Defaults Are Not the Same by Default

Disney World is the land of magic and fairy tales, but even there you cannot escape science.

When ordering something to eat, one of us (Jon) noticed that the default choices in kids’ meals were all geared toward healthier options. (When you research decision-making for a living, it’s hard not to observe choice architecture everywhere, even on vacation.)

The menu swapped soda for juice and french fries for fruits and vegetables. Indeed, a recent study shows that this change in Disney World’s policy lead to the consumption of 21 percent less calories, 44 percent less fat, and 43 percent less sodium. These defaults are helping “the happiest place on Earth” become a healthier one.

Defaults are one of applied behavioral science’s biggest success stories. There are two reasons underlying their widespread adoption: first, defaults can be very simple, even consisting of just the one-word difference between, “If you want to be an organ donor, please check here,” (opt-in) and, “If you don’t want to be an organ donor, please check here” (opt-out). Second, defaults are surprisingly effective in a variety of contexts, in retirement planning decisions, health decisions, as well as consumer decisions.

Despite, or perhaps because of, the widespread use and success of defaults, a few important questions have remained in the background: How have defaults been implemented? Does it matter how they are implemented?

Knowing when and why defaults work highlights the importance of actively, rather than passively, considering and applying choice-architecture tools.

There are many ways researchers, policymakers, and other practitioners have attempted to use defaults. As alluded to above, defaults can be implemented in a variety of domains, such as in consumer settings (CFL versus incandescent lightbulbs) or health domains (organ donations). Defaults can also vary in how easy it is to opt out, ranging from a click on a website to requesting several forms under Austria’s organ donation law.

The second question revolves around how to see the effectiveness and widespread adoption of defaults in context: defaults are only one of many tools available in a choice architects toolbox. For example, while citizens could be defaulted into health insurance plans, they could also be asked to select their health insurance plan from a smaller, curated set. Similarly, employees could be defaulted into retirement savings plans when joining a company, or, alternatively, they could be given a limited time window in which to sign up. Policymakers thus have an array of options to choose from, beyond defaults, when determining how to use choice architecture to attain desired outcomes.

What matters, then, is understanding how effective defaults are as a choice architecture tool, as well as how different kinds of implementations alter a default’s effectiveness. This was the aim of a meta-analysis of all prior default studies, which we recently published in Behavioural Public Policy. Meta-analysis helps provide a summary statistic that reflects how strong a default is, on average, in prior work. Because there is variation in the effectiveness of defaults across different studies, we can exploit this variation to help us understand when defaults are more likely to be effective.

In total, we found 58 default studies with a total sample size of 73,675 participants. The studies came from a wide variety of contexts, topics, fields, and countries. One thing became apparent in our analysis: on average, defaults are a strong choice architecture tool, shifting decisions by 0.63 to 0.68 standard deviations. What this means is that in decisions where there are two possible options, the option that is preselected is on average chosen 27 percent more often than the option that is not preselected. That means that the average default study was about two times more effective in changing behaviors as other strong behavioral interventions that shift decisions by 0.2 to 0.3 standard deviations—one of them being, for example, Opower’s social norm intervention on energy savings, another widely popular choice architecture tool. So, on the one hand, defaults work!

On the other hand, there were also substantial differences in the effectiveness of defaults. In some studies, a default was far more effective than in other studies; and in others yet, defaults did not alter participants’ decisions. This is an important caveat, which highlights that choice architects should not blindly apply defaults to all situations, but instead be more careful in when and how they implement defaults.

We wondered what factors make defaults particularly more likely to be effective. To do so, we drew on a theoretical framework which highlights that defaults operate through three channels: first, defaults work because they reflect an implicit endorsement from the choice architect—your company’s HR department, your city’s policy office, your credit card company, your child’s school. Second, defaults work because staying with the defaulted choice is easier than switching away from it. Third, defaults work because they endowdecision makers with an option, meaning they’re less likely to want to give it up, now that it’s theirs. As a result, we hypothesized that default designs that trigger more of these channels (also called the three Es: endorsement, ease, and endowment) would be more effective.

In our analysis, we find partial support for this idea. That is, we find that studies that were designed to trigger endorsement (defaults that are seen as conveying what the choice architect thinks the decision maker should do) or endowment (defaults that are seen as reflecting the status quo) were more likely to be effective.

