Tuesday, July 27, 2021

Improving air quality reduces dementia risk, multiple studies suggest

ALZHEIMER'S ASSOCIATION

IMAGE: AAIC LOGO view more

CREDIT: ALZHEIMER'S ASSOCIATION

DENVER, JULY 26, 2021 -- Improving air quality may improve cognitive function and reduce dementia risk, according to several studies reported today at the Alzheimer's Association International Conference® (AAIC®) 2021 in Denver and virtually.

Previous reports have linked long-term air pollution exposure with accumulation of Alzheimer's disease-related brain plaques, but this is the first accumulated evidence that reducing pollution, especially fine particulates in the air and pollutants from the burning of fuel, is associated with lower risk of all-cause dementia and Alzheimer's disease.

Both increasing levels of air pollution and increasing cases of dementia are worldwide public health crises. While research has linked air quality and cognition previously, these new data at AAIC 2021 explore how air pollutants might impact dementia and what reducing them might mean for long-term brain health. Among the key findings are:

- Reduction of PM2.5 concentration over 10 years was associated with a reduced risk of all-cause dementia in French individuals by 15% and of Alzheimer's disease by 17% for every microgram of gaseous pollutant per cubic meter of air (μg/m3) decrease in PM2.5.

- Long-term exposure to air pollutants was associated with higher beta amyloid levels in the blood in a large U.S. cohort, showing a possible biological connection between air quality and physical brain changes that define Alzheimer's disease.

"We've known for some time that air pollution is bad for our brains and overall health, including a connection to amyloid buildup in the brain," said Claire Sexton, DPhil, Alzheimer's Association director of scientific programs and outreach. "But what's exciting is we're now seeing data showing that improving air quality may actually reduce the risk of dementia. These data demonstrate the importance of policies and action by federal and local governments, and businesses, that address reducing air pollutants."

Air Quality Improvement May Slow Cognitive Decline and Reduce Dementia Risk in Older U.S. Women

Although studies have found that improved air quality is associated with better respiratory health and longer life expectancy, it's unknown if improved air quality can also improve brain health. To investigate this further, Xinhui Wang, Ph.D., assistant professor of research neurology at University of Southern California, and colleagues investigated whether older women living in locations with greater reduction in air pollution may have slower decline in their cognitive function and be less likely to develop dementia.

Wang and team looked at a group of older women (aged 74-92) in the U.S. from the National Institutes of Health-funded Women's Health Initiative Memory Study-Epidemiology of Cognitive Health Outcomes (WHIMS-ECHO) who did not have dementia at the beginning of the study. Participants were followed from 2008-2018 and detailed cognitive function tests were done every year to determine whether they developed dementia. Participants' home addresses were noted and mathematical models were used to estimate the air pollution levels at these locations over time.

The researchers found that, in general, air quality greatly improved over the 10 years before the study began. During a median of six years of follow-up, cognitive functions tended to decline as women aged, as expected. However, for those living in locations with greater reduction per 10% of the EPA's current standard in both PM2.5 (fine particles that are 30 times thinner than a human hair) and NO2 (indicator of traffic-related pollutants), their risk of dementia decreased by 14% and 26%. This was similar to the lower level of risk seen in women two to three years younger.

Benefits were also seen for slower decline in overall cognitive function and memory, similar to women one to two years younger, and on specific tests of working memory, episodic memory and attention/executive function -- cognitive domains with early decline detectable in dementia at the preclinical stage. These benefits were seen regardless of age, level of education, the geographic region where they lived and whether they had cardiovascular disease.

"Our findings are important because they strengthen the evidence that high levels of outdoor air pollution in later life harm our brains, and also provide new evidence that by improving air quality we may be able to significantly reduce risk of cognitive decline and dementia," Wang said. "The possible benefits found in our studies extended across a variety of cognitive abilities, suggesting a positive impact on multiple underlying brain regions."

Reduction of Fine Particulates is Associated with Reduced Risk of Dementia in Older French Adults

In a similarly structured study, Noemie Letellier, Ph.D., postdoctoral scholar at University of California, San Diego, and colleagues worked with the French Three-City Study, a large cohort of more than 7,000 participants aged 65 or older, to investigate the links between air pollution exposure and dementia risk. The researchers observed reduction of PM2.5 concentration between 1990-2000, which was associated with a 15% reduced risk of all-cause dementia and a 17% reduced risk of Alzheimer's disease for every microgram of gaseous pollutant per cubic meter of air (μg/m3) decrease in PM2.5, independent of socio-demographic and health behaviors factors, and APOE genotype.

