Free EMR 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 EMR and EHR for FREE!

The Secret to Coding Accuracy Is In The Training Tools

Posted on September 24, 2018 I Written By

The following is a guest blog post by Scot Nemchik, Vice President of Coding Education and Auditing at Ciox.

Accurate coding has become more important to healthcare organizations and more critical to their bottom lines than ever before. While the traditional value of coding to an organization was simply in its effect on timely reimbursement, outside entities like IBM Watson Health and the U.S. News & World Report, among many others, are today utilizing the same broader organizational coding data to assess outcomes, provide company profiles, drive news, assign ratings and rankings, and determine value in the healthcare organizations they assess.

Because the impact of accurate coding in the modern era extends beyond reimbursement into reputation, perception, and new business development capabilities, it’s clear that the stakes have been raised for most organizations. With added importance assigned to coding accuracy, many of these companies are today assessing how to drive greater coding accuracy within their organization. Yet, the methodologies by which organizations assess new hires for coding capabilities, and by which they train and enhance their existing workforce, are largely unchanged in the last decade or more.

Coding is an industry that requires specialized skills, and so it is important for several reasons to make quality hires at the onset. It is far more profitable for an organization to retain its coders, which requires better upfront assessment. A study from the Society for Human Resources Management (SHRM) on employee retention suggests that the cost to an organization in replacing an employee is between 50 and 75 percent of their salary. In an industry like medical coding, better screening measures must be in place to get the right people involved on the team the first time.

One of the primary ways companies can look to achieve better candidate hires is by moving away from simple multiple-choice assessments of coding skill during the screening process, as those assessments are not as predictive of coding aptitude as modern measures. A more effective approach is achieved through the use of platform-based assessment techniques, in which the candidate can respond to hypothetical medical reports with actual codes, providing more meaningful insight into coding aptitude.

Those same training platforms also serve as a solution for companies looking to bolster the accuracy of their existing coding teams. Traditionally, organizations have relied heavily on passive forms of training (e.g., webinars, LMS assignments) to convey important coding instruction, hoping that instruction is put into practice in the daily work settings. Today, through active, platform-based training, the results are far more scalable and effective.

Coders Learn by Coding

By training in an active coding learning environment, coders learn by doing, a proven method which accelerates learning and optimizes retention. Through a hands-on learning approach, coders can put their skills to the test and learn from any mistakes in real time.

Platform learning provides not only pre-hire testing, but also baseline performance assessment. By giving new hires and existing teams alike the same metric tests, organizations can identify their best assets. Additionally, platforms for coding training offer effective and efficient cross-training, allowing organizations to diversify the capabilities of their coders and cross-pollinate or backfill specific coding teams for more flexibility. Beyond cross training, existing teams benefit from the development of their assets through ongoing education. Coding is a dynamic field with annual changes, and access to the newest codes and guidelines is critical. A comprehensive learning platform offers all of these capabilities and measurements in real-time.

As companies look for ways to improve the accuracy of their coding staff, whether through new hires or incremental improvements to existing teams, transitioning to a platform-based training and assessment environment, with a host of experiential and measurement capabilities, can provide the solution.

About Ciox
Ciox, a health technology company and proud sponsor of Healthcare Scene, is dedicated to significantly improving U.S. health outcomes by transforming clinical data into actionable insights. Combined with an unmatched network offering ubiquitous access to healthcare data, Ciox’s expertise, relationships, technology and scale allow for the extraction of insights from structured and unstructured clinical data to create value for healthcare stakeholders. Through its HealthSource technology platform, which includes solutions for data acquisition, release of information, clinical coding, data abstraction, and analytics, Ciox helps clients securely and consistently solve the last mile challenges in clinical interoperability. Ciox improves data management and sharing by modernizing workflows and increasing the accuracy and flow of information, while providing transparency across the healthcare ecosystem and helping clients manage disparate medical records. Learn more at www.ciox.com

How to Text PHI with Patients and Stay Compliant

Posted on September 19, 2018 I Written By

The following is a guest blog post by Jim Higgins, Founder & CEO at Solutionreach. You can follow him on twitter: @higgs77

Did you know that 73 percent of Americans say it is difficult to reach them by phone? In fact, Americans ignore 337 calls each year and that number is rising. Even if you leave a message, chances are high no one will ever hear it—80 percent of people report that they don’t even bother leaving a voicemail anymore because they don’t believe it will get listened to. More and more, phone calls are seen as invasive, outdated, or ineffective. Instead, people prefer to communicate via modern methods such as text message.

