I enjoyed an article today in IT Business Edge about the ways that Big Data is improving outcomes. We hear that all the time, right? But what does it really mean? Why does more (and better) patient data lead to improved healthcare for all? When business intelligence is leveraged properly to deliver insights to healthcare providers, we see the following:
“Allowing for previously unknown factors involved in disease to be discovered and utilized as drug targets or disease biomarkers.”
“We are able to align and compare multiple data points from various sources, tailoring individualized treatment plans for each patient.”
She’s right. Diagnoses vary from physician to physician based on his or her background and experience. Not any more! As this article states, we’re facing a “datafication” of patient samples.
“A vast quantity of knowledge that can be statistically analyzed and quickly reviewed by multiple clinicians for solid diagnosis”
You’ve heard of wearables in healthcare technology, but have you considered swallowables? Swallowing a piece of electronics is something that people are actually willing to try.
Just this morning, Intel released results from a very compelling study on a range of consumer interest in electronic “wearables” and monitors. They asked people how willing they are to try:
I was recently a panelist for a Dataversity webinar/discussion focused on the future of data modeling tools, functionality, and practice. Given the holiday season, the panelists discussed their wish list for modeling tools – from currently practical (but maybe not economically viable) to futuristic (e.g., using a 3D printer to print models for model reviews, using Google Glass to move objects around on the model).
Of course, many modeling tools already support a vast array of functionality and sometimes can be difficult to use some of the non-core functionality without experiencing some unintended consequences, and so more intelligent guides and better semantics in the modeling tool will make these easier to use – so modelers can focus more on modeling and less on the technology.
More important than the technology – as important and interesting as that is – is having solid processes and modeling standards in place to ensure better model quality, reuse, and understandability.
The healthcare industry in the United States is entering an intense, intricate, complex, and dynamic period of growth and modification. Many of the modifications have not been implemented for a significant period of time, such as the medical coding transition from ICD-9 to ICD-10. Additionally, the healthcare industry will integrate information technology and systems in its regular operational methodologies, while other industries have already undergone these changes. An apparent question to present is understanding the reasons why healthcare is behind in implementing changes than other industries. We can examine the reasons for this by including global and multicultural influences.
While healthcare resources and services can be limited domestically, other industries include global exchange and interactions as essential to industry efficiency and success. Therefore, modifications and updates had to happen regularly and periodically to accompany multicultural specifications. Examples include the transportation and financial industries that both rely on partnering countries and cannot be limited to operations within the United States. Therefore, it is reasonable to include the concept that the healthcare industry does and will rely on the same premise that eventually the success of domestic healthcare delivery systems will rely on partnering organizations on a global platform. As a result, this will lead to more frequent upgrade and standardization in healthcare as well.
Guilty! I text while I drive…eek! I know, I know, it is really bad and those anti-texting and driving commercials get me too. That is why I am making a concentrated effort to ease up this one vice (stop laughing those that know me!) of mine. Instead, I am beginning to use the voice text option and good ole Siri on my phone, which when I speak like a robot and articulate every word, does alright. But old habits die hard, which is why I understand and sympathize with physicians constantly having to change their behavior in light of all the regulatory demands in recent years.
One behavior that physicians are being asked to change is their practice patterns of dictating or handwriting clinical notes and discharge summaries. The change comes from the desire to move away from unstructured data to more structured data for consistent, easily minable and extractable information for more robust and quality reporting and analytics. 80% of clinical documentation that exists in healthcare today is unstructured and is buried in electronic medical records (EMR) and clinical notes1. Many healthcare providers are looking to natural language processing (NLP) technologies to assist in taking their valuable unstructured data, and turning it into meaningful and actionable structured data to improve patient care.
Natural Language Processing and Clinical Language Understanding
In its simplest definition, NLP is the interaction between artificial intelligence and linguistics. It encompasses anything a computer needs to understand typed or spoken language and also generate the language2. More specifically, NLP applied to the medical domain is called Clinical Language Understanding (CLU), with the main difference being that CLU works off of a complete, highly granular medical ontology, which has been tuned to relate and identify all kinds of medical facts so that the underlying NLP engine can “understand” what the caregiver is saying1. NLP has been around for years, but it wasn’t till recently that healthcare industry took notice of the value of this effectively powerful technology.
