Background: Artificial intelligence (AI) is heralded as an approach that might augment or substitute for the limited processing power of the human brain of primary health care (PHC) professionals. However, there are concerns that AI-mediated decisions may be hard to validate and challenge, or may result in rogue decisions. Objective: To form consensus about perceptions, issues, and challenges of AI in primary care. Method: A three-round Delphi study was conducted. Round 1 explored experts’ viewpoints on AI in PHC (n=20). Round 2 rated the appropriateness of statements arising from round one (n=12). The third round was an online panel discussion of findings (n=8) with the members of both the International Medical Informatics Association and the European Federation of Medical Informatics Primary Health Care Informatics Working Groups. Results: PHC and informatics experts reported AI has potential to improve managerial and clinical decisions and processes, and this would be facilitated by common data standards. The respondents did not agree that AI applications should learn and adapt to clinician preferences or behaviour and they did not agree on the extent of AI potential for harm to patients. It was more difficult to assess the impact of AI-based applications on continuity and coordination of care. Conclusion: While the use of AI in medicine should enhance healthcare delivery, we need to ensure meticulous design and evaluation of AI applications. The primary care informatics community needs to be proactive and to guide the ethical and rigorous development of AI applications so that they will be safe and effective.

PURPOSE Rapid increases in technology and data motivate the application of artificial intelligence (AI) to primary care, but no comprehensive review exists to guide these efforts. Our objective was to assess the nature and extent of the body of research on AI for primary care. METHODSWe performed a scoping review, searching 11 published or gray literature databases with terms pertaining to AI (eg, machine learning, bayes* network) and primary care (eg, general pract*, nurse). We performed title and abstract and then full-text screening using Covidence. Studies had to involve research, include both AI and primary care, and be published in English. We extracted data and summarized studies by 7 attributes: purpose(s); author appointment(s); primary care function(s); intended end user(s); health condition(s); geographic location of data source; and AI subfield(s). RESULTSOf 5,515 unique documents, 405 met eligibility criteria. The body of research focused on developing or modifying AI methods (66.7%) to support physician diagnostic or treatment recommendations (36.5% and 13.8%), for chronic conditions, using data from higher-income countries. Few studies (14.1%) had even a single author with a primary care appointment. The predominant AI subfields were supervised machine learning (40.0%) and expert systems (22.2%).CONCLUSIONS Research on AI for primary care is at an early stage of maturity. For the field to progress, more interdisciplinary research teams with end-user engagement and evaluation studies are needed. Ann Fam Med 2020;18:250-258. https://doi.

BackgroundMaternal mortality is still a major risk for women of childbearing age in Nigeria. In 2008, Nigeria bore 14% of the global burden of maternal mortality. The national maternal mortality ratio has remained elevated despite efforts to reduce maternal deaths. Though health disparities exist between the North and South of Nigeria, there is a dearth of evidence on the estimates and determinants of maternal mortality for these regions.MethodsThis study aimed to assess differences in the levels and determinants of maternal mortality in women of childbearing age (15–49 years) in the North and South of Nigeria. The Nigeria Demographic and Health Surveys (2008 and 2013) were used. The association between maternal mortality (outcome) and relevant sociocultural, economic and health factors was tested using multivariable logistic regression in a sample of 51,492 living or deceased women who had given birth.ResultsThere were variations in the levels of maternal mortality between the two regions. Maternal mortality was more pronounced in the North and increased in 2013 compared to 2008. For the South, the levels slightly decreased. Media exposure and education were associated with maternal mortality in the North while contraceptive method, residence type and wealth index were associated with maternal death in the South. In both regions, age and community wealth were significantly associated with maternal mortality.ConclusionsDifferences in the levels and determinants of maternal mortality between the North and South of Nigeria stress the need for efforts to cut maternal deaths through new strategies that are relevant for each region. These should improve education of girls in the North and access to health information and services in the South. Overall, new policies to improve women’s socioeconomic status should be adopted.

Findings highlight that it is not sufficient to engage patients in the use of a portal; it is critical that patients be engaged in the early stages of implementation. With many health and fitness electronic tools available (e.g. Fitbit©), this study remind us that tools are not enough. Patient engagement requires patient-centred partnerships between patients and health care providers.