Texting Reigns as Favorite Communication Tool

We all know that pretty much everyone with a cell phone texts friends and family regularly. What is less well-known is that people would like to extend their texting habits to their healthcare provider. According to the 2017 Patient-Provider Relationship Study, 60 percent of patients want text reminders. Seven out of ten patients say they would like text communication beyond just reminders as well. It’s not just millennials. Around half of baby boomers also prefer text messages.

Unfortunately, many practices have shied away from texting or emailing patients through unsecured channels, wary of running into compliance issues. This is especially true when it comes to texting patients when those messages may include protected health information (PHI).

In fact, I suspect that if you were to poll a group of healthcare workers concerning the legality of sending PHI through unsecured text message, you would probably get answers all along the spectrum. Yes, no, maybe so? Many just don’t know.

Last March, at the HIMSS health IT conference Roger Severino, Director of the US Department of Health and Human Services Office for Civil Rights (OCR), the HIPAA enforcement agency, clarified the confusion.  According to Severino, providers may share PHI with patients through unsecure text messages as long as they have informed their patient that texting is not secure, asked for permission, and documented that consent.

“I think it’s empowering the patient, making sure that their data is as accessible as possible in the way they want to receive it, and that’s what we want to do.” Severino said.

Implementing Texting in a Compliant Way

This announcement was a big deal. Patients want to text you…and they want you to text them back. You significantly increase the value you offer to patients simply by giving them this option. So how does the implementation of Severino’s suggestions look in practice? Let’s say that you receive a text message from a patient named Mary asking you for some health-related information. In response, you can send something like this: “Hi Mary. I would love to chat with you more about your health. Text message is not a secure way to do that. Would you still like to continue this conversation?” If you are the one to initiate the conversation, you can send a similar message requesting permission before continuing.

Once Mary agrees and you document that permission, you are then allowed to continue the conversation without concern of violation. A key piece to remember here is that it is important that you make sure your patients are aware that texting is not secure. Then, if the patient feels uncomfortable communicating via that channel, you should move the conversation to a secure method such as a phone call, secure patient portal, or in-office visit. Remember—you are required to make patients aware of unsecured communication and receive authorization before discussing PHI on an unsecured channel.

As one final best practice, always include an opt-out message. Even if a patient has given consent in the past, you must always offer the option to discontinue the communication. This means that it is best to include a message such as “Reply STOP to opt-out” in your text messages.

In summary, if a healthcare provider would like to share PHI with a patient through regular, unsecured text messages, they must first:

  • Inform the patient that texting is not secure
  • Receive permission from the patient to continue
  • Document the patients’ consent
  • Offer an opt-out option

If you are not yet texting with patients (or only sending basic text reminders), this is a critical time to make a change. There is no other form of communication that has such a high level of adoption and engagement. Texting improves the health outcomes for patients as well as the financial outcomes for practices. With this recent clarification of policy by compliance officials, we can expect that the use of text will continue to grow dramatically as we move into the future.

Solutionreach is a proud sponsor of Healthcare Scene. As the leading provider of patient relationship management solutions, Solutionreach is dedicated to helping practices improve the patient experience while saving time for providers and staff.

Don’t Be The Last Practice To “Get” Digital Health

Posted on September 14, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

Physicians, are you savvy about the digital health technologies your patients use? Do you make it easy for them to interact with you digitally and share the health data they generate? If not, you need to move ahead and get there already. While you may be satisfied with sidestepping the whole subject, patients aren’t, a recent report suggests.

As you probably know already a growing number of patients, most notably millennials, are integrating digital health tools into their everyday lives.

Research from Rock Health, which surveyed about 4,000 consumers, found that the share of respondents using at least one digital tool (such as telemedicine, digital health tracking apps or wearables) hit 87% last year. To get a sense of how impressive this is, bear in mind that just five years ago, only a tiny handful of consumers had given any of these tools a try.

