Tagged Health Industry

HHS Has Been Quietly Reversing Strides Made In Fostering, Protecting LGBT Heath Care

The LGBT population can be vulnerable to discrimination in health care settings, but the Trump administration says the changes within HHS are part of an approach to include LGBT health as part of its broader strategy. Meanwhile, a top HHS communications official becomes the latest in the administration to move to the Office of National Drug Control Policy.

HHS Has Been Quietly Reversing Strides Made In Fostering, Protecting LGBT Heath Care

The LGBT population can be vulnerable to discrimination in health care settings, but the Trump administration says the changes within HHS are part of an approach to include LGBT health as part of its broader strategy. Meanwhile, a top HHS communications official becomes the latest in the administration to move to the Office of National Drug Control Policy.

Investigation In Aetna’s Approval Process Expands Into More States

The inquiry kicked off after statements by a former medical director came to light that he never looked at patients’ records when deciding whether to approve or deny care. Aetna says the comments were taken out of context. Meanwhile, Anthem is changing its emergency room program after it received pushback from providers and lawmakers.

Investigation In Aetna’s Approval Process Expands Into More States

The inquiry kicked off after statements by a former medical director came to light that he never looked at patients’ records when deciding whether to approve or deny care. Aetna says the comments were taken out of context. Meanwhile, Anthem is changing its emergency room program after it received pushback from providers and lawmakers.

Listen: Got A Sky-High Bill? Don’t Write The Check.

Have you gotten a medical bill that sounds way too expensive or is just downright confusing? Elisabeth Rosenthal, the editor-in-chief of Kaiser Health News, says don’t be intimidated — and don’t just pay that bill. Call, discuss and negotiate, instead.

And if you are up for it, share your bill and your experience with KHN and NPR. On Friday, Rosenthal and NPR Morning Edition Host Steve Inskeep discussed the launch of “Bill Of The Month,” a crowdsourced investigation.

Listen below.

‘Bill Of The Month’: A College Student’s $17,850 Drug Test

This is the debut of a monthly feature from Kaiser Health News and NPR that will dissect and explain real medical bills in order to shed light on U.S. health care prices and to help patients learn how to be more active in managing costs. Do you have a medical bill that you’d like us to see and scrutinize? Submit it here and tell us the story behind it.

In her late 20s and attending college in Texas, Elizabeth Moreno suffered from debilitating back pain caused by a spinal abnormality. “I just could not live with the pain,” she said. “I couldn’t get dressed by myself, I couldn’t walk across my house, let alone to class, and nothing, no drug that had been prescribed to me, even dulled the pain.”

Moreno says she also tried chiropractic medicine and acupuncture, but they didn’t make the pain go away. Finally, a doctor at the student health center referred her to an orthopedic specialist who performed tests and concluded a disc was blocking nerves down her legs and needed to be removed. Moreno’s father, a retired Ohio doctor who had seen many failed back surgeries over his career, agreed it was the best course.

In late 2015, Moreno had the operation in Houston, which she described as “a complete success.” She gave it little thought when the surgical office asked her to leave a urine sample for a drug test.

Then the bill came.

Patient: Elizabeth Moreno, then 28, a student at Texas State University in San Marcos.

Total bill: $17,850 for a urine test in January 2016

Service provider: Sunset Labs LLC of Houston

Medical treatment: Moreno had a disc removed from her back in December 2015. Her surgeon prescribed an opioid painkiller, hydrocodone. At a follow-up office visit in mid-January 2016, the staff asked her to leave a urine sample, which she figured was routine. In March 2017, over a year later, the lab sent her a bill for $17,850 for testing her urine for a slew of drugs, including cocaine, methadone, anti-anxiety drugs and several other drugs she had never heard of.

(Story continues below.)

What gives: Urine drug testing has exploded over the past decade amid alarm over rising opioid overdose deaths. Many doctors who prescribe the pills rely on the urine tests to help reduce drug abuse and keep patients with chronic pain safe. Yet the tests have become a cash cow for a burgeoning testing industry, and critics charge that unneeded and often expensive ones are sometimes ordered for profit rather than patient care. Doctors can decide whether to test patients who take opioids for short periods, such as after an operation. Moreno’s surgeon would not discuss her urine test — why he ordered it and why the sample was tested for so many substances.

