Tag Archives: medical

How a synthetic data approach is helping COVID-19 research

As medical researchers around the world race to find answers to the COVID-19 pandemic, they need to gather as much clinical data as possible for analysis.

A key challenge many researchers face with clinical data is privacy and the mandate to protect confidential patient information. One way to overcome that privacy challenge is by using synthetic data, an approach that creates data that is not linked to personally identifiable information. Rather than encrypting or attempting to anonymize data to protect privacy, synthetic data represents a different approach that can be useful for medical researchers.

With synthetic data there are no real people, rather the data is a synthetic copy that is statistically comparable, but entirely composed of fictional patients, explained Ziv Ofek, founder and CEO of health IT vendor MDClone, based in Beer Sheba, Israel.

Other popular methods of protecting patient privacy, such as anonymization and encryption, aim to balance patient privacy and data utility. However, a privacy risk still remains because embedded within the data, even after diligent attempts to protect privacy, are real people, Ofek argued.

“There are no real people embedded within the synthetic data,” Ofek said. “Instead, the data is a statistical representation of the original and the risk of reidentification is no longer relevant, even though it may appear as real people and can be analyzed as if it were and yielding the same conclusions.”

Synthetic Data Engine from MDClone
MDClone Synthetic Data Engine creates anonymous data statistically identical to the original.

Synthetic data in the real world

MDClone’s synthetic data technology is being used by Sheba Medical Center in Tel Aviv as part of its COVID-19 research.

Synthetic data provides an opportunity to get quick answers to data-related questions … [and] allows users to work on the data in their own environment, something we do not allow with real data.
Eyal Zimlichman, M.D.Deputy director general, Sheba Medical Center

The MDClone system is critical to his organization’s data efforts to gain more insights into COVID-19, the disease caused by the novel coronavirus, said Eyal Zimlichman, M.D., deputy director general, chief medical officer and chief innovation officer at Sheba Medical.

By regulation, synthetic data is not considered patient data and therefore is not subject to the IRB process. As opposed to real patient data, Ofek noted that synthetic data can be accessed freely by researchers, so long as the institution agrees to provide access.

“Synthetic data provides an opportunity to get quick answers to data-related questions without the need for an IRB approval,”Zimlichman said. “It also allows users to work on the data in their own environment, something we do not allow with real data.”

Zimlichman added that data science groups both within and outside the hospital are using the MDClone system to help predict COVID-19 patient outcomes, as well as to aid in determining a course of action for therapy.

Synthetic data accelerates time to insight

The MDClone platform includes a data engine for collecting and organizing patient data, the discovery studio for analysis and the Synthetic Data Engine for creating data. The vendor on April 14 released the MDClone Pandemic Response Package, which includes a predefined set of visualizations and analyses that are COVID-19-specific. The engine enables clients and networks to ask questions of COVID-19-related data and generate meaningful analysis, including cohort and population-level insights.

In the event a client wants to use their data to share, compare and collaborate with others, they can convert their original data into a synthetic copy for shared review and insight development.

“A synthetic collaboration model allows for that conversation to take place with data flows and analysis performed across both systems without patient privacy and security risks,” Ofek said.

Ofek added that the synthetic model and platform access capability enables clients to invite research and collaboration partners into their data environment rather than simply sharing files on demand. With MDClone, the client’s research and collaboration partners are able to log in to the MDClone data lake and then get access to the data and exploration tools with synthetic output.

“In the context of the pandemic, organizations leveraging the platform can offer partners unfettered synthetic access to accelerate exploration into new avenues for treatment,” Ofek said. “Idea generation and data reviews that enable real-world analysis is our pathway to finding and broadcasting the best healthcare professionals can offer as we combat the disease.”

Go to Original Article

Emsisoft, Coveware offer free ransomware services to hospitals

As the coronavirus pandemic continues to overwhelm healthcare and medical facilities, another complication has surfaced: the possibility of a ransomware attack, which have been shown to spike during the spring and summer months, according to antimalware vendor Emsisoft.

In anticipation of such attacks, Emsisoft and incident response company Coveware partnered for an initiative to give healthcare providers access to both companies’ complete range of ransomware response services at no cost for the duration of the crisis. The aim is to get impacted providers operational again in the shortest possible time so that patient care is minimally disrupted, Emsisoft threat analyst Brett Callow said.

