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!

Partners AI System Gives Clinicians Better Information

Posted on January 25, 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 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.

While HIT professionals typically understand AI technology, clinicians may not. After all, using AI usually isn’t part of their job, so they can be forgiven for ignoring all of the noise and hype around it.

Aware of this problem, Partners Connected Health and partner Hitachi have come together to create an AI-driven process which isolates data physicians can use. The new approach, dubbed ‘explainable AI,’ is designed to list the key factors the system has relied upon in making projections, making it easier for physicians to make relevant care decisions.

Explainable AI, a newer term used by the two organizations, refers not only to the work being done to develop the Partners system, but also a broader universe in which machines can explain their decisions and actions to human users. Ultimately, explainable AI should help users trust and use AI tools effectively, according to a Hitachi statement.

Initially, Partners will use the AI system to predict the risk of 30-day readmissions for patients with heart failure. Preventing such readmissions can potentially save $7,000 per patient per year.

The problem is, how can organizations like Partners make AI results useful to physicians? Most AI-driven results are something of a black box for clinicians, as they don’t know what data contributed to the score. After all, the algorithm analyses about 3,000 variables that might be a factor in readmissions, drawing from both structured and unstructured data. Without help, there’s little chance physicians can isolate ways to improve their own performance.

But in this case, the AI system offers much better information. Having calculated the predictive score, it isolates factors that physicians can address directly as part of the course of care. It also identifies which patients would be the best candidates for a post-discharge program focused on preventing readmissions.

All of this is well and good, but will it actually deliver the results that Partners hoped for? As it turns out, the initial results of a pilot program are promising.

To conduct the pilot, the Partners Connected Health Innovation team drew on real-life data from heart failure patients under its care. The patients were part of the Partners Connected Cardiac Care Program, a remote monitoring education program focused on managing their care effectively in reducing the risk of hospitalization.

The test compared the results calculated by the AI system with real-life results drawn from about 12,000 heart failure patients hospitalized and discharged from the Partners HealthCare network in 2014 in 2015. As it turned out, there was a high correlation between actual patient readmissions and the level predicted by the system. Next, Partners will share a list of variables that played the biggest role in the AI’s projects. It’s definitely a move in the right direction.

Remote Patient Monitoring and Small Practices

Posted on February 18, 2015 I Written By

John Lynn is the Founder of the 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 and John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

We’ve started to see the proliferation of wireless health devices that can track a wide variety of health data and more of these devices are becoming common place in the home. Here’s a great tweet that contains an image of some of the popular devices:

While many of these devices are being purchased by the patients and used in the home, there are a number of other programs where healthcare organizations (usually hospitals) are purchasing the devices for the patients who then use the device at home. These programs are designed for hospitals to remotely monitor a patient and identify potential health issues early in order to avoid a hospital readmission.

For those who work in hospitals, you know how important (financially and otherwise) it is for hospitals to reduce their readmissions. While this is great for hospitals, how does this apply to small practices and general and family practice doctors in particular. There’s no extra payment for a small practice doctor to help reduce the readmission of their patient to the hospital. At least I haven’t seen a hospital pay a doctor for their help in this service yet.

What then would motivate a small practice doctor to leverage these types of remote patient monitoring tools?

Sadly, I don’t think there is much motivation for the standard small practice office to use them. It’s easy to see where a concierge doctor might be interested in these technologies. As a concierge doctor or direct primary care doctor, it’s in their best interest to keep their patient population as healthy as possible. As this form of care becomes more popular, I think these types of technology will become incredibly important to their business model.

The other trend in play is the shift to value based reimbursement and ACOs. Will these types of remote patient monitoring technologies become important in this new reimbursement world? I think the jury is still out on this one, but you could see how they could work together.

I’ve recently had a number of doctors hammering me on Twitter and in the comments of blog posts about how technology is not the solution to the problems and that technology is just getting in the way of the personal face to face connection that doctors have been able to make in the office visit of the past. Their concern is real and those implementing the technology need to take this into account. The technology can get in the way if it’s implemented poorly.

However, these people who smack the technology down are usually speaking from a very narrow perspective. EHR and other technology can and does disrupt many office visits. We all know the common refrain that the doctor was looking at the computer not at me. This is a challenge that can be addressed.

While the above is true, how impersonal is a rushed 10-15 minute office visit with a doctor? How impersonal is it for the doctor to prescribe a medication to you and never know if you actually filed it? How impersonal is it for a doctor to prescribed a treatment and never follow up with you to know if the treatment worked? How impersonal is it for the doctor to never talk or interact with you and your health unless you proactively go to that doctor because you’re sick?