In addition, we find that defaults in consumer domains tend to be more effective, and that defaults in pro-environmental domains (such as green energy defaults) tend to be less effective. What this highlights is that the intensity and the distribution of decision makers’ underlying preferences—what it is that they care about and want—plays an important role in how effective defaults are. When decision makers care less about a particular choice, a default may be more persuasive in swaying their decision. Likewise, when preferences within a population are more varied, such that some people may have preferences that align with the default, but many people may not, then a default may be less effective.

When decision makers care less about a particular choice, a default may be more persuasive in swaying their decision.

One domain that people tend to care about deeply —and which tends to be divisive—is their environmental attitudes. As a result, someone who holds more pro-environmental attitudes may be more likely to stick with a default that offsets the carbon emissions arising from their flight, while someone who holds anti-environmentalism attitudes may be more likely to switch away from the default. In addition, environmental attitudes tend to vary broadly throughout the population, as research on the acknowledgement of human-caused climate change, or lack thereof, shows. As a result, both the strong intensity with which people hold environmental attitudes and their broad distribution in the population make it less likely that defaults will be effective.

In contrast, a domain that people tend to care less deeply about—and which tends to be less divisive—is which search engine they use. While there are many search engines available,  like DuckDuckGo or Qwant, more than 75 percent of searchers currently go through Google. This metric is accounted for in part because Google is the default search engine on a number of browsers, including the company-owned Chrome, but also Firefox and Safari—a default setting that prompted Google to pay Mozilla and Apple billions of dollars last year. Because people don’t care very deeply about which search engine they use, a default setting is likely to be more effective.

To help understand how to best design defaults, using the three Es and taking into account intensity and distribution of preferences, we put together a checklist of questions that policymakers and other practitioners could ask themselves during the next choice-architecture design meeting. We note that these questions are not exhaustive but highlight specific aspects to pay attention to when designing defaults.

Our research exploring when and why defaults work highlights the importance of actively, rather than passively, considering and applying choice-architecture tools. It also shows the benefits of understanding how they work. Such ideas may help us predict how well a default could operate in a given setting and figure out how to design defaults that work better. In addition, defaults may not always be the most effective solution. They represent just one of many tools in the choice architect’s toolbox. To better explore when defaults should be used over other tools, choice architects should also evaluate the effectiveness of defaults versus other possible interventions.

When introducing defaults into complex real-world environments, choice architects thus need to be mindful that defaults are not the same by default.

Defaults Are Not the Same by Default

Rite Aid Touts ‘Transparent’ PBM Amid Industry Turmoil

Rite Aid’s pharmacy benefit manager is beating some expectations as a steady growth engine for the embattled drug store chain during a period of consolidation and scrutiny on drug pricing.

In the wake of Rite Aid’s plummeting stock price, executive suite shakeupand two failed mergers, the growth of the PBM EnvisionRxOptions is eclipsing some goals during a turbulent time for the industry. The PBM could help Rite Aid become an attractive buyout target.

Rite Aid executives are stressing its PBM business model as the Trump administration and Congress intensify their focus on the PBM’s role as a middleman between drug makers and consumers and its share of rebates — the portion of the drug returned by the seller to the buyer.

“The transparent PBM model is an important option right now, and no organization has more experience with it than Envision,” EnvisionRx CEO Ben Bulkley, who joined Rite Aid earlier this year, told analysts on a call last week to discuss fiscal fourth quarter earnings.

The growth of Rite Aid’s PBM has triggered speculation that EnvisionRx could be key to the drugstore chain’s future if the company tries to find another merger partner. Rite Aid’s board is amid a search for a new CEO to replace John Standley who is leaving once his successor is named, the company said a month ago.

Some investors who opposed Rite Aid’s failed merger with the grocer Albertsons have thought EnvisionRx was undervalued and would like to see the PBM sold to boost Rite Aid’s beleaguered stock price, which is now hovering around 50 cents a share.

Rite Aid didn’t begin to instill optimism among investors generally after the company said last week ongoing prescription reimbursement pressures helped contribute to a $255.6 million loss from continuing operations in the period ended March 2. Fourth quarter revenues were largely flat at $5.38 billion compared to $5.39 billion in the year-ago quarter.

