Liza Haar

The problem with the hype about big data is that hype tends to overpromise, Paul Chang, MD, of the University of Chicago, said at RSNA 2016.

“Whenever there is some potentially disruptive or transformative change, we reinvent ourselves,” he said. The role of the radiologist before PACS is drastically different than their role today, Chang said. Notably, the change didn’t kill radiologists, it probably made them better.

The misunderstanding about big data, Chang said, is that it’s something new. But radiology has always had a big data problem.

Chang explains in the video whether radiology is ready for big data and how radiologists can prepare.

Videos

[VIDEO] IT and radiology have to prepare for big data, together.

Big Data Problem in Radiology

ACR’s annual analysis of the radiology workforce reveals telling trends about the profession, and this year’s 

 has an especially powerful finding: the number of radiologists is expected to increase.

2017 ACR Commission on Human Resources Workforce Survey

 analyzes the anatomy of the radiology workforce and predicts hiring trends for the coming year. In 2017, researchers expect to see a 14.1% increase in hiring from 

. The higher end of predicted job openings, 2,370, is a 68% increase from the number of hires made in 2012. In the infographic below, we highlight some of the noteworthy data from this year’s survey.


Practice leaders completed an electronic survey asking them to self-identify their type of practice and the makeup of their groups. Twenty-six percent of practice leaders responded to the survey, which the ACR deemed to represent 33% of all practicing radiologists in the United States. This was a decrease in the 39% of practicing radiologists represented in the 


The makeup of females in radiology continues to be a topic of discussion. About 21% of radiologists are female, 8% of which are practice leaders. This is not statistically significant when compared with the gender distribution of all full-time radiologists, according to the study.


Radiologists continue to pay close attention to retirement trends. A quarter of practice leaders reported having a radiologist retire in 2017, and 50% of retirees were older than 65. Sixty-two percent of all radiologists are between the ages of 35 and 55.


Since 2012, the percentage of general radiologists has dropped significantly: 32.5% of radiologists reporting as general radiologists in 2012 and only 10.4% reporting as general radiologists in 2017. Body imagers make up the largest subspecialty, general interventional radiology and neuroradiology are close seconds.


Other notable trends, according to the study authors, is the number of part-time radiologists (16%) and the number of practices employing part-time radiologists (76%). Researchers also attribute increasing 

 to the decrease in the number of practices registered with the Practice of Radiology Environment Database.
[[{"type":"media","view_mode":"media_crop","fid":"62582","attributes":{"alt":"","class":"media-image","id":"media_crop_8454356682918","media_crop_h":"0","media_crop_image_style":"-1","media_crop_instance":"7951","media_crop_rotate":"0","media_crop_scale_h":"0","media_crop_scale_w":"0","media_crop_w":"0","media_crop_x":"0","media_crop_y":"0","title":" ","typeof":"foaf:Image"}}]]

Articles

The anatomy of the radiology workforce in 2017.

Who is Radiology in 2017?

The most common cause of malpractice litigation in radiology historically has been failure to diagnose, or errors, Leonard Berlin, MD, of the Radiology Department at Skokie Hospital, said at ACR 2016.

Even today, failure to diagnose is still the number one cause of malpractice in radiology. Missed or delayed diagnosis of breast cancer is the leading diagnosis failure, Berlin said, followed by lung cancer and fractures.

Slowly creeping up, however, is failure to communicate, Berlin added. Radiology reports not making it to referring physicians or making it to referring physicians and not patients is the culprit behind failure to communicate, which essentially, can be filed under delayed diagnosis, Berlin said. The increase in failure to communicate is rooted in the volume of work radiologists are responsible for today.

The ACR parameters on communication are the most controversial, Berlin said. Significant, unexpected findings are where the malpractice suits tend to lurk. Berlin cited an ACR study that showed 28% of radiologists call the referring physician for significant, unexpected findings.

“That’s the problem,” he said. “That’s where the law suits occur.”

[VIDEO] Leonard Berlin, MD, talks malpractice at ACR 2016.