In the event of a ransomware attack, Emsisoft and Coveware will provide services to hospitals and medical facilities that include technical analysis of the ransomware; the development of a decryption tool, if possible; and “as a last resort, ransom negotiation, including transaction handling and recovery assistance including replacement of the decryption tool supplied by the criminals with a custom tool that will recover data faster and with less chance of data loss,” according to a blog post from Emsisoft.

Bill Siegel, CEO of Coveware, cautioned that a ransomware attack on a healthcare organization will still have devastating consequences, regardless of how Emsisoft and Coveware can mitigate it. “Even with our help, it will likely result in unnecessary causalities because of the disruption,” Siegel said.

Bracing for ransomware attacks

Emsisoft’s blog said, “it is likely that there will be an increase in the number of healthcare providers impacted by ransomware in the coming months and unfortunately this increase may coincide with the peak of the COVID-19 outbreak. Further, the spikes may be more pronounced than in previous years due to security weaknesses resulting from hastily introduced work-from-home arrangements, personal device usage and staffing shortages.”

A ransomware attack could hinder response efforts, communications and treatments during the pandemic.

Even prior to the pandemic, healthcare facilities were a common target of ransomware attacks. At least 764 healthcare providers were impacted by ransomware in 2019, according to the Emsisoft report, titled “The State of Ransomware in the U.S.: Report and Statistics 2019.”

However, two ransomware gangs, Maze and DoppelPaymer, announced Wednesday they would cease ransomware attacks on medical and healthcare facilities during the COVID-19 pandemic. Despite these promises, the problem persists, according to Callow.

“I saw a medical research company in the U.K. was attacked a couple days ago by a group who steals data and threatens to release it if you don’t pay,” Callow said, referencing the Maze group.

Siegel said he hopes the promise made by ransomware gangs is genuine.

“It will be interesting to see if Defray/777 ransomware affiliates adhere, as that variant almost exclusively targeted healthcare providers prior to the pandemic,” Siegel said.

Since the announcement on Wednesday, no one has yet to take up the free offer, and both Callow and Siegel said they hope no one will need to.

Go to Original Article

Delivering information and eliminating bottlenecks with CDC’s COVID-19 assessment bot – The Official Microsoft Blog

In a crisis like the COVID-19 pandemic, it’s not only important to deliver medical care but to also provide information to help people make decisions and prevent health systems from being overwhelmed.

Microsoft is helping with this challenge by offering its Healthcare Bot service powered by Microsoft Azure to organizations on the frontlines of the COVID-19 response to help screen patients for potential infection and care.

For example, the U.S. Centers for Disease Control and Prevention (CDC) just released a COVID-19 assessment bot that can quickly assess the symptoms and risk factors for people worried about infection, provide information and suggest a next course of action such as contacting a medical provider or, for those who do not need in-person medical care, managing the illness safely at home.

The bot, which utilizes Microsoft’s Healthcare Bot service, will initially be available on the CDC website.

Public health organizations, hospitals and others on the frontlines of the COVID-19 response need to be able to respond to inquiries, provide the public with up-to-date outbreak information, track exposure, quickly triage new cases and guide next steps.  Many have expressed great concern about the overwhelming demand COVID-19 is creating on resources such as urgent, emergency and nursing care.

In particular, the need to screen patients with any number of cold or flu-like symptoms — to determine who has high enough risk factors to need access to limited medical resources and which people may more safely care for themselves at home — is a bottleneck that threatens to overwhelm health systems coping with the crisis.

Microsoft’s Healthcare Bot service is one solution that uses artificial intelligence (AI) to help the CDC and other frontline organizations respond to these inquiries, freeing up doctors, nurses, administrators and other healthcare professionals to provide critical care to those who need it.

The Healthcare Bot service is a scalable Azure-based public cloud service that allows organizations to quickly build and deploy an AI-powered bot for websites or applications that can offer patients or the general public personalized access to health-related information through a natural conversation experience. It can be easily customized to suit an organization’s own scenarios and protocols.

To assist customers in the rapid deployment of their COVID-19 bots, Microsoft is making available a set of COVID-19 response templates that customers can use and modify:

  • COVID-19 risk assessment based on CDC guidelines
  • COVID-19 clinical triage based on CDC protocols
  • COVID-19 up-to-date answers to frequently asked questions
  • COVID-19 worldwide metrics
COVID-19 assessment bot screenshots
Screenshots from the U.S. Centers for Disease Control and Prevention COVID-19 assessment bot.