But Envision CEO Bulkley said the quarter results included a “$4.5 million increase in adjusted EBITDA primarily driven by continued growth in Medicare Part D enrollment.” Bulkley said Rite Aid’s Medicare part D drug plan business now has “roughly 635,000 enrolled” for 2019. “In terms of open enrollment for the planned year 2019, we added 95,000 new lives,” the PBM’s top executive said.

“We expect Med D membership to grow over 10% for the planned year 2019,” Bulkley said. “The strategic decisions over the last few years are beginning to pay off. Most notably our number of chooser members in our plans has increased from 77,000 in calendar 2016 to 352,000 today.”Bulkley also said Envision has added new commercial clients that will add more than 220,000 lives to its PBM business for 2020.

Rite Aid’s PBM is much smaller than UnitedHealth Group’s OptumRx, Cigna’s Express Scripts PBM and CVS Health’s Caremark PBM but some believe there will be more consolidation as bigger players are forced to grow by acquisition given new rules could limit other revenue growth.

“Envision is well positioned to take advantage of the consolidation that is occurring in the marketplace,” Bulkley told analysts last week. “In addition, we’re also excited about how Envision can play a key role in defining an integrated value proposition for payers as Rite Aid positions its unique assets to drive the greatest value to the enterprise.”

https://www.forbes.com/sites/brucejapsen/2019/04/15/rite-aid-touts-transparent-pbm-amid-industry-turmoil-and-consolidation/#3b280dc66ebc

Liver disease strikes Latinos like 'silent tsunami'

About 1 in 4 people in the U.S. have fatty liver disease. But among Latinos, especially of Mexican and Central American descent, the rate is significantly higher.

---

KEY TAKEAWAYS

More than half of the 2016 deaths attributed to fatty liver disease were among Latinos — nearly double their proportion of total deaths in Los Angeles County.
A variant of a gene called PNPLA3 significantly increased the risk of the disease. About half of Latinos have one copy of that high-risk gene, and a quarter have two copies.

Saira Diaz uses her fingers to count the establishments selling fast food and sweets near the South Los Angeles home she shares with her parents and 13-year-old son. "There's one, two, three, four, five fast-food restaurants," she says. "And a little mom and pop store that sells snacks and sodas and candy."
In that low-income, predominantly Latino neighborhood, it's pretty hard for a kid to avoid sugar. Last year, doctors at St. John's Well Child and Family Center, a nonprofit community clinic seven blocks away, became alarmed by the rising weight of Diaz's son, Adrian Mejia. They persuaded him to join an intervention study run by the University of Southern California and Children's Hospital Los Angeles (CHLA) that weans participants off sugar in an effort to reduce the rate of obesity and diabetes among children.

 

It also targets a third condition fewer people have heard of: fatty liver disease.
Linked both to genetics and diets high in sugar and fat, "fatty liver disease is ripping through the Latino community like a silent tsunami and especially affecting children," said Dr. Rohit Kohli, chief of gastroenterology, hepatology and nutrition at CHLA.
Recent research shows about 1 in 4 people in the U.S. have fatty liver disease. But among Latinos, especially of Mexican and Central American descent, the rate is significantly higher. One large study in Dallas found that 45% of Latinos had fatty livers.

 

