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 HIPAA for FREE!!

EMR Information Management Tops List Of Patient Threats

Posted on March 23, 2017 I Written By

Anne Zieger is a healthcare journalist who has written about the industry for 30 years. Her work has appeared in all of the leading healthcare industry publications, and she's served as editor in chief of several healthcare B2B sites.

A patient safety organization has reached a conclusion which should be sobering for healthcare IT shops across the US. The ECRI Institute , a respected healthcare research organization, cited three critical health IT concerns in its list of the top 10 patient safety concerns for 2017.

ECRI has been gathering data on healthcare events and concerns since 2009, when it launched a patient safety organization. Since that time, ECRI and its partner PSOs have collected more than 1.5 million event reports, which form the basis for the list. (In other words, the list isn’t based on speculation or broad value judgments.)

In a move that won’t surprise you much, ECRI cited information management in EMRs as the top patient safety concern on its list.

To address this issue, the group suggests that healthcare organizations create cross-functional teams bringing varied perspectives to the table. This means integrating HIM professionals, IT experts and clinical engineers into patient safety, quality and risk management programs. ECRI also recommends that these organizations see that users understand EMRs, report and investigate concerns and leverage EMRs for patient safety programs.

Implementation and use of clinical decision support tools came in at third on the list, in part because the potential for patient harm is high if CDS workflows are flawed, the report says.

If healthcare organizations want to avoid these problems, they need to give a multidisciplinary team oversight of the CDS, train end users in its use and give them access to support, the safety group says. ECRI also recommends that organizations monitor the appropriateness of CDS alerts, evaluating the impact on workflow and reviewing staff responses.

Test result reporting and follow-up was ranked fourth in the list of safety issues, driven by the fact that the complexity of the process can lead to distraction and problems with follow-up.

The report recommends that healthcare organizations respond by analyzing their test reporting systems and monitor their effectiveness in triggering appropriate follow-ups. It also suggests implementing policies and procedures that make it clear who is accountable for acting on test results, encouraging two-way conversations between healthcare professionals and those involved in diagnostic testing and teaching patients how to address test information.

Patient identification issues occupied the sixth position on the list, with the discussion noting that about 9 percent of misidentification problems lead to patient injury.

Healthcare leaders should prioritize this issue, engaging clinical and nonclinical staffers in identifying barriers to safe identification processes, the ECRI report concludes. It notes that if a provider has redundant patient identification processes in place, this can increase the probability that identification problems will occur. Also, it recommends that organizations standardize technologies like electronic displays and patient identification bands, and that providers consider bar-code systems and other patient identification helps.

In addition to health IT problems, ECRI identified several clinical and process issues, including unrecognized patient deterioration, problems with managing antimicrobial drugs, opioid administration and monitoring in acute care, behavioral health issues in non-behavioral-health settings, management of new oral anticoagulants and inadequate organization systems or processes to improve safety and quality.

But clearly, resolving nagging health IT issues will be central to improving patient care. Let’s make this the year that we push past all of them!

E-Patient Update: Patients Need Better Care Management Workflows

Posted on March 10, 2017 I Written By

Anne Zieger is a healthcare journalist who has written about the industry for 30 years. Her work has appeared in all of the leading healthcare industry publications, and she's served as editor in chief of several healthcare B2B sites.

Now and then, I get a little discouraged by the state of my health data. Like providers, I’m frustrated as heck by the number of independent data sources I must access to get a full picture of my medications, care and health status. These include:

* The medication tracker on my retail pharmacy’s site
* My primary care group’s portal
* My hospital’s Epic MyChart portal
* A medication management app to track my compliance with my regimen
* A health tracker app in which I track my blood pressure
* My Google calendar, to keep up with my health appointments
* Email clients to exchange messages with some providers

That’s not all – I’m sure I could think of other tools, interfaces and apps – but it offers a good idea of what I face. And I’m pretty sure I’m not unusual in this regard, so we’re talking about a big issue here.

By the way, bear in mind I’m not just talking about hyperportalotus – a fun term for the state of having too many portals to manage – but rather, a larger problem of data coordination. Even if all of my providers came together and worked through a shared single portal, I’d still have to juggle many tools for tracking and documenting my care.