Providence, one of the largest health systems in the U.S. headquartered near Seattle and serving seven Western states, had previously used Microsoft’s Healthcare Bot service running on Azure to create a healthcare chatbot named Grace that could help answer patient’s questions online. Using CDC guidelines and its own clinical protocols, Providence was able to build a similar Coronavirus Assessment Tool in just three days to help people in the communities it serves know whether they should seek medical attention for their respiratory symptoms.

The tool, which launched in early March, can bring a prospective patient directly into a telehealth session with a clinician to get immediate care.  It also aims to prevent healthy people or those with mild symptoms from showing up at clinics and emergency departments, which helps to limit community infection and save hospital beds and equipment for those who need it.

Other providers who are now using Microsoft’s Healthcare Bot service to respond to COVID-19 inquiries include:

Virginia Mason Health System, based in Seattle and serving the Pacific Northwest region, has created a patient assessment Healthcare Bot to help its patients understand whether care is needed. The instance is live and has thousands of daily users.

Novant Health, a healthcare provider in four states in the Southeast with one of the largest medical groups in the country, has created a Healthcare bot for COVID-19 information that went live on its website within a few days, with thousands of daily users since its launch.

Across all users, customized instances of Microsoft’s Healthcare Bot service are now fielding more than 1 million messages per day from members of the public who are concerned about COVID-19 infections — a number we expect to escalate quickly to meet growing needs. We hope the answers it can provide will curb anxiety that the “worried well” may experience without clear guidance and save lives by speeding the path to care for those who need it most.

Tags: ,

Go to Original Article
Author: Microsoft News Center

Medline streamlines workflow by automating accounts payable

Medline Industries, a manufacturer and distributor of medical supplies, based in Northfield, Ill., is growing quickly, said Sarah Stokes, director of accounts payable at the company. That means double-digit sales growth year over year, she said, but it also means more paperwork.

“Our biggest challenge is trying to keep up with the volume,” Stokes said.

To help tackle the 2,000 invoices the company receives each day, Medline has turned to optical character recognition (OCR) technology from vendor Abbyy, paired with platforms from several RPA vendors. The combination has gone a long way in automating accounts payable, Stokes said.

Automating accounts payable

Setting up automation for the accounts payable invoice paperwork took around seven months, Stokes said. The accounts payable department first brought in a few RPA vendors, eventually choosing UiPath.

UiPath, a major RPA vendor, provides a bot platform for automating routine tasks. It partners with other vendors, including computer vision and machine learning vendors, to enable customers to imbue their bots with additional skills.

Understanding they needed an OCR vendor as well, the accounts payable team asked the RPA vendors they brought in for recommendations. The vendors, according to Stokes, recommended Abbyy.


A longtime vendor of content capture and document data extraction software, Abbyy maintains partnerships with a number of RPA vendors, Abbyy CEO Ulf Persson said.

Through a suite of intelligent document capturing products, Abbyy can enable RPA users to take “unstructured data or semi-structured data [and turn it] into structured data that can be used in the process automation,” Persson said.

There are literally hundreds of processes in a company that can, or should, undergo automation.
Ulf PerssonCEO, Abbyy

By pairing traditional OCR and document capture technologies with RPA and intelligent content management, Abbyy can touch more markets, Persson said.

“As a capture vendor, you would touch maybe 20% of the automation enterprise. … Now, we can touch 100%,” he said. “That’s tremendously exciting.”

Abbyy works within a range of industries, Persson said, as automation can benefit virtually any company.

“There are literally hundreds of processes in a company that can, or should, undergo automation,” he said.

Saving time

That holds true for Medline. In addition to automating accounts payable invoices, the cash application group is looking at implementing Abbyy, Stokes said. Other divisions of the company also automate processes, she continued, although she couldn’t point to exactly which ones.

Abbyy has been useful, she said, and pairing it with UiPath has saved employees a lot of time. Using automation, only “half of our total head count” works on invoices, she said.

Still, her department did initially face some challenges with Abbyy.

Abbyy CEO Ulf Persson at the Content IQ Summit
Abbyy CEO Ulf Persson speaks at Abbyy’s recent Content IQ Summit.

“Our biggest struggle is we didn’t realize how important the view to the vendor database was,” Stokes said.

Because of the way Abbyy is set up, it needs a clean view of the vendor database. If it sees duplicate vendors, then training batches aren’t understood, she said.

In order to use the platform properly, accounts payable had to identify duplicates and fix them. The process took about three months, she said.