The illness, diagnosed when more than 5% of the liver's weight is fat, does not cause serious problems in most people. But it can progress to a more severe condition called nonalcoholic steatohepatitis, or NASH, which is linked to cirrhosis, liver cancer and liver failure. This progressive form of fatty liver disease is the fastest-growing cause of liver transplants in young adults.
The USC-CHLA study is led by Michael Goran, director of the Diabetes and Obesity Program at CHLA, who last year made an alarming discovery: Sugar from sweetened beverages can be passed in breast milk from mothers to their babies, potentially predisposing infants to obesity and fatty livers.
Called HEROES, for Healthy Eating Through Reduction of Excess Sugar, his program is designed to help children like Adrian, who used to drink four or more sugary drinks a day, shed unhealthy habits that can lead to fatty liver and other diseases.
Fatty liver disease is gaining more attention in the medical community as lawmakers ratchet up pressure to discourage the consumption of sugar-laden drinks. Legislators in Sacramento are mulling proposals to impose a statewide soda tax, put warning labels on sugary drinks and bar beverage companies from offering discount coupons on sweetened drinks.
"I support sugar taxes and warning labels as a way to discourage consumption, but I don't think that alone will do the trick," Goran said. "We also need public health strategies that limit marketing of sugary beverages, snacks and cereals to infants and children."
William Dermody, a spokesman for the American Beverage Association said: "We understand that we have a role to play in helping Americans manage consumption of added sugars, which is why we are creating more drinks with less or no sugar."
In 2016, 45 deaths in Los Angeles County were attributed to fatty liver disease. But that's a "gross underestimate," because by the time people with the illness die, they often have cirrhosis, and that's what appears on the death certificate, said Dr. Paul Simon, chief science officer at the L.A. County Department of Public Health.
Still, Simon said, it was striking that 53% of the 2016 deaths attributed to fatty liver disease were among Latinos — nearly double their proportion of total deaths in the county.
Medical researchers consider fatty liver disease a manifestation of something called metabolic syndrome — a cluster of conditions that include excess belly fat and elevated blood pressure, blood sugar and cholesterol that can increase the risk of heart disease, stroke and diabetes.
Until 2006, few doctors knew that children could get fatty liver disease. That year Dr. Jeffrey Schwimmer, a professor of pediatrics at the University of California-San Diego, reviewed the autopsies of 742 children and teenagers, ages 2 to 19, who had died in car crashes or from other causes, and he found that 13% of them had fatty liver disease. Among obese kids, 38% had fatty livers.
After Schwimmer's study was released, Goran began using MRIs to diagnose fatty liver in living children.
A 2008 study by another group of researchers nudged Goran further. It showed that a variant of a gene called PNPLA3 significantly increased the risk of the disease. About half of Latinos have one copy of that high-risk gene, and a quarter have two copies, according to Goran.
He began a new study, which showed that among children as young as 8, those who had two copies of the risky gene and consumed high amounts of sugar had three times as much fat in their livers as kids with no copy of the gene. Now, in the USC-CHLA study, he is testing whether reduced consumption of sugar decreases the fatty liver risk in children who have the PNPLA3 gene variant.
At the start of the study, he tests kids to see if they have the PNPLA3 gene, uses an MRI to measure their liver fat and catalogs their sugar intake. A dietitian on his team educates the family about the impact of sugar. Then, after four months, they measure liver fat again to assess the impact of the intervention. Goran expects to have results from the study in about a year.
More recently, Goran has been investigating the transmission of sugar from mothers to their babies. He showed last yearthat in nursing mothers who drank beverages sweetened with high-fructose corn syrup — the primary sweetener in standard formulations of Coca-Cola, Pepsi and other sodas — the fructose level in their breast milk rose and stayed elevated for several hours, ensuring that the baby ingested it.
This early exposure to sugar could be contributing to obesity, diabetes and fatty livers, based on previous research that showed fructose can enhance the fat storage capacity of cells, Goran said.
At Torrance Memorial Medical Center, Dr. Karl Fukunaga meets with a patient, Margarita Marrou, a retired medical clerk originally from Peru. She was diagnosed several years ago with a severe form of fatty liver disease and has cut down her sugar consumption and lost weight. (Rob Waters for KHN)
In neighborhoods like South Los Angeles, where Saira Diaz and Adrian Mejia live, a lack of full-service markets and fresh produce makes it harder to eat healthily. "Access to unhealthy food options — which are usually cheaper — is very high in this city," Derek Steele, director of health equity programs at the Social Justice Learning Institute in Inglewood, Calif., told Kaiser Health News.
The institute has started farmers markets, helped convert two corner stores into markets with healthier food options and created 109 community gardens on public and private lands in South L.A. and neighboring Inglewood, which has 125 liquor and convenience stores and 150 fast-food outlets.
At Torrance Memorial Medical Center, 10 miles down the road, Dr. Karl Fukunaga, a gastroenterologist with Digestive Care Consultants, said he and his colleagues are seeing so many patients with fatty liver disease that they plan to start a clinic to address it. He urges his patients to avoid sugar and cut down on carbohydrates.
Adrian Mejia and his mother received similar advice from a dietitian in the HEROES program. Adrian gave up sugary beverages, and his liver fat dropped 43%. Two months ago, he joined a soccer league.
"Before, I weighed a lot and it was hard to run," he said. "If I kept going at the pace I was going, probably later in my life I would be like my [diabetic] grandma. I don't want that to happen."
https://www.healthleadersmedia.com/clinical-care/liver-illness-strikes-latino-children-silent-tsunami

Why Hospitals Should Fear Blue Cross Primary Care Centers

As if hospitals and health systems didn’t have enough emerging threats with big well capitalized publicly-traded insurance companies and drugstore chains developing primary care clinics and urgent care centers in their backyards.