The bottom line is that given the obstacles I face, my self-care process is very inefficient. And while we spend a lot of time talking about clinician workflow (which, of course, is quite important) we seldom talk about patient/consumer health workflow. But it’s time that we did.

Building a patient workflow

A good initial step in addressing this problem might be to create a patient self-care workflow builder and make it accessible website. Using such a tool, I could list all of the steps I need to take to manage my conditions, and the tool would help me develop a process for doing so effectively.

For example, I could “tell” the software that I need to check the status of my prescriptions once a week, visit certain doctors once a month, check in about future clinical visits on specific days and enter my data in my medication management app twice a day. As I did this, I would enter links to related sites, which would display in turn as needed.

This tool could also display critical web data, such as the site compiling the blood sugar readings from my husband’s connected blood glucose monitor, giving patients like me the ability to review trends at a glance.

I haven’t invented the wheel here, of course. We’re just talking about an alternate approach to a patient portal. Still, even this relatively crude approach – displaying various web-based sources under one “roof” along with an integrated process – could be quite helpful.

Eventually, health IT wizards could build much more sophisticated tools, complete with APIs to major data sources, which would integrate pretty much everything patients need first-hand. This next-gen data wrangler would be able to create charts and graphs and even issue recommendations if the engine behind it was sophisticated enough.

Just get started

All that being said, I may be overstating how easy it would be to make such a solution work. In particular, I’m aware that integrating a tool with such disparate data sources is far, far easier said than done. But why not get started?

After all, it’s hard to overestimate how much such an approach would help patients, at least those who are comfortable working with digital health solutions. Having a coordinated, integrated tool in place to help me manage my care needs would certainly save me a great deal of time, and probably improve my health as well.

I urge providers to consider this approach, which seems like a crying need to me. The truth is, most of the development money is going towards enabling the professionals to coordinate and manage care. And while that’s not a bad thing, don’t forget us!

HIMSS17: Health IT Staff, Budgets Growing

Posted on March 1, 2017 I Written By

Anne Zieger is a healthcare journalist who has written about the industry for 30 years. Her work has appeared in all of the leading healthcare industry publications, and she's served as editor in chief of several healthcare B2B sites.

A new study announced last week at the HIMSS17 event concludes that demand for health IT staff continues to grow as employers expand their budgets. Not surprisingly, given this growth, the healthcare employers are having trouble recruiting enough IT staffers to meet their growing needs.

Results from the HIMSS Leadership and Workforce Survey reflect responses from 368 U.S. health IT leaders made between November 2016 and early January 2017. Fifty-six of respondents from vendors and consulting firms were in executive management, as compared with 41% of providers.

The survey concluded that the majority of health IT respondents have positions they’d like to fill, including 61% of health IT vendors/consultants and 43% of providers who responded. Only 32% of vendor/consultant organizations and 38% or providers said they were fully staffed, HIMSS said. We’ve seen this challenge from many of the healthcare IT companies which post their jobs on Healthcare IT Central.

Demand for IT recruits grew last year, as well. Researchers found that 61% of vendors/consultants responding and 42% of providers responding saw IT staffing increases over the past year, and that the majority of respondents in both groups expect to increase their IT staffing levels or at least hold them steady next year.

Of course, someone has to pay for these new team members. HIMSS researchers found that IT budgets were continuing to rise over time. Roughly nine out of ten vendors/consultants and 56% of providers said they expected to see increases in their IT budgets this year.

As often happens, however, vendors and consultants and providers seem to have different HIT priorities. While vendors seem to be addressing new technology issues, providers are still focused on how to manage their existing EMR infrastructure investments, HIMSS said.

That being said, the survey found, health IT stakeholders have many overlapping concerns, including privacy and security, population health, care coordination and improving the culture of care.

One of the key insights from this study – that vendors/consultants and providers have different views on the importance of enhancing existing EMRs – is borne out by another study released at the HIMSS event.

