Dalla Lana School of Public Health

Health care organizations are looking to artificial intelligence (AI) tools to improve patient care, but their translation into clinical settings has been inconsistent, in part because evaluating AI in health care remains challenging. In a new article, researchers propose a framework for using AI that includes practical guidance for applying values and that incorporates not just the tool's properties but the systems surrounding its use. Health care organizations are looking to artificial intelligence (AI) tools to improve patient care, but their translation into clinical settings has been inconsistent, in part because evaluating AI in health care remains challenging. In a new article, researchers propose a framework for using AI that includes practical guidance for applying values and that incorporates not just the tool's properties but the systems surrounding its use. The article was written by researchers at Carnegie Mellon University, The Hospital for Sick Children, the Dalla Lana School of Public Health, Columbia University, and the University of Toronto. It is published in Patterns. "Regulatory guidelines and institutional approaches have focused narrowly on the performance of AI tools, neglecting knowledge, practices, and procedures necessary to integrate the model within the larger social systems of medical practice," explains Alex John London, K&L Gates Professor of Ethics and Computational Technologies at Carnegie Mellon, who coauthored the article. "Tools are not neutral -- they reflect our values -- so how they work reflects the people, processes, and environments in which they are put to work." London is also Director of Carnegie Mellon's Center for Ethics and Policy and Chief Ethicist at Carnegie Mellon's Block Center for Technology and Society as well as a faculty member in CMU's Department of Philosophy. London and his coauthors advocate for a conceptual shift in which AI tools are viewed as parts of a larger "intervention ensemble," a set of knowledge, practices, and procedures that are necessary to deliver care to patients. In previous work with other colleagues, London has applied this concept to pharmaceuticals and to autonomous vehicles. The approach treats AI tools as "sociotechnical systems," and the authors' proposed framework seeks to advance the responsible integration of AI systems into health care. Previous work in this area has been largely descriptive, explaining how AI systems interact with human systems. The framework proposed by London and his colleagues is proactive, providing guidance to designers, funders, and users about how to ensure that AI systems can be integrated into workflows with the greatest potential to help patients. Their approach can also be used for regulation and institutional insights, as well as for appraising, evaluating, and using AI tools responsibly and ethically. To illustrate their framework, the authors apply it to the development of AI systems developed for diagnosing more than mild diabetic retinopathy. "Only a small majority of models evaluated through clinical trials have shown a net benefit," says Melissa McCradden, a Bioethicist at the Hospital for Sick Children and Assistant Professor of Clinical and Public Health at the Dalla Lana School of Public Health, who coauthored the article. "We hope our proposed framework lends precision to evaluation and interests regulatory bodies exploring the kinds of evidence needed to support the oversight of AI systems."

Researchers investigated the associations of weight changes later in life with exceptional longevity and found that women who maintained their body weight after age 60 were more likely to reach exceptional longevity. Reaching the age of 90, 95 or 100, known as exceptional longevity, was more likely for women who maintained their body weight after age 60, according to a multi-institutional study led by University of California San Diego. Older women who sustained a stable weight were 1.2 to 2 times more likely to achieve longevity compared to those who experience a weigh loss of 5 percent or more. Reporting in the Aug. 29, 2023 online issue of the Journal of Gerontology: Medical Sciences, researchers investigated the associations of weight changes later in life with exceptional longevity among 54,437 women who enrolled in the Women's Health Initiative, a prospective study investigating causes of chronic diseases among postmenopausal women. Throughout the follow up period, 30,647, or 56 percent of the participants, survived to the age of 90 or beyond. Women who lost at least 5 percent weight were less likely to achieve longevity compared to those who achieved stable weight. For example, women who unintentionally lost weight were 51 percent less likely to survive to the age of 90. However, gaining 5 percent or more weight, compared to stable weight, was not associated with exceptional longevity. "It is very common for older women in the United States to experience overweight or obesity with a body mass index range of 25 to 35. Our findings support stable weight as a goal for longevity in older women," said first author Aladdin H. Shadyab, Ph.D., M.P.H., associate professor at the Herbert Wertheim School of Public Health and Human Longevity Science at UC San Diego. "If aging women find themselves losing weight when they are not trying to lose weight, this could be a warning sign of ill health and a predictor of decreased longevity." The findings suggest that general recommendations for weight loss in older women may not help them live longer. Nevertheless, the authors caution that women should heed medical advice if moderate weight loss is recommended to improve their health or quality of life. The data expands on the growing research linking the relationship between weight change and mortality. Notably, this is the first large study to examine weight change later in life and its relation to exceptional longevity. Co-authors include: Matthew A. Allison and Andrea Z. LaCroix, UC San Diego; JoAnn E. Manson, Brigham and Women's Hospital and Harvard Medical School and Harvard T.H. Chan School of Public Health; Deepika Laddu, University of Illinois Chicago; Sylvia Wassertheil-Smoller, Albert Einstein College of Medicine; Linda Van Horn, Northwestern University Feinberg School of Medicine; Robert A. Wild, University of Oklahoma Health Sciences Center; Hailey R. Banack, Dalla Lana School of Public Health; Fred K. Tabung, Ohio State University; Bernhard Haring, University of Wurzburg and Albert Einstein College of Medicine; Yangbo Sun, University of Tennessee Health Science Center; Erin S. LeBlanc, Kaiser Permanente; Jean Wactawski-Wende, University at Buffalo -- SUNY; Meryl S. LeBoff, Harvard Medical School; Michelle J. Naughton, Ohio State University; Juhua Luo, Indiana University Bloomington; Peter F. Schnatz, Reading Hospital/Tower Health; Ginny Natale, Stony Brook University; and Robert J. Ostfeld, Montefiore Health System. This research was funded, in part, by the National Institutes of Health, National Heart, Lung, and Blood Institute, and U.S. Department of Health and Human Services (75N92021D00001, 75N92021D00002, 75N92021D00003, 75N92021D00004 and 75N92021D00005).