Now come the nation’s largest Blue Cross and Blue Shield plans that dominate big diverse markets like Florida, Illinois, Texas and New Jersey. These Blues plans are backed by their own financing, venture capital funds and primary care partners looking to expand doctor offices, urgent care and health centers in communities across the country.

The latest such venture is bankrolled by primary care provider Sanitas USAand the venture capital arm of Health Care Service Corp., which owns Blue Cross and Blue Shield plans in Illinois, Montana, New Mexico, Oklahoma and Texas where the Texas Blues plan is opening up 10 centers.

Sanitas already has an established primary care partnership to open Sanitas centers in several Florida markets with Blue Cross and Blue Shield of Florida, the state’s largest health insurer, and Horizon Blue Cross Blue Shield of New Jersey where centers are expanding.

Florida Blue executives say the now four-year-old partnership with Sanitashas shown to reduce the need for more expensive hospital care by improving healthcare quality and health outcomes of thousands of health plan enrollees. Its success is a key reason more Blue Cross plans are adopting the model, executives close to the plans say.

“The unique care model, with its comprehensive set of services and culturally tailored patient experience, has positively affected member service and lowered medical care costs,” Florida Blue spokesman Paul Kluding said.

Patients managed in the Sanitas clinics had 32% lower inpatient admissions and 20% lower emergency room visits “compared to similar groups” of Florida Blue members, the insurer said, citing 2018 data. Florida Blue, which opened its 23^rd Sanitas Center in Orlando earlier this month, is now serving 200,000 health plan enrollees primarily in south Florida and the Orlando market. The first such center opened in 2015 less than a year after Florida Blue’s parent, Guidewell, first partnered with Organizacion Sanitas Internacional to create a new company.

The closer ties between Blues plans and medical care providers comes as CVS Health, the operator of thousands of retail pharmacies and retail health clinics, is preparing to roll out new primary care models following its acquisition of Aetna. And UnitedHealth Group, the nation’s largest health insurer, has been expanding primary care operations through its Optum health services unit, that includes doctor practices and MedExpress urgent care centers across the country in dozens of markets across the U.S.

Health insurers are moving away from fee-for-service medicine to value-based models that pay medical care providers based on quality of care and health outcomes of patients. If providers and insurers are even more integrated, supporters of such arrangements believe quality and costs can be more closely monitored.

Health Care Service’s Texas Blues plan subsidiary is partnering with SanitasUSA to initially open 10 primary care centers in the Dallas and Houston markets. The centers will be owned via a joint venture of Sanitas and HCSC Ventures, which is a part of Health Care Services Corp.

The medical centers include urgent care, lab and diagnostic imaging services, wellness and disease management and some of them are open 365 days a year to give patients less reason to go to a hospital emergency room.

Those involved won’t disclose how much money they plan to spend on the Sanitas centers in Texas, but said they will be looking to expand in the four other states where Health Care Service operates Blues plans. Combined, the plans cover nearly 17 million health plan members and Blue Cross want them to have more options for quality low-cost medical care so the market potential is large.

“We are excited to begin our journey with Blue Cross and Blue Shield of Texas and look forward to working closely together to bring more value to their members and communities,” Joseba Grajales, president of Keralty Group, the parent company of Sanitas USA said in announcing the partnership with Health Care Service and the Texas Blues earlier this month. “Our approach to care is centered on our patients and their families, giving them more time with the doctor and the convenience of a one-stop medical center for their everyday health care needs. Our expansion to Texas will continue to build on our success in Florida, New Jersey and Connecticut, serving more than 200,000 patients in diverse communities.”

Elsewhere, Blue Cross and Blue Shield plans are investing in other value-based initiatives with primary care providers to ensure care is delivered in the right place, in the right amount and at the right time.