The study, which was backed by voice recognition software vendor Nuance Communications, found that providers are broadly interested in implementing new technologies that enhance their EMR, especially computer-assisted physician documentation, mobility and speech recognition tools.

However, when asked to be specific about which tools interested them, they were less enthusiastic, with 44% showing an interest in mobility tools, 38% computer-assisted physician documentation and 25% speech recognition. Documentation tools that enhanced existing functions were especially popular, with 54% of respondents expecting to see them support a reduction in denied claims, 52% improved performance under bundled payments, 38% reduced readmissions and 38% better physician time management which improves patient flow.

This survey also found that the most popular strategy for enhancing physician satisfaction with health IT tools was providing clinician training and education (chosen by 82%). Since their EMR is probably their biggest IT investment, my guess is that the training will focus there. And that suggests that EMRs are still the center of their universe, doesn’t it?

Patient Misidentification Remains Common

Posted on February 27, 2017 I Written By

Anne Zieger is a healthcare journalist who has written about the industry for 30 years. Her work has appeared in all of the leading healthcare industry publications, and she's served as editor in chief of several healthcare B2B sites.

The following information was released several weeks ago, but I just found it and thought readers would still find it relevant. The research, from security researcher Ponemon Institute, concludes that patient misidentification is relatively common and continues to impact patient safety and experience.

Late last year, Ponemon surveyed 503 healthcare professionals from across the US, including nurses, physicians, IT practitioners and leaders in financial operations, on the frequency and root causes of patient misidentification, as well as the consequences.

According to the researchers, 86% of respondents said they’d witnessed or know of medical errors resulting from patient misidentification. And 67% said that when searching for patient information, they find duplicate medical records for that patient almost all of the time. Along the way, about three-quarters of respondents agreed that use of biometrics could reduce patient misidentification and by extension, cut down on medical errors.

The most common root cause of patient misidentification was incorrect identification at registration (chosen by 63%), followed by time pressure when treating patients (60%), insufficient employee/clinician training and awareness (35%), too many duplicate medical records in system (34%), registrar errors (32%), turf wars between departments (29%), inadequate safety procedures (20%), over-reliance on homegrown or obsolete identification systems (15%) and misinformation provided by patient (9%). (The remaining 3% was reported as “other”.)

The key causes of misidentification named in the survey included the inability to find a patient’s chart or medical record (68% of respondents), a search or query which brings up multiple or duplicate medical records for a patient (67%), patient associated with incorrect records due to same names and/or dates of birth (56%), or having the wrong record pulled up for a patient because another record in the registration system or EMR has the same name and/or date of birth (61%).

Not surprisingly, the survey also suggests that widespread patient misidentification can have a serious financial impact. On average, Ponemon says, respondents said that more than one-third of all denied claims resulted directly from an inaccurate patient identification or inaccurate/incomplete information. This costs the average healthcare facility $1.2 million per year, they reported.

Meanwhile, patient identification problems have a negative impact on patient experience, the survey concluded. Sixty-nine percent of respondents told researchers that staff spent up to or more than 30 minutes per shift contacting medical records or HIM departments to get critical patient information.

Not only that, misidentifying patients can have a ripple effect, with missing or incomplete information leading to patient care delays. Thirty-seven percent of respondents said that they spent an hour or more contacting medical records or HIM departments to get critical patient information.

E-Patient Update:  You Need Our Help

Posted on January 20, 2017 I Written By

Anne Zieger is a healthcare journalist who has written about the industry for 30 years. Her work has appeared in all of the leading healthcare industry publications, and she's served as editor in chief of several healthcare B2B sites.

I just read the results of a survey by Black Book Research suggesting that many typical consumers don’t trust, like or understand health IT.

The survey, which reached out to 12,090 adult consumers in September 2016, found that 57% of those interacting with health IT at hospitals or medical practices were skeptical of its benefit. Worse, 87% said they weren’t willing to share all of their information.

Up to 70% of consumers reported that they distrusted patient portals, medical apps and EMRs. Meanwhile, while many respondents said they were interested in using health trackers, 94% said that their physicians weren’t willing or able to synch wearables data with their EMR.