Failure to Diagnose and Communicate in Radiology

One of the biggest challenges in radiology is the quality of data received from referring physicians, Melody W. Mulaik, MSHS, president and co-founder of Coding Strategies, said at AHRA 2016.The issue can be overwhelming, she said, but with buy in from the department, administration, and radiologists, it is possible to get better data. She offered seven tips on how to tackle the issue.

Slideshows

How radiology practices can get better data.

7 Tips for Getting Better Data from Referring Physicians

Pressure from the government to comply is fueling mergers and acquisitions in radiology, Rick Padelford, executive vice president, San Diego Imaging Medical Group, said at RBMA 2016.

PQRS, MIPS, MACRA, and interoperability are just a few of the mandates that have radiology practices feeling the pressure to grow or combine in order to keep up, he said.

Padelford leads a group that merged with a neighboring group in San Diego county.

“Many of us had been friends with each other for quite a while and we got together and said we think we can do something good here,” Padelford said. “We think we can do something that would help improve our service to our hospitals that would improve the coordination of care to our community and do it on a larger geographic scale.”

The groups weren’t natural competitors with one another, which helped drive a friendly merge.

“We looked at the world of radiology the same way, so it was a natural marriage to come together,” he said.

There were still challenges, though. Discrepancies in income level and work schedules were an initial concern. The groups approached this by creating a divisional structure in which each group could operate independently internally, but still promote as one brand and one group when it came to negotiating hospital contracts and external relationships.

Originally, separate internal divisions was considered a temporary structure but after three years, most of the group seems to like this type of governance, Padelford said.

Ultimately, being part of a larger group gives them resources to invest capital in IT and interoperability in response to increasing external pressure. What’s mitigated is the pressure to compete with each other, Padelford said.

[VIDEO] Insight from the inside of a radiology group merger, from RBMA 2016.

How Two Radiology Groups Survived a Merger

With some exceptions, if you didn’t reach nine PQRS measures in 2015, you will see a 2% reduction in your Medicare payments in 2017, Michael Bohl, CEO at Radiology Group PC, SC, told 

PQRS, the physician quality reporting system, is a CMS mandate that requires physicians report specific quality measures. Historically, physicians were responsible for reporting three measures, but in 2015, practices had to start submitting nine measures per physician, Bohl said.

PQRS has specific measures and then also includes quality registries that CMS has approved as alternatives to the basic PQRS measures, he said.

In order to avoid a cut in Medicare payments, physicians and practices need to decide which avenue they need to use to get to a total of nine measures, Bohl said. Bohl’s practice used the ACR Clinical Data registry to help them meet their PQRS measures.

“I was not going to get to nine for any of our doctors using basic PQRS measures,” he said. “It would have been very challenging.”

Exceptions are made for radiologists that have a very narrow practice, but most diagnostic radiologists have a broad enough practice that would make it difficult for them to qualify for exceptions, Bohl said.

[VIDEO] What radiology practices need to know about PQRS, explained by Michael Bohl at RBMA 2016.

PQRS for Radiology

Radiology vendors advised groups at SIIM 2016 on key considerations before deciding to switch to a VNA. Fred Behlen, PhD, a medical physicist and founder of Laitek, Inc. offered eight tips for practices to consider.

1. List all use cases, identify how each one would work in the clinical workflow. Pay attention to the readiness of the systems for VNA. Don't leave PACS out of the planning, that may seem a bit obvious but there are people out there who think you can buy a VNA without telling the PACS company up front. PACS has to work with the VNA, it's just a matter of going through each use case. Think of everything it has to do, make sure you know how it's going to do it. Will it be fast enough? How much storage do you need in the PACS?