Related Story: Pain Hits Long After Surgery When Doctor’s Daughter Is Stunned By $17,850 Urine Test

Three experts contacted by Kaiser Health News questioned the need for such extensive testing and were shocked to hear of the lab’s prices. They said these tests rarely cost more than $200, and typically much less, depending on the complexity and the technology used. Some doctors’ offices use a simple cup test, which can detect several classes of drugs on the spot and could be purchased for about $10. Bills can climb higher when labs run tests to detect the quantity of specific drugs and bill for each one, as the lab did here.

The experts KHN interviewed said that the lab’s prices for individual tests were excessive, such as charging $1,700 to check for amphetamines or $425 to identify phencyclidine, an illegal hallucinogenic drug also known as PCP. They also criticized a charge of $850 for two tests to verify that her urine sample had not been adulterated or tampered with.

Moreno’s insurer, Blue Cross and Blue Shield of Texas, refused to pay any of the bill, arguing that the lab was out-of-network and thus not covered. Had it chipped in, it would have covered the service at $100.92, according to an explanation of benefits the insurance company sent to Moreno.

Sunset Labs says its list prices were “in line” with its competitors in the area. It also said doctors treating pain agree extensive urine testing is “the best course of action” and that a lab “is not in the position” to question tests ordered by a doctor.

Resolution: Fearing damage to his daughter’s credit rating, Moreno’s father, Dr. Paul Davis, paid the lab $5,000 in April 2017 to settle the bill. A retired doctor, he also has filed a formal complaint about the bill with the Texas attorney general’s office, accusing the lab of “price gouging of staggering proportions.” The lab’s attorney said he was not aware of the complaint. A Texas attorney general’s spokesperson confirmed to KHN that the office had received complaints about the lab, but declined further comment.

The takeaway: When a physician asks for a urine or blood sample, always ask what it’s for. Insist that it be sent to a lab in your insurance network.

Source: AG complaint; interviews

Pain Hits After Surgery When A Doctor’s Daughter Is Stunned By $17,850 Urine Test

After Elizabeth Moreno had back surgery in late 2015, her surgeon prescribed an opioid painkiller and a follow-up drug test that seemed routine — until the lab slapped her with a bill for $17,850.

A Houston lab had tested her urine sample for a constellation of legal and illicit drugs, many of which, Moreno said, she had never heard of, let alone taken.

“I was totally confused. I didn’t know how I was going to pay this,” said Moreno, 30, who is finishing a degree in education at Texas State University in San Marcos and is pregnant with twins.

Related: Bill Of The Month: A College Student’s $17,850 Urine Test

Her bill shows that Sunset Labs LLC charged $4,675 to check her urine for a slew of different types of opioids: $2,975 for benzodiazepines, a class of drugs for treating anxiety, and $1,700 more for amphetamines. Tests to detect cocaine, marijuana and phencyclidine, an illegal hallucinogenic drug also known as PCP or angel dust, added $1,275 more.

The lab also billed $850 to test for buprenorphine, a drug used to treat opioid addiction, and tacked on an $850 fee for two tests to verify that nobody had tampered with her urine specimen.

Total bill: $17,850 for lab tests that her insurer, Blue Cross and Blue Shield of Texas, refused to cover, apparently because the lab was not in her insurance network. The insurer sent Moreno an “explanation of benefits” that says it would have valued the work at just $100.92.

Moreno’s father, in a complaint to the Texas attorney general’s office about the bill, identified the Houston surgeon who ordered the costly test as Dr. Stephen Esses. His office told Kaiser Health News the surgeon would have no comment.

Sunset Labs is part of a network of pain clinics and other medical businesses founded by Houston anesthesiologist Phillip C. Phan, according to Texas secretary of state filings and court records. Court records say Phan’s companies also own the facility where Moreno had her operation.

Three experts interviewed by KHN said the lab grossly overcharged; they also doubted the need for the test.

“This just blows my mind,” said Jennifer Bolen, a former federal prosecutor and lab and pain management consultant. “It’s very high and incredibly out of the norm.”

Dan Bowerman, a medical fraud expert, called the lab bill “outrageous” and “unconscionable” and said it should have prompted an investigation.