On the surface, these stats are discouraging. At a minimum, they suggest that getting patients and doctors on the same page about health IT continues to be an uphill battle. But there’s a powerful tactic providers can use which – to my knowledge – hasn’t been tried with consumers.

Introducing the consumer health IT champion

As you probably know, many providers have recruited physician or nurse “champions” to help their peers understand and adjust to EMRs. I’m sure this tactic hasn’t worked perfectly for everyone who’s tried it, but it seems to have an impact. And why not? Most people are far more comfortable learning something new from someone who understands their work and shares their concerns.

The thing is, few if any providers are taking the same approach in rolling out consumer health IT. But they certainly could. I’d bet that there’s at least a few patients in every population who like, use and understand consumer health technologies, as well as having at least a sense of why providers are adopting back-end technology like EMRs. And we know how to get Great-Aunt Mildred to consider wearing a FitBit or entering data into a portal.

So why not make us your health IT champions? After all, if you asked me to, say, hold a patient workshop explaining how I use these tools in my life, and why they matter, I’d jump at the chance. E-patients like myself are by our nature evangelists, and we’re happy to share our excitement if you give us a chance. Maybe you’d need to offer some HIT power users a stipend or a gift card, but I doubt it would take much to get one of us to share our interests.

It’s worth the effort

Of course, most people who read this will probably flinch a bit, as taking this on might seem like a big hassle. But consider the following:

  • Finding such people shouldn’t be too tough. For example, I talk about wearables, mobile health options and connected health often with my PCP, and my enthusiasm for them is a little hard to miss. I doubt I’m alone in this respect.
  • All it would take to get started is to get a few of us on board. Yes, providers may have to market such events to patients, offer them coffee and snacks when they attend, and perhaps spend time evaluating the results on the back end. But we’re not talking major investments here.
  • You can’t afford to have patients fear or reject IT categorically. As value-based care becomes the standard, you’ll need their cooperation to meet your goals, and that will almost certainly include access to patient-generated data from mobile apps and wearables. People like me can address their fears and demonstrate the benefits of these technologies without making them defensive.

I hope hospitals and medical practices take advantage of people like me soon. We’re waiting in the wings, and we truly want to see the public support health IT. Let’s work together!

IBM Watson Partners With FDA On Blockchain-Driven Health Sharing

Posted on January 16, 2017 I Written By

Anne Zieger is a healthcare journalist who has written about the industry for 30 years. Her work has appeared in all of the leading healthcare industry publications, and she's served as editor in chief of several healthcare B2B sites.

IBM Watson Health has partnered with the FDA in an effort to create scalable exchange of health data using blockchain technology. The two will research the exchange of owner-mediated data from a variety of clinical data sources, including EMRs, clinical trial data and genomic health data. The researchers will also incorporate data from mobiles, wearables and the Internet of Things.

The initial project planned for IBM Watson and the FDA will focus on oncology-related data. This makes sense, given that cancer treatment involves complex communication between multispecialty care teams, transitions between treatment phases, and potentially, the need to access research and genomic data for personalized drug therapy. In other words, managing the communication of oncology data is a task fit for Watson’s big brain, which can read 200 million pages of text in 3 seconds.

Under the partnership, IBM and the FDA plan to explore how the blockchain framework can benefit public health by supporting information exchange use cases across varied data types, including both clinical trials and real-world data. They also plan to look at new ways to leverage the massive volumes of diverse data generated by biomedical and healthcare organizations. IBM and the FDA have signed a two-year agreement, but they expect to share initial findings this year.

The partnership comes as IBM works to expand its commercial blockchain efforts, including initiatives not only in healthcare, but also in financial services, supply chains, IoT, risk management and digital rights management. Big Blue argues that blockchain networks will spur “dramatic change” for all of these industries, but clearly has a special interest in healthcare.  According to IBM, Watson Health’s technology can access the 80% of unstructured health data invisible to most systems, which is clearly a revolution in the making if the tech giant can follow through on its potential.