2. Consider consistency of presentation between diagnostic and clinical displays, especially annotations. There are varying degrees of how important annotations are, but even in some cases people are using them for laterality corrections, so annotations can become a patient safety issue. You'll have to migrate annotations, a lot of storage systems don't have annotations in DICOM format, you just have to make sure that's covered.[[{"type":"media","view_mode":"media_crop","fid":"49905","attributes":{"alt":"Fred Behlen, PhD","class":"media-image media-image-right","id":"media_crop_2367516329680","media_crop_h":"0","media_crop_image_style":"-1","media_crop_instance":"6071","media_crop_rotate":"0","media_crop_scale_h":"0","media_crop_scale_w":"0","media_crop_w":"0","media_crop_x":"0","media_crop_y":"0","style":"height: 200px; width: 200px; border-width: 0px; border-style: solid; margin: 1px; float: right;","title":"Fred Behlen, PhD","typeof":"foaf:Image"}}]]

3. Clinical photography, non-DICOM imaging, enterprise imaging, the best thing to do is to provide for encapsulation into DICOM and store them in the VNA. There are DICOM web services, and new tools such as IHE web image capture that should make DICOM implementation of those things easier

4. On your VNA, make sure that it's provision to handle data migration inflows, the inflows can be in excess of a terabyte a day, the VNA ought to be able to handle it but sometimes it requires adequate provisioning.

5. Some groups are doing a best of breed or deconstructed PACS as VNA implementation, if you are thinking of doing this make sure you know what you're doing and have the resources to integrate your own PACS. There is a lot that PACS companies have done in providing these integrated solutions, make sure you know how to do all of those things.

6. Consider the alternatives to VNA. One way to approach it is to maybe expand the role of your PACS to cover enterprise imaging.

7. Make sure that you don't get locked in to your new vendor, allow for multiple viewers, even if you are starting with one supposedly universal viewer, you may want to add others in the future. That's an EHR and a VNA architecture question, keep your connections to the VNA pure vanilla DICOM, in other words don't abuse or overuse tag morphing capabilities.

8. Require full read access to the VNA database and storage, even if you don't plan to use it, get the passwords and get contractual rights to passwords, you will never have more negotiating leverage than you have now.

Radiology vendors advise groups at SIIM 2016 on key considerations before deciding to switch to a VNA. 

8 Considerations Before Switching to a VNA

There is a lot of hope and a lot of hype in health care, Rasu Shrestha, MD, MBA, CIO at UPMC, said at SIIM 2016.Patients have a lot of hope in health care because they want to know that everything will be OK, Shrestha said. But the rush to embrace digital has led to mixed up priorities. Shrestha, a champion for patient-centered care, thrives on innovation and wants radiologists to understand that the patient needs to come first and the culture of treating a series of images needs to change.In the SIIM 2016 opening session, Shrestha offered his seven tips for patient-centered care.

Tips for patient-centered care in radiology, from SIIM 2016.

7 Tips for Patient-Centered Care

Radiology has done a great job of mastering the first two levels of 

 in diagnostic imaging: technical efficacy and diagnostic accuracy efficacy, but improving the value of care lies in those not yet mastered levels, Hanna Zafar, MD, assistant professor of radiology at the Hospital of the University of Pennsylvania, said at ACR 2016.

“People want to know about diagnostic efficacy, treatment efficacy, patient outcomes, and societal efficacy,” she said. “And that’s where a lot of the interest is in improving the value of care we deliver in radiology.”

Radiologists need to be at the forefront of this movement and conduct the research that allows imaging to be correlated with patient outcomes, Zafar said.

Zafar applauded women’s imaging and BI-RADS for its successful correlation with patient outcomes. BI-RADS’ success stems from the set lexicon that translates into codes that all radiologists understand, she said.

“The codes are then associated with a set management algorithm and we know what the likelihood of malignancy is that’s associated with each code,” she added.

Zafar described an initiative at Penn called Code Abdomen in which they tried to mimic the same idea, and hopefully the same successful measure of patient outcomes. They decided to tackle non-emergent actionable imaging findings. Abdominal imaging, in particular, is rife with non-emergent actionable imaging findings, which are found not only in patients with known cancer diagnoses, but also in patients with no cancer diagnoses, she said.

