A Road Map for Translational Research on Artificial Intelligence in Medical Imaging: From the 2018 National Institutes of Health/RSNA/ACR/The Academy Workshop.

Advances in machine learning in medical imaging are occurring at a rapid pace in research laboratories both at academic institutions and in industry. Important artificial intelligence (AI) tools for diagnostic imaging include algorithms for disease detection and classification, image optimization, radiation reduction, and workflow enhancement. Although advances in foundational research are occurring rapidly, translation to routine clinical practice has been slower. In August 2018, the National Institutes of Health assembled multiple relevant stakeholders at a public meeting to discuss the current state of knowledge, infrastructure gaps, and challenges to wider implementation. The conclusions of that meeting are summarized in two publications that identify and prioritize initiatives to accelerate foundational and translational research in AI for medical imaging. This publication summarizes key priorities for translational research developed at the workshop including: (1) creating structured AI use cases, defining and highlighting clinical challenges potentially solvable by AI; (2) establishing methods to encourage data sharing for training and testing AI algorithms to promote generalizability to widespread clinical practice and mitigate unintended bias; (3) establishing tools for validation and performance monitoring of AI algorithms to facilitate regulatory approval; and (4) developing standards and common data elements for seamless integration of AI tools into existing clinical workflows. An important goal of the resulting road map is to grow an ecosystem, facilitated by professional societies, industry, and government agencies, that will allow robust collaborations between practicing clinicians and AI researchers to advance foundational and translational research relevant to medical imaging.

Self-report measures of medication adherence behavior: recommendations on optimal use.

Medication adherence plays an important role in optimizing the outcomes of many treatment and preventive regimens in chronic illness. Self-report is the most common method for assessing adherence behavior in research and clinical care, but there are questions about its validity and precision. The NIH Adherence Network assembled a panel of adherence research experts working across various chronic illnesses to review self-report medication adherence measures and research on their validity. Self-report medication adherence measures vary substantially in their question phrasing, recall periods, and response items. Self-reports tend to overestimate adherence behavior compared with other assessment methods and generally have high specificity but low sensitivity. Most evidence indicates that self-report adherence measures show moderate correspondence to other adherence measures and can significantly predict clinical outcomes. The quality of self-report adherence measures may be enhanced through efforts to use validated scales, assess the proper construct, improve estimation, facilitate recall, reduce social desirability bias, and employ technologic delivery. Self-report medication adherence measures can provide actionable information despite their limitations. They are preferred when speed, efficiency, and low-cost measures are required, as is often the case in clinical care.

Understanding the context of health for persons with multiple chronic conditions: moving from what is the matter to what matters.

PURPOSE: An isolated focus on 1 disease at a time is insufficient to generate the scientific evidence needed to improve the health of persons living with more than 1 chronic condition. This article explores how to bring context into research efforts to improve the health of persons living with multiple chronic conditions (MCC). METHODS: Forty-five experts, including persons with MCC, family and friend caregivers, researchers, policy makers, funders, and clinicians met to critically consider 4 aspects of incorporating context into research on MCC: key contextual factors, needed research, essential research methods for understanding important contextual factors, and necessary partnerships for catalyzing collaborative action in conducting and applying research. RESULTS: Key contextual factors involve complementary perspectives across multiple levels: public policy, community, health care systems, family, and person, as well as the cellular and molecular levels where most research currently is focused. Needed research involves moving from a disease focus toward a person-driven, goal-directed research agenda. Relevant research methods are participatory, flexible, multilevel, quantitative and qualitative, conducive to longitudinal dynamic measurement from diverse data sources, sufficiently detailed to consider what works for whom in which situation, and generative of ongoing communities of learning, living and practice. Important partnerships for collaborative action include cooperation among members of the research enterprise, health care providers, community-based support, persons with MCC and their family and friend caregivers, policy makers, and payers, including government, public health, philanthropic organizations, and the business community. CONCLUSION: Consistent attention to contextual factors is needed to enhance health research for persons with MCC. Rigorous, integrated, participatory, multimethod approaches to generate new knowledge and diverse partnerships can be used to increase the relevance of research to make health care more sustainable, safe, equitable and effective, to reduce suffering, and to improve quality of life.

Moving the science of behavioral change into the 21st century: part 2.