Now, however, Abbyy and UiPath are up and running, and those initial challenges have been ironed out, Stokes said, and adoption of those tools are growing. “It’s getting bigger,” she said.

Go to Original Article

How autonomous systems use AI that learns from the world around it

Millions of engineers across industries such as automotive, aerospace, industrial machinery and medical devices have already built models of the systems they work on using MATLAB or Simulink. This new partnership allows users to bring simulation models built using MATLAB and Simulink to Microsoft’s Azure cloud computing platform, enabling unprecedented scalability and making it easier for developers and engineers building autonomous systems.

“Our core interest really comes down to engineering productivity — the ability to succeed at a task in the least amount of time possible,” said Loren Dean, MathWorks senior director of engineering for MATLAB products.  “This partnership allows engineers to stay in a familiar workflow to learn and apply AI without having to do the things that are non-traditional for them, like setting up the infrastructure to run a bunch of simulations at once. They’re shielded from all that.”

By running hundreds or thousands of simulations in parallel in Azure and learning from massive amounts of data at once, deep reinforcement learning algorithms can find optimal solutions to chaotic, real-world control problems that other types of AI still struggle to solve.

It turns out these problems are everywhere, said Gurdeep Pall, Microsoft’s corporate vice president for Business AI. Microsoft received three times more interest than it expected after opening its autonomous systems limited preview program in May.

The companies who have applied to work with Microsoft’s autonomous systems team and partners are looking to develop control systems to intelligently stitch fabric, optimize chemical engineering processes, manufacture durable consumer goods and even process food. The potential goes far beyond robotics or autonomous vehicles, Microsoft says.

“These are the kinds of diverse use cases for autonomous systems that we’re starting to see emerge,” Pall said.  “As customers learn about the capabilities of our toolchain, we’re seeing them apply it in really interesting ways because these control problems exist almost everywhere you look.”

Most customer use cases Microsoft has seen so far involve helping existing employees do their jobs more efficiently, safely or with higher quality, said Mark Hammond, Microsoft general manager for Business AI and the former CEO of the startup Bonsai, which Microsoft acquired last year. As sensors in modern workplaces collect ever more data, it can become difficult for any one operator — such as someone who is guiding a drill bit or calibrating expensive equipment — to track it all. AI tools can process that data and bring the most relevant patterns to that operator’s attention, enabling them to make more informed decisions.

“The journey from automated to autonomous systems is a spectrum of solutions, and very few of the engagements we’re seeing are in that fully autonomous with no humans in the loop zone,” Hammond said. “The vast majority are assistive technologies that work with people.”

Training AI systems in virtual worlds

Traditionally, AI models have often relied on labor-intensive labeled data for training, which works well for many problems but not for those that lack real-world data. Now, Microsoft and partners like MathWorks are expanding the use of AI into more areas such as those that require learning from the three-dimensional physical world around them — through the power of reinforcement learning and simulation.

Engineers have long used simulations to mathematically model the systems they work with in the real world. This allows them to estimate how a particular change in a chemical, manufacturing or industrial process may affect performance, without having to worry about slowing production or putting people or equipment at risk.

Now, those same simulations can be used to train reinforcement learning algorithms to find optimal solutions, Dean said.

“The AI is really augmenting how these traditional systems have worked — it just gives you greater confidence in your design and gives you additional capabilities that either had to be done manually before or were difficult to solve,” Dean said.

Imagine a building engineer whose job is to calibrate all the heating and cooling systems in a large commercial building to keep each room at a comfortable temperature as people stream in and out for meetings and outside weather fluctuates — while using as little energy as possible. That could involve tuning dozens of different parameters and might take many cycles of modeling and measuring changes for that engineer to find the best balance of controls.

With the new Microsoft and MathWorks partnership, that engineering expert could use machine teaching tools to help an AI system focus on the most important dimensions of the problem, set safety limits and figure out how to reward success as the algorithms learn. This allows for greater transparency and trust in how the AI system is making decisions and also helps it work more efficiently than randomly exploring all possibilities.

The engineer could train the AI using models that he or she already developed in MATLAB or Simulink. The simulations can be automatically scaled up in the Azure cloud — which means the engineer doesn’t have to worry about learning how to host and manage computing clusters.

The end result is the building engineer uses AI to zero in on promising solutions much faster — but still uses his or her judgment to decide what works best.

“This partnership really marries the best of MathWorks’ capabilities for modeling and simulation with the best of Microsoft’s capabilities for cloud computing and AI,” Microsoft’s Hammond said.