The problem with these findings, Zafar said, lies in the free text report and its heterogeneity as to how radiologists report findings.

“We don’t do a great job internally at agreeing on the words or the lexicon that we should be putting into those reports,” she said. “In the free text report, you are going to have a very hard time identifying patients with those worrisome findings between two different radiology reports.”

The communication piece is a significant factor. Oftentimes, radiologists rely on the provider to tell the patient to get follow-up, but there is also the question as to whether follow-up is clinically indicated, which the radiologists don’t always know because their workflow doesn’t provide time to dig around in the EMR.

In Code Abdomen, Zafar’s group combined a prospective and retrospective approach in an effort to standardize radiology report codes or language while using natural language processing to mine large amounts of data. The project required months of preparation and a multidisciplinary team effort.

At first, they focused on four organs that commonly have non-emergent actionable findings: liver, pancreas, kidney, and adrenals. The system assigns masses to three different categories, benign, indeterminate, and suspicious.

“It’s similar to BI-RADS, but we are starting off way back in the beginning of the system,” she said. “We don’t have the lexicon yet, we don’t have evidence-based guidelines for every type of mass in every organ.”

Radiologists were instructed to use Bosniak or LI-RADS when applicable, but if there wasn’t a system, they should put in their Code Abdomen impression and their recommendations for how to proceed. The codes range from 0 to 7, and 99 which is for technically inadequate examinations. Each code classifies how the masses break down into the three main categories with a description and specific language that is associated with each code. It’s not enough for radiologists to just describe what they see, though.

“We have forced the radiologist to make up their mind and commit,” she said. “How concerned are you that this is a cancer?”

About two years after the project was first proposed came another big change for radiologists.

“We began to actually require that codes for indeterminate masses had to give a modality and a timing for follow up,” Zafar said. “Radiologists had to give some sort of guidance to the ordering clinician as to what they think a reasonable follow-up plan would be.”

Once the follow-up became a required data element, Zafar’s team was able to look at all of the data as a whole and move towards measuring outcomes.

“The standardized codes facilitate identification of detailed clinical data and allows you to start measuring variability between organs, modalities, and radiologists,” she said.

They can identify which organs have the vast majority of these findings (liver and kidney), and what the vast majority of lesions are (no mass or benign), they can also look at codes in a single organ and track how those have changed over time.


All of this data was a step towards measuring patient outcomes. Most notably, this system allowed Zafar’s team to identify patients at risk of falling through the cracks.

“We know that physicians fail to acknowledge abnormal results in the EMR about 1/3 of the time, and we also know that 1/3 of providers don’t tell patients about abnormal test results,” she said. But in order to study a problem, you have to be able to measure it and, historically, it has been difficult for radiologists to identify what proportion of patients aren’t getting their recommended follow up.

By standardizing the report language, Zafar’s team was able to build a database that sits on the RIS and mines information out of the RIS to identify patients that have the applicable codes. The database can then check within the RIS if patients have any relevant completed or scheduled imaging, which allows them to identify patients at risk of not receiving recommended follow up.

A three-month manual review of the data shed light on a few kinks. Radiologists weren’t familiar with the codes so the number of patients requiring follow up was inflated. They were putting the too small to characterize lesions in the 0 and 3 bucket because they didn’t know how else to classify them.

“After a while, we started talking about this and they realized that’s not really appropriate,” she said. “The overwhelming majority of these are going to be benign, and we know that based on the literature, unless the patient has a known cancer.”

Incomplete chart documentation also posed a challenge.

“We don’t do a great job of capturing data on who our providers are that are taking care of patients,” she said. This is especially a problem in the emergency department or with inpatients. Also, providers don’t always document why follow up is not clinically indicated, she said.

Zafar’s team also used the data to look at how many patients in the same time interval actually had a path-proven cancer or underwent a surgery that showed a malignancy. Nine percent of their applicable patient population had cancer.

Leadership buy-in and patience were imperative to this project, Zafar said. But she urged that initiatives like this one can be achieved outside of tertiary care systems.