"These data, for the first time, highlight the beneficial effects of reduced air pollution on the incidence of dementia in older adults." Letellier said. "The findings have important implications to reinforce air quality standards to promote healthy aging. In the context of climate change, massive urbanization and worldwide population aging, it is crucial to accurately evaluate the influence of air pollution change on incident dementia to identify and recommend effective prevention strategies."

Long-Term Air Pollution is Associated with Increased Beta Amyloid Plaques

Accumulation of beta amyloid plaques is one of the hallmarks of Alzheimer's disease. While a relationship between air pollution and increased beta amyloid production has been found in animal and human studies, relatively little is known about the effects of long-term exposure to air pollution on beta amyloid.

Christina Park, doctoral student in the Department of Epidemiology at University of Washington, and colleagues examined associations between exposure to air pollutant levels of fine particulate matter (PM2.5), larger particles (PM10) and nitrogen dioxide (NO2), and levels of Aβ1-40 (one of the major protein components of plaques) in more than 3,000 individuals who were dementia-free at the beginning of the Ginkgo Evaluation of Memory Study. The study evaluated and averaged air pollution levels at participant residential addresses for time periods up to 20 years prior to taking blood tests to measure individuals' beta amyloid.

People who were in the study longer (eight years) showed a strong link between all three air pollutants and Aβ1-40. These are some of the first human data suggesting long-term exposure to air pollutants is associated with higher Aβ1-40 levels in the blood.

"Our findings suggest that air pollution may be an important factor in the development of dementia," Park said. "Many other factors that impact dementia are not changeable, but reductions in exposure to air pollution may be associated with a lower risk of dementia. More research is needed."

###

About the Alzheimer's Association International Conference (AAIC)

The Alzheimer's Association International Conference (AAIC) is the world's largest gathering of researchers from around the world focused on Alzheimer's and other dementias. As a part of the Alzheimer's Association's research program, AAIC serves as a catalyst for generating new knowledge about dementia and fostering a vital, collegial research community.

AAIC 2021 home page: http://www.alz.org/aaic/

AAIC 2021 newsroom: http://www.alz.org/aaic/pressroom.asp

AAIC 2021 hashtag: #AAIC21

About the Alzheimer's Association

The Alzheimer's Association is a worldwide voluntary health organization dedicated to Alzheimer's care, support and research. Our mission is to lead the way to end Alzheimer's and all other dementia -- by accelerating global research, driving risk reduction and early detection, and maximizing quality care and support. Our vision is a world without Alzheimer's and all other dementia®. Visit alz.org or call 800.272.3900.

Development of a novel technology to check body temperature with smartphone camera

Technology for low-cost, thermal-imaging sensors that operate well at temperatures as high as 100 °C has been developed. Expected to be actively used in thermal-imaging applications in smartphones and autonomous vehicles

Peer-Reviewed Publication

NATIONAL RESEARCH COUNCIL OF SCIENCE & TECHNOLOGY

Bolometer device — IMAGE: IMAGE OF ELECTRON MICROSCOPE (LEFT) AND FORMULA (RIGHT) OF BOLOMETER DEVICE view more
CREDIT: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY(KIST)

Thermal-imaging sensors that detect and capture images of the heat signatures of human bodies and other objects have recently sprung into use in thermostats to check facial temperatures in a contactless attempt to screen for COVID-19 at several building entrances. Under these circumstances, the smartphone industry is actively considering the incorporation of such sensors as portable features to create the add-on function of measuring temperature in real time. Additionally, the application of such technology to autonomous vehicles may facilitate safer autonomous driving.

A research team lead by Dr. Won Jun Choi at the Center for Opto-Electronic Materials and Devices in the Korea Institute of Science and Technology (KIST) has announced the development of a thermal-imaging sensor that overcomes the existing problems of price and operating-temperature limitations through convergence research with the team of Prof. Jeong Min Baik from Sungkyunkwan University (SKKU). The sensor developed in this work can operate at temperatures upto 100 °C without a cooling device and is expected to be more affordable than standard sensors on the market, which would in turn pave the way for its application to smartphones and autonomous vehicles.

