AI Health

Friday Roundup

The AI Health Friday Roundup highlights the week’s news and publications related to artificial intelligence, data science, public health, and clinical research.

August 12, 2022

In today’s Roundup: assessing the health merits of fitness trackers; Florence Nightingale’s contributions to data visualization; racial inequity in uterine cancer; emergency departments under strain; how “social capital” shapes our world; educational tech and cyber risk; why evidence-based medicine needs implementation science; the hidden chaos of living systems; much more:

AI, STATISTICS & DATA SCIENCE

Andrea Leopardi/Unsplash
  • “Activity trackers appear to be effective at increasing physical activity in a variety of age groups and clinical and non-clinical populations. The benefit is clinically important and is sustained over time. Based on the studies evaluated, there is sufficient evidence to recommend the use of activity trackers.” A systematic review and meta-analysis of the literature concerning the utility of wearable fitness tracker devices for increasing physical activity, recently published in Lancet Digital Health by Ferguson and colleagues, finds in favor of the devices.
  • An article published in Science by Wang and colleagues introduces “constrained hallucination” as part of deep learning approach for describing protein folding: “We refer to this process as ‘hallucination,’ as it produces solutions that the network considers to be ideal proteins but that do not correspond to any known natural protein; crystal and nuclear magnetic resonance structures confirm that the hallucinated sequences fold to the hallucinated structures…”
  • “Physical scientists seem to find the phenomenon of chaos everywhere: in the orbits of planets, in weather systems, in a river’s swirling eddies. For nearly three decades, ecologists considered chaos in the living world to be surprisingly rare by comparison. A new analysis, however, reveals that chaos is far more prevalent in ecosystems than researchers thought.” Quanta’s Joanna Thompson describes recent research that reveals a greater role for chaotic systems in living things than previously understood.
  • “Cloud computing isn’t going anywhere, but some companies that use machine learning models and the tech vendors supplying the platforms to manage them say machine learning is having an on-premises moment. For many years, cloud providers have argued that the computing requirements for machine learning would be far too expensive and cumbersome to start up on their own, but the field is maturing.” Protocol’s Kate Kaye explains why some enterprises are taking a step back from cloud computing for machine learning applications.
  • “Recognizing that few people actually read statistical tables, Nightingale and her team designed graphics to attract attention and engage readers in ways that other media could not….Nightingale packaged her charts in attractive slim folios, integrating diagrams with witty prose. Her charts were accessible and punchy. Instead of building complex arguments that required heavy work from the audience, she focused her narrative lens on specific claims. It was more than data visualization—it was data storytelling.” A fascinating article by RJ Andrews at Scientific American traces Florence Nightingale’s foundational contributions to modern data visualization.
  • “Over the last decade, tech companies and education reformers have pushed schools to adopt software systems that can catalog and categorize students’ classroom outbursts, absenteeism and learning challenges. The intent of such tools is well meaning: to help educators identify and intervene with at-risk students. As these student-tracking systems have spread, however, so have cyberattacks on school software vendors…” An article by the New York Times’ Natasha Singer explores how recent adoption of a multitude of educational software may be exposing students to the consequences of cyberattacks.
  • MIT Technology Review’s Melissa Heikkilä reports that after a remarkable run of success in predicting protein structures, DeepMind’s AlphaFold is releasing its enormous library of hundreds of millions of proteins, free to all comers.