“Sounds real fishy,” added Charles Root, a veteran industry adviser. He wondered if the lab had “misplaced the decimal point,” because such a test should cost a few hundred dollars, tops.

The lab disagrees.

Sunset’s billings “are in line with the charges of competing out-of-network labs in the geographical area,” lab attorney Justo Mendez said in an emailed statement.

Mendez said pain doctors agree that extensive urine testing is “the best course of action” and that a lab “is not in the position” to question tests ordered by a doctor.

Urine testing for patients with chronic pain has grown explosively over the past decade amid a rising death toll from opioid abuse. Pain doctors say drug testing helps them make sure patients are taking the drugs as prescribed and not mixing them with illegal substances.

Yet the testing boom costs billions of dollars annually and has raised concerns that some labs and doctors run urine tests needlessly — or charge exorbitant rates — to boost profits.

Some insurers have refused to pay, which can leave patients like Moreno threatened with ruinously high bills they had no idea they had incurred.

“Surprise bills larded with unexpected expenses and little explanation inflict sticker shock on vulnerable patients,” said James Quiggle, communications director of the Coalition Against Insurance Fraud, whose members include insurers, consumer groups and government agencies. Quiggle said many “puffed-up bills straddle a fine line between abuse and outright fraud.”

Moreno said her insurance covered the disc removal surgery in December 2015. She said the operation went well and she weaned off the hydrocodone pain pills. To her surprise, on a second return about a month later, the surgeon’s office asked her to leave a urine sample.

“I didn’t think anything of it,” Moreno said of the test. “I said fine, whatever.”

More than a year later, she said, the lab phoned while she was driving and asked her to pay the $17,850 bill. The lab then sent her an invoice, dated March 10, 2017, which states: “[B]ased upon information from your health plan, you owe the amount shown.”

(Story continues below.)

Luckily, her father, Dr. Paul Davis, was visiting her in Texas at the time. Davis, 66, is a retired family practice doctor from Findlay, Ohio.

Davis doubted the need for the test, not to mention what he thought was a sky-high price. He said the University of Findlay, where he helped train physician assistants, gave applicants a basic drug test at a cost of $174, while the local juvenile courts in Ohio paid $10 for a simple drug screen.

Fearing it would ruin his daughter’s credit scores, Davis said, he called Sunset and settled the bill in April 2017 by paying $5,000, which he said he now regrets. The lab sent Moreno a receipt that said it discounted her bill because of “financial need/hardship.”

Asked for comment, Blue Cross spokesman James Campbell said he couldn’t discuss a specific case but noted:

”We are disappointed as well as concerned about transparency whenever [any] member is surprised by an excessive charge for a seemingly routine service or received services that may not have been medically necessary.”

Campbell also said the lab was out-of-network and “we do not control how much they charge for services rendered.” The insurer encourages patients to confirm that all medical care they seek comes from medical providers in the Blue Cross network, he added.

Prices for urine tests can vary widely depending upon complexity and the technology used. Some doctors’ offices use a simple cup test, which can detect several classes of drugs on the spot. These tests rarely cost more than $200, and typically much less.

Bills climb higher when labs check for levels of multiple drugs and bill for each one, a practice insurers argue is seldom medically justified. But even labs sued by insurers alleging wildly excessive testing typically have billed $9,000 or less, court records show. One insurer sued a lab for charging $1,845 for a drug test, for instance.

Davis said Sunset Labs ignored his requests for a full explanation of the charges. In May, he filed a written complaint about the bill with the Texas attorney general’s office that included a copy of the bill and accused the lab of “price gouging of staggering proportions.”

“Young people just starting out, such as my daughter, may not have the ability to pay and this could result in damaged credit ratings or even bankruptcy,” he wrote.

Davis got a letter back from Attorney General Ken Paxton, who said the office would “review the information.” A spokesperson for Paxton told KHN: “We have received complaints about that business, but we can’t comment on anything else.” Sunset attorney Mendez said the lab is “not aware” of any such complaints.