According to Scott Lundstrom, group vice president and general manager of IDC Government and Health Insights, blockchain may solve some of the healthcare industry’s biggest data management challenges, including a distributed, immutable patient record which can be secured and shared, s. In fact, this idea – building a distributed, blockchain-based EMR — seems to be gaining traction among most health IT thinkers.

As readers may know, I’m neither an engineer nor a software developer, so I’m not qualified to judge how mature blockchain technologies are today, but I have to say I’m a bit concerned about the rush to adopt it nonetheless.  Even companies with a lot at stake  — like this one, which sells a cloud platform backed by blockchain tech — suggest that the race to adopt it may be a bit premature.

I’ve been watching tech fashions come and go for 25 years, and they follow a predictable pattern. Or rather, they usually follow two paths. Go down one, and the players who are hot for a technology put so much time and money into it that they force-bake it into success. (Think, for example, the ERP revolution.) Go down the other road, however, and the new technology crumbles in a haze of bad results and lost investments. Let’s hope we go down the former, for everyone’s sake.

Connected Wearables Pose Growing Privacy, Security Risks

Posted on December 26, 2016 I Written By

Anne Zieger is a healthcare journalist who has written about the industry for 30 years. Her work has appeared in all of the leading healthcare industry publications, and she's served as editor in chief of several healthcare B2B sites.

In the past, the healthcare industry treated wearables as irrelevant, distracting or worse. But over that last year or two, things have changed, with most health IT leaders concluding that wearables data has a place in their data strategies, at least in the aggregate.

The problem is, we’re making the transition to wearable data collection so quickly that some important privacy and security issues aren’t being addressed, according to a new report by American University and the Center for Digital Democracy. The report, Health Wearable Devices in the Big Data Era: Ensuring Privacy, Security, and Consumer Protection, concludes that the “weak and fragmented” patchwork of state and federal health privacy regulations doesn’t really address the problems created by wearables.

The researchers note that as smart watches, wearable health trackers, sensor-laden clothing and other monitoring technology get connected and sucked into the health data pool, the data is going places the users might not have expected. And they see this as a bit sinister. From the accompanying press release:

Many of these devices are already being integrated into a growing Big Data digital health and marketing ecosystem, which is focused on gathering and monetizing personal and health data in order to influence consumer behavior.”

According to the authors, it’s high time to develop a comprehensive approach to health privacy and consumer protection, given the increasing importance of Big Data and the Internet of Things. If safeguards aren’t put in place, patients could face serious privacy and security risks, including “discrimination and other harms,” according to American University professor Kathryn Montgomery.

If regulators don’t act quickly, they could miss a critical window of opportunity, she suggested. “The connected health system is still in an early, fluid stage of development,” Montgomery said in a prepared statement. “There is an urgent need to build meaningful, effective, and enforceable safeguards into its foundation.”

The researchers also offer guidance for policymakers who are ready to take up this challenge. They include creating clear, enforceable standards for both collection and use of information; formal processes for assessing the benefits and risks of data use; and stronger regulation of direct-to-consumer marketing by pharmas.

Now readers, I imagine some of you are feeling that I’m pointing all of this out to the wrong audience. And yes, there’s little doubt that the researchers are most worried about consumer marketing practices that fall far outside of your scope.

That being said, just because providers have different motives than the pharmas when they collect data – largely to better treat health problems or improve health behavior – doesn’t mean that you aren’t going to make mistakes here. If nothing else, the line between leveraging data to help people and using it to get your way is clearer in theory than in practice.

You may think that you’d never do anything unethical or violate anyone’s privacy, and maybe that’s true, but it doesn’t hurt to consider possible harms that can occur from collecting a massive pool of data. Nobody can afford to get complacent about the downside privacy and security risks involved. Plus, don’t think the nefarious and somewhat nefarious healthcare data aggregators aren’t coming after provider stored health data as well.

What Would A Community Care Plan Look Like?

Posted on November 16, 2016 I Written By

Anne Zieger is a healthcare journalist who has written about the industry for 30 years. Her work has appeared in all of the leading healthcare industry publications, and she's served as editor in chief of several healthcare B2B sites.

