Welcome to our Publications page, where we highlight the latest research and publications in predictive analytics for healthcare. Our team of experts is committed to staying at the forefront of research and innovation in healthcare analytics, and we are dedicated to sharing our insights and findings with the wider healthcare community.
Here are a few publications related to predictive analytics labs that you may find helpful:
| COVID-19 | |
|---|---|
|
Deep learning framework for early detection of COVID-19 using X-ray images
The proposed framework presents a transfer learning technique to increase the performance of the deep learning-based Covid-19 detection method. Moreover, the Comparative evaluation presents that the proposed framework outperforms existing methods. Close results show that VGG-16 on a large dataset correctly identified COVID-19. Covid-19 Deep learning Prediction Transfer learning Chest X-ray Achieved Accuracy: 99.86% |
Tuberculosis (TB) |
|
Tuberculosis chest X-ray detection using CNN-based hybrid segmentation and classification approach.
This research proposes two deep learning-based computer-aided diagnosis (CAD) approaches, for accurate segmentation of lungs regions and precise classification of tuberculosis images based on X-ray imaging, achieving high results compared to state-of-the-art methods in terms of accuracy. Hybrid segmentation and classification Computer-aided diagnosis Pneumonia, COVID-19,Tuberculous Intelligent Features fusion Efficient Tuberculosis detection Achieved Accuracy: 95% |
|
|
An efficient deep learning-based framework for tuberculosis detection using chest X-ray images
The research proposes an accurate and efficient deep learning network which can classify a large number of TB CXR images with an accuracy of on Dataset A and Dataset B respectively, and has validated its generalizability against Dataset C. Efficeint Tuberculosis detection Computer aided diagnosis (CAD) Lungs disease screening Fusion layer Three datasets Achieved Accuracy: 98.98% |
|
|
A machine learning-based framework for Predicting Treatment Failure in tuberculosis: A case study of six countries
This study aims to identify features strongly correlated with treatment failure in tuberculosis using machine learning and data analytics approaches, demonstrating the validation of features using different classification algorithms and providing a demographic-based feature association of six highly burdened treatment failure countries. Pulmonary Tuberculosis Treatment Failure Feature selection techniques Classification algorithms Accuracy combine data: 78% Accuracy Romania's data: 92% |
Colonoscopy |
|
A deep ensemble learning method for colorectal polyp classification with optimized network parameters
This study aims to identify features strongly correlated with treatment failure in tuberculosis using machine learning and data analytics approaches, demonstrating the validation of features using different classification algorithms and providing a demographic-based feature association of six highly burdened treatment failure countries. Colorectal polyp classification Ensemble learning Transfer-learning Virtual biopsy Prediction Achieved Accuracy: 96.3%, 81.2% |
|
|
An ensemble framework of deep neural networks for colorectal polyp classification
This study aims to propose a prediction framework for the accurate identification of defaulters in the Expanded Program on Immunization (EPI) in Pakistan, addressing limitations in previously proposed models by categorizing children into five stages and prioritizing vaccination in high and low coverage areas. Colorectal polyp classification Gastrointestinal (GI) cancer Polypectomy Transfer-learning Prediction Achieved F1-micro (0.80), F1-macro (0.81) |
Expanded Program on Immunization (EPI) |
|
Smart Healthcare Using Data-Driven Prediction of Immunization Defaulters in Expanded Program on Immunization (EPI)
This study proposes a defaulter prediction model to accurately identify children at high risk of defaulting from the Expanded Program on Immunization in Pakistan, which can reinforce immunization programs and reduce dropouts by expediting targeted action through predictive analytics and targeted messages sent to at-risk parents' and caretakers' consumer devices. Smart healthcare Routine immunization Predictive analytics Targeted messaging Defaulters vaccination Achieved Accuracy: 98.5% |
|
|
A data-driven framework for introducing predictive analytics into expanded program on immunization in Pakistan
This study proposes a defaulter prediction model to accurately identify children at high risk of defaulting from the Expanded Program on Immunization in Pakistan, which can reinforce immunization programs and reduce dropouts by expediting targeted action through predictive analytics and targeted messages sent to at-risk parents' and caretakers' consumer devices. Smart healthcare Machine Learning Vaccination Association rule mining Intelligent analysis Achieved Accuracy: 98.5% |
|
|
Critical Review of Data Analytics Techniques used in the Expanded Program on Immunization (EPI)
This paper critically reviews the existing machine learning-based data analytics techniques for immunization and highlights the need to consider the complete complexity of Expanded Program on Immunization, including the lack of centralized data repository in developing countries, to improve vaccination coverage and predict future trends using the right set of machine learning and Artificial Intelligence-based techniques. Data analytics Infectious diseases Vaccination Expanded Program on Immunization Critically reviewed redicting the future trends |
Maternal and Newborn Child Health (MNCH) |
|
Predictive analytics framework for accurate estimation of child mortality rates for Internet of Things enabled smart healthcare systems
The study proposes a predictive analytics framework that utilizes machine learning classifiers to accurately predict under-five child mortality rates and identify significant determinants using information gain ranking, with classifier yielding the highest average accuracy, thus contributing towards reducing child mortality in developing countries. Child mortality Predictive analytics Smart healthcare Demographic Health Survey Children deaths Achieved Accuracy:96.4% |