In an interview, Davis also questioned the need for his daughter’s urine test because she received opioids only for a short period and the results would have had no impact on her treatment. In his complaint to the attorney general, Davis said the surgeon told him he ordered the tests because he feared possible retribution from the state medical licensing board for not testing patients who had been prescribed an opioid. The Texas Medical Board doesn’t require urine tests for patients receiving opioids for short-term pain, said spokesman Jarrett Schneider. That’s a “question of independent medical judgment as to whether the physician believes a drug test should be required,” he said.

Bad Reviews

Sunset Labs has an “F” rating with the Houston Better Business Bureau, which on its website posts an August 2017 complaint from a patient charged $16,150 for a urine test.

“This is not covered under my health insurance so I am expected to pay this excessive bill,” the complaint reads.

A second website that publishes government billing numbers of doctors and medical businesses includes a comment section with more than a dozen negative “reviews,” mostly complaints that the lab slammed patients with thousands of dollars in fees their insurers balked at paying.

In a pair of lawsuits filed in 2015, three doctors seeking to quit working at pain clinics operated by Phan accused the facilities of improper billing practices, including unnecessary urine testing. The doctors said they feared losing their medical licenses unless they severed their ties.

In one suit, Drs. Purvi Patel and Lance LaFleur also alleged that the pain clinics “pressured” doctors to overprescribe medical gear and genetic tests to insured patients “regardless of medical necessity.” The case did not go forward because the doctors did not pursue it. Neither doctor would comment.

In the second legal case, pain specialist Dr. Baominh Vinh said he resigned in April 2015 “based on certain questionable business practices … that are inconsistent with my ethical boundaries.” Vinh also alleged urine testing was overused. In a countersuit against Vinh, the pain clinics called his allegations a “falsehood” to justify violation of his employment contract.

The parties settled in March of last year. Terms are confidential, but a lawyer for the pain clinics said Vinh paid money to the company “and not vice versa.”

FDA Head Vows To Tackle High Drug Prices And Drugmakers ‘Gaming The System’

Food and Drug Administration Commissioner Scott Gottlieb said he will do everything “within my lane” to combat high drug prices and that he sees drug companies “gaming the system to try to block competition” in a multitude of ways in the marketplace.

In a wide-ranging interview with Kaiser Health News on Thursday, Gottlieb also said that he wants to speed up the U.S. approval process for generic and “biosimilar” versions of biologic drugs, which are drugs comprised of living organisms, such as plant or animal cells.

“Where we see things that we can address, we’re going to take action,” Gottlieb said, adding that he is most bothered when brand-name companies use tactics to block makers of generics and biosimilars from developing drugs. He deflected questions about whether the FDA approves drugs of questionable value that carry exorbitant prices.

“I think we should have a free market for how products are priced,” Gottlieb said. A free market “provides proper incentives for entrepreneurs who are going to make the big investments needed to innovate. But that system is predicated on a premise that when patents have lapsed you’ll have vigorous competition from generic drugs.”

The FDA, Gottlieb said, worked with the White House on a proposal to bring generics to market faster by ensuring that a 180-day exclusivity period isn’t used by drugmakers to block competition. He said there are “situations where you see deals cut” in which a drugmaker will get the 180-day exclusivity and then be persuaded to sit on it without ever selling the drug — essentially delaying the brand drug from facing generic competition.

Currently, generics makers must buy large quantities of the brand-name product in the U.S. to run their own clinical trials. But the companies that make brand-name medicines, in some cases, are making it very difficult for makers of generics to purchase their drugs, he said.

“They are adopting all kinds of commercial restrictions with specialty pharma distributors and wholesalers” to prevent sales to generic companies, Gottlieb said, adding that not every branded company is using the tactic, but it is “going on across the board.”

To come up with a generic, a drugmaker needs 2,000 to 5,000 doses for testing, Gottlieb said. He said the companies were willing to pay sticker price but are being blocked in other ways.

The FDA is now exploring whether generics makers could buy the drugs they need in the less-expensive European market without having to do additional work to prove the biologics from Europe are the same — even though the American and European versions are often manufactured in the same plants. Gottlieb wants to get rid of such tests, known as “bridging” studies.

“I have lawyers now looking at this,” Gottlieb said. The FDA has been exploring the issue for a couple of months, he said, and he thinks it may be “hard for us to get there without legislation, but we’re not done yet looking at this; we’re still pressing on this.”