Go to Original Article
Author: Microsoft News Center

CAE’s training simulators make us safer – from the hospitals to the heavens | Transform

The birth was seconds away. The mother rested on her back while a medical student sat at the foot of the bed, blue surgical gloves on her hands – a scene common to delivery rooms everywhere. Except the mom was a manikin, her fetus was a manikin and the student wore Microsoft HoloLens.

Using the device, the student looked at the mother’s abdomen and saw a hologram of the fetus inside the womb before it rotated and descended the birth canal. Then, her mixed-reality training session got tricky.

Suddenly, the baby’s shoulders became stuck inside the mother, a risky complication – but an emergency purposely triggered by a classroom instructor. The student had to act fast. She placed her hands on the tiny manikin and gently freed the shoulders, safely completing another digital delivery.

CAE LucinaAR – the first human-patient simulator augmented with HoloLens – simultaneously delivered another digital lesson. The technology comes from CAE, a Canadian company that offers virtual-to-live training solutions to assess human performance, improving overall safety from health care to civil aviation to defense operations.

A medical student practices delivering a baby with the use of a virtual-to-live patient simulator and Hololens.
A medical student practices delivering a baby with CAE LucinaAR and HoloLens.

“CAE operates in three sectors where the stakes are high, where there’s no room for error and where the people need to be properly trained to be ready for unlikely situations that could lead to catastrophes,” says Dr. Robert Amyot, president of CAE Healthcare, one of CAE’s three business segments.

“On-the-job training is dangerous and costly,” adds Amyot, a cardiologist by trade. “So, we train pilots to make flying safer. We train the forces in our defense and security division to make them more prepared for their missions. And we train clinicians and health care providers to improve patient safety.”

By going digital, each of those training regimens is becoming more precise at pegging and addressing human vulnerabilities, says Marc Parent, the CEO at CAE.

In the realm of aviation, CAE guides pilots to prep for potential airborne adversities by using individualized simulations built with artificial intelligence and the Internet of Things (IoT).

A new pilot trains on a CAE flight simulator.
A new pilot trains on a CAE flight simulator.

“Although it’s the safest mode of transportation in the world, pilots have long been assessed in a subjective way,” Parent says. “But now, by leveraging the data that our simulators are giving us – powered by the cloud – we can give them an objective assessment in real time. That’s invaluable.

“When the pilots go into our simulator, we are able to give them personalized insights into their skills, into how they perform different operational practices. This raises their level,” Parent says. “And practice makes perfect.”

Missouri hospital sued over medical records breach

A hospital in Missouri faces a lawsuit after a medical records breach occurred as a result of an email phishing scam, something that’s difficult to protect against within healthcare organizations, according to a security expert.  

In January, Children’s Mercy Hospital in Kansas City, Mo., notified 63,049 individuals who were potentially affected by the medical records breach, according to Jake Jacobson, Children’s Mercy director of public relations.

An investigation led by the hospital determined that the mailbox accounts of four of five affected employees had been downloaded by unauthorized individuals. According to the notification, information accessed during the incident varied by individual, but could include information such as medical record number, first and last name, date of birth, gender, age, height, weight, body mass index, admission and discharge date, procedure date, diagnostic and procedure codes, demographic information, clinical information, conditions and diagnosis, and other treatment information and identifying or contact information.

Fight back with email screening tools

Security expert Larry Ponemon said a number of healthcare providers are particularly susceptible to phishing scams because cybersecurity is not their “highest priority” and they often lack a “good governance process” for controlling data access. Ponemon is the founder of Ponemon Institute, which studies data protection and information security.

“It seems like the healthcare industry, healthcare providers [are] the most vulnerable relative to the industries we study,” Ponemon said.

Within the healthcare industry there’s “not really a great technology that could identify a phishing email,” Ponemon said. He noted that implementing employee training and installing email screening tools that scour incoming emails, attachments and embedded URLs to identify potential phishing attacks could go a long way toward keeping such incidents at bay.

It seems like the healthcare industry, healthcare providers [are] the most vulnerable relative to the industries we study.
Larry Ponemonfounder, Ponemon Institute

“A lot of phishing scams I’ve seen have not been all that difficult to see,” Ponemon said. “If you look at the information, read the link, you can guess with about 90% accuracy that basically this is not real and [is] likely to be a phishing email. But people in healthcare are under a lot of pressure, so when they get an email they don’t necessarily stop and check the terms in each email.”