What’s also of note is that some of these consumers were willing to skip insurance and pay out of pocket for digital care. One particularly clear example of this involves live video telemedicine; Sixty-nine percent of consumers who paid out of pocket for such consults said they were “extremely satisfied” with the experience.

Patients who reported having a chronic health condition seemed less likely to use digital tools to track their health metrics. Case in point: When it came to blood pressure tracking, just 11% captured this data with a digital app or journal. However, this may reflect the higher-than-average of those diagnosed with elevated pressures, a senior population with a lower level of tech sophistication.

Lest all of this sound intimidating, there’s at least some good news here. Apparently, a full 86% of respondents said that they’d be willing to share data with their physician, a much larger share than those who would exchange data with a health plan (58%) or pharmacy (52%). In other words, they trust you, which is a big asset under these circumstances.

If you want to dive into digital health more deeply, here’s a few obvious places to start:

  • Link in-person and telemedicine visits: Rock Health found that a whopping 92% pf respondents who had an in-person visit first were satisfied with their video visit.
  • Be vigilant about data security: Almost 9 out of 10 consumers participating in the survey said that they would be willing to share data with you. Don’t lose that trust to a health data breach; it will be hard if not impossible to get it back.
  • Bring chronically-ill seniors on board: While this group may not be terribly inclined to digitize their healthcare, doing so can help you treat them more effectively, so you’ll probably want to make that point up front.

Like it or not, wearables, fitness bands, mobile health apps, and other digital health tools have arrived. It’s no longer a matter of if you take advantage of them, but when and how. Don’t be the last practice in your neighborhood that just doesn’t get it.

It’s Time To Work Together On Technology Research

Posted on September 12, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

Bloggers like myself see a lot of data on the uptake of emerging technologies. My biggest sources are market research firms, which typically provide the 10,000-foot view of the technology landscape and broad changes the new toys might work in the healthcare industry. I also get a chance to read some great academic research, primarily papers focused on niche issues within a subset of health IT.

I’m always curious to see which new technologies and applications are rising to the top, and I’m also intrigued by developments in emerging sub-disciplines such as blockchain for patient data security.

However, I’d argue that if we’re going to take the next hill, health IT players need to balance research on long-term adoption trends with a better understanding of how clinicians actually use new technologies. Currently, we veer between the micro and macro view without looking at trends in a practical manner.

Let’s consider the following information I gathered from a recent report from market research firm Reaction Data.   According to the report, which tabulated responses from a survey of about 100 healthcare leaders, five technologies seem to top the charts as being set to work changes in healthcare.

The list is topped by telemedicine, which was cited by 29% of respondents, followed by artificial intelligence (20%), interoperability (15%), data analytics (13%) and mobile data (11%).

While this data may be useful to leaders of large organizations in making mid- to long-range plans, it doesn’t offer a lot of direction as to how clinicians will actually use the stuff. This may not be a fatal flaw, as it is important to have some idea what trends are headed, but it doesn’t do much to help with tactical planning.

On the flip side, consider a paper recently published by a researcher with Google Brain, the AI team within Google. The paper, by Google software engineer Peter Lui, describes a scheme in which providers could use AI technology to speed their patient documentation process.

Lui’s paper describes how AI might predict what a clinician will say in patient notes by digging into the content of prior notes on that patient. This would allow it to help doctors compose current notes on the fly.  While Lui seems to have found a way to make this work in principle, it’s still not clear how effective his scheme would be if put into day-to-day use.

I’m well aware that figuring out how to solve a problem is the work of vendors more than researchers. I also know that vendors may not be suited to look at the big picture in the way of outside market researcher firms can, or to conduct the kind of small studies the fuel academic research.

However, I think we’re at a moment in health IT that demands high-level research collaboration between all of the stakeholders involved.  I truly hate the word “disruptive” by this point, but I wouldn’t know how else to describe options like blockchain or AI. It’s worth breaking down a bunch of silos to make all of these exciting new pieces fit together.

2019 CPT Codes To Cover Remote Monitoring And Digital Care Coordination

Posted on September 10, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

The American Medical Association has released CPT code set changes 2019, and among them are some new options specific to digital health practices.

