Free Hospital EMR and EHR Newsletter Want to receive the latest news on EMR, Meaningful Use, ARRA and Healthcare IT sent straight to your email? Join thousands of healthcare pros who subscribe to Hospital EMR and EHR for FREE!

Facebook Partners With Hospital On AI-based MRI Project

Posted on August 23, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

I’ve got to say I’m intrigued by the latest from Facebook, a company which has recently been outed as making questionable choices about data privacy. Despite the kerfuffle, or perhaps because of it, Facebook is investing in some face-saving data projects.

Most recently, Facebook has announced that it will collaborate with the NYU School of Medicine to see if it’s possible to speed up MRI scans.  The partners hope to make MRI scans 10 times faster using AI technology.

The NYU professors, who are part of the Center for Advanced Imaging Innovation and Research, will be working with the Facebook Artificial Intelligence Research group. Facebook won’t be bringing any of its data to the table, but NYU will share its imaging dataset, which consists of 10,000 clinical cases and roughly 3 million images of the knee, brain and liver. All of the imaging data will be anonymized.

In taking up this effort, the researchers are addressing a tough problem. As things stand, MRI scanners work by gathering raw numerical data and turning that data into cross-sectional images of internal body structures. As with any other computing platform, crunching those numbers takes time, and the larger the dataset to be gathered, the longer the scan takes.

Unfortunately, long scan times can have clinical consequences. While some patients can cope with being in the scanner for extended periods, children, those with claustrophobia and others for whom lying down is painful might have trouble finishing the scanning session.

But if MRI scanning times can be minimized, more patients might be candidates for such scans. Not only that, physicians may be able to use MRI scans in place of X-ray and CT scans, both of which generate potentially harmful ionizing radiation.

Researchers hope to speed up the scanning process by modifying it using AI. They believe it may be possible to capture less data, speeding up the process substantially, while preserving or even enhancing the rich content gathered by an MRI machine. To do this, they will train artificial neural networks to recognize the underlying structure of the images and fill in visual information left out of the faster scanning process.

The NYU research team admits that meeting its goal will be very difficult. These neural networks would have to generate absolutely accurate images, and it’s not clear how possible this is as of yet. However, if the researchers can reconstruct high-value images in a new way, their work could have an impact on medicine as a whole.

Deep Learning System Triages Terminally Ill Hospital Patients

Posted on January 26, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

Researchers at Stanford have developed a new tool designed to coordinate end-of-life care for critically ill patients. While the pilot study has generated screaming newspaper headlines (“AI tool predicts when people will die!”) researchers say that the system is best thought of as a triage option which helps hospitals and hospices provide timely palliative care to those who need it. It can also help terminally ill patients — most of whom would prefer to die at home — make plans for their passing and avoid dying in their hospital bed.

According to an article in tech publication Gizmodo, the Stanford set-up combines EHR data with other sources of information such disease type, disease state and severity of admission. The information is then processed by a form of AI known as deep learning, in which a neural network “learns” by digesting large amounts of data.

To conduct the study, researchers fed 2 million records from adult and child patients admitted to either Stanford Hospital or Lucile Packard Children’s Hospital. The system then identified 200,000 patients who met the study’s criteria. In addition to clinical criteria, the system also reviewed associated case reports diagnoses, number of scans ordered, number of procedures performed and other data.

After reviewing 160,000 case reports, the deep learning system was instructed to predict the mortality of a given patient within three to 12 months of a particular date using EHR data from the previous year. The algorithm included a requirement to ignore patients who appeared to have less than three months to live, as this window was too short for providers to make preparations to offer palliative care.

Then, the AI algorithm calculated the odds of patient death in the 3 to 12-month timespan extending from the original date. Its predictions turned out to be quite accurate. For one thing, it predicted patient mortality within the 3 to 12-month window accurately in nine out of 10 cases, a performance that few clinicians could match. Meanwhile, roughly 95% of patients considered to have a low probability of dying within 12 months actually lived beyond that point.

It’s worth noting that while the deep learning tool made fairly accurate predictions of patient mortality, the system doesn’t let healthcare providers know what treatment patients need or even how it makes its predictions. Luckily, researchers say, the system allows them to get a look at individual cases to better understand its deductions.

For example, in one case the system predicted accurately that a patient with bladder and prostate cancer would die within a few months. While there were many clues that he was near death, the system weighted the fact the scans were made of his spine and a catheter used in his spinal cord heavily in its calculations. Only later did the researchers realize that an MRI of the spinal cord most likely suggested a deadly cancer of the spinal cord which was likely to metastasize.

It’s worth remembering these results were produced as part of a pilot project, and that the predictions the system makes might not be as accurate for other data sets. However, these results are an intriguing reminder of the possibilities AI offers for hospitals.