BASIC SCIENCE, CLINICAL RESEARCH & PUBLIC HEALTH

Mat Napo/Unsplash
  • “Unless the capacity of emergency departments and their hospitals is expanded, the number of patients being cared for in ED hallways (known as boarders) and in hospital ward hallways (the relatively new practice of ED boarders initially being cared for in beds lining the hallways of in-patient units) will inevitably grow. Hovering over this practice is a body of high-quality research that demonstrates that the care hallway patients receive is subpar.” An article in STAT News by Stephen Bohan traces a growing crisis in the availability of resources and capacity for emergency medicine.
  • “For many other cancers, researchers have been successful in seeing overall declines in incidence and mortality rates as well as in reducing the gap between Black and white patient outcomes, said Nichols. Yet she said these improvements have not occurred with endometrial cancer primarily because it’s been underfunded and understudied.” North Carolina Health News’ Rachel Crumpler examines the persistent disparities in uterine cancer affecting Black women in North Carolina.
  • “Having evidence-based health care interventions languish without being adopted is neither unusual or new. The field of implementation science has emerged to help rectify that problem….Scientific evidence, no matter how voluminous or solid, is not enough to translate research into practice. That’s where implementation science comes in.” A perspective in STAT News by Mark S. Bauer explains why simply accruing medical evidence is not itself enough to change medical practice.
  • “A leading independent image analyst and several top Alzheimer’s researchers—including George Perry of the University of Texas, San Antonio, and John Forsayeth of the University of California, San Francisco (UCSF)—reviewed most of Schrag’s findings at Science’s request. They concurred with his overall conclusions, which cast doubt on hundreds of images, including more than 70 in Lesné’s papers. Some look like “shockingly blatant” examples of image tampering, says Donna Wilcock, an Alzheimer’s expert at the University of Kentucky.” A stunning report by Science’s Charles Piller documents the work of data sleuths who may have uncovered a massively consequential episode of academic fraud at the foundations of 15 years’ worth of research into beta amyloid as a therapeutic target in Alzheimer disease. In tangentially related news, Reuters reports that Cassava Sciences is facing a criminal investigation into allegations of scientific fraud related to one of its Alzheimer candidate drugs.
  • “Brutal heat waves are quickly becoming the hallmark of the summer of 2022….And even as climate change continues to crank up the temperature, scientists are working fast to understand the limits of humans’ resilience to heat extremes. Recent research suggests that heat stress tolerance in people may be lower than previously thought. If true, millions more people could be at risk of succumbing to dangerous temperatures sooner than expected.” At Science News, Carolyn Gramling examines recent studies that suggest humans may be at higher risk from extreme heat than had been assumed.
  • “We found little to no evidence for a causal connection between game play and well-being. However, results suggested that motivations play a role in players’ well-being. For good or ill, the average effects of time spent playing video games on players’ well-being are probably very small, and further industry data are required to determine potential risks and supportive factors to health.” Good news (maybe?) for gamers: a recent study by Vuorre and colleagues, published in Royal Society Open Science, finds negligible evidence for a causal relationship between the amount of time spent playing video games and mental well-being.
  • “We show the earliest known COVID-19 cases from December 2019, including those without reported direct links, were geographically centered on [the Huanan Seafood Wholesale Market in Wuhan, China] …While there is insufficient evidence to define upstream events, and exact circumstances remain obscure, our analyses indicate that the emergence of SARS-CoV-2 occurred via the live wildlife trade in China, and show that the Huanan market was the epicenter of the COVID-19 pandemic.” A paper published this Tuesday in Science by Worobey and colleagues helps narrow down the possible jumping-off point for the COVID pandemic.

COMMUNICATION, Health Equity & Policy

Marvin Meyer/Unsplash
  • “The bottom line is that, surprisingly, digital literacy may not be a key factor for predicting who spreads misinformation on social media. No one is immune from the potential to spread misinformation—so be sure to stop and ask yourself whether the news you see is accurate before you click ‘share.’” At Scientific American, David Rand and Nathaniel Sirlin explain why the idea that people fall for online misinformation due to a lack of digital savvy is at best simplistic, and in many cases flatly wrong.
  • “…the current studies highlight the value of collecting large-scale data on social capital. Although some forms of capital, such as gross domestic product, are now routinely collected by governments and reported annually, measurement of other forms of capital — such as human11 and social capital — is still much too infrequent. As Chetty and colleagues’ work makes clear, it is worth making the same effort for social capital.” An editorial in Nature by Angrist and Sacerdote introduces new research (a pair of papers by Chetty and colleagues) that explore the role that “social capital” plays in a person’s economic outcomes.
  • “Hospitals are in a unique position to directly address challenges faced by their sociodemographically complex patients. Many hospitals, particularly those with advanced financial risk-sharing arrangements, are investing in efforts to address SDOH, although the level of investments and nature of interventions vary. Examples of population-level interventions include data analytic technologies to identify high-risk patient populations, screening programs connecting patients with community resources, and transition of care and community care management programs, including community economic development.” An article in Health Affairs by Senathirajah and colleagues makes a case for a “social needs index” that could help hospitals provide better, more equitable care for all of their patients.