While providing such codes is a no-brainer — and if anything, the AMA is late to the party – it’s still a bit of noteworthy news, as it could have an impact on the progress of digital care.  After all, the new codes to make it easier to capture the value of some activities providers may be self-funding at present. They can also help physicians track the amount of time they spend on remote monitoring and digital care coordination more easily.

The 2019 release includes 335 changes to the existing code set, such as new and revised codes for adaptive behavior analysis, skin biopsy and central nervous system assessments. The new release also includes five new digital care-related codes.

The 2019 code set includes three new remote patient monitoring codes meant to capture how clinicians connect with patients at home and gather data from care management and coordination, and two new “interprofessional” Internet consult codes for reporting on care coordination discussions between a consulting physician and the treating physician

It’s good to see the AMA follow up with this issue. To date, there have been few effective ways to capture the benefits of interactive care online or even via email exchanges between physician and patient.

As a result, providers have been trapped in a vicious circle in which virtual care doesn’t get documented adequately, payers don’t reimburse because they don’t have the data needed to evaluate its effectiveness and providers don’t keep offering such services because they don’t get paid for performing them.

With the emergence of just five new CPT codes, however, things could begin to change for the better. For example, if physicians are getting paid to consult digitally with their peers on patient care, that gives vendors incentives to support these activities with better technology. This, in turn, can produce better results. Now we’re talking about a virtuous circle instead.

Obviously, it will take a lot more codes to document virtual care processes adequately. The introduction of these five new codes represents a very tentative first step at best. Still, it’s good to see the AMA avoid the chicken-and egg-problem and simply begin to lay the tracks for better-documented digital care. We’ve got to start somewhere.

 

Patient Directed Health Data Exchange on The Blockchain

Posted on September 7, 2018 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

I’ve long been friends with Dr. Tom Giannulli who most of you will probably have known as the CMO of Kareo. I first met Dr. Tom back when he created what I would call the first iPad optimized EHR interface back when Dr. Tom was at Epocrates and before they sold that EHR to Kareo. Needless to say, Dr. Tom is the kind of guy that likes to sit on the cutting edge of technology and how it applies to healthcare. So, it was no surprise to me when he came to me with his patient directed health data exchange called PatientDirected.io which is built on the blockchain.

While a lot of people talk about blockchain and theories about how blockchain could help healthcare, a lot of what people were doing was just talk. What I like about Dr. Tom and PatientDirected.io is that they just put out a video demo of a patient chart being requested from Kareo by the patient and then the patient sending that chart to Epic. Check it out to see what I mean:

Many of you that watch this demo might be asking. How is this on the blockchain? That’s one of the things that many people don’t understand about blockchain. If it’s done right, you won’t know anything about the blockchain. However, the blockchain can do things like creating smart contracts with providers which can create trusted connections. The blockchain is distributed, so your data isn’t stored on a central server that’s owned and controlled by PatientDirected.io. Basically, blockchain has a number of benefits, but it’s the “Intel Inside” and so it’s not something you should see as an end user, but it could provide some great benefits.

I also like that PatientDirected.io isn’t trying to reinvent the wheel. They’re using trusted third party applications like Verato to handle their master patient index and for verifying patients identity. There’s a lot more to explore when it comes to identity management, but it’s smart to work with companies that are doing this all across healthcare.

I was also impressed with the detailed sharing permissions that were available in PatientDirected.io. At first glance, a part of me wonders if it’s too complex for most patients. However, as long as the options are there, the interface can adapt to allow for specific patient preferences when it comes to data sharing. Of course, it’s nice that all of the sharing of this data will be tracked on the blockchain.

The key to all of this working for me is the integration with the EHR vendor. It looks like it’s using Direct to handle the messaging to the EHR vendor and back. This is good because I believe all certified EHR (which is pretty much all of them) have direct messaging built in. Some have integrated it better than others, but they all have this capability. My big concern with it though is whether what’s being shared by EHR vendors using Direct is enough data. And will that data that gets sent from one EHR to another appear in a format that’s useful to the receiving physician? If it’s not, then it doesn’t solve much of anything. Plus, I wonder what happens when a doctor gets a record request and doesn’t respond. This is especially true for EHR vendors who haven’t integrated Direct into the core EHR workflow. Will this take a culture change to not leave patients waiting for records that will never come?