To be integrated with the hardware of smartphones and autonomous vehicles, sensors must operate stably without any difficulties at high temperatures of 85 °C and 125 °C, respectively. For conventional thermal-imaging sensors to meet this criterion, an independent cooling device would be required. However, high-end cooling devices that promise quality come at a price of over two million Korean won; even such devices do not make the sensor suitable for operations at temperatures as high as 85 °C. Therefore, the conventional thermal-imaging sensors have not been applied in these fields.

A joint research team from KIST and SKKU has developed a device using a vanadium dioxide (VO2)-B film that is stable at 100 °C. This device detects and converts the infrared light generated by heat into electrical signals; this eliminates the need for cooling devices, which account for over 10% of the cost of thermal-imaging sensors and consume large amounts of electricity. The device was able to obtain the same level of infrared signals at 100 °C as at room temperature. Furthermore, as a result of fabricating and using an infrared absorber that can absorb as much external infrared light as possible, heat signatures were detected with three times more sensitivity and converted into electrical signals. The device shows around 3 milliseconds of response time even at 100 °C, which is about 3~4 times faster than conventional ones. Such high response speeds enable the device to capture thermal images at 100 frames per second, far exceeding the conventional level of 30-40 frames per second. This makes the device an interesting candidate for use in autonomous vehicles, as well.

Dr. Choi of the KIST said, "By means of our work with convergence research in this study, we have developed a technology that could dramatically reduce the production cost of thermal-imaging sensors. Our device, when compared to more conventional ones, has superior responsivity and operating speed. We expect this to accelerate the use of thermal-imaging sensors in the military supply, smartphone, and autonomous vehicle industries."

###

This research was conducted as KIST's institutional R&D project, supported by the Ministry of Science and ICT (MSIT), and as a project of the KIST-UNIST Ulsan Center for Convergent Materials. It has been published in the latest issue of "Applied Surface Science" (in the top 3.28% of the JCR field).

JOURNAL

Applied Surface Science

DOI

10.1016/j.apsusc.2021.149142

New US and German collaboration aims to produce green hydrogen more efficiently

Meeting Announcement

UNIVERSITY OF ILLINOIS COLLEGE OF LIBERAL ARTS & SCIENCES

Research team — IMAGE: A NEW RESEARCH PROJECT THAT AIMS TO PRODUCE GREEN HYDROGEN MORE EFFICIENTLY BRINGS TOGETHER A MULTIDISCIPLINARY TEAM COMPRISING PROFESSORS HONG YANG AND NICOLA PERRY AT THE UNIVERSITY OF ILLINOIS URBANA-CHAMPAIGN AND PROFESSOR ANDREAS KLEIN AT THE TECHNICAL UNIVERSITY OF DARMSTADT. view more
CREDIT: UNIVERSITY OF ILLINOIS/TECHNICAL UNIVERSITY OF DARMSTADT

Through a new award program, the U.S. National Science Foundation and the Deutsche Forschungsgemeinschaft (German Research Foundation, DFG) have joined forces to award the University of Illinois Urbana-Champaign and Technical University of Darmstadt a three-year $720,000 research grant ($500,000 from NSF) to explore opportunities to more efficiently produce green hydrogen, a clean and renewable source of energy.

This project is among the first supported by the NSF-DFG Lead Agency Activity in Electrosynthesis and Electrocatalysis (NSF-DFG EChem), an international effort to support collaborative work between U.S. researchers and their German counterparts on engineering science projects for novel and fundamental electrochemical reactions and studies. The new project assembles a multidisciplinary team, comprising Professors Hong Yang and Nicola Perry at UIUC and Professor Andreas Klein at TU Darmstadt.

"Our society is making great strides toward a future powered by renewable sources," said the project's principal investigator Hong Yang, Alkire Chair professor of chemical and biomolecular engineering and affiliate professor of chemistry at UIUC. "Green hydrogen can fuel cars and semi-trucks or used as commodity chemicals for industrial manufacturing--but there is work to be done to ensure that green hydrogen production is viable and scalable."

Green hydrogen is made from splitting water molecules with a device called an electrolyzer that uses electric energy from renewable sources--but this process currently requires a lot of energy, and it is still not cost-effective.

This newly funded research project aims to increase the efficiency and stability of electrolysis for water splitting via understanding the engineering science of new classes of electrocatalysts such as pyrochlores.