Last fall, Gottlieb said that he wanted to “end the shenanigans” that interfere with competition in the marketplace. Since then, the FDA has released a steady stream of action plans and new guidance that tinkers with the drug development system.

“All of these steps are going to have an impact, and I don’t think there’s one silver bullet,” Gottlieb said. “If anyone [thinks] there is one thing you can do with policy intervention that is going to dramatically change drug prices, that’s not true.”

Instead, he said, there are “layers of things that we can do to try to make sure the system is working.”

The agency has been approving drugs at a fast clip: The FDA’s Center for Drug Evaluation and Research approved a record 46 new drugs in 2017, including treatments for sickle cell disease and Batten disease and new cancer therapies. The list doesn’t include landmark gene and cellular therapies and vaccines that are regulated as biologics.

That rate of approvals has raised concerns about the value and quality of drugs being approved. Specifically, criticism of the FDA’s handling of cancer drugs has increased in recent years.

Although some patient advocates want the FDA to approve new drugs more quickly, others charge that the agency greenlights mediocre cancer drugs that do little to prolong survival or improve quality of life. A 2014 study found that the cancer drugs approved from 2002 to 2014 extended survival by an average of just 2.1 months. For many cancer drugs, there is no evidence showing they prolong life.

Once drugs are on the market, companies can charge whatever the market will bear; prices for cancer therapies now routinely top $100,000 a year.

But Gottlieb said it’s not his job to help insurance companies or government programs decide which drugs to cover. Health systems and insurers “have a difficult time saying no,” Gottlieb said, “so they want to put the regulator in the position of saying no.”

Gottlieb acknowledged that it can be difficult for insurance plans to decide which drugs they should include on their drug list. But insurance plans “ought to have the confidence to make [such decisions] and not say, ‘Well, it’s the job of the federal government to make those decisions for us.’”

Gottlieb defended his agency’s approval of drugs that help the average cancer patient live just two or three extra months, noting that some patients do much better than average on cancer drugs — perhaps living months or even years longer than expected. He also said it would be wrong to make cancer patients wait years to try a drug that has a chance to help them.

“We’re ultimately going to learn why some patients respond really well and some don’t,” he said. If you “try to have all that information upfront when you approve a drug, [you’ll] end up having a development process that is very long and very costly and a lot fewer products will be developed.”

Gottlieb maintains that the FDA sets a high standard for approving drugs.

“It is important that we have a rigorous bar” for approval, he said, “but a bar that doesn’t impede these products from coming to the market.”

Surge Of Babies Born Addicted To Opioids Has Outpaced Science Of How To Treat Them

Hospitals around the United States are taking a scattershot approach to treating the tremors, hard-to-soothe crying, diarrhea, and other hallmark symptoms of newborn abstinence syndrome. In other news: a medication-assisted treatment program in Rhode Island jails shows success; public health advocates are concerned with the pick for “drug czar”; the surgeon general has advice about supporting long-time recovery in those battling addiction; senators want information on if new opioid rules are working; and more.

Colorado Joins Inquiry Into Aetna’s Approval Practices Following Former Medical Director’s Testimony

Dr. Jay Iinuma admitted under oath he never looked at patients’ records when deciding whether to approve or deny care. Instead, he relied on nurses employed by Aetna to review the medical records and feed him pertinent information. California regulators have also launched an investigation into the company’s practices.

Colorado Joins Inquiry Into Aetna’s Approval Practices Following Former Medical Director’s Testimony

Dr. Jay Iinuma admitted under oath he never looked at patients’ records when deciding whether to approve or deny care. Instead, he relied on nurses employed by Aetna to review the medical records and feed him pertinent information. California regulators have also launched an investigation into the company’s practices.

The Training Of Dr. Robot: Data Wave Hits Medical Care

The technology used by Facebook, Google and Amazon to turn spoken language into text, recognize faces and target advertising could help doctors combat one of the deadliest killers in American hospitals.

Clostridium difficile, a deadly bacterium spread by physical contact with objects or infected people, thrives in hospitals, causing 453,000 cases a year and 29,000 deaths in the United States, according to a 2015 study in the New England Journal of Medicine. Traditional methods such as monitoring hygiene and warning signs often fail to stop the disease.

