Machine learning and deep learning technologies have been successfully employed to solve problems in public health with outstanding performances. With the emerging use of “big data” in public health, such as electronic medical records, claims data, search engine query logs, social network contexts, satellite images, self-reported data, and others, the application of machine learning technologies are expected to fulfill itself and play an important role in disease screening, diagnosis, and surveillance.
The primary purpose of disease screening is to detect early disease or risk factors for disease in healthy individuals. Machine learning technologies have been widely applied to help risk factors and high-risk individuals identification. On the other hand, a diagnostic test is to establish the presence of disease. Based on the diagnostic test results, the machine learning models are developed and integrated into the health information systems to assist diagnostic decisions. After diagnosis, the public health authorities monitor the trend of disease incidence and make policies in accordance with the data. Nowadays, disease surveillance is moving toward using a fusion of data sources including claims data that appear to be highly sensitive, electronic laboratory data that afford high specificity but appear to miss cases, and the other novel data source that might close to real-time surveillance, such as engine query logs, social network contexts, and satellite images. Machine learning technologies can also be used in data processing and trend prediction afterward.
The aims of this Research Topic are 1) to highlight the applications of machine learning technologies and their contributions in public health, and 2) to present the state-of-the-art research on machine learning used in disease screening, diagnosis, or surveillance. Researchers are encouraged to submit high-quality Original Research or Review articles in broad areas relevant to machine learning technologies for public health, disease screening, and disease surveillance.
The focuses of this Research Topic, but are not limited to, the following:
· New or improved decision support tools for disease screening, diagnosis, or surveillance;
· Prediction models, methods, and algorithms for disease screening, diagnosis, or surveillance;
· Identification of risk factors for diseases progression;
· Big data in public health: data collection, processing, analytics, and datasets;
· Identification of novel data source for disease screening, diagnosis, or surveillance;
· Text mining in public health;
Machine learning and deep learning technologies have been successfully employed to solve problems in public health with outstanding performances. With the emerging use of “big data” in public health, such as electronic medical records, claims data, search engine query logs, social network contexts, satellite images, self-reported data, and others, the application of machine learning technologies are expected to fulfill itself and play an important role in disease screening, diagnosis, and surveillance.
The primary purpose of disease screening is to detect early disease or risk factors for disease in healthy individuals. Machine learning technologies have been widely applied to help risk factors and high-risk individuals identification. On the other hand, a diagnostic test is to establish the presence of disease. Based on the diagnostic test results, the machine learning models are developed and integrated into the health information systems to assist diagnostic decisions. After diagnosis, the public health authorities monitor the trend of disease incidence and make policies in accordance with the data. Nowadays, disease surveillance is moving toward using a fusion of data sources including claims data that appear to be highly sensitive, electronic laboratory data that afford high specificity but appear to miss cases, and the other novel data source that might close to real-time surveillance, such as engine query logs, social network contexts, and satellite images. Machine learning technologies can also be used in data processing and trend prediction afterward.
The aims of this Research Topic are 1) to highlight the applications of machine learning technologies and their contributions in public health, and 2) to present the state-of-the-art research on machine learning used in disease screening, diagnosis, or surveillance. Researchers are encouraged to submit high-quality Original Research or Review articles in broad areas relevant to machine learning technologies for public health, disease screening, and disease surveillance.
The focuses of this Research Topic, but are not limited to, the following:
· New or improved decision support tools for disease screening, diagnosis, or surveillance;
· Prediction models, methods, and algorithms for disease screening, diagnosis, or surveillance;
· Identification of risk factors for diseases progression;
· Big data in public health: data collection, processing, analytics, and datasets;
· Identification of novel data source for disease screening, diagnosis, or surveillance;
· Text mining in public health;