Catalysts speed up chemical reactions. The research team will use cutting-edge techniques to reveal their complex surface and bulk structures, which influence catalyst performance and reaction rates. Their goal is to identify the specific chemistry--down to the atomic level--that creates the most reactive and stable electrocatalysts for water splitting.

Ultimately, better catalysts are needed to reduce electricity usage and meet the stability requirement to produce green hydrogen at a reduced cost.

"Our team brings together diverse methods and disciplinary lenses that, when combined, have potential to provide unique insights for the development of practical green hydrogen catalysts," said the project's co-principal investigator Nicola Perry, a materials science and engineering professor at UIUC. "This interdisciplinary and internationally collaborative environment will also provide a rich, formative context for student researcher training."

Perry will lead the growth of thin-film catalysts, as a model platform enabling fundamental insights. She will also oversee the analysis of defect chemistry, which is the study of populations of active atomic-scale anomalies under dynamic operating conditions and their impact on catalyst performance. Perry and Yang are also members of the Materials Research Lab, where some of this work will take place.

Andreas Klein, a professor of materials and earth sciences at TU Darmstadt, will develop a new framework to study the surface structures using X-ray photoelectron spectroscopy (XPS) in realistic conditions.

"Hydrogen is expected to play an important role for carbon-neutral technology," Yang said. "I am excited to help develop the sustainable technologies to make green hydrogen to fuel cars, and one day, our society at large."

CAPTION

This pyrochlore electrocatalyst unit cell is the smallest repeating unit of atoms that make up the catalyst.

CREDIT

Hong Yang

Reprogrammed whale neurons predict neurotoxicity of environmental pollutants

Using neurons directly reprogrammed from tissues of stranded whales to assess brain health

Peer-Reviewed Publication

EHIME UNIVERSITY

Exposure of a PCB metabolite to whale-derived induced neurons caused apoptosis and neurodegeneration — IMAGE: EXPOSURE OF A PCB METABOLITE TO WHALE-DERIVED INDUCED NEURONS CAUSED APOPTOSIS AND NEURODEGENERATION view more
CREDIT: ENVIRONMENTAL SCIENCE & TECHNOLOGY © 2021 AMERICAN CHEMICAL SOCIETY

Whales accumulate large burdens of environmental pollutants that threaten their survival and health. Toxicological studies on cetacean species have been extremely challenging because invasive studies are restricted by legal and ethical considerations and sampling of wild cetaceans is highly opportunistic. Although model animal studies can provide data from practical experiments, extrapolating the toxicological effects to cetaceans is limited due to the large interspecies susceptibility to chemical exposure. The types of whale cells that can be cultured are limited, and cell-specific assays for whales have not been developed. A research team of the Center for Marine Environmental Studies (CMES) of Ehime University, Japan succeeded in direct reprogramming the fibroblasts of stranded melon-headed whales (Peponocephala electra) to neurons, not through the induction of pluripotent stem cells (iPSCs), but by using a cocktail of small compounds. Using whale induced neurons, they have investigated the neurotoxicity of an environmental pollutant on cetacean neurons for the first time. Their research was recently published in Environmental Science & Technology.

Reprogramming from fibroblasts to neuronal cells

The research team obtained tissue samples from melon-headed whales mass stranded along the coast of Hokota-city, Ibaraki, Japan. After a few weeks of treatment with a cocktail of small compounds, the morphology of the fibroblast cells derived from the melon-headed whale tissues changed to neuron-like cells. Reprogramming of the fibroblasts to neurons, induced neuronal cells (iNCs), was confirmed by positive signals for neuronal markers: beta-III tubulin (Tuj-1) and microtubule associated protein 2 (MAP2), and negative signals for astrocyte and oligodendrocyte markers: glial fibrillary acidic protein (GFAP) and 2’,3’-cyclic nucleotide 3’-phosphodiesterase (CNPase), respectively. Transcriptome analysis of the whale iNCs also supported the success in reprogramming, showing downregulation of a fibroblast marker elastin (ELN) and upregulation of neuron-related genes such as synaptic genes: synaptophysin (SYP) and stathmin 3 (STMN3).

Apoptosis assay

Apoptosis was measured by detecting nuclear chromatin fragmentation by TUNEL assay. Over 80% of whale iNCs have led to apoptosis after 24hr exposure to 20μM 4’OH-CB72, with apoptosis-positive cells increasing 1.8-2.4 times compared to vehicle controls.