But what if it were possible to systematically target those most vulnerable to C-diff? Erica Shenoy, an infectious-disease specialist at Massachusetts General Hospital, and Jenna Wiens, a computer scientist and assistant professor of engineering at the University of Michigan, did just that when they created an algorithm to predict a patient’s risk of developing a C-diff infection, or CDI. Using patients’ vital signs and other health records, this method — still in an experimental phase — is something both researchers want to see integrated into hospital routines.

The CDI algorithm — based on a form of artificial intelligence called machine learning — is at the leading edge of a technological wave starting to hit the U.S. health care industry. After years of experimentation, machine learning’s predictive powers are well-established, and it is poised to move from labs to broad real-world applications, said Zeeshan Syed, who directs Stanford University’s Clinical Inference and Algorithms Program.

“The implications of machine learning are profound,” Syed said. “Yet it also promises to be an unpredictable, disruptive force — likely to alter the way medical decisions are made and put some people out of work.

Machine learning (ML) relies on artificial neural networks that roughly mimic the way animal brains learn.

As a fox maps new terrain, for instance, responding to smells, sights and noises, it continually adapts and refines its behavior to maximize the odds of finding its next meal. Neural networks map virtual terrains of ones and zeroes. A machine learning algorithm programmed to identify images of coffee cups might compare photos of random objects against a database of coffee cup pictures; by examining more images, it systematically learns the features to make a positive ID more quickly and accurately.

Shenoy and Wiens’ CDI algorithm analyzed a data set from 374,000 inpatient admissions to Massachusetts General Hospital and the University of Michigan Health System, seeking connections between cases of CDI and the circumstances behind them.

The records contained over 4,000 distinct variables. “We have data pertaining to everything from lab results to what bed they are in, to who is in the bed next to them and whether they are infected. We included all medications, labs and diagnoses. And we extracted this on a daily basis,” Wiens said. “You can imagine, as the patient moves around the hospital, risk evolves over time, and we wanted to capture that.”

As it repeatedly analyzes this data, the ML process extracts warning signs of disease that doctors may miss — constellations of symptoms, circumstances and details of medical history most likely to result in infection at any point in the hospital stay.

Such algorithms, now commonplace in internet commerce, finance and self-driving cars, are relatively untested in medicine and health care. In the U.S., the transition from written to electronic health records has been slow, and the format and quality of the data still vary by health system — and sometimes down to the medical practice level — creating obstacles for computer scientists.

But other trends are proving inexorable: Computing power has grown exponentially while getting cheaper. Once, creating a machine learning algorithm required networks of mainframe computers; now it can be done on a laptop.

Radiology and pathology will experience the changes first, experts say. Machine learning programs will most easily handle analyzing images. X-rays and MRI, PET and CT scans are, after all, masses of data. By crunching the data contained in thousands of existing scan images along with the diagnoses doctors have made from them, algorithms can distill the collective knowledge of the medical establishment in days or hours. This enables them to duplicate or surpass the accuracy of any single doctor.

Machine learning algorithms can now reliably diagnose skin cancers (from photographs) and lung cancer, and predict the risk of seizures.

Google research scientist Lily Peng, a physician, led a team that developed a machine learning algorithm to diagnose a patient’s risk of diabetic retinopathy from a retinal scan. DR, a common side effect of diabetes, can lead to blindness if left untreated. The worldwide rise in diabetes rates has turned DR into a global health problem, with the number of cases expected to rise from 126.6 million in 2011 to 191 million by 2030 — an increase of nearly 51 percent. Its presence is indicated by increasingly muddy-looking scan images.

Peng’s team gathered 128,000 retinal scans from hospitals in India and the U.S. and assembled a team of 54 ophthalmologists to grade them on a 5-point scale for signs of the disease. Multiple doctors reviewed each image to average out individual differences of interpretation.

Once “trained” on an initial data set with the diagnoses, the algorithm was tested on another set of data — and there it slightly exceeded the collective performance of the ophthalmologists.

Now Peng is working on applying this tool in India, where a chronic shortage of ophthalmologists means DR often goes undiagnosed and untreated until it’s too late to save a patient’s vision. (This is also a problem in the U.S., where 38 percent of adult diabetes patients do not get the recommended annual eye check for the disease, according to the Centers for Disease Control.)

