Artificial intelligence and the future of global health

Abstract

Concurrent advances in information technology infrastructure and mobile computing power in many low and middle-income countries (LMICs) have raised hopes that artificial intelligence (AI) might help to address challenges unique to the field of global health and accelerate achievement of the health-related sustainable development goals. A series of fundamental questions have been raised about AI-driven health interventions, and whether the tools, methods, and protections traditionally used to make ethical and evidence-based decisions about new technologies can be applied to AI. Deployment of AI has already begun for a broad range of health issues common to LMICs, with interventions focused primarily on communicable diseases, including tuberculosis and malaria. Types of AI vary, but most use some form of machine learning or signal processing. Several types of machine learning methods are frequently used together, as is machine learning with other approaches, most often signal processing. AI-driven health interventions fit into four categories relevant to global health researchers: (1) diagnosis, (2) patient morbidity or mortality risk assessment, (3) disease outbreak prediction and surveillance, and (4) health policy and planning. However, much of the AI-driven intervention research in global health does not describe ethical, regulatory, or practical considerations required for widespread use or deployment at scale. Despite the field remaining nascent, AI-driven health interventions could lead to improved health outcomes in LMICs. Although some challenges of developing and deploying these interventions might not be unique to these settings, the global health community will need to work quickly to establish guidelines for development, testing, and use, and develop a user-driven research agenda to facilitate equitable and ethical use.

Artificial Intelligence-based Disease Surveillance Amid COVID-19 and Beyond: A Systematic Review Protocol

“…To locate research on AI-based disease surveillance amid COVID-19, we will administer our search in databases including PubMed, IEEE Explore, ACM Digital Library, and Science Direct to identify all potential records. Search strategies were developed based on a preliminary review of the literature [50,62,63,77,78]. Overall, our search terms were developed based on three concepts: AI, disease, and surveillance.…”

“…Adding the fact that global health crises can often cause economic fallout and resources constraints, the cost-effective nature of technological solutions increases their potential as candidate solutions for solving various healthcare issues [37,[41][42][43]. Lastly, and perhaps most importantly, the potential for some technological-based solutions, such as arti cial intelligence (AI) powered disease surveillance systems, in identifying infection cases with high accuracy, may be the most desirable quality governments need to effectively control the spread of diseases [44][45][46][47][48][49][50]. AI can be understood as "the theory and development of computer systems able to perform tasks normally requiring human intelligence, such as visual perception ... and decision-making" [51].…”

Deep learning for neonatal seizure detection: a friend rather than foe

“…However, in the past decade, this vision has made great strides, not only in medicine, as a result of the development of sophisticated deep-learning methods based on the input of a set of data in a computer that will correlate them more or less independently. 2 In particular, deep learning offers the benefits of identifying patterns in complex data and out-of-sample prediction and has demonstrated superior performances in solving many problems in various fields of medicine-eg, radiology, pathology, and drug discovery-compared with traditional machine-learning techniques. 2 Machine learning applied to epilepsy is still in its nascent stages, but there have been promising results in automated seizure detection from electroencephalography (EEG), imaging analysis, pre-surgical planning, and prediction of medication response and clinical outcomes using a wide range of data sources.…”

“…2 In particular, deep learning offers the benefits of identifying patterns in complex data and out-of-sample prediction and has demonstrated superior performances in solving many problems in various fields of medicine-eg, radiology, pathology, and drug discovery-compared with traditional machine-learning techniques. 2 Machine learning applied to epilepsy is still in its nascent stages, but there have been promising results in automated seizure detection from electroencephalography (EEG), imaging analysis, pre-surgical planning, and prediction of medication response and clinical outcomes using a wide range of data sources. [3][4][5] However, few neonatal seizure detection algorithms have been developed to assist health-care professionals with objective decision support.…”

The Promise of Clinical Decision Support Systems Targetting Low-Resource Settings

“…Nonetheless, there have been several successes in India [15]. Artificial intelligence has recently been discussed in the context of rural health applications [16] and global health [17]. However, no-one, to the best of our knowledge, has explored the role of CDSS and outlined existing implementations within low-resource clinical settings.…”