Transcriptome analysis of whale neuronal cells exposed to 4’OH-CB72

Upregulation of the genes related to apoptosis in whale iNCs was also confirmed by transcriptome analysis. Genes such as apoptosis inducing factor mitochondria associated 1 (AIFM1), BH3 interacting domain death agonist (BID), and tumor necrosis factor (TNF) receptor associated factor 2 (TRAF2) were upregulated in whale iNCs. On the other hand, cell survival-related genes were downregulated in whale iNCs. Additionally, many genes involved in neurodegenerative diseases such as Alzheimer’s disease, amyotrophic lateral sclerosis, and Huntington’s disease were altered in whale iNCs exposed to 4'OH-CB72.

Bioinformatics analyses using differentially expressed genes upon exposure to 4’OH-CB72 suggested that the cellular signaling pathways of mitochondrial dysfunction, chromatin degradation, axonal transport, and ubiquitin−proteasome system were disrupted by this pollutant. These effects ultimately lead to neurodegeneration through neuronal apoptosis and cell death.

Future perspectives

Since cetaceans are chronically exposed to a variety of environmental pollutants, not only 4’OH-CB72, but also other PCBs, the neurotoxicity of other compounds is also of concern. This approach may be useful for other marine mammals for which there is yet no effective means of neurotoxicity testing.

###

DOI

10.1021/acs.est.1c01074

SEXIST RACIST MEDICINE USA

Heart failure diagnoses may be missed in a primary care setting for women, Black adults

Circulation: Heart Failure Journal Report

Peer-Reviewed Publication

AMERICAN HEART ASSOCIATION

DALLAS, July 27, 2021 -- Many heart failure diagnoses may be missed in a primary care setting. Women, Black adults and individuals with lower net worth are significantly more likely to be diagnosed with heart failure in an acute care setting such as the emergency room or during a hospitalization, even if they reported symptoms of heart failure during a routine, outpatient health care appointment during the previous six months, according to new research published today in Circulation: Heart Failure, an American Heart Association journal.

"This national study raises concerns that many heart failure diagnoses may be missed in a primary care setting," said Rebecca Tisdale, M.D., M.P.A., co-first author and health services research and development fellow at the U.S. Department of Veterans Affairs and Stanford University in Palo Alto, California. "Our results suggest acute care diagnosis rates for heart failure may be reduced if signs and symptoms of heart failure are more closely assessed in a primary care setting, particularly among women and Black adults."

Heart failure occurs when the heart cannot pump enough blood and oxygen to support other organs in the body. Heart failure is a serious condition that requires treatment; however, it does not mean that the heart has stopped beating. According to the American Heart Association 2021 Statistical Update, an estimated 6 million Americans ages 20 and older have been diagnosed with heart failure, with the rate of death within one year of diagnosis exceeding 20%. Previous studies have found that heart failure is frequently first diagnosed in an acute care setting.

"Patients diagnosed with heart failure in the emergency room or during inpatient hospitalization often have more advanced heart failure and complications with worse prognoses than individuals diagnosed with heart failure in a primary care setting," said Alexander Sandhu, M.D., M.S., lead author of the study, an instructor of medicine in advanced heart failure in the division of cardiovascular medicine and the Stanford Cardiovascular Institute at Stanford University in Stanford, California. "Since earlier recognition and treatment may prevent some of the serious complications and costs of heart failure, our analysis focused on evaluating whether heart failure is identified before the patient is in the emergency room or the hospital."

Researchers used a national database of commercial insurance and Medicare Advantage health care claims from 2003-2019 to evaluate if patients with new incidence of heart failure were diagnosed in an outpatient (primary care) or acute care (emergency room or urgent care) setting. The analysis included nearly one million adults ages 18 or older with a first-time heart failure diagnosis.

The results found that a large proportion of new heart failure diagnoses occurred in the emergency room or during hospitalization, particularly among women and Black adults, yet many had potential heart failure symptoms in the months before their acute care visits. Detailed analysis found:

Among patients with newly diagnosed heart failure, 38% were diagnosed in acute care settings.
Of the patients diagnosed in the acute care setting, 46% had potential heart failure symptoms during primary care clinic visits in the previous six months, including edema (15%), cough (12%), shortness of breath (11%), and chest pain (11%).
Heart failure diagnosis in an acute care setting was higher for women compared with men, and also higher for Black adults compared with white adults.
People with a net worth of under $25,000 had 39% higher odds of receiving heart failure diagnoses in an acute care setting compared to people with a net worth of over $500,000.

