This study explores the application of Deep Learning in combating neglected vector-borne Diseases, a significant global health concern, particularly in resource-limited areas. It examines areas where Deep Learning has proven effective, compares popular Deep Learning techniques, focuses on interdisciplinary approaches with translational impact, and finds untapped potential for deep learning application. Thorough searches across multiple databases yielded 64 pertinent studies, from which 16 were selected based on inclusion criteria and quality assessment. Deep Learning applications in disease transmission risk prediction, vector detection, parasite classification, and treatment procedure optimization were investigated and focused on diseases such as Schistosomiasis, Chagas disease, Leishmaniasis, Echinococcosis, and Trachoma. Convolutional neural networks, artificial neural networks, multilayer perceptrons, and AutoML algorithms surpassed traditional methods for disease prediction, species identification, and diagnosis. The interdisciplinary integration of Deep Learning with public health, entomology, and epidemiology provides prospects for improved disease control and understanding. Deep Learning models automate disease surveillance, simplify epidemiological data processing, and enable early detection, particularly in resource-constrained settings. Smartphone apps driven by deep learning allow for rapid disease diagnosis and identification, boosting healthcare accessibility and global health outcomes. Improved algorithms, broadening the scope of applications to areas such as one health approach, and community engagement, and expanding deep learning applications to diseases such as lymphatic filariasis, hydatidosis, and onchocerciasis hold promise for improving global health outcomes.
BT - International Journal of System Assurance Engineering and Management DO - 10.1007/s13198-024-02380-1 LA - ENG M3 - Article N2 -This study explores the application of Deep Learning in combating neglected vector-borne Diseases, a significant global health concern, particularly in resource-limited areas. It examines areas where Deep Learning has proven effective, compares popular Deep Learning techniques, focuses on interdisciplinary approaches with translational impact, and finds untapped potential for deep learning application. Thorough searches across multiple databases yielded 64 pertinent studies, from which 16 were selected based on inclusion criteria and quality assessment. Deep Learning applications in disease transmission risk prediction, vector detection, parasite classification, and treatment procedure optimization were investigated and focused on diseases such as Schistosomiasis, Chagas disease, Leishmaniasis, Echinococcosis, and Trachoma. Convolutional neural networks, artificial neural networks, multilayer perceptrons, and AutoML algorithms surpassed traditional methods for disease prediction, species identification, and diagnosis. The interdisciplinary integration of Deep Learning with public health, entomology, and epidemiology provides prospects for improved disease control and understanding. Deep Learning models automate disease surveillance, simplify epidemiological data processing, and enable early detection, particularly in resource-constrained settings. Smartphone apps driven by deep learning allow for rapid disease diagnosis and identification, boosting healthcare accessibility and global health outcomes. Improved algorithms, broadening the scope of applications to areas such as one health approach, and community engagement, and expanding deep learning applications to diseases such as lymphatic filariasis, hydatidosis, and onchocerciasis hold promise for improving global health outcomes.
PB - Springer Science and Business Media LLC PY - 2024 T2 - International Journal of System Assurance Engineering and Management TI - Deep learning in neglected vector-borne diseases: a systematic review SN - 0975-6809, 0976-4348 ER -