A group of Indian hospitals is now testing the algorithm. Ordinarily, a scan is done, and a patient may wait days for results after a specialist — if available — reads the image. The algorithm, via software running on hospital computers, makes the results available immediately and a patient can be referred to treatment.

Last year, the Food and Drug Administration approved the first medical machine learning algorithm for commercial use by the San Francisco company Arterys. Its algorithm, “DeepVentricle,” performs in 30 seconds a task doctors typically do by hand — drawing the contours of ventricles from multiple MRI scans of the heart muscle in motion, in order to calculate the volume of blood passing through. That takes an average of 45 minutes. “It’s automating something that is important — and tedious,” said Carla Leibowitz, Arterys’ head of strategy and marketing.

If adopted on a broad scale, such technologies could save lots of time and money. But such change is disruptive.

“The fact that we have identified potential ways to gut out costs is good news. The problem is the people who get gutted are not going to like it — so there will be resistance,” said Eric Topol, director of the Scripps Translational Science Institute. “It undercuts how radiologists do their work. Their primary work is reading scans — what happens when they don’t have to do that?”

The shift may not put a lot of doctors out of work, said Topol, who co-authored a piece in JAMA exploring the issue. Rather, it will likely push them to find new ways to apply their expertise. They may focus on more challenging diagnoses where algorithms continue to fall short, for instance, or interact more with patients.

Beyond this frontier, algorithms can provide a more precise prognosis for the course of a disease — potentially reshaping treatment of progressive ailments or addressing the uncertainties in end-of-life care. They can anticipate fast-moving infections like CDI and chronic ailments such as heart failure.

As the U.S. population ages, heart failure will be a rising burden on the health system and on families.

“It’s the most expensive single disease as a category because of the extreme disability it causes and the high demand for care it imposes, if not managed really tightly,” said Walter “Buzz“ Stewart, vice president and chief research officer at Sutter Health, a health system in Northern California. “If we could predict who was going to get it, perhaps we could begin to intervene much earlier, maybe a year or two years earlier than when it usually happens — when we admit a patient to the hospital after a cardiac event or crash.”

Stewart has collaborated on several studies aiming to address that problem. One, done with Georgia Tech computer scientist Jimeng Sun, predicts whether a patient will develop heart failure within six months, based on 12 to 18 months of outpatient medical records.

These tools, Stewart said, are leading to the “mass customization of health care.” Once algorithms can anticipate incipient stages of conditions like heart failure, doctors will be better able to offer treatments tailored to the patient’s circumstances.

Despite its scientific promise, machine learning in medicine remains terra incognita in many ways. It adds a new voice — the voice of the machine — to key medical decisions, for instance. Doctors and patients may be slow to accept that. Adding to potential doubts, machine learning is often a black box: Data go in, and answers come out, but it’s often unclear why certain patterns in a patient’s data point, say, to an emerging disease. Even the scientists who program neural networks often don’t understand how they reach their conclusions.

“It’s going to make a big difference in how decisions are made — things will become much more data-driven than they used to be,” said John Guttag, a professor of computer science at MIT. Doctors will rely on these increasingly complex tools to make decisions, he said, and “have no idea how they work.” And, in some cases, it will be hard to figure out why bad advice was given.

And while health data are proliferating, the quantity, quality and format vary by institution, and that affects what the algorithms “learn.”

“That is a huge issue with modeling and electronic health records,” Sun said. “Because the data are not curated for research purposes. They are collected as a byproduct of care in day-to-day operations, and utilized mainly for billing and reimbursement purposes. The data is very, very noisy.”

This also means that data may be inconsistent, even in an individual patient’s records. More important, one size does not fit all: An algorithm developed with data from one hospital or health system may not work well for another. “So you need models for different institutions, and the models become quite fragile, you might put it,” Sun said. He is working on a National Institutes of Health grant studying how to develop algorithms that will work across institutions.

And the tide of available medical data continues to rise, tantalizing scientists. “Think about all the data we are collecting right now,” Wiens said. “Electronic health records. Hospitalizations. At outpatient centers. At home. We are starting to collect lots of data on personal monitors. These data are valuable in ways we can’t yet know.”