Additionally, Ponemon said healthcare organizations often operate a “flat network,” instead of having layers, meaning when something happens in one device, it can spread very quickly to multiple devices, which he described as a “lateral infection.”

“Malware infections on one system can actually touch hundreds or even thousands of systems in the world of IoT; in healthcare everything is about an IoT device,” Ponemon said. “That’s why it’s easy for bad stuff, malware, phishing scams, to spread quickly.”

Jacobson, with Children’s Mercy, said the hospital has taken steps to protect against further incidents, including implementing additional technical control of multifactor authentication. Additionally, the hospital has installed a call center and informational webpage to provide answers to families who might have been affected and is offering free identify theft protection to those families.

Medical records breaches not new

The lawsuit against Children’s Mercy Hospital was filed by the firm McShane & Brady in July. Attorney Maureen Brady said the firm would like to see medical records breaches stopped.

“It’s very hard because you can’t unring that bell,” Brady said. “Once the information is out, it’s out forever; you can’t get it back … the anxiety and embarrassment and humiliation that goes along with this type of disclosure is astronomical.”

The threat of a medical records breach occurring is not new to the healthcare community. Though 2017 saw fewer massive health data breaches compared to 2016, 5.6 million Americans suffered from a medical records breach, an average of at least one medical records breach per day throughout the year, according to data released last year by Protenus.

In addition to the newly filed lawsuit, Children’s Mercy Hospital has faced other lawsuits in the past for medical records breaches.

Why healthcare APIs will save lives, money and time

Stan Huff, M.D., chief medical informatics officer at Intermountain Healthcare, made a strong case for medical platform interoperability, healthcare APIs and an open source approach to health IT at an Object Management Group conference in Boston on Monday.

IT departments in most industries have long been enthusiastic users of APIs – standard software building blocks that make development and interoperability easier. They’ve also participated in the open source movement, where code is shared, reused and improved upon for the common good.

In the health IT space, however, these concepts have been slower to gain traction, and Apple just recently became the first company to open up its Health Record API to developers. Apple’s API is based on the Fast Healthcare Interoperability Resources (FHIR) standard, which was created in 2014 and is arguably the most talked about of the healthcare APIs today.

But being talked about is a long way from being implemented, and that, Huff was quick to stress, is the major problem. “FHIR is really easy to implement,” he told a room full of physicians. “It’s had unprecedented support from EHR companies. But it’s young still. We have a vision, but we just need to get there.”

What healthcare APIs can jump-start

The vision is a world where any electronic health record system could communicate with any other system; data could be gathered and mined; and, ultimately, decision engines could be built that could improve patient care, cut costs, reduce medical errors and even help with doctor burnout, Huff said.

To make his point, he shared some stark data. Citing a Johns Hopkins study, Huff said approximately 250,000 people die a year due to medical error, making errors the third-leading cause of death in the U.S. That is five times the amount of people who die in auto accidents, he said.

And then there is the issue of cost, because each EHR system at each hospital needs unique applications created for it. “That’s like saying we need 50 different versions of Yelp for each hospital,” he said. “Our architecture is wrong. It’s set up so that we can’t share what we’ve created. We’re paying an incredible price for software. Each useful app is created or re-created on each platform, and we pay for it.”

To be more specific, Huff said Intermountain, based in Murray, Utah, has developed 150 clinical decision support engines that offer best practices and advice on everything from diabetes to heart health.

“But that 150 really represents the low-hanging fruit,” he said. “We need 5,000 rules or modules, and there’s no scalable path to get there. And there’s no scalable path to pass that information on to community hospitals.”

If we do this right, we could save 100,000 lives a year.
Stan HuffM.D., chief medical informatics officer, Intermountain Healthcare

One large hospital was able to develop 13 of these decision engines in six months, but they’re specific to the EHR in use and would be “cost-prohibitive” to share with other hospitals.

To get started with healthcare APIs and down the path of interoperability, Huff said IT professionals need to ask themselves three questions:

  • What data should be collected?
  • How should the data be modeled?
  • And what does the data mean?

Asking, and then answering, those questions will kick-start the interoperability journey, help decide on the correct healthcare APIs and eventually will lead to sweeping changes in medicine.

“If we do this right, we could save 100,000 lives a year,” he said. “We could go from being right 50% of the time to 80% of the time. And we could get new EHR systems for millions, rather than billions.”