Recently, I wrote an article about the benefits of a longitudinal patient record and community care plan to patient care. I picked up the idea from a piece by an Orion Health exec touting the benefits of these models. Interestingly, I couldn’t find a specific definition for a community care plan in the article — nor could I dig anything up after doing a Google search — but I think the idea is worth exploring nonetheless.

Presumably, if we had a community care plan in place for each patient, it would have interlocking patient-specific and population health-level elements to it. (To my knowledge, current population health models don’t do this.) Rather than simply handing patients off from one provider to another, in the hope that the rare patient-centered medical home could manage their care effectively on its own, it might set care goals for each patient as part of the larger community strategy.

With such a community care strategy, groups of providers would have a better idea where to allocate resources. It would simultaneously meet the goals of traditional medical referral patterns, in which clinicians consult with one another on strategy, and help them decide who to hire (such as a nurse-practitioner to serve patient clusters with higher levels of need).

As I envision it, a community care plan would raise the stakes for everyone involved in the care process. Right now, for example, if a primary care doctor refers a patient to a podiatrist, on a practical level the issue of whether the patient can walk pain-free is not the PCP’s problem. But in a community-based care plan, which help all of the individual actors be accountable, that podiatrist couldn’t just examine the patient, do whatever they did and punt. They might even be held to quantitative goals, if the they were appropriate to the situation.

I also envision a community care plan as involving a higher level of direct collaboration between providers. Sure, providers and specialists coordinate care across the community, minimally, but they rarely talk to each other, and unless they work for the same practice or health system virtually never collaborate beyond sharing care documentation. And to be fair, why should they? As the system exists today, they have little practical or even clinical incentive to get in the weeds with complex individual patients and look at their future. But if they had the right kind of community care plan in place for the population, this would become more necessary.

Of course, I’ve left the trickiest part of this for last. This system I’ve outlined, basically a slight twist on existing population health models, won’t work unless we develop new methods for sharing data collaboratively — and for reasons I be glad to go into elsewhere, I’m not bullish about anything I’ve seen. But as our understanding of what we need to get done evolves, perhaps the technology will follow. A girl can hope.

Apple’s Healthcare Data Plans Become Clearer

Posted on October 3, 2016 I Written By

Anne Zieger is a healthcare journalist who has written about the industry for 30 years. Her work has appeared in all of the leading healthcare industry publications, and she's served as editor in chief of several healthcare B2B sites.

Though it’s not without competitors, I’d argue that Apple’s HealthKit has stood out since its inception, in part because it was relatively early to the game (mining patient-centered data) and partly because Apple products have a sexy reputation. That being said, it hasn’t exactly transformed the health IT industry either.

Now, though, with the acquisition of Gliimpse, a startup which pulls data from disparate EMRs into a central database, it’s become clearer what Apple’s big-picture goals are for the healthcare market – and if its business model works out they could indeed change health data industry.

According to a nifty analysis by Bloomberg’s Alex Webb, which quotes an Apple Health engineer, the technology giant hopes to see the health data business evolve along the lines of Apple’s music business, in which Apple started with a data management tool (the iPod) then built a big-bucks music platform on the device. And that sounds like an approach that could steal a move from many a competitor indeed.

Apple’s HealthKit splash
Apple made a big splash with the summer 2014 launch of HealthKit, a healthcare data integration platform whose features include connecting patient generated health data with traditional systems like the Epic EMR. It also attracted prominent partners like Cedars-Sinai Medical Center and Ochsner Health System within a year or so of its kickoff.

Still, the tech giant has been relatively quiet about its big-picture vision for healthcare, leaving observers like yours truly wondering what was up. After all, many of Apple’s health data moves have been incremental. For example, a few months ago I noted that Apple had begun allowing users to store their EMR data directly in its Health app, using the HL7 CCD standard. While interesting, this isn’t exactly an earth-shattering advance.

But in his analysis — which makes a great deal of sense to me – Bloomberg’s Webb argues that Apple’s next act is to take the data it’s been exchanging with wearables and put it to better use. Apple’s long-awaited big idea is to turn Apple’s HealthKit into a system that can improve diagnoses, sources told Bloomberg.