As you could imagine, PatientDirected.io has an ICO offering on StartEngine.com. Looks like it just got started, but there’s an opportunity to buy their tokens if you’re interested and believe they’re on to something special.

I think there is a space for a patient directed health information exchange assuming we can make the exchange of information between disparate providers very simple. There are still some challenges for patients when it comes to getting access to their health information, but the law is clear that patients should have access to their health information. Now we just need the user interfaces to be as simple as clicking a button like is demonstrated in the video above and we’ll see much more patient directed health information exchange.

The Ambulatory EHR Market with Raul Villar, Jr. CEO of AdvancedMD

Posted on September 5, 2018 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

The ambulatory EHR market is near to my heart since that’s where I started when I entered this world of healthcare IT. My first job was implementing an EHR in a small ambulatory practice. As regular readers know, I’ve commented on how the independent small practice is in trouble. I’m not suggesting this is what I’d like to happen or what should happen, but there are certainly a lot of challenging pressures on small practices.

Along with these pressures, the ambulatory EHR market is extremely different today than it was 5-10 years ago. The $36 billion funded meaningful use era of EHR adoption was what I call the golden age of EHR. We could argue whether it was a golden calf or not, but from a market standpoint, the meaningful use money fueled adoption of the EHR.

Today’s ambulatory EHR market is very different. That’s why we were excited to sit down with Raul Villar, Jr. CEO of AdvancedMD to talk about his perspective on the ambulatory EHR market. We also talk with him about the evolution of AdvancedMD as it went from ownership by ADP to now being owned by Marlin Equity Partners and what those changes mean for their customers. Plus, we go over AdvancedMD’s acquisition of NueMD and what their strategy is behind the acquisition. Finally, we talk about EHR vendors as a platform and where he sees AdvancedMD taking their platform in the future.

If you’re interested in the ambulatory EHR market or in AdvancedMD, you’ll enjoy this interview with Raul Villar, Jr.

If you enjoyed this video interview, be sure to Subscribe to Healthcare Scene on YouTube and watch all of our healthcare IT interviews.

3 Types of Medical Billing Companies

Posted on August 31, 2018 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

I was recently talking with the CEO of an EHR vendor. As we talked about their EHR software and what they were working on in the future, the CEO made a really important comment. He said, “The EHR can be great, but if you don’t take care of the medical billing the right way then none of that matter.”

This was such an important point and one that I’d seen first hand. An OB/GYN friend of mine had an EHR that they loved. As the doctor, she loved it for her clinical work. The problem was that it wasn’t tied to a great practice management system. So, she was having issues with her billing. The problem was so bad that she ended up leaving the EHR she loved clinically to find something that would solve her billing problems. Don’t ever underestimate the importance of medical billing.

I recently came across an article on the Kareo blog which highlighted 3 levels of medical billing and RCM (revenue cycle management) services billing companies can offer a practice:

Light

Level of service offered by many billing software vendors.

Full-Service

Level of service offered by some software vendors and most traditional billing services.

Boutique

Level of service typically offered by smaller “mom and pop” billing companies who have expertise in a limited number of specialties and/or provide more oversight.

As you evaluate medical billing companies for your practice, this is a nice framework for evaluating the various medical billing companies that are out there. Each one provides a different set of expertises to help your practice. Understanding that difference is key to choosing one that will work best for you.

What’s been your experience with medical billing companies? Do these 3 types make sense to you or would you look at them from a different angle?

Real-world Health AI Applications in 2018 and Further

Posted on August 29, 2018 I Written By

The following is a guest blog post by Inga Shugalo, Healthcare Industry Analyst at Itransition.

In contrast to legacy systems that are just algorithms performing strict tasks, artificial intelligence can extend the task itself, creating new insights from the information fed to it. Current healthcare AI is powerful enough to undertake such complex challenges as automated diagnosis, medical image analysis, virtual patient assistance, and risk analysis, supporting health specialists in making more swift and informed decisions.

