Sema Sgaier, Ph.D.

Health care leaders are embracing AI. But by conducting an extensive review of case studies and research literature, we’ve found that their AI initiatives are predominantly focused on developing algorithms that can predict a problem such as cancer in order to make diagnoses better, faster, and less expensively. Rarely, are their organizations devoting resources to AI efforts aimed at understanding why diseases occur. To intervene as effectively as possible, both kinds of algorithms are crucial.

Machine learning is neither a panacea nor as technically daunting as some believe. When it comes to global development, the key is to ask the right questions, and then see if and how it can help.

One-size-fits-all interventions that aim to change behavior are a missed opportunity to improve human health and well-being, as they do not target the different reasons that drive people’s choices and behaviors.

To improve quality of care before, during, and after childbirth, the global health community must develop new, evidence-backed interventions that address the underlying – often hidden – reasons why health-care providers fail to take the necessary steps. The first step is to identify what those reasons are.

Inadequate quality of care in healthcare facilities is one of the primary causes of patient mortality in low- and middle-income countries, and understanding the behavior of healthcare providers is key to addressing it. Much of the existing research concentrates on improving resource-focused issues, such as staffing or training, but these interventions do not fully close the gaps in quality of care. By contrast, there is a lack of knowledge regarding the full contextual and internal drivers–such… Show more

Inadequate quality of care in healthcare facilities is one of the primary causes of patient mortality in low- and middle-income countries, and understanding the behavior of healthcare providers is key to addressing it. Much of the existing research concentrates on improving resource-focused issues, such as staffing or training, but these interventions do not fully close the gaps in quality of care. By contrast, there is a lack of knowledge regarding the full contextual and internal drivers–such as social norms, beliefs, and emotions–that influence the clinical behaviors of healthcare providers. We aimed to provide two conceptual frameworks to identify such drivers, and investigate them in a facility setting where inadequate quality of care is pronounced. Show less

A pressing goal in global development and other sectors is often to understand what drives people’s behaviors, and how to influence them. Yet designing behavior change interventions is often an unsystematic process, hobbled by insufficient understanding of contextual and perceptual behavioral drivers and a narrow focus on limited research methods to assess them. We propose a toolkit (CUBES) of two solutions to help programs arrive at more effective interventions.

It is imperative to include customers in solving problems, but jumping straight into human-centered design misses the rich and insightful data required to shift the system and achieve better results.

Most global development programs still segment people by demographics when trying to change their behavior. We must learn from the private sector and segment people based on the reasons behind their actions.

Numerous public-health interventions have demonstrated effectiveness in pilots or on a small scale, but have proven challenging to scale up for population-level impact.

Public health programs are starting to recognize the need to move beyond a one-size-fits-all approach in demand generation, and instead tailor interventions to the heterogeneity underlying human decision making. Currently, however, there is a lack of methods to enable such targeting.

By the end of 2014, an estimated 8.5 million men had undergone voluntary medical male circumcision (VMMC) for HIV prevention in 14 priority countries in eastern and southern Africa, representing more than 40% of the global target. However, demand, especially among men most at risk for HIV infection, remains a barrier to realizing the program's full scale and potential impact. We analyzed current demand generation interventions for VMMC by reviewing the available literature and reporting on… Show more

By the end of 2014, an estimated 8.5 million men had undergone voluntary medical male circumcision (VMMC) for HIV prevention in 14 priority countries in eastern and southern Africa, representing more than 40% of the global target. However, demand, especially among men most at risk for HIV infection, remains a barrier to realizing the program's full scale and potential impact. We analyzed current demand generation interventions for VMMC by reviewing the available literature and reporting on field visits to programs in 7 priority countries. We present our findings and recommendations using a framework with 4 components: insight development; intervention design; implementation and coordination to achieve scale; and measurement, learning, and evaluation. Show less

Scaling up HIV prevention programming among key populations (female sex workers and men who have sex with men) has been a central strategy of the Government of India. However, state governments have lacked the technical and managerial capacity to oversee and scale up interventions or to absorb donor-funded programs.

By December 2013, it was estimated that close to 6 million men had been circumcised in the 14 priority countries for scaling up voluntary medical male circumcision (VMMC), the majority being adolescents (10-19 years). This article discusses why efforts to scale up VMMC should prioritize adolescent men, drawing from new evidence and experiences at the international, country, and service delivery levels.

This review provides an overview of findings from the PLOS Collection "Voluntary Medical Male Circumcision for HIV Prevention: Improving Quality, Efficiency, Cost Effectiveness, and Demand for Services during an Accelerated Scale-up." The use of devices for VMMC is also explored.