those of other illnesses. In such circumstances, technology emerges as a key player. Machine Learning, a field focused on computer algorithms that learn from past experiences, has gained widespread usage and proven to be highly effective in healthcare. This project aims to develop a model that leverages various Machine Learning Algorithms by training a combination of classifiers to create super learners and meta learners. A user-friendly Graphical User Interface (GUI) will be designed to collect symptoms from the user. By utilizing Machine Learning algorithms such as Support Vector Machines (SVM), decision trees, logistic regression, Naive Bayes, and boosting algorithms like AdaBoost and XGBoost, the model will predict the disease based on the symptoms provided by the user. This prediction will assist the user in identifying the potential illness they may be experiencing. As the saying goes, "Prevention is better than cure," and this project emphasizes the significance of early disease detection. It provides a detailed explanation of how the model identifies diseases based on different symptoms using various algorithms. Armed with this information, individuals can promptly contact the appropriate healthcare professionals and take proactive steps to maintain their well-being and overall health.

show abstract

Section: Literature Surveymentioning

confidence: 99%

A Framework on Combining the Symptoms With Dissimilar Features to Predict Multiple Diseases Using Machine Learning Algorithms

Gantayat,

Suru

2023

Preprint

View full text Add to dashboard Cite

show abstract

Accelerometer-Based Bed Occupancy Detection for Automatic, Non-Invasive Long-Term Cough Monitoring

et al. 2023

Self Cite

View full text Add to dashboard Cite

We present a new machine learning based bed occupancy detection system that uses only the accelerometer signal captured by a bed-attached consumer smartphone. Automatic bed occupancy detection is necessary for automatic long-term cough monitoring since the time that the monitored patient occupies the bed is required to accurately calculate a cough rate. Accelerometer measurements are more cost-effective and less intrusive than alternatives such as video monitoring or pressure sensors. A 249-hour dataset of manually-labelled acceleration signals gathered from seven patients undergoing treatment for tuberculosis (TB) was compiled for experimentation. These signals are characterised by brief activity bursts interspersed with long periods of little or no activity, even when the bed is occupied. To process them effectively, we propose an architecture consisting of three interconnected components. An occupancy-change detector locates instances at which bed occupancy is likely to have changed, an occupancy-interval detector classifies periods between detected occupancy changes and an occupancy-state detector corrects falsely-identified occupancy changes. Using long short-term memory (LSTM) networks, this architecture achieved an AUC of 0.94. To demonstrate the application of this bed occupancy detection system to a complete cough monitoring system, the daily cough rates along with the corresponding laboratory indicators of a patient undergoing TB treatment were estimated over a period of 14 days. This provides a preliminary indication that automatic cough monitoring based on bed-mounted accelerometer measurements may present a noninvasive, non-intrusive and cost-effective means of monitoring the long-term recovery of patients suffering from respiratory diseases such as TB and COVID-19.INDEX TERMS accelerometer, bed occupancy, cough monitoring, long short-term memory (LSTM) machine learning

show abstract

Automatic Tuberculosis and COVID-19 cough classification using deep learning

Pahar

Klopper

Reeve

et al. 2022

2022 International Conference on Electrical, Computer and Energy Technologies (ICECET)

View full text Add to dashboard Cite

Machine Learning Prediction of Hospitalization due to COVID-19 based on Self-Reported Symptoms: A Study for Brazil

Cited by 4 publications

References 16 publications

A Framework on Combining the Symptoms With Dissimilar Features to Predict Multiple Diseases Using Machine Learning Algorithms

A Framework on Combining the Symptoms With Dissimilar Features to Predict Multiple Diseases Using Machine Learning Algorithms

Accelerometer-Based Bed Occupancy Detection for Automatic, Non-Invasive Long-Term Cough Monitoring

Automatic Tuberculosis and COVID-19 cough classification using deep learning

Contact Info

Product

Resources

About