Access To Electronic Health Data Saves Money In Emergency Department

Posted on October 24, 2016 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

A new research study has found that emergency department patients benefit from having their electronic health records available when they’re being treated. Researchers found that when health information was available electronically, the patient’s care was speeded up, and that it also generated substantial cost savings.

Researchers with the University of Michigan School of Public Health reviewed the emergency department summaries from 4,451 adult and pediatric ED visits for about one year, examining how different forms of health data accessibility affected patients.

In 80% of the cases, the emergency department had to have all or part of the patient’s medical records faxed to the hospital where they were being treated. In the other 20% of the cases, however, where the ED staff had access to a patient’s complete electronic health record, they were seen much more quickly and treatment was often more efficient.

Specifically, the researchers found that when information requests from outside organizations were returned electronically instead of by fax, doctors saw that information an hour faster, which cut a patient’s time in the ED by almost 53 minutes.

This, in turn, seems to have reduced physicians’ use of MRIs, x-rays and CT scans by 1.6% to 2.5%, as well as lowering the likelihood of hospital admission by 2.4%. The researchers also found that average cost for care were $1,187 lower when information was delivered electronically.

An interesting side note to the study is that when information was made available electronically on patients, it was supplied through Epic’s Care Everywhere platform, which is reportedly used in about 20% of healthcare systems nationwide. Apparently, the University of Michigan Health System (which hosted the study) doesn’t belong to an HIE.

While I’m not saying that there’s anything untoward about this, I wasn’t surprised to find principal author Jordan Everson, a doctoral candidate in health services at the school, is a former Epic employee. He would know better than most how Epic’s health data sharing technology works.

From direct experience, I can state that Care Everywhere isn’t necessarily used or even understood by employees of some major health systems in my geographic location, and perhaps not configured right even when health systems attempt to use it. This continues to frustrate leaders at Epic, who emphasize time and again that this platform exists, and that is used quite actively by many of its customers.

But the implications of the study go well beyond the information sharing tools U-M Health System uses. The more important takeaway from the study is that this is quantitative evidence that having electronic data immediately available makes clinical and financial sense (at least from the patient perspective). If that premise was ever in question, this study does a lot to support it. Clearly, making it quick and easy for ED doctors to get up to speed makes a concrete difference in patient care.

Thoughts On Hospital Telecommunications Infrastructure

Posted on August 31, 2016 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

Given the prevalence of broadband telecom networks in place today, hospital IT leaders may feel secure – that their networks can handle whatever demands are thrown at them. But given the progress of new health IT initiatives and data use, they still might face bandwidth problems. And as healthcare technical architect Lanny Hart notes in a piece for SearchHealthIT, the networks need to accommodate new security demands as well.

These days, he notes healthcare networks must carry not only more-established data and voice data, but also growing volumes of EMR traffic. Not only that, hospital IT execs need to plan for connected device traffic and patient/visitor access to Wi-Fi, along with protecting the network from increasingly sophisticated data thieves hungry for health data.

So what’s a healthcare CIO to do when thinking about building out hospital telecommunications infrastructure?  Here’s some of Hart’s suggestions:

  • When building your network, keep cybersecurity at the top of your priorities, whether you handle it at the network layer or on applications layered over the network.
  • Use an efficient network topology. At most, create a hub-and-spoke design rather than a daisy chain of linked sub-networks and switches.
  • Avoid establishing a single point of failure for networks. Use two separate runs of fiber or cable from the network’s edge switches to ensure redundancy and increase uptime.
  • Use virtual local area networks for PACS and for separate hospital departments.
  • Segment access to your virtual networks – including your guest Wi-Fi service – allowing only authorized users to access individual networks.
  • Build as much wireless network connectivity into new hospital construction, and blend wireless and wired networks when you upgrade networks in older buildings.
  • When planning network infrastructure, bear in mind that hospital networks can’t be completely wireless yet, because big hardware devices like CT scans and MRIs can’t run off of wireless connections.
  • Bigger hospitals that use real-time location services should factor that traffic in when planning network capacity.

In addition to all of these considerations, I’d argue that hospital network planners need to keep a close eye on changes in network usage that affect where demand is going. For example, consider the ongoing shift from desktop computers to mobile devices use of cellular networks have on network bandwidth requirements.

If physicians and other clinical staffers are using cell connections to roam, they’re probably transferring large files and perhaps using video as well. (Of course, their video use is likely to increase as telemedicine rollouts move ahead.)

If you’re paying for those connections, why not evaluate whether there’s ways you could save by extending Internet connectivity? After all, closing gaps in your wireless network could both improve your clinicians’ mobile experience and help you understand how they work. It never hurts to know where the data is headed!