Technology is going to be the way that we bridge that gap and these remote patient monitoring technologies are one piece of that puzzle. I believe these technologies and others make healthcare so much more personal than it is today. It changes a short office visit to treat a chief complaint into actually caring for the patient.

This is what most doctors I know would rather be doing anyway. They don’t want to churn patients anymore than the patient wants to be churned, but that’s how they get paid. Hopefully the tide is changing and we’ll see more and more focus on paying providers for using technology that provides this type of personal care.

Apervita Creates Health Analytics for the Millions

Posted on January 9, 2015 I Written By

Andy Oram is an editor at O'Reilly Media, a highly respected book publisher and technology information provider. An employee of the company since 1992, Andy currently specializes in open source, software engineering, and health IT, but his editorial output has ranged from a legal guide covering intellectual property to a graphic novel about teenage hackers. His articles have appeared often on EMR & EHR and other blogs in the health IT space. Andy also writes often for O'Reilly's Radar site ( and other publications on policy issues related to the Internet and on trends affecting technical innovation and its effects on society. Print publications where his work has appeared include The Economist, Communications of the ACM, Copyright World, the Journal of Information Technology & Politics, Vanguardia Dossier, and Internet Law and Business. Conferences where he has presented talks include O'Reilly's Open Source Convention, FISL (Brazil), FOSDEM, and DebConf.

Health officials are constantly talking up the importance of clinical decision support, more popularly known now as evidence-based medicine. We’re owning up to the awkward little fact–which really should embarrass nobody–that most doctors lack expertise on many of the conditions they encounter and can’t read the thousands of relevant studies published each year. New heuristics are developed all the time for things such as predicting cardiac arrest or preventing readmissions after surgery. But most never make their way into the clinic.

Let’s look at what has to happen before doctors and patients can benefit from a discovery:

  1. The researcher has to write a paper with enough detail to create a working program from the heuristic, and has to publish the paper, probably in an obscure journal.

  2. A clinician or administrator has to find the article and line up staff to write and thoroughly test a program.

  3. If the program is to be used outside the hospital where it was created, it has to be disseminated. The hospital is unlikely to have an organization set up to package and market the program. Even if it is simply put out for free use, other institutions have to learn about it and compile it to work on their systems, in order for it to spread widely. Neither the researcher nor the hospital is likely to be compensated for the development of the program.

  4. The program has to be integrated into the doctor’s workflow, by being put on a menu or generating an alert.

Evidence-based medicine, therefore, is failing to tap a lot of resources that could save lives. A commonly cited observation is that research findings take 17 years to go into widespread practice. That’s 17 years of unnecessary and costly suffering.

I have often advocated for better integration of analytics into everyday medical practice, and I found a company called Apervita (originally named Pervasive Health) that jumps off in the right direction. Apervita, which announced a Series A round of funding on January 7, also has potential users outside of clinical settings. Pharma companies can use it to track adverse drug events, while payers can use it to predict fraud and risks to patients. There is not much public health data in the platform yet, but they’re working on it. For instance, Leapfrog group has published hospital safety info through their platform, and Diameter Health provides an all-cause 30-day readmissions prediction for all non-maternal, non-pediatric hospitalizations.

Here’s how the sequence of events I laid out before would go using Apervita:

  1. The researcher implements her algorithm in Python, chosen because Python is easy for non-programmers to learn and is consequently one of the most popular programming languages, particularly in the sciences. Apervita adds functions to Python to make it easy, such as RangeCompute or tables to let you compute with coefficients, and presents these through an IDE.

  2. The researcher creates an analytic on the Apervita platform that describes and publishes the analytic, along with payment terms. Thus, the researcher derives some income from the research and has more motivation to offer the analytic publicly. Conversely, the provider pays only for usage of the analytic, and does not have to license or implement a new software package.

  3. Clinicians search for relevant analytics and upload data to generate reports at a patient or population level. Data in popular formats such as Excel or comma-separated value (CSV) files can be uploaded manually, while programmers can automate data exchange through a RESTful web service, which is currently the most popular way of exchanging data between cooperating programs. Rick Halton, co-founder and Chief Marketing Officer of Apervita, said they are working on support for HL7’s CCD, and are interested in Blue Button+ button, although they are not ready yet to support it.