The disparities in heart failure diagnosis within clinical practices persisted nationally across race, gender and economic status, suggesting potential differences in either quality of care or local resource availability. In addition, acute care heart failure diagnoses increased by 3.2% annually during the 16-year study period.

Timely heart failure diagnosis can lead to referrals to specialists, prescription of specific therapies, patient counseling and ultimately, improved patient outcomes. Rapid treatment is critical for reducing the progression of heart failure and its serious complications. However, previous research has shown that both women and Black adults are less likely to be referred to a cardiologist or to promptly receive advanced heart failure treatment.

"Further research is needed to better understand the factors influencing these disparities," Sandhu added. "It is important to note that we only analyzed patients with health insurance, raising concerns that inequities may be even larger among people who are uninsured, marginally insured or those who have less access to care."

###

Co-authors are Rebecca Tisdale, M.D., M.P.A.; Fatima Rodriguez, M.D., M.P.H.; Randall S. Stafford, M.D., Ph.D.; David J. Maron, M.D.; Tina Hernandez-Boussard, Ph.D., M.P.H., M.S.; Eldrin Lewis, M.D.; Paul A. Heidenreich, M.D., M.S. Author disclosures are in the manuscript.

Additional Resources:

Available multimedia is on right column of release link - https://newsroom.heart.org/news/heart-failure-diagnoses-may-be-missed-in-a-primary-care-setting-for-women-black-adults?preview=91c68fd399e3109f7fc6ba0e12b2df8e

After July 27, view the manuscript online.

Women received less aggressive care than men after a heart attack with pumping failure
Go Red For Women - Health Equity
Heart failure deaths are highest in the poorest U.S. counties
Racial disparities: Young, Black adults had significantly worse heart transplant outcomes

Follow AHA/ASA news on Twitter @HeartNews

Follow news from the AHA's Circulation: Heart Failure journal @CircHF

Statements and conclusions of studies published in the American Heart Association's scientific journals are solely those of the study authors and do not necessarily reflect the Association's policy or position. The Association makes no representation or guarantee as to their accuracy or reliability. The Association receives funding primarily from individuals; foundations and corporations (including pharmaceutical, device manufacturers and other companies) also make donations and fund specific Association programs and events. The Association has strict policies to prevent these relationships from influencing the science content. Revenues from pharmaceutical and biotech companies, device manufacturers and health insurance providers and the Association's overall financial information are available here.

About the American Heart Association

The American Heart Association is a relentless force for a world of longer, healthier lives. We are dedicated to ensuring equitable health in all communities. Through collaboration with numerous organizations, and powered by millions of volunteers, we fund innovative research, advocate for the public's health and share lifesaving resources. The Dallas-based organization has been a leading source of health information for nearly a century. Connect with us on heart.org, Facebook, Twitter or by calling 1-800-AHA-USA1.

Machine learning for cardiovascular disease improves when social, environmental factors are included

Research emphasizes the need for algorithms that incorporate community-level data, studies that include more diverse populations

Peer-Reviewed Publication

NEW YORK UNIVERSITY

Machine learning can accurately predict cardiovascular disease and guide treatment--but models that incorporate social determinants of health better capture risk and outcomes for diverse groups, finds a new study by researchers at New York University's School of Global Public Health and Tandon School of Engineering. The article, published in the American Journal of Preventive Medicine, also points to opportunities to improve how social and environmental variables are factored into machine learning algorithms.

Cardiovascular disease is responsible for nearly a third of all deaths worldwide and disproportionately affects lower socioeconomic groups. Increases in cardiovascular disease and deaths are attributed, in part, to social and environmental conditions--also known as social determinants of health--that influence diet and exercise.

"Cardiovascular disease is increasing, particularly in low- and middle-income countries and among communities of color in places like the United States," said Rumi Chunara, associate professor of biostatistics at NYU School of Global Public Health and of computer science and engineering at NYU Tandon School of Engineering, as well as the study's senior author. "Because these changes are happening over such a short period of time, it is well known that our changing social and environmental factors, such as increased processed foods, are driving this change, as opposed to genetic factors which would change over much longer time scales."