Also, Apple intends to integrate health records as closely with its proprietary devices as possible, offering not only data collection but suggestions for better health in a manner that can’t be easily duplicated on Android platforms. As Webb rightly points out, such a move could undermine Google’s larger healthcare plans, by locking consumers into Apple technology and discouraging a switch to the Google Fit health tracking software.

Big vision, big questions
As we know, even a company with the reputation, cash and proprietary user base enjoyed by Apple is far from a shoo-in for consumer health data dominance. (Consider the fate of Microsoft HealthVault and Google Health.) Its previous successes have come, as noted, by creating a channel then dominating that channel, but there’s no guarantee it can pull off such a trick this time.

For one thing, the wearables market is highly fragmented, and Apple is far from being the leader. (According to one set of stats, Fitbit had 25.4% of the global wearables market as of Q2 ’16, Xiaomi 14%, and Apple just 7%.) That doesn’t bode well for starting a health tracker-based revolution.

On the other hand, though, Apple did manage to create and dominate a channel in the music business, which is also quite resistant to change and dominated by extremely entrenched powers that be. If any upstart healthcare player could make this happen, it’s probably Apple. It will be interesting to see whether Apple can work its magic once again.

Can Machine Learning Tame Healthcare’s Big Data?

Posted on September 20, 2016 I Written By

Anne Zieger is a healthcare journalist who has written about the industry for 30 years. Her work has appeared in all of the leading healthcare industry publications, and she's served as editor in chief of several healthcare B2B sites.

Big data is both a blessing and a curse. The blessing is that if we use it well, it will tell us important things we don’t know about patient care processes, clinical improvement, outcomes and more. The curse is that if we don’t use it, we’ve got a very expensive and labor-hungry boondoggle on our hands.

But there may be hope for progress. One article I read today suggests that another technology may hold the key to unlocking these blessings — that machine learning may be the tool which lets us harvest the big data fields. The piece, whose writer, oddly enough, was cited only as “Mauricio,” lead cloud expert at Cloudwards.net, argues that machine learning is “the most effective way to excavate buried patterns in the chunks of unstructured data.” While I am an HIT observer rather than techie, what limited tech knowledge I possess suggests that machine learning is going to play an important role in the future of taming big data in healthcare.

In the piece, Mauricio notes that big data is characterized by the high volume of data, including both structured and non-structured data, the high velocity of data flowing into databases every working second, the variety of data, which can range from texts and email to audio to financial transactions, complexity of data coming from multiple incompatible sources and variability of data flow rates.

Though his is a general analysis, I’m sure we can agree that healthcare big data specifically matches his description. I don’t know if you who are reading this include wild cards like social media content or video in their big data repositories, but even if you don’t, you may well in the future.

Anyway, for the purposes of this discussion, let’s summarize by saying that in this context, big data isn’t just made of giant repositories of relatively normalized data, it’s a whirlwind of structured and unstructured data in a huge number of formats, flooding into databases in spurts, trickles and floods around the clock.

To Mauricio, an obvious choice for extracting value from this chaos is machine learning, which he defines as a data analysis method that automates extrapolated model-building algorithms. In machine learning models, systems adapt independently without any human interaction, using automatically-applied customized algorithms and mathematical calculations to big data. “Machine learning offers a deeper insight into collected data and allows the computers to find hidden patterns which human analysts are bound to miss,” he writes.

According to the author, there are already machine learning models in place which help predict the appearance of genetically-influenced diseases such as diabetes and heart disease. Other possibilities for machine learning in healthcare – which he doesn’t mention but are referenced elsewhere – include getting a handle on population health. After all, an iterative learning technology could be a great choice for making predictions about population trends. You can probably think of several other possibilities.

Now, like many other industries, healthcare suffers from a data silo problem, and we’ll have to address that issue before we create the kind of multi-source, multi-format data pool that Mauricio envisions. Leveraging big data effectively will also require people to cooperate across departmental and even organizational boundaries, as John Lynn noted in a post from last year.

Even so, it’s good to identify tools and models that can help get the technical work done, and machine learning seems promising. Have any of you experimented with it?