  4. Clinicians can also make the results easy to consume through personalized dashboards (web pages showing visualizations and current information) or by triggering alerts. A typical dashboard for a hospital administrator might show a graphical thermometer indicating safety rankings at the hospital, along with numbers indicating safety grades. Each department or user could create a dashboard showing exactly what a clinician cares about at the moment–a patient assessment during an admission, or statistics needed for surgical pre-op, for instance.

  5. Apervita builds in version control, and can automatically update user sites with corrections or new versions.

I got a demo of Apervita and found the administration pretty complex, but this seems to be a result of its focus on security and the many options it offers large enterprises to break staff into groups or teams. The bottom line is that Apervita compresses the difficult processes required to turn research into practice and offers them as steps performed through a Web interface or easy programming. Apervita claims to have shown that one intern can create as many as 50 health analytics in one week on their platform, working just from the articles in journals and web resources.

The platform encrypts web requests and is HIPAA-compliant. It can be displayed off-platform, and has been integrated with at least one EHR (OpenMRS).

Always attuned to the technical difficulties of data use, I asked Halton how the users of Apervita analytics could make sure their data formats and types match the formats and types defined by the people who created the analytics. Halton said that the key was the recognition of different ontolgies, and the ability to translate between them using easy-to-create “codesets.”

An ontology is, in general, a way of representing data and the relationships between pieces of data. SNOMED and ICD are examples of common ontologies in health care. An even simpler ontology might simply be a statement that units of a particular data field are measured in milliliters. Whether simple or complex, standard or custom-built, the ontology is specified by the creator of an analytic. If the user has data in a different ontology, a codeset can translate between the two.

As an example of Apervita’s use, a forward prediction algorithm developed by Dr. Dana Edelson and others from the University of Chicago Medical Center can predict cardiac arrests better than the commonly used VitalPAC Early Warning Score (ViEWS) or Modified Early Warning Score (MEWS). Developed from a dataset of over 250,000 patient admissions across five hospitals, “eCART” (electronic Cardiac Arrest Triage) can identify high-risk hospital ward patients and improve ICU triage decisions, often as much as 48 hours in advance.

The new funding will allow Apervita to make their interface even easier for end-users, and to solicit algorithms from leading researchers such as the Mayo Clinic.

Halton heralds Apervita as a “community” for health care analytics for authors and providers. Not only can the creators of analytics share them, but providers can create dashboards or other tools of value to a wide range of colleagues, and share them. I believe that tools like Apervita can bridge the gap between the rare well-funded health clinic with the resources to develop tools, and the thousands of scattered institutions struggling to get the information that will provide better care.

Laying the Best Foundation for Medication Reconciliation

Posted on September 6, 2013 I Written By

John Lynn is the Founder of the 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 and 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 following is a guest blog post by Brian Levy, MD, Senior Vice President and Chief Medical Officer for Health Language.
Levy Low Res
Effective medication reconciliation across the continuum of care is a critical element to eliminating medication errors and adverse drug events (ADEs). It is a focal point of such national initiatives as Meaningful Use (MU) and the Joint Commission’s National Patient Safety Goals and will also be crucial to ensuring performance metrics are met under Value-Based Purchasing and the Hospital Readmissions Reduction Program.

Simply put, one of the primary end-goals of current industry movements is to eliminate the revolving door effect in healthcare where patients are readmitted soon after discharge due to ADEs or lack of good information across the continuum. A growing body of research points to enhanced medication reconciliation as an effective way for hospitals to reduce readmission rates to meet this objective.

A 2012 study published in the Joint Commission Journal on Quality and Patient Safety found that accurate preadmission medication lists—acquired as part of medication reconciliation strategies— reduced ADEs both in the hospital and following discharge. Another paper published in the November 2012 edition of Pharmacotherapy also points to the critical role ADEs play in readmission rates and how ineffective care transitions, especially as they relate to medication management, exacerbate the situation.

The logistics of medication reconciliation has historically been an uphill battle for many clinicians. Without an electronic method for capturing information, the scene usually comes down to a Q&A session where physicians, nurses or other clinicians rely on patients to give them an accurate medication list. When a patient is unaware of the name of a medication, it usually results in a protracted delay in patient care while phone calls are made and consults conducted to accurately identify medications and avoid the potential for error.

EHRs provide the first step to correcting this inefficient way of gathering information. And while these systems are great repositories of patient information, the difficulty for medication reconciliation has been a lack of standards—specifically the lack of a standardized medical vocabulary. A number of proprietary medical terminologies exist within the industry, and without a standard for information exchange, the risk is that one drug could be identified by a number of different terminology codes depending on the proprietary system used.