Attending Dreamforce in San Francisco last month, I was reminded of an article I read in All Things Digital about the role of Identity and the Internet of Things. Apparently Marc Benioff, salesforce.com’s CEO, mentioned during a presentation at the Bank of America Merrill Lynch 2013 Technology Conference, that Phillips, the electronics company long known for staple consumer products like TVs, cameras and audio equipment, was working on a new toothbrush. The toothbrush under development was not just any ordinary toothbrush but included GPS, Wi-Fi and “realtime” feedback on how a person brushes their teeth. Voila, no more lying to your dentist – self-quantification will rat you out with your own data.
While the concept of “The Internet of Things” like the high-tech toothbrush isn’t new, salesforce.com’s forward thinking CEO was previewing a new trend — connected devices are becoming inextricably tied to identity. Just like my registration email at Dreamforce using a barcode to speed check-in and attendance at sessions. My identity was tied to a “thing” in the Internet of Things. Lots of my personal devices are internet-enabled as well, connecting my identity to how far I walk for exercise, where I travel, what hotels I stay at, etc. In the world of social, devices like the smartphone, activity tracking wristbands, etc. are creating comprehensive profiles of our “real” behaviors like brushing our teeth.
It doesn’t take a big leap to understand the impact of connecting my identity and devices on managing my health or lifestyle. You can easily imagine a healthcare plan, like Geico does on cars, offering a discounted health plan in exchange for your comprehensive lifestyle profile, or at least lower deductibles for positive behaviors, including taking your medications on time. The challenge will be making certain that your identity is truly linked to your proper information in healthcare systems and there are clear safeguards in place. As the article in All Things Digital states
“And to be clear, trust-based relationships with users means that privacy must be accounted for and the right controls must be in place before businesses start collecting and using this data. With the proper opt-in/out privacy controls in place, identity-defining traits like hometown, religious beliefs, relationships status, likes, activities and social graph can be available to marketers and used to drive hyper-relevant marketing campaigns.”
As the list of connected “things” in our lives grows and uses our identity to tie our behavior profile to our healthcare management, the pressure will be increased for outstanding master data management by healthcare providers and healthcare plans. It is amazingly difficult for healthcare companies to conquer enterprise-level master patient indexes to resolve your one identity and create a combined view of your medical history. While your smartphone revolves around your Facebook username and password, Twitter log-ins, etc. to know you, the fragmented healthcare system must piece together that you go by your middle name, use a nickname or don’t really know your actual Social Security Number.
Master Data Management and Identity Management for healthcare is literally a matter of life and death, especially for people with medication allergies, chronic conditions like diabetes and people with medical implants like pacemakers. Dick Chaney took the extreme step of firewalling his wireless connection on his pacemaker, for example, to block terrorists from attacking him based on his device and identity. While we enjoy the idea of our exercise wrist band taking to our smart thermostat to cool down the house after a run, we need to understand the broader implication of this degree of connectivity into our own safety as patients.
You may laugh the next time that the hospital asks you your name for the umpteenth time or marks the site of your surgery with a marker, but identity matters in healthcare and as that industry becomes more connected like your devices, make sure that your information is correct, up to date and is “real.” It could literally save your life.
The healthcare IT field is rapidly developing and changing. Emerging technology and updated regulations put pressure on healthcare providers and health plans to stay ahead of the curve. Perficient creates a monthly list that explores some of the current topics and issues in health IT. This list examines the most talked about issues and technologies that are currently affecting the industry.
Healthcare entities, both payers and providers, have been making an increased effort to capture market share and dominate their geography. Smaller players are being picked up by larger players, consolidating physician practices and health plans. These mergers have driven digital strategy projects and paperless environments, with an increased interest in advertising and public facing websites to try to attract market share.
Healthcare professionals have been very vocal about the challenges that come along with electronic medical record systems. The workflow in many EMR systems was created by a programmer and works the way it was programmed, not the way healthcare professionals work. Several technology tools were made to extend or approve upon EMRs without ripping the code apart, often by putting it into a browser or allowing it to be mobile.
Whether it is real or perceived, the digital divide is often used as an excuse for non-adoption of mobile health. What is the “digital divide” exactly? The term is meant to describe the differences between people, households, or demographic/socioeconomic groups with regards to access to information technology and the knowledge and skills needed to use the information gained through technology. Factors such as gender, age, ethnicity, income, and educational attainment are often used when describing the digital divide in the United States. It isn’t uncommon for me to hear, “…but I don’t think our patients actually use mobile phones.”
