Patient Engagement Platform Sees Explosive Growth
Health Data Management
HDM: Historically, the way people end up choosing a doctor or a hospital has often defied conventional marketing methods.
Your new post is loading...
he human brain may be nature’s finest computer, but artificial intelligences fed on big dataare making a convincing challenge for the crown. In the realm of healthcare, natural language processing, associative intelligence, and machine learning are revolutionizing the way physicians make decisions and diagnose complex patients, significantly improving accuracy and catching deadly issues before symptoms even present themselves.
In this case study examining the impact of big data analytics on clinical decision making, Dr. Partho Sengupta, Director of Cardiac Ultrasound Research and Associate Professor of Medicine in Cardiology at the Mount Sinai Hospital, has used an associative memory engine from Saffron Technology to crunch enormous datasets for more accurate diagnoses. Using 10,000 attributes collected from 90 metrics in six different locations of the heart, all produced by a single, one-second heartbeat, the analytics technology has been able to find patterns and pinpoint disease states more quickly and accurately than even the most highly-trained physicians.Dr. Sengupta explained his ongoing work with big data analytics to HealthITAnalytics, and discussed the impact such technologies can have on cardiology patients and their outcomes.What were the underlying medical issues you were trying to solve with this study?One of the most commonly ordered diagnostic tests in cardiology is the echocardiogram. We were amazed at the amount of information that was coming in during each patient consultation, so the biggest challenge was how to make the information, which is extremely rich, easily understandable and use it in real-time in patient care scenarios. Working with Saffron, we decided that we will look into a scenario which is extremely complex which usually requires a lot of expertise, and it usually is associated with fairly complex sets of information.We decided to do a pilot test with two diseases: cardiomyopathy, which affects the heart, and pericarditis, which masquerades as if the heart is involved, but actually the heart muscle is not involved. Both diseases present with heart failure, and patients are very complex in their assessments. If you make the correct diagnosis the treatments are very disparate, very different. For pericarditis, you would do a surgery, whereas if it’s cardiomyopathy, it’s a different course. It’s medical management or a heart transplant.Misdiagnosis of these conditions is a fatal error, because if you make the wrong decision, you’re going to send a patient who’s going to be treatable by surgery to get a heart transplant and vice versa. If you open up a patient because you think they have pericarditis, and then you have to close the patient because the patient didn’t have the thickening of the membranes around the heart, that’s expensive for the hospital and puts the patient at an unnecessary risk of complications. So that’s why we use this particular technology on these diseases, because the risk of not diagnosing this disease properly is immense.How can clinical analytics supplement human intelligence to identify patterns and make diagnoses?For the study, we took a lot of the ultrasound information, which is the first step for diagnosing these patients. We took the information, which is extremely complex and started working on that using the natural intelligence platform to see if we could come up unique characterization of the disease, so that the information can be clustered for pattern recognition. You use a lot of intuitive skills to go through these datasets. I was interested in seeing how processing this data through clinical analytics can provide better decision support.The problem is that the data is scattered everywhere. It’s in the EMR, but everything is still in siloes. So either you have to make an effort to look in the EMR, then look into the e-measures, which may be existing on another system, look at the PACS system, and the himself patient is somewhere else. So, they’re all in different locations. How do we take all the information just coming from different sources and merge them together, so that we can apply it right away to the patient in real-time? That’s what we are currently focused on.Let’s say I just analyzed an echocardiogram of a patient and I track the information into am Excel file. You open that Excel file, and it will have about 30 columns and 50 to 60 rows. What we do right now is go row by row, and it’s very painful. But the analytics engine takes an entire dataset all at once, and then comes out with these rich associations. Based upon its previous learning, using its associative memory capabilities, it can tell that this dataset looks like this disease, and that dataset looks like another disease.This kind of an application can be done for any scenario. For example, diabetes can produce some very early changes in the heart muscle which the patient doesn’t even know about. He’s completely asymptomatic. You might have a signal present in this big data, but you might not be able to discover it on your own. You might not even really be looking for it, but when you process it through a complex