Testing Healthcare AI Algorithms with Quantum Computing: Enhancing Validation and Accuracy (Published)
Due to its capacity to handle information in fundamentally new ways, leading to computational powers that were previously unreachable, the multidisciplinary subject of quantum computing has recently grown and attracted significant interest from both academia and industry. Quantum computing has great promise, but how exactly it will change healthcare is still largely unknown. The potential of quantum computing to transform compute-intensive healthcare tasks like drug discovery, personalized medicine, DNA sequencing, medical imaging, and operational optimization is the primary focus of this survey paper, which offers the first comprehensive analysis of quantum computing’s diverse capabilities in improving healthcare systems. A new era in healthcare is on the horizon, thanks to quantum computing and AI coming together to transform complicated biological simulations, the processing of genetic data, and advances in drug development. Biological data may be extremely large and complicated, making it difficult for traditional computing tools to handle. This slows down and impairs the accuracy of medical discoveries. Combining the predictive power of AI with the exponential processing speed of quantum computers presents a game-changing opportunity to speed up biological research and clinical applications. The function of quantum machine learning in improving drug discovery molecular dynamics simulations powered by artificial intelligence is discussed in this article. Quickly modeling chemical interactions, analyzing drug-receptor binding affinities, and predicting pharmacokinetics with extraordinary precision are all possible with quantum-enhanced algorithms. To further improve disease progression prediction and therapeutic target identification, we also investigate quantum-assisted deep learning models for understanding complex biological processes like protein folding, epigenetic changes, and connections between metabolic pathways.
Keywords: AI, CNN, Healthcare, quantum computing, reinforcement learning
A Survey on Techniques of Wireless Capsule Endoscopy for Image Enhancement and Disease Detection (Published)
Wireless capsule endoscopy (WCE) is the gold standard for diagnosing small bowel disorders and is considered the future of effective diagnostic gastrointestinal (GI) endoscopy. Patients find it comfortable and more likely to adopt it than traditional colonoscopy and gastroscopy, making it a viable option for detecting cancer or ulcerations. WCE can obtain images of the GI tract from the inside, but pinpointing the disease’s location remains a challenge. This paper reviews studies on endoscopy capsule development and discusses techniques and solutions for higher efficiency. Research has demonstrated that artificial intelligence (AI) enhances the accuracy of disease detection and minimizes errors resulting from physicians’ fatigue or lack of attention. When it comes to WCE, deep learning has shown remarkable success in detecting a wide variety of disorders.
Keywords: CNN, Location, bowel, detection, wireless capsule endoscopy