In 2016, Frost & Sullivan predicted the healthcare AI market to reach $6.6 billion by 2021. Meanwhile, 2017’s Accenture report estimates AI saving $150 billion annually for the U.S. healthcare economy by 2026. “At hyper-speed, AI is re-wiring our modern conception of healthcare delivery,” researchers from Accenture say.

Standing in the middle of 2018, the industry already hints on its course regarding further AI expansion. Spoiler alert: as well as with blockchain AR, VR, and any other kind of innovative custom medical software, the adoption challenges persist.

Current and prospective AI directions in healthcare

Diagnosis support

One of the most fascinating and valuable directions for AI to evolve is its ability to help providers diagnose patients more accurately and at a higher pace. We are thrilled to see how 2018 erupts with many healthcare organizations adopting artificial intelligence and creating unprecedented cases of assisted diagnostics with it.

Geisinger specialists applied AI to analyze CT scans of patients’ heads and detect intracranial hemorrhage early. Intracranial hemorrhage is a life-threatening form of internal bleeding, affecting about 50,000 patients per year, with 47% dying within 30 days.

Geisinger was able to automatically pinpoint and prioritize the cases of intracranial hemorrhage, focusing the attention of radiologists on them and thus allowing for timely interventions. This approach reduced the time to diagnosis by 96%.

Mayo Clinic currently uses IBM Watson’s superpowers to match patients with fitting clinical trials. The clinic’s officials stated that only 5% of patients enrolled in trials in the U.S., which significantly hinders clinical research and innovation in cancer therapies. On the other side, manual patient-trial matching is a time-exhausting process.

Watson runs this process on the background, comparing the patients’ conditions with available trials and suggesting the appropriate trials for providers and patients to consider including in a treatment plan. Since its implementation in 2016, Watson was able to deliver about an 80% increase in enrollment to Mayo’s trials for breast cancer.

Patient risk analysis

“…Healthcare is one of the most important fields AI is going to transform,” Google CEO Sundar Pichai noted during the Google I/O 2018 keynote. Last year, the event presented Google AI, a “collection of our teams and efforts to bring the benefits of AI to everyone.”

In 2018, Google uses their AI to tap into critical patient risks, such as mortality, readmission, and prolonged LOS. Cooperating with UC San Francisco, The University of Chicago Medicine, and Stanford Medicine, they analyzed over 46 billion anonymized retrospective EHR data points collected from over 216 thousand adult patients hospitalized for at least 24 hours at two US academic medical centers.

The deep learning model built by researchers reviewed each patient’s chart as a timeline, from its creation to the point of hospitalization. This data allowed clinicians to make various predictions on patient health outcomes, including prolonged length of stay, 30-day unplanned readmission, upcoming in-hospital mortality, and even a patient’s final discharge diagnosis. Remarkably, the model achieved an accuracy level that significantly outperformed traditional predictive models.

According to Pichai, “If you go and analyze over 100,000 data points per patient, more than any single doctor could analyze, we can actually quantitatively predict the chance of readmission 24 to 48 hours earlier than traditional methods. It gives doctors time to act.”

Of course, researchers don’t claim that their approach is ready for implementation in clinical settings, but they are looking forward to collaborating with providers to test this model further. Hopefully, we will see field trials and, who knows, even early adoption in 2019.

EHRs “on steroids”

HIMSS18 was all about artificial intelligence and machine learning. Surprisingly, all major EHR vendors – Allscripts, Cerner, athenahealth, Epic, and eClinicalWorks – came up with a promise to include AI into upcoming iterations of their platforms.

At the event, Epic announced a new partnership with Nuance to integrate their AI-powered conversational virtual assistant into the Epic EHR workflow. Particularly, the assistant will enable health specialists to access patient information and lab results, record patient vitals as well as check schedules and manage patient appointments using voice.

Similarly, eClinicalWorks puts AI into work on voice control but also prioritizes telemedicine, pop health, and clinical decision support. According to the company’s CEO Girish Navani, “We spent the last decade putting data in EHRs. The next decade is about intelligence and creating inferences that improve care outcomes. We can have the computer do things for the clinician to make them aware of actions they can take.” The new EHR’s launch is expected in late 2018 or early 2019.