Who is using mobile technology?
In fact, there is 91% US adult adoption of mobile technology, which can be compared to 85% adoption a year ago. Does that mean that 91% of the population has access to mobile apps? Not exactly. There is a comparative 56% adoption of smart phones. Even still, not having access to mobile apps does not close the door to the use of mobile to impact population health in a major way.
There are great ways to reach that entire 91% through the use of text messaging as a mobile health tool. Here are some examples:
Text4baby is a free mobile health service provided by National Healthy Mothers, Healthy Babies Coalition that is aimed at promoting pre-natal and child health through text messaging. Women who text BABY (BEBE en Español) to 511411 receive three free text messages per week. These text messages are timed to either due date or a baby’s birth date and continue through pregnancy and up until the baby’s first birthday. The messages address topics like labor signs, prenatal care, developmental milestones, immunizations, nutrition, birth defect prevention, safe sleep, and more. Text4baby has reached over half a million moms since its launch in 2010.
The emergency department at Los Angeles County Hospital of University of Southern California studied 128 Type 2 diabetes patients to assess the impact of mobile health on a population whose primary source of care is the ER. These patients, who have long been noted as a significant drain on the healthcare system, were enrolled in TExt-MED (now called myAgileLife) while a similar control group received normal care. The representative sample was 70% Latino and 14% black in order to accurately sample the population in question. The experimental group received non-interactive text messages two times a day for six months. The study showed a statistically significant impact on increased medication compliance and decreased emergency room visits. However, there was not a statistically significant impact on HbA1c hemoglobin levels. Those results were slightly better for the experimental group, but they still fell within the margin of error. The results of the study also showed that text intervention was more effective for Spanish speakers than English speakers.
Duke Obesity Prevention Program
Duke University conducted a randomized control pilot study to calculate the impact of daily text messages on weight control among racial and ethnic minority women. This program enabled daily self-monitoring of diet and physical activities to evaluate the feasibility of text message prevention for weight loss among predominantly black women. Fifty obese women were either a part of a 6-month intervention using a fully automated system that included text messages and brief feedback and tips or they were part of an education only control group. Weight was measured for six months. Nearly 70% of study participants strongly agreed that daily texting was both helpful and easy. 76% felt the frequency of texts was appropriate. At the end of 6 months, the experimental group lost more weight than the control group. They also found that greater text message program adherence was associated with a higher percentage of weight loss.
This is where healthcare providers must think like advertisers. If you wish to change or cause a behavior, then your message and calls to action need to be in those places where your consumers are. Patients only spend 1% of their time in the clinical care setting. In person outreach is not enough. However, for 91% of the population, mobile technology is in hand a large portion of every day. Given the increasing use of mobile devices, text messaging may be one of the most useful tools for the management of weight control, diabetes, pre-natal care and many other conditions that impact population health
Healthcare reform, ACA, Business Intelligence, Enterprise Portals, predictive analytics, pay for performance, the Triple Aim, total cost of care, patient safety….these, and many more, are the buzzwords in healthcare and medicine these days. Install this system, connect that system, run these reports, use this “intelligent program”… Do you ever wonder if we can solve all of these problems with just technology?
As a clinically oriented physician working in a technology world, I need to take a step back and look at behaviors and workflow. How can we mentor the next generation of physicians, nurses and allied health professionals, teach them skills and foster their curiosity while encouraging them to be technologically savvy? I believe there are two critical keys to success: critical thinking and decision support. Both are crucial and neither should exist without the other. Here’s why.
Critical thinking is an essential tool for physicians. Physicians who have this innate ability are often the most successful at diagnosing and treating their patients well. It is part art and part skill but ultimately, it affects patient safety and wellness. I was pleased to see that medical school curriculums are now focusing on this as a fundamental skill. According to the recent Wall Street Journal article, “The Biggest Mistake Doctors Make,” the program at Dalhousie University “aims to help trainees step back and examine how biases may affect their thinking. Developed by Pat Croskerry, a physician known for his research on the role of cognitive error in diagnosis, it uses a list of 50 different types of bias that may lead to diagnostic error”. Couple this with technology driven decision support at the point of care, which assists but never negates clinical judgment, and you have a winning combination. These basic building blocks allow clinicians to concentrate on their craft: diagnosing and treating patients safely and effectively.