analytics engine, you might be able to come up with some kind of signal that will show the early disease state.Diseases come in clusters, so heart disease, cancer, Alzheimer’s, they don’t come independently. They all together in one given patient, so my hope is that in future we will be able to take all the risk factors, which are common for these diseases, which are growing to epidemic proportions, and we will be able to deliver forecasting models based upon them.That’s kind of the vision. I think it would be really terrific to have a forecasting model, so then this patient has such risk factors, goes into the hospital for, let’s say a knee surgery, what are his chances he’s going to develop a heart attack when he comes out of the surgery? That’s the kind of the risk modeling we’ll be very interested to develop in the future.After using the clinical analytics engine to examine the data, what results did you find?In the initial pilot phase, when I did my own statistical algorithms, we had about 73% ability to differentiate the two diseases. But when the initial pilot run happened, we were very pleased to see that there was a discrimination of 90% between the two datasets and without any human intervention. What that means is that the highly complex analyses that were done produced a discrimination which exceeded human ability to diagnose the two conditions. Having said that, you have to be extremely cautious, but it’s very exciting that machine learning and learning intelligence platforms can reach the ability to do this differentiation, if not exceed it.Related White Papers:Webcast: Gain Deeper Insight into your EMR with Care Systems Analytics from VMwareActionable Analytics: 10 Steps to Improve Profitability and Patient ExperienceImprove Outcomes with the VMware Care Systems Analytics SolutionPredictions for Big Data in Large and Small PracticesHL7 Survival GuideBrowse all White PapersRelated Articles:NIH to boost role of genomics in research, clinical analyticsGenomics, big data can thrive through CDS, analytics tools2.5 petabytes of centralized cancer data to accelerate genomicsNew law would increase access to Medicare data for analyticsHow big pharma uses big data to develop better drugs
Via nrip, dbtmobile
Many in the health care industry are wary of jumping on the social media bandwagon due to legal limitations, fear of exposing privileged information, and damaging relationships with patients and partners. Be that as it may, social networking is just too big for many people to ignore.
Stats from Nielsen report that sites like Facebook and Twitter now account for 22.7% of the time spent on the Internet. In comparison, E-mail as a percentage of online time use has plunged from 11.5% to 8.3% from June 2009 to June 2010.
Social media marketing in health care can be an easy way to stay connected with customers and prospects. The good news is that utilizing social networking sites, such as Google+, Facebook, Twitter, YouTube, and LinkedIn, doesn’t have to be scary. Social media disaster can easily be avoided by following simple guidelines and methods.
The American Medical Association suggests the following as basics for all clinicians using social media. These basics can easily be applied to product manufacturers, as well:
Mayo Clinic suggests speaking in the first person and distinguishing personal thoughts and beliefs from those of your organization. The Mayo Clinic also stresses the importance of disclosing a connection to the company you are associated with when communicating public interest about the organization.
So what is there to talk about? Here are a few ideas to get you started:
Kestrel Health Information maintains a presence on LinkedIn, Twitter, Google+ and Facebook, connecting with both clinicians and product manufacturers alike. Through a combination of product-related information and niche specific news media, these social media sites provide valuable points of contact, as well as a platform for industry-related discussions.
The purpose of social media is to interact, and build relationships. It allows customers to forge personal connections with professionals and businesses that were not previously possible.
For a business this can mean building a loyal customer base, or utilizing customer feedback in order to improve service. It can also help your company generate new leads to convert into new customers.
Follow these suggestions and begin using social media to increase your visibility right away.
Via Plus91, Giuseppe Fattori, Art Jones
To meet the challenges and complexities created by the passage of the Patient Protection and Affordable Care Act, hospitals and health systems must now devise new strategies to effectively market physicians. Since the PPACA, physician alignment activities have escalated, including employment, consolidations and affiliation relationships. The increased pressure to generate revenue and grow market share, combined with the high cost of IT solutions, add to the escalation. Given the changing physician-marketing environment, many hospital and health system leaders, marketers and physician relations professionals are re-thinking their understanding of the basic day-to-day do's and don'ts of regulatory requirements. Below are seven key challenges that hospitals and health systems face and suggestions on how to best navigate the waters.