Athenahealth also added a virtual assistant into their EHRs to improve mobile connectivity and welcomes NoteSwift’s AI-based Samantha technology to enhance clinical workflows by introducing robust automation. Samantha can grasp free-text and natural language, process information, structure it, assign ICD-10, SNOMED or CPT codes, prepare e-prescriptions and orders.

Pre-existing challenges for healthcare AI adoption

Gartner predicted that 50% of organizations will miss AI and data literacy skills to gain business value by 2020. Certainly, a lot of healthcare organizations will get in this 50%, and there are two reasons for that.

Regulations and security concerns are the main pre-existing challenges that delay practically any technology adoption in healthcare and entail an array of new challenges along with them.

First, an AI application or device has to be approved by the FDA. The catch is that the existing process focuses on the hardware or the way that algorithms work, but not the data it should or would interact with.

Speaking of data, another challenge is security breaches. Safeguarding sensitive information is a must for healthcare because patient data is a constant target for identity theft and reimbursement fraud. In Accenture’s new report, nearly 25% of healthcare execs admitted experiencing “adversarial AI behaviors, like falsified location data or bot fraud.” While this doesn’t mean AI threatens patient data, such claims do increase the concerns related to its adoption.

Still, artificial intelligence is growing in healthcare and will continue to do so. Maybe not at rocket speed, but the most recent cases show consistent improvements in major care delivery gaps. Healthcare AI’s future appears bright.

About Inga Shugalo
Inga Shugalo is a Healthcare Industry Analyst at Itransition. She focuses on Healthcare IT, highlighting the industry challenges and technology solutions that tackle them. Inga’s articles explore diagnostic potential of healthcare IoT, opportunities of precision medicine, robotics and VR in healthcare and more.

AI-Based Tech Could Speed Patient Documentation Process

Posted on August 27, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

A researcher with a Google AI team, Google Brain, has published a paper describing how AI could help physicians complete patient documentation more quickly. The author, software engineer Peter Lui, contends that AI technology can speed up patient documentation considerably by predicting its content.

On my initial reading of the paper, it wasn’t clear to me what advantage this has over pre-filling templates or even allowing physicians to cut-and-paste text from previous patient encounters. Still, judge for yourself as I outline what author Liu has to say, and by all means, check out the write-up.

In its introduction, the paper notes that physicians spend a great deal of time and energy entering patient notes into EHRs, a process which is not only taxing but also demoralizing for many physicians. Choosing from just one of countless data points underscoring this conclusion, Liu cites a 2016 study noting that physicians spend almost 2 hours of administrative work for every hour of patient contact.

However, it might be possible to reduce the number of hours doctors spend on this dreary task. Google Brain has been working on technologies which can speed up the process of documentation, including a new medical language modeling approach. Liu and his colleagues are also looking at how to represent an EHR’s mix of structured and unstructured text data.

The net of all of this? Google Brain has been able to create a set of systems which, by drawing on previous patient records can predict most of the content a physician will use next time they see that patient.

The heart of this effort is the MIMIC-III dataset, which contains the de-identified electronic health records of 39,597 patients from the ICU of a large tertiary care hospital. The dataset includes patient demographic data, medications, lab results, and notes written by providers. The system includes AI capabilities which are “trained” to predict the text physicians will use in their latest patient note.

In addition to making predictions, the Google Brain AI seems to have been able to pick out some forms of errors in existing notes, including patient ages and drug names, as well as providing autocorrect options for corrupted words.

By way of caveats, the paper warns that the research used only data generated within 24 hours of the current note content. Liu points out that while this may be a wide enough range of information for ICU notes, as things happen fast there, it would be better to draw on data representing larger windows of time for non-ICU patients. In addition, Liu concedes that it won’t always be possible to predict the content of notes even if the system has absorbed all existing documentation.

However, none of these problems are insurmountable, and Liu understandably describes these results as “encouraging,” but that’s also a way of conceding that this is only an experimental conclusion. In other words, these predictive capabilities are not a done deal by any means. That being said, it seems likely that his approach could be valuable.

I am left with at least one question, though. If the Google Brain technology can predict physician notes with great fidelity, how does that differ than having the physician cut-and-paste previous notes on their own?  I may be missing something here, because I’m not a software engineer, but I’d still like to know how these predictions improve on existing workarounds.