Six ransomware prevention tips for healthcare organizations

In healthcare, medical practices are in the business of treating patients for illness and disease. Some of the…


* remove unnecessary class from ul
$(“#inlineregform”).find( “ul” ).removeClass(“default-list”);

* Replace “errorMessageInput” class with “sign-up-error-msg” class
function renameErrorMsgClass() {
$(“.errorMessageInput”).each(function() {
if ($(this).hasClass(“hidden”)) {
$(this).removeClass(“errorMessageInput hidden”).addClass(“sign-up-error-msg hidden”);
} else {

* when validation function is called, replace “errorMessageInput” with “sign-up-error-msg”
* before return
function validateThis(v, form) {
var validateReturn = urValidation.validate(v, form);
return validateReturn;

* DoC pop-up window js – included in moScripts.js which is not included in responsive page
$(“#inlineRegistration”).on(“click”,”a.consentWindow”, function(e) {
window.open(this.href, “Consent”, “width=500,height=600,scrollbars=1”);

conditions healthcare providers encounter can be prevented if a patient takes preventative steps. In a similar fashion, healthcare organizations should follow ransomware prevention tips to combat cyberattacks and data breaches. 

In the on-going fight between cyberattackers and security software firms, the most common casualties are those who don’t employ adequate protections in their systems — from small medical practices that have limited budgets and IT knowledge all the way to large healthcare organizations. With so much at risk for healthcare organizations, IT must implement proactive steps to help mitigate their risks and keep attacks at bay.

Here are six ransomware prevention tips healthcare organizations should include as part of their ongoing security strategy.

Email protections can reduce potential attacks

Small and large organizations should recognize that email is one of the preferred methods cybercriminals use to execute malicious code. This allows attackers to reach as many potential victims as possible by hiding behind phishing attempts and fake emails to persuade recipients to open an attachment. As a result, cyberattackers are able to infect a user’s machine and take control of it and hold their data for ransom. IT must ensure adequate protections and filters are applied at the email level, and users should have limited permissions to network resources to limit damage in the case of successful infections. 

End-user education and awareness

Educating users on how to determine whether an email is safe to open and review its attachment is a critical step to reduce the potential of a successful infection. Unfortunately, cybercriminals have also adopted new methods that allow them to disguise themselves behind email addresses of the recipient’s co-workers and other services to make the email look like it is coming from a trusted source. IT departments must spend more time upfront educating their end users and adopting security campaigns.

Implementing protections at multiple entry points

Protecting against attacks requires organizations to cover multiple fronts from which attackers attempt to infect and gain access to systems. As a result, healthcare organizations must invest in having the proper security tools for the following three areas: email, network environment and endpoint devices. This approach helps create a fence that plays a critical role at stopping hacking and phishing attempts.

A working backup with a tested recovery plan

In the unfortunate event that a user or organization is faced with a successful ransomware infection, one of the best defenses that an organization has is when they are able to successfully recover their data and restore all the affected information successfully. Part of this recovery exercise comes from the requirement for an organization to ensure that they have tested their DR plan to ensure a quick and successful recovery.

Employee advanced threat protection for emails and systems

For IT to feel comfortable that their systems are protected, intelligent systems that can monitor network and user activities 24/7/365 are one of the most recommended ransomware prevention tips. Today IT departments in healthcare are installing tools that offer advanced threat protection, including machine learning that analyzes all activities around a system to identify abnormal activities that could signal an infection or hacking attempt. These systems are also supplementing traditional antivirus tools that primarily rely on signature-based virus definition to detect possible malicious code based on behavior and not signature.

All systems must stay up to date

For a cyberattacker to take control of a victim’s computer, their malicious code must locate a vulnerability and exploit it to execute itself. Targeted systems include the browser, the network firewall, the operating system, smartphone platforms and device firmware. Fortunately, most software vendors are continuously updating their software and ensuring their products are secure. Although there are cases when patching occurs after an initial exploit is discovered by hackers, most companies can quickly react and offer fixes for their vulnerabilities. IT must ensure that all their systems remain up to date when it comes to patches and updates to address any potential vulnerabilities that may exist in their systems.

Investing in end-user training, security tools and continuous system monitoring is becoming the norm for IT across hospitals and other healthcare organizations. With the increasing threats and sophistication of tools used by cybercriminals today, healthcare entities cannot rely solely on legacy antivirus tools and traditional firewalls to keep them protected. The damages from data breaches or infections have serious implications, and organizations can ensure their IT has the funding and support to build their defenses against this threat by following the ransomware prevention tips above.