Challenge 1: Defining "marketing." The term marketing is often an umbrella term for all types of physician promotions, whether paid or unpaid, in the context of a hospital medical staff, its affiliated physicians or market area physicians. Marketing can cover anything from the press release written for an independent physician joining an integrated network to the dollars put on the table to advertise a newly employed physician or to the office practice doors knocked on by physician liaisons. In addition, marketing may be subject to fraud and abuse laws, such as Stark and the Anti-Kickback Statute. Do not fall into the trap of using words other than marketing in the hope of avoiding government scrutiny. The terms public relations, physician relations and promotion can still trigger the need for a fraud and abuse analysis.
Challenge 2: Maintaining consistency across departments and entities. Rules differ for marketing among various physician types: employed, subsidized, independent, in co-management agreements, medical directorships, networks, physicians without hospital privileges and so on. These rules can vary from state to state as well. It is highly recommended that hospitals and health systems develop or maintain a strong set of policies and practices to guide each type of relationship. These can come in the form of system or department policies. When there are documented procedures to follow, conversations with physicians, who are making certain requests, can be more straightforward. Consistency is the key to improving physician interactions, ensuring compliant relationships and maintaining a sense of equality.
Challenge 3: Determining legal compliance of marketing activities. Many times, a physician expects his or her marketing to be the responsibility of the hospital and health system based on an employment or other type of specific contractual arrangement. However, sometimes no provisions or covenants are made within the physician's agreement with the hospital for marketing support. If you do not include specific written language in the contract regarding marketing activities, you may tie the hands of the marketer trying to help the physician and the hospital.
In addition, it is advisable to include contract language that sets out specific marketing dollars or hospital-approved activities. Without such a provision, the physician's expectations may be broader than the budget allows or permitted under the law. The best strategy is to collaborate before signing a physician contract, so all hospital stakeholders (administration, legal and marketing) have what they need to successfully onboard an employed physician or support independent physician alignment activities. For example, under Stark, you will want to consult legal counsel to determine if a financial relationship with the physician exists, if the arrangement involves a designated health service or if there is a permissible exception.
Challenge 4: Advertise physicians appropriately. Historically, physician marketing has been an area of ethical debate among healthcare trade associations, marketers and legal departments. Today, hospital/physician network competition is fierce, consumers are determined to select the right physicians and some physicians need to diversify their practice volumes. All this makes certain types of advertising helpful to both physicians and consumers. However, if you do not know how to appropriately market a certain type of physician, your effort could be less effective and, possibly, run contrary to fraud and abuse laws.
Many times we see media releases or other types of promotions that direct the consumer to visit an independent physician practice's website or call that practice to request information or make an appointment. Hospitals need to tread carefully to ensure they are not violating Stark and AKS requirements and that such direction generates the right type of call to action for the right type of physician relationship. When creating an advertising campaign, the type of physician relationship determines your ability to advertise on behalf of that physician or group and influences the development of your message. When creating a message, stay away from superlatives like "the best," "the highest quality," "world-class," and "extraordinary" unless you can prove and defend them with credible data, research or other reputable sources (preferably not paid for by the hospital and unbiased). If you decide to make similar statements, refer to the federal and state laws directly related to marketing and fraud, such as the Stark, AKS, Medicare Advantage marketing guidelines, accountable care organization marketing activities and state fraud laws.
Challenge 5: Equality vs. preferential treatment. Hospital marketers may be inclined to avoid promoting physicians who they know have low activity at their organizations. They may argue that precious dollars should be spent on driving business growth and on those who help the hospital reach its goals. In traditional and non-traditional advertising, public relations events, call centers, directories, websites and other marketing efforts, providing preferential treatment or favoring certain physicians can be a violation of fraud and abuse laws. It is important that your policies and procedures outline how certain categories of physicians, whether active, courtesy, honorary or within an affiliated network, will be marketed and how those policies can be defended. For example, if your hospital's website includes a list of physicians on the medical staff, you will want to include, at a minimum, all active physicians. In addition, every hospital should have an "opt out" procedure for physicians who do not want be involved in marketing activities.