What follows is the second part of a two-part special series of articles that illustrate through examples the breadth and depth of the field of behavioral-change science and highlight the challenges in moving it in to the 21st century. The first part appeared in the September/October issue of IEEE Pulse (see [1]-[3]).

Mobile health technology evaluation: the mHealth evidence workshop.

Creative use of new mobile and wearable health information and sensing technologies (mHealth) has the potential to reduce the cost of health care and improve well-being in numerous ways. These applications are being developed in a variety of domains, but rigorous research is needed to examine the potential, as well as the challenges, of utilizing mobile technologies to improve health outcomes. Currently, evidence is sparse for the efficacy of mHealth. Although these technologies may be appealing and seemingly innocuous, research is needed to assess when, where, and for whom mHealth devices, apps, and systems are efficacious. In order to outline an approach to evidence generation in the field of mHealth that would ensure research is conducted on a rigorous empirical and theoretic foundation, on August 16, 2011, researchers gathered for the mHealth Evidence Workshop at NIH. The current paper presents the results of the workshop. Although the discussions at the meeting were cross-cutting, the areas covered can be categorized broadly into three areas: (1) evaluating assessments; (2) evaluating interventions; and (3) reshaping evidence generation using mHealth. This paper brings these concepts together to describe current evaluation standards, discuss future possibilities, and set a grand goal for the emerging field of mHealth research.

Maintenance of long-term behavior change.

OBJECTIVES: To describe the formation and work of the Health Maintenance Consortium (HMC), a collaborative of researchers funded by the National Institutes of Health to study long-term behavior change across a variety of diseases and conditions. METHODS: The historical development of the program, especially the focus on behavior change maintenance, is briefly described. Previous work on behavior change that paved the way for the HMC is also discussed. RESULTS: Aiming to accelerate the pace of discovery and application, NIH funding to create the HMC has created a strong research base for making progress toward filling key knowledge and intervention gaps in long-term behavior change. CONCLUSIONS: Investments in behavior change and maintenance have yielded important information that can be used to guide the development of future programs to improve health.

Learning difficulties among children separated from a parent.

OBJECTIVE: To study the relationship between experiencing separation from parents and having learning difficulties among children in a community-based sample. METHODS: In 2003, parents of children entering kindergarten in the city of Rochester completed a survey assessing the child's social background, medical history, and behavioral profile. Children separated from parents for >1 month were compared with those who had never been away for >1 month on 4 validated developmental measures (range, 1-4): a learning scale, an expressive language scale, a preliteracy scale, and a speech scale. Bivariate analyses and multivariate logistic regression analyses were used to determine associations between separation from parents and learning difficulties. RESULTS: Among the 1619 children, 18% had been separated from a parent for >1 month at least once (11% once, 7% > or =2 times). Separated children scored worse compared with those without separations on learning (3.14 vs 3.28, P = .001) and preliteracy (2.21 vs 2.35, P = .03). Higher rates of learning difficulties (26.7% vs 16.7%, P < .001) and preliteracy problems (25.9% vs 18.7%, P = .01) were noted among those who had been separated versus those who had not. In multivariable modeling, separation was associated with learning problems (adjusted odds ratio, 1.71; 95% confidence interval, 1.18-2.49) and preliteracy problems (adjusted odds ratio, 1.46; 95% confidence interval, 1.04-2.05) when adjusted for demographic, medical, and social factors. CONCLUSIONS: Urban children who have experienced separation from a parent may have more learning difficulties at entrance to kindergarten. Screening and intervention practices to remedy these challenges may better equip such young children to succeed when they enter school.

Peer suicidal behavior and adolescent risk behavior.

The relationship between adolescent suicide attempts and death by suicide and psychosocial functioning of peers remains poorly understood, especially in the myriad ways that these suicidal behaviors might impact friends. This study explored the relationship between peer suicidal behavior and adolescent risk behavior using a large, nationally representative sample of adolescents (N = 5852). Results indicate that youth exposed to peer suicidal behavior are significantly more likely to have their own suicidal ideation and attempts, and to smoke cigarettes and marijuana, binge drink, be involved in a serious physical fight, and have inflicted injuries that require medical attention. These results highlight the need for professionals to be aware of these risks in friends of those who have attempted or died by suicide. Assessment and intervention for peers is appropriate and required for this at-risk group.