Clinicians need an effective method for exchanging patient medication information between disparate systems in a standardized format that can be translated accurately by various healthcare organizations, providers and departments involved in patient care. MU is addressing this issue on one level through the introduction of RxNorm, a normalized naming system produced by the National Library of Medicine for generic and branded drugs and a tool that supports semantic interoperability between drug terminologies and pharmacy knowledge base systems.

RxNorm is a critical first step to ensuring the feasibility of building and accessing an accurate medication summary, thus minimizing the possibility of duplicate therapies, drug allergies and drug interactions. By adopting this standard, healthcare organizations and providers will begin receiving RxNorm codes in important CCD summary of care documents and HL7 messages. This standard will complement the use of the Systematized Nomenclature Of Medicine Clinical Terms (SNOMED CT®), a widely-used clinical terminology set also required under MU for the creation of problem lists.

While RxNorm provides efficient and accurate capture of medication information from external systems, healthcare organizations and providers will still require a method of converting codes from RxNorm to internal systems and visa-versa. This step ensures that internal medicine systems and drug information and interactions databases like Medi-Span, First Databank, Micromedex and Multum can also reconcile important patient medication information.

To address the full picture of data normalization, healthcare providers can leverage a healthcare terminology management solution to ensure automated mapping of patient medication data received from disparate sources to standardized terminologies. This process de-duplicates data, creating a normalized code across all clinical systems used internally, minimizing the potential for error.

This approach also provides an effective way for leveraging a comprehensive, longitudinal patient record, which is a primary goal of the health IT movement to enhance patient care. A foundation of standardized codes enables healthcare organizations to more fully develop advanced clinical decision support functions, where alerts can be received immediately for clinical activity impacting individual patients or within populations of patients.

As the healthcare’s industry move toward higher-quality care and more efficient care delivery continues to mature, the use of standardized medical terminologies will be paramount to effective clinical information exchange. While some initiatives like RxNorm and SNOMED CT are addressing this need for standardization, healthcare organizations can further advance data normalization strategies by leveraging the efficiencies and advantages of healthcare terminology management solutions.

Patient Accountability and Responsibility

Posted on February 22, 2013 I Written By

John Lynn is the Founder of the 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 and 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 think you can add this post to my series of posts on the Physician Revolt that I talked about earlier. The following message is from a doctor who emailed me. Obviously, they didn’t realize it would be published, so ignore some of the grammar errors, but the message is a good one that we should be discussing.

The doctors are going to be graded on the health outcomes but yet patients are going to do whatever. Nowhere in the law it states that patient is responsible for anything.

So while the ACOs are going to offer coverage…… there is going to be no immediate access due to shortage of MDs and the current MDs whose slots are overfilled are going to be dinged with penalties for not taking care of their patients completely (ie. all time coverage for all patients all the time). which means the MD has to refund the already reduced reimbursements back to the government because patients will complain about this.

Of course, the patients themselves will not tighten their belt and become personally responsible for their health so that they take up less appointment slots……..

So the significant question is Where are the patients held accountable in all these free health care reforms?

This is an important question as we shift to an ACO model. I think the above narrative places a little too much blame on the patient for the higher healthcare costs. Certainly there are things that doctors and our health system can do to lower costs that are outside of the patient. A simple example is 2 doctors ordering duplicate tests. If they just transferred the data, they’d provide the same care for a much lower cost. Plus, I think there are ways that a doctor together with a clinical care team can improve the overall quality of care of a patient population regardless of the patient’s choices. Another example of this is the hospital to PCP hand off. Doing this right can lower healthcare costs by reducing hospital readmissions.

While much can be done by doctors and the healthcare system as a whole, the doctor does raise a good question about patient responsibility. In what ways could we incentivize patients to take some accountability and responsibility for their healthcare as well?

The first thing that popped in my head was the way car insurance companies are doing it. One of the insurance companies is tapping into your car’s computer to monitor safe driving and then they provide discounts to you for being a safe driver. Are we going to have the same models in healthcare? In some ways we do, since if you’re a non-smoker your health insurance costs a lot less. Will health insurance companies start lowering a patient’s health insurance costs based on data from a wearable device that monitors your activity?

I’m honestly not sure how it’s all going to play out, but I am sure that healthcare IT is going to play a role in the process. We’ll never totally solve the issue of patient responsibility and accountability. That’s a feature of life, but I think that technology can help to hold us all more accountable for our health choices. What technologies do you see helping this?