The coding system shed light on the power of informatics, not just in standardizing radiology reporting and communication, but in identifying cohorts of patients and the ability to track their outcomes.

How informatics and inform and improve patient outcomes in radiology, from ACR 2016.

Informatics and Patient Outcomes in Radiology

A high-level view of a radiologist’s career might include working with cutting-edge technology, saving lives, making a difference in patient care, being the doctor’s doctor.

How about being the cheapest radiologist that doesn’t stink? Not exactly what medical ambitions are made of. But if radiology can’t prove that it improves outcomes or reduces costs, being cheap and adequate might be the business in which radiology is headed, James Whitfill, MD, CMO, Scottsdale Health Partners, warned at ACR 2016.

Whitfill was talking more specifically about health care reform and the new era of value-based care. He addressed head on the sentiment that we’ve seen change before.

As percentage of GDP spent on health care reaches 20% and above, most economists would say that health care’s ability to compete in a global economy becomes significantly impaired, Whitfill said. “But that’s not enough, the explosion of baby boomers aging into Medicare keeps CMS awake at night; not only are we spending more of our national economic pie on health care, but we have a huge number of people coming into the Medicare system.”

Adding more strain to health care is the growth in high deductible plans which change the way consumers think about health care.

“The traditional ways of just trying to maximize revenue from a fee for service perspective is altered because people have to put their own dollars into this,” Whitfill said. When consumers were insulated from financial decisions, fee for service was an easy sell. He gave the example of a “seismic” event in the Pacific Northwest, when Boeing told its employees they could go wherever they wanted for their hip replacement, but if they went to the Cleveland Clinic, Boeing would cover all of the costs, including travel. Alternatively, they could see their local surgeon and pay their deductible. It’s not difficult to guess which option most employees took.

People are quick to blame politics for changing health care, but Whitfill said health care improvements stem from an economic issue, not a political issue.

Practice models won’t change overnight, but they have already changed drastically in some parts of the country. In Whitfill’s market, unless providers are part of a large clinically integrated network, they are being cut from insurance plans. Clinically integrated networks, like other new payment models, don’t have an immediate role for radiology, though, and this is concerning and dangerous.

“In most of our clinically integrated networks, we are following metrics around congestive heart failure, coronary artery disease, diabetes, COPD,” Whitfill said. “Besides some chest X-rays, there isn’t a ton of radiology changing those outcomes.”

In fact, Whitfill said, some ACOs have very simple tools that look at how much they are spending on high technology and try to lower those costs because they don’t’ know what else to do about radiology.

The value metrics in radiology, like turnaround time and peer review are important, Whitfill said. “But we are in a world where we need to show patient outcomes like not being dead or being at work or not being in the hospital, those are the tangible outcomes that people are looking for.”

Whoever can figure out how radiology can prove tangible outcomes will be an important savior for the field, Whitfill said, but bundled payment models might provide an opportunity.

In a bundled payment, base costs attached to care are adjusted for severity, complications are modeled, and then one lump sum is assigned to an entire episode of care.

“These create a tremendous incentive for specialists to come together, organize themselves, and cut costs,” he said. If radiologists can show that they improve outcomes, surgical colleagues will be incentivized to include radiology in their bundle. But if radiologists aren’t able to prove that they get the patient back to work faster, reduce readmissions, or get the OR time down, radiologists risk commodification, he said.

Whitfill encourages radiology to look closely at oncology bundles, though.

“Radiology has a particularly strong use case for showing the impact of being able to get to diagnosis faster and monitor disease,” he said. “Oncology bundles are one of the first places that cross sectional imagers should really look at for potential of showing the benefit of radiology.”

The bundled procedure model is just one cost saving, value-based approach, though. As financial risk is pushed to providers more innovative and significant changes will be necessary.

“If radiologists can show how to reduce total medical costs, you will be highly sought after,” Whitfill said. “If you can’t, it will be a very unpleasant future.”

Radiology at risk of commodification, from ACR 2016.