Four months ago, Blue Cross and Blue Shield of North Carolina and Aledade, which helps doctors run their practices, launched a venture designed to support independently owned and operated primary care clinics to form accountable care organizations (ACOs), a proliferating value-based care model that contracts with health insurers to improve quality, lower costs and allows the providers involved to keep any money saved from year to year based on the arrangement with the health plan.

“Primary care physicians influence a vast majority of health care spending, and their role in this transformation is critical,” Blue Cross NC CEO Dr. Patrick Conway said in announcing the partnership. “We want to provide primary care physicians across North Carolina the tools they need to be best-in-class and succeed in a remodeled health care system built on the foundation of value-based, patient-centered care.”

https://www.forbes.com/sites/brucejapsen/2019/04/18/why-hospitals-should-fear-blue-cross-primary-care-centers/#23ab9ed83ceb

More Americans under the age of 40 are having heart attacks

Days after Luke Perry’s death at 52 from a stroke, a new study on heart-attack rates has another grim reminder that the young are far from invincible — and maybe even more vulnerable than they used to be.

Heart-attack rates are rising for adults under age 40, researchers found after comparing data of heart attack survivors ages 41 to 50 with those survivors who were 40 and younger.

The youngest patients were more likely to use marijuana and cocaine compared to slightly older counterparts, even if they drank less alcohol.

In fact, the proportion of heart-attack patients under age 40 has been climbing 2% every year for the last 10 years, according to findings presented at the American College of Cardiology’s annual scientific session last month.

The researchers tried to unearth the risk factors explaining the rise and said substance abuse might share part of the blame. The youngest patients were more likely to use marijuana and cocaine compared to slightly older counterparts, even if they drank less alcohol.

“It seems that we are moving in the wrong direction,” said Dr. Ron Blankstein, a Harvard Medical School professor and a preventive cardiologist at Brigham and Women’s Hospital.

It was once “incredibly rare” to see heart attack patients under age 40, Blankstein noted. But some heart patients coming into emergency rooms now were in their 20s and early 30s, he said. He examined patient treatment information for over 2,000 people hospitalized from 2006 to 2016.

Although some heart attack patients were younger, they had the same risks of subsequent death from a repeat heart attack or stroke as patients in their 40s.

It was once ‘incredibly rare’ to see heart attack patients under age 40, but some heart patients coming into emergency rooms now were in their 20s and early 30s.

—Ron Blankstein, a Harvard Medical School professor

About 735,000 Americans suffer heart attacks every year, according to the Centers for Disease Control and Prevention. Over 600,000 people die annually from heart disease, which encompasses heart attacks plus several other types of conditions. It’s America’s leading cause of death.

There’s evidence stroke rates are climbing for younger Americans though strokes often target older individuals, according to Dr. Mitchell S.V. Elkind, chair of the American Stroke Association Advisory Committee. Strokes like the one that killed Luke Perry take the lives of 140,000 people annually in America.

The authors of the current findings said fewer heart attacks are happening in America, thanks to statins and less smoking, and that’s in spite of the country’s obesity epidemic. Nevertheless, the upward trend for the younger demographics was troubling.

“It all comes back to prevention,” Blankstein said. “Many people think that a heart attack is destined to happen, but the vast majority could be prevented with earlier detection of the disease and aggressive lifestyle changes and management of other risk factors.”

He advised a good diet, exercise, avoiding tobacco and swearing off “cocaine and marijuana because they’re not necessarily good for your heart.”

https://www.marketwatch.com/story/heart-attack-risks-for-americans-under-the-age-of-40-2019-03-07?siteid=rss&rss=1

Crowdsourced AI learns to target lung tumors for radiation

In many parts of the world there are not enough radiation oncologists to design and deliver radiation treatments for lung cancer patients, but that gap could one day be filled with the help of artificial intelligence, researchers suggest in a new study.

In a novel approach to the problem, the authors turned to crowdsourcing to help them develop a computer algorithm that would take over some of the duties of an experienced radiation oncologist.

“Lung cancer is a major global health problem,” said the study’s lead author, Dr. Raymond Mak, an associate professor of radiation oncology at Harvard Medical School, the Dana Farber Institute and Brigham and Women’s Hospital in Boston. “It’s the number one cancer killer in the world. Close to a million patients will need radiation therapy at some point.”

