Big Data in Public Health: Terminology, Machine Learning, and Privacy

Abstract

The digital world is generating data at a staggering and still increasing rate. While these "big data" have unlocked novel opportunities to understand public health, they hold still greater potential for research and practice. This review explores several key issues that have arisen around big data. First, we propose a taxonomy of sources of big data to clarify terminology and identify threads common across some subtypes of big data. Next, we consider common public health research and practice uses for big data, including surveillance, hypothesis-generating research, and causal inference, while exploring the role that machine learning may play in each use. We then consider the ethical implications of the big data revolution with particular emphasis on maintaining appropriate care for privacy in a world in which technology is rapidly changing social norms regarding the need for (and even the meaning of) privacy. Finally, we make suggestions regarding structuring teams and training to succeed in working with big data in research and practice.

Cyber–Physiochemical Interfaces

“…), and environmental parameters (noise, light, etc.) are usually heterogenous, sparse, irregular, temporal‐dependent, and even highly dimensional . Understanding and utilizing these meaningful data will further improve the quality of life.…”

“…are usually heterogenous, sparse, irregular, temporaldependent, and even highly dimensional. [305][306][307] Understanding www.advmat.de www.advancedsciencenews.com and utilizing these meaningful data will further improve the quality of life. However, there remains a key challenge for gaining insights from these complicated sensing data, due to the lack of sufficient domain knowledge and effective algorithms.…”

“…[307] Artificial intelligence (AI) technologies with the cores of machine learning and big data, have paved a promising way to enable these intelligent applications and services. [305,[308][309][310][311][312][313][314][315][316][317][318][319][320] In machine learning algorithms, computers can automatically learn knowledge from historical experiences data and make prediction on unknown tasks. With the improvement of data acquisition and computing infrastructure, machine learning (especially emerging deep learning) has recently shown or even exceeded the capabilities of human experts in the tasks of image classification, speech recognition, and natural language processing.…”

Para além da privacidade: direito à informação na saúde, proteção de dados pessoais e governança

“…The rapid evolution of information and communication technologies, especially the intensive use of the Internet, unlimited in time and space, has led to a growing volume and variety of data that can be combined, increasing the risk of reidentification even after anonymization or de-identification of single databases 10 . Acknowledgement of the limited effectiveness of such procedures as anonymization, de-identification, and informed consent in the protection of privacy has increasingly highlighted the need for mechanisms to allow greater control over the use of data 11 .…”

Big Data Technology for Scientific Applications

“…From the structure of the Internet of Things, data mining for big data is significant for IoT to advance the intelligence assistance in several applications [2]. The conception and availability of big data, mainly effluent data, have cherished privacy interests among the common public and these concerns are expected to grow and diversify [3].…”