Loading...
Rupali Chaure is a Research Scholar in the Department of Computer Science and Engineering at RNTU, Bhopal, Madhya Pradesh, India. Her academic activities involve research in computer science and engineering. Her professional development focuses on scholarly investigation and technology-related applications. Her contribution to this chapter addresses AI-based infectious disease detection and classification.
Infectious diseases continue to provide a considerable challenge to global public health due to their swift spread, varied clinical presentations, and ability to result in serious illness and death. Prompt identification and precise categorisation are crucial for prompt intervention, infection management, epidemic avoidance, and efficient public health strategising. Conventional diagnostic methods, such as laboratory analyses, clinical assessments, microscopy, molecular tests, and medical imaging, are beneficial but can be limited by turnaround time, resource constraints, and inconsistencies in diagnostic efficacy. AI and ML provide avenues for the examination of clinical manifestations, laboratory data, medical imaging, pathogen-associated information, and epidemiological statistics to aid in the identification and categorisation of infectious diseases. This section explores AI-driven methodologies for identifying and categorising infectious diseases, such as respiratory infections, tuberculosis, malaria, dengue, sepsis-related infections, and several other transmissible ailments. It addresses data collection, preprocessing, feature extraction, traditional machine learning, deep learning, natural language processing, multimodal learning, interpretable AI, and model assessment.