Healthcare reform is necessary but it does not have to undermine the knowledge and experience of our clinicians. Adding technology, such as Natural Language Processing (NLP), real time decision support, predictive analytics, patient entered data via portals, mobile healthcare management apps and yes, even Watson, can only enhance and advance healthcare, streamline treatment and decrease costs. Simple? Let me know your thoughts!
The FDA’s recent ruling on monitoring mobile medical applications tells us something: there are so many health apps on the market that the FDA has to focus on approving only those which are using mobile technology to make a specific diagnosis or that transform mobile devices into a regulated medical device. So with thousands of applications available, which ones should doctors focus on? Doctor Eric Topol recommends the top mobile apps for doctors to focus on:
EPOCRATES: One of the oldest and most established medical apps, Epocrates gives doctors basic information about drugs, the right dosing for adults and children, and warnings about harmful interactions.
ISABEL: Doctors enter symptoms, and the app lists possible diagnoses as well as medications that could cause the symptoms.
ALIVECOR: This portable heart monitor and app—one of the programs that opened Dr. Topol’s eyes—runs on a patient’s smartphone to produce electrocardiograms.
IHEALTH WIRELESS PULSE OXIMETER: People with trouble sleeping can use this app to record their blood-oxygen level during the night—data that can help a doctor diagnose whether they have sleep apnea.
RESOLUTIONMD: Doctors can look at X-rays and other images on a smartphone or tablet when they use this app
CELLSCOPE OTO: A smartphone becomes an otoscope, the instrument doctors use to look into the ear, thanks to this app and optical device.
ISCRUB: This infection-control app collects and rapidly displays data on whether hospital staff are being scrupulous about washing their hands.
BREAST CANCER DIAGNOSIS GUIDE: Using this app, breast-cancer patients enter and track details of their disease and treatment, from the size of the tumor to the presence or absence of estrogen receptors.CLINICAM: Increasingly, doctors are using their phones to take photos of a patient’s condition—such as a rash or wound—and to upload the images to the patient’s electronic medical record.
A few weeks ago, Apple announces the free upgrade to OS Mavericks. My neighbor upgraded immediately and everything was working fine.
Prior to his endocrinologist appointments each quarter, he logs onto a website where he can quickly and easily upload his blood sugar numbers prior to his doctor appointment. It’s amazing technology that allows the doctor to track his sugar levels day by day and make the appropriate adjustments to his insulin pump.
This morning, when he logged on, he saw a screen that said that he could not access the website. This is when he called me to come over to figure out the problem. Unfortunately, the problem was OS Mavericks. The medical site was only able to be accessed using Snow Leopard. His other option was to access it from a PC (which he doesn’t own), but not with the most recent versions of Chrome or Firefox.
He had to go to his doctors appointment without providing this information. They were able to pull it off of his pump when he arrived, but the doctor was very frustrated because he wants his patients to upload their information on a regular basis so that he can closely monitor them and make changes immediately.
Technology is moving fast and when one cog in the wheel changes, the rest need to move swiftly to catch up. Meanwhile, my neighbor who has been rigorous in monitoring his diabetes for over 30 years, is now contemplating adding a PC to his list of tools in his arsenal.
It is commonly accepted that successful integration and update of healthcare information systems with clinical management will entail bridging communication between medical professional and technical expertise in data management, processing, and reporting. However, we should also account for sectors of the healthcare industry that are not as directly related as healthcare delivery systems and information processing. Common sectors include public health awareness professionals, patient advocates, social and counseling services, and financial management. While healthcare delivery and information systems are primary, these mentioned secondary industry sectors are required to support and enhance the entire efficiency of patient clinical management.
Within the secondary sectors, there are additional categories of analyses, measurement, and review that can be applied to introduce additional layers of detail that can optimize performance and quality of patient management. These include determining factors of measurement that can be linked among two or more secondary sectors. These links may include assessment of end goals and predictive expectations. Public health indicators such as scheduled preventive care can be paralleled with primary care physician visits with related diagnoses and treatment. More intricate analyses will include the mapping and review of multiple factors per sector.