PALO ALTO, Calif., Feb. 1, 2023 /PRNewswire/ -- Healint, the developer and owner of Migraine Buddy – the world's largest migraine tracking and research platform used by more than 3 million people and tens of thousands of migraine and pain clinics – and - The world first hyperlocal & AI based migraine weather-forecast website - is announcing a collaboration today with the University of Toronto. PhD student Andrea Portt works under the supervision of Dr Peter Smith, President of the Institute for Work & Health. Ms. Portt will be analyzing data obtained from Migraine Buddy, in conjunction with data obtained from Environment and Climate Change Canada, in order to analyze the impact on air pollution on migraine in Ontario. This research is funded by a grant from Dalla Lana School of Public Health's Data Science Interdisciplinary Research Cluster to cover the cost of administrative data access. Healint's objective is to help research and promote a better understanding of migraine to improve disease management. In that frame, data and support provided by Healint is free of charge, the time allocated and resources provided by Healint are sponsored by the migraine-buddy users. "This is another example of "Patient Driven Research", patients selected weather as a top research interest, shared some high-level anonymous data to support this research, this is extremely exciting!" said François Cadiou, CEO and co-founder of Healint. The objective of the study will be to determine the association between air pollution and risk of migraine attack onset using administrative and smartphone data. The researchers hope this will provide insights into the effect of the environment on this neurological disease. Given that exposure to air pollution is ubiquitous, an association of migraine with air pollution would have important worldwide implications for public health and environmental monitoring and intervention. Air pollution causes oxidative stress. Neuronal membranes are vulnerable to this stress, which is thought to lead to neuroinflammation that could trigger migraine attacks. Identifying triggers is a coping strategy for people suffering from this disease. Establishing a pollution-migraine link could lead to health advice for those with migraines, such as avoiding exercising in high-traffic streets or avoiding areas with idling cars. So far, studies examining the potential relationship between migraine and air pollution have produced inconsistent results, mostly due to the limited sample size or lack of availability of pollution data. This project allows for more granularity and a bigger sample size. Emergency department reports, data from patients using the Migraine Buddy app, and air pollution estimates in Ontario will be used in an integrated manner with a novel statistical technique. In parallel to the analysis of retrospective data, a prospective study will be conducted to analyse the emergency department usage in Ontario by Migraine Buddy users. "This collaboration with Healint is a great opportunity for us to access data otherwise unavailable and address current gaps in the understanding of migraine triggers," said Ms. Portt. About Healint Healint Pte Ltd is a leading healthcare technology company transforming how patients manage chronic diseases related to the brain and the immune system. Healint puts healthcare in the hands of patients and empowers them to be active participants in the participation to clinical trials and real-world studies. The Migraine Buddy platform and its apps for tracking and weather sensitivity have over three million engaged users. Find out more at [] & Contact * Name: Bo Zhang * Email: [email protected] * Contact number: +65 8657 9176 * Designation: VP, Business Solutions SOURCE Healint Pte Ltd