Currently, radiation oncologists determine where to send the beams of radiation by drawing the outlines of the tumor and surrounding organs. The first step is to do a CT scan of the patient’s tumor and surrounding tissues. The scan will produce multiple cross-sectional images, or “slices,” which together effectively yield a 3D image.

“You take your medical imaging – there can be 100 images that are slices through the tumor – and hand-draw on each slice where the tumor is,” Mak explained. “Then you draw in where the organs are. And then you determine how to aim the radiation.”

That prep can take hours, Mak said. “It’s very time consuming,” he added. “And there’s lots of variation even between experts. When you miss and the radiation doesn’t go to the right place it can directly impact patient care.”

When you look at the issue from a global perspective, there’s also the problem of lack of access, Mak said. Many places do not have enough specialists to draw the tumors accurately.

To determine whether artificial intelligence could fill the void, Mak and his colleagues set up a contest on a website called Topcoder.com that hosts challenges for a community of more than a million programmers around the world, who compete for prizes by solving computational problems.

In this case, the researchers had $50,000 in prize money to offer coders who could come up with “new AI techniques that could train machines to replicate an expert clinician’s ability to target a tumor,” Mak said.

A total of 564 contestants from 62 countries registered for the challenge, which was to design a program that would allow a computer to look at multiple expert-drawn tumors and thereby learn to draw itself.

In the end, 10 independent winning algorithms, filed by 9 participants, were chosen. Then the top five algorithms were combined into one “ensemble” program, which did fairly well when put up against the work of actual radiation oncologists.

“We compared the performance of the algorithms, that is, compared algorithm-generated (drawings) versus the human expert to generate a performance score on each case, and then benchmarked against the variation seen between multiple human experts against the study’s expert, and also the intra-observer variation, that is the same expert doing the same task twice,” Mak said. “The ensemble of the best algorithms had overlap scores in 75 percent of the cases that matched intra-observer score.”

The new approach may help fill the global shortage of radiation oncologists, said Dr. Sushil Beriwal, a professor of radiation oncology and deputy director of radiation services at the Hillman Cancer Center at the University of Pittsburgh Medical Center in Pennsylvania.

“One of the biggest challenges to targeting tumors is the lack of manpower,” said Beriwal, who was not involved in the new research. “The eventual goal is to come out with a product that can be used to help where an expert is not available and to use as a second check (of the radiation oncologist’s own work).”

In the final iteration of the project, “they were very close to the variation you would expect between physicians,” Beriwal said.

Dr. Nicholas Sanfilippo welcomed the new research. “It’s an exciting new technology,” said Sanfilippo, a radiation oncologist at NewYork-Presbyterian/Weill Cornell Medical Center in New York City, who also wasn’t involved in the study. “As clinicians we should look to making it complement the care of the physician, especially in underserved areas.”

SOURCE: bit.ly/2VNQrWF and bit.ly/2UrxRSy JAMA Oncology, online April 18, 2019.

https://www.reuters.com/article/us-health-radiotherapy-crowdsource-ai/crowdsourced-ai-learns-to-target-lung-tumors-for-radiation-idUSKCN1RU2H5

Mental health apps are sharing data without proper disclosure

It’s important for health apps to keep your data under lock and key, but it’s not clear that’s the case for some mental health apps. A study of 36 mental health apps (not named in the public release) has revealed that 29 of them were sharing data for advertising or analytics to Facebook or Google, but many of them weren’t disclosing that to users. Only six out of 12 Facebook-linked apps told users what was happening, while 12 out of 28 Google-linked apps did the same. Out of the entire bunch, just 25 apps had policies detailing how they used data in any form, while 16 described secondary uses.

A handful of these apps (which revolved around issues like depression and quitting smoking) shared particularly sensitive data like health diaries and voluntary substance use reports. As the University of Toronto’s Qunn Grundy (not involved in the study) told The Verge, this info could give outsiders a picture of your mental health that you might not want to share. You might see ads for health consultations or even addictive substances.

The immediate solution is a familiar one: verify that an app has a privacy policy, and check to see where your data is going before you use the app in earnest. Study co-author John Torous also suggested sticking to apps from more trustworthy sources like health care providers and the government. In the long term, though, there may need to be stricter requirements to ensure that your health information only goes where it’s truly necessary.

https://www.engadget.com/2019/04/20/mental-health-apps-share-data/