Cloud Computing and Data Science

AI-Driven Federated and Transfer Learning Platform for Health Predictions

Venkatesh Upadrista, Alejandro Martinez Galindo, Murthy S — Wed, 13 Nov 2024 00:00:00 +0800

Medical negligence, errors, and delayed diagnoses lead to preventable deaths and serious health issues. These problems are mainly caused by a shortage or lack of access to qualified healthcare professionals. In the U.S. alone, medical errors cause an estimated 44,000 to 98,000 deaths annually. The rise of artificial intelligence in healthcare has introduced new opportunities for more accurate diagnoses and predictions, with numerous artificial intelligence (AI)-driven tools now available for detecting diseases such as cancer, heart conditions, lung diseases, and liver diseases. While these tools have revolutionized diagnostics, they are primarily designed for healthcare professionals, limiting their accessibility to the general public. Providing patients with a reliable platform to help them accurately assess their health condition can be transformative, reducing medical errors, enhancing patient engagement, and improving overall care. This study introduces E-Doctor, a Generative AI-powered platform designed to provide reliable second opinions for medical diagnoses. Utilizing advanced AI technologies such as BioBERT for analyzing medical texts and federated learning for maintaining data privacy, the platform addresses the shortage of professional healthcare advice. E-Doctor platform achieved high accuracy rates: 92.4% for heart attack-related advice, 90.2% for full-body checkups, and 93.9% for Deep Vein Thrombosis prediction. By combining medical image analysis with AI-driven learning models, e-Doctor offers a robust platform for enhancing patient outcomes, while ensuring data privacy and security.

An Efficient Automatic Detection of Cardiovascular Disease Based on Machine Learning

Mohammad Karimi Moridani — Fri, 23 Aug 2024 00:00:00 +0800

Cardiovascular diseases have become one of the most common threats to human health worldwide. As a non-invasive diagnostic tool, heart sound detection techniques play an important role in predicting cardiovascular diseases. Although the Electrocardiogram (ECG) signal is generally used to diagnose heart disease, due to the low spatial resolution of this signal, the Phonocardiogram (PCG) signal and methods based on sound processing can be used. In this paper, after extracting different features from PCG, patients were classified with the help of algorithms based on artificial intelligence. The simulation results showed that using the eXtreme Gradient Boosting(XGBoost) algorithm has a better performance in detecting cardiovascular patients than other methods. The values of specificity, sensitivity, and accuracy were obtained as 99±1.93%, 98±2.76% and 99±1.78%, respectively. Using the method proposed in this paper can greatly help doctors make accurate and quick diagnoses of cardiovascular patients and be effective in screening patients. In the future, this method can be developed to diagnose heart valve diseases.

Developing BI Scorecards for Assessing Higher Education Quality Dashboards Using Human-Computer Interaction Concept: A Case Study

Ali Sorour, Anthony Atkins — Fri, 06 Dec 2024 00:00:00 +0800

As Higher Education Institutions (HEIs) in the Kingdom of Saudi Arabia (KSA) have difficulties in monitoring their compliance with the national Quality Assurance (QA) standards, a Holistic Framework for Monitoring Quality in Higher Education Institutions using Business Intelligence Dashboards (HF-HEQ-BI) was used to address this challenge. This paper presents the development and evaluation of Business Intelligence (BI) scorecards for assessing BI dashboards within Higher Education (HE) context based on the Human-Computer Interaction (HCI) principles. It explores the implementation of a Holistic Framework for Monitoring Quality in Higher Education Institutions using Business Intelligence Dashboards (HF-HEQ-BI) in Saudi Arabian HEIs. The paper outlines the development of an evaluation tool for BI dashboards design based on the HF-HEQ-BI framework, emphasising usability, ease of learning, and user interaction as key metrics. A dashboard developed using the HF-HEQ-BI framework was assessed by a panel of experts in Quality Assurance (QA) from Saudi HEIs. The evaluation showed high usability and acceptance rates, indicating that the HF-HEQ-BI framework effectively supports the development of dashboards that meet QA requirements and enhance decision-making processes in HEIs. The study concludes with recommendations for future work, including further development of the HF-HEQ-BI framework and continuous monitoring capabilities in BI dashboards.