Dig Deeper on Electronic medical records security and data loss prevention

Radiology AI and deep learning take over RSNA 2017

CHICAGO — As the medical imaging world debates whether machines are supplanting humans, veteran radiology AI thinker Curtis Langlotz, M.D., offered what is becoming a widely held view of the profession’s technology future.

“To the question, will AI replace radiologists, I say the answer is no. But radiologists who do AI will replace radiologists who don’t,” Langlotz, professor of radiology and biomedical informatics at Stanford University School of Medicine, said to a packed hall at the RSNA 2017 conference.

The setting was a scientific panel during the 103rd Scientific Assembly and Annual Meeting of the Radiological Society of North America, held at the McCormick Place conference center.

RSNA show vigorous in its second century

RSNA, with more than 54,000 members from around the world, annually stages what is the biggest healthcare conference and exposition on the continent. This year, the event attracted some 50,000 attendees, with nearly half of them medical imaging professionals, and 667 exhibitors — mostly vendors.

In addition to artificial intelligence and various forms of machine learning, RSNA 2017 was more deeply immersed than ever before in value-based imaging, the pursuit of quality over volume, as the U.S. healthcare system moves in that direction.

The RSNA 2017 exposition floor at the McCormick Place conference center in Chicago.
The RSNA 2017 exposition floor at the McCormick Place conference center in Chicago.

Deconstructing PACS

Also as strong as ever were picture archiving and communications systems (PACS) and vendor-neutral archive (VNA) technologies and systems for storing and viewing complex medical images, including the increasingly popular strategy of “deconstructing PACS” — stitching together parts of PACS from various vendors.

But radiology AI and deep learning — a subset of machine learning that uses advanced statistical techniques to enable computers to improve at tasks with experience — were probably the hottest topics at RSNA 2017.

Indeed, Langlotz’s session — and dozens of other panels on AI, deep learning and machine learning in radiology and other imaging-intensive specialties — drew overflow crowds.

Radiology AI excitement and reality

To the question, will AI replace radiologists, I say the answer is no. But radiologists who do AI will replace radiologists who don’t.
Curtis LanglotzM.D., professor of radiology and biomedical informatics at Stanford University School of Medicine

“We’re definitely right in the eye of the storm of the hype cycle,” Rasu Shrestha, M.D., chief innovation officer at University of Pittsburgh Medical Center, told SearchHealthIT on the busy “technical exhibition,” or show, floor. “Having said that, that hype is being driven by an immense amount of hope. Could AI and machine learning solve for the complexities of healthcare?”

Langlotz acknowledged that radiology AI has already been through a number of hype-bust cycles in recent decades, but his work and that of colleagues at the Mayo Clinic and The Ohio State University, among others, shows that AI and machine learning have made dramatic progress.

Luciano Prevedello, M.D., division chief for medical imaging informatics at The Ohio State University Wexner Medical Center, said at the same deep learning session that “from 2014 to 2015 is when the algorithms started surpassing the human ability to classify” medical image data.

Experts say AI can aid imaging now

The radiology AI and deep learning experts said the software technologies, which require supercomputer-level computing power, can help radiologists and other imaging professionals on a practical basis.

For example, today, AI and deep learning can help physicians more efficiently produce images, improve quality of images, triage and classify images, serve in computer-aided detection of medical problems, and perform automated report drafting, Langlotz said.

As for value-based imaging, one radiology IT expert, Jim Whitfill, M.D., chief medical officer at Innovation Care Partners, a physician-led accountable care organization in Scottsdale, Ariz., said radiologists have opportunities to benefit financially from value-based care if they take on financial risk as ACOs do.

Value-based care and imaging not going away

During a panel on ACOs and value-based care, Whitfill noted that despite recent moves by the administration of President Donald Trump to trim several value-based care programs, federal healthcare officials are still behind the healthcare reimbursement approach, which Whitfill said has firm supporters.

“It’s absolutely critical that radiologists bring their talent around leadership, information technology and the larger healthcare system to bear as organizations begin to make this shift” toward value-based care, Whitfill said.

In an interview, Whitfill said one of the biggest technological advances in medical imaging that will help in the move toward value-based area is enterprise imaging.

“Historically we’ve been very focused on radiology in the PACS system,” Whitfill said. “But now, organizations are not only adding cardiology images, but also ophthalmology images, dermatology images and others, so we’re seeing a revolution in terms of the imaging platforms moving all these images into one place.”