Machine learning--a type of artificial intelligence used to detect patterns in data--is being rapidly developed in cardiovascular research and care to predict disease risk, incidence, and outcomes. Already, statistical methods are central in assessing cardiovascular disease risk and U.S. prevention guidelines. Developing predictive models gives health professionals actionable information by quantifying a patient's risk and guiding the prescription of drugs or other preventive measures.

Cardiovascular disease risk is typically computed using clinical information, such as blood pressure and cholesterol levels, but rarely take social determinants, such as neighborhood-level factors, into account. Chunara and her colleagues sought to better understand how social and environmental factors are beginning to be integrated into machine learning algorithms for cardiovascular disease--what factors are considered, how they are being analyzed, and what methods improve these models.

"Social and environmental factors have complex, non-linear interactions with cardiovascular disease," said Chunara. "Machine learning can be particularly useful in capturing these intricate relationships."

The researchers analyzed existing research on machine learning and cardiovascular disease risk, screening more than 1,600 articles and ultimately focusing on 48 peer-reviewed studies published in journals between 1995 and 2020.

They found that including social determinants of health in machine learning models improved the ability to predict cardiovascular outcomes like rehospitalization, heart failure, and stroke. However, these models did not typically include the full list of community-level or environmental variables that are important in cardiovascular disease risk. Some studies did include additional factors such as income, marital status, social isolation, pollution, and health insurance, but only five studies considered environmental factors such as the walkability of a community and the availability of resources like grocery stores.

The researchers also noted the lack of geographic diversity in the studies, as the majority used data from the United States, countries in Europe, and China, neglecting many parts of the world experiencing increases in cardiovascular disease.

"If you only do research in places like the United States or Europe, you'll miss how social determinants and other environmental factors related to cardiovascular risk interact in different settings and the knowledge generated will be limited," said Chunara.

"Our study shows that there is room to more systematically and comprehensively incorporate social determinants of health into cardiovascular disease statistical risk prediction models," said Stephanie Cook, assistant professor of biostatistics at NYU School of Global Public Health and a study author. "In recent years, there has been a growing emphasis on capturing data on social determinants of health--such as employment, education, food, and social support--in electronic health records, which creates an opportunity to use these variables in machine learning studies and further improve the performance of risk prediction, particularly for vulnerable groups."

"Including social determinants of health in machine learning models can help us to disentangle where disparities are rooted and bring attention to where in the risk structure we should intervene," added Chunara. "For example, it can improve clinical practice by helping health professionals identify patients in need of referral to community resources like housing services and broadly reinforces the intricate synergy between the health of individuals and our environmental resources."

###

In addition to Chunara and Cook, study authors include Yuan Zhao, Erica Wood, and Nicholas Mirin, students at the NYU School of Global Public Health. The research was supported by funding from the National Science Foundation (IIS-1845487).

About the NYU School of Global Public Health

At the NYU School of Global Public Health (NYU GPH), we are preparing the next generation of public health pioneers with the critical thinking skills, acumen, and entrepreneurial approaches necessary to reinvent the public health paradigm. Devoted to employing a nontraditional, interdisciplinary model, NYU GPH aims to improve health worldwide through a unique blend of global public health studies, research, and practice. The School is located in the heart of New York City and extends to NYU's global network on six continents. Innovation is at the core of our ambitious approach, thinking and teaching. For more, visit: http://publichealth.nyu.edu/

About the New York University Tandon School of Engineering

The NYU Tandon School of Engineering dates to 1854, the founding date for both the New York University School of Civil Engineering and Architecture and the Brooklyn Collegiate and Polytechnic Institute. A January 2014 merger created a comprehensive school of education and research in engineering and applied sciences as part of a global university, with close connections to engineering programs at NYU Abu Dhabi and NYU Shanghai. NYU Tandon is rooted in a vibrant tradition of entrepreneurship, intellectual curiosity, and innovative solutions to humanity's most pressing global challenges. Research at Tandon focuses on vital intersections between communications/IT, cybersecurity, and data science/AI/robotics systems and tools and critical areas of society that they influence, including emerging media, health, sustainability, and urban living. We believe diversity is integral to excellence, and are creating a vibrant, inclusive, and equitable environment for all of our students, faculty and staff. For more information, visit engineering.nyu.edu.