Challenge 6: Tracking non-monetary compensation to physicians. Under Stark, hospitals may provide non-monetary compensation to physicians up to an aggregate amount of $385 per calendar year for the year 2014. With so many departments reaching out to physicians in different ways, it is challenging for hospitals to keep track of their conversations with physicians. It is imperative (and, in fact, required) that hospitals track non-monetary compensation across the system to ensure compliance and review it regularly so as not to exceed regulatory limits. The annual limit applies to each physician, but cannot be aggregated to make a larger gift to a group practice or other group of physicians. For example, a $500 basket of edible goodies cannot be given to a three-physician practice and divided by three. Under Stark, this gift is indivisible and represents a $500 gift to each of the three physicians. There are three exceptions to the federal Stark non-monetary compensation requirements:
Gift cards or "cash equivalents" are considered "non-monetary." It is not just cash that counts. For example, hospitals may need to track Doctors' Day gifts, free car washes, dinners and tickets to events. Other rules exist for food in medical staff lounges and other incidental expenses up to $32 for calendar year 2014, but they must be offered to all medical staff members.
Challenge 7: Assessing risks and opportunity of physicians and social media. The channels for communicating with physicians are changing rapidly and there is no denying that social media is a force to be reckoned with when it comes to managing reputation and potentially building business. While many hospitals and physicians still fear or ignore the use of social media as a channel for communication, many have embraced ways to manage the risks and rewards. For hospitals and physicians considering entering the social media space, defining a strong policy and providing training is key to laying a good foundation. HIPAA training is not enough. The hospital and physicians also need to invest in resources that continuously and rigorously monitor social media activity and be committed to creating rich and appropriate content applicable to these channels. The greatest challenge for physicians is to separate themselves personally and professionally and understand that if they put it in writing, by tweet or otherwise, it may be discoverable during a lawsuit or by the government.
Via Alex Butler, Bart Collet, dbtmobile
The Future of Healthcare: The Connected HospitalShare this infographic:
Learn more about Healthcare Integration Solutions from MuleSoft »
Searching online for a travel destination or a recipe is simple enough. But what if you wanted to diagnose a medical condition? 35 percent of US adults say they’ve used search tools to find a diagnosis.
Perhaps not surprising to physicians, of these “online diagnosers” less than half (41 percent) got their diagnosis right.
Rare Diseases and Online Community
For rare disease patients, finding others with the same unusual set of symptoms can be a lifeline. With a confirmed diagnosis, patients can connect digitally in a way that is often impossible in real life.
Rare disease is defined in the US as having less than 200,000 patients; in the EU it is one in every 2,000 people. Inherently, patients are sparse for the7,000+ known rare diseases. Only about 50 percent have advocacy groups or organizations fighting on their behalf.
Rare Disease Patients Are Power Internet Users
The Pew Research Internet Project found rare disease patients use the internet to connect with others in far greater numbers than other patients. Overall, only five percent of patients say they have interacted online with a fellow patient, but 50 percent of rare disease patients say they have connected with others sharing their condition.
The mother of a patient in the study noted,
Where Does the Online Search Begin?
Seventy-seven percent of online health-seekers start with major search engines such as Google or Bing. No matter how their searches begin, physicians wish their clicks would lead them away from social media and toward more technical information sites.
In a recent survey, we asked Sermo member physicians, “Where should rare disease patients search online for information?”
69 percent preferred medical literature sites such as the Journal of the American Medical Association or the New England Journal of Medicine.54 percent approved of research hospital sites such as Massachusetts General Hospital or Stanford Medical.32 percent gave a nod to patient communities such as Patients Like Me.11 percent approved of social media sites such as Facebook or Twitter.
Registries Can Be Life Saving
Rare disease patients like to connect for emotional support and information as their issues progress. For researchers and physicians, online registries are a boon. Clinical trials can find participants quickly and speed the path of a drug to market, potentially saving lives and easing symptoms.
In an NPR article, Sue Byrnes, a patient and founder of a rare lung disease registry said,
Overall, rare disease patients use online resources to connect, for support in their diagnoses, to compare treatment notes and to participate in research studies. Physicians and researchers use online connections to find patients and collaborate on treatment plans.
As a physician, have you directed a rare disease patient to an online resource? Have you found patients have better outcomes if they have an emotional connection? Has a rare disease patient ever questioned your treatment plan based on information they received online?
Via Plus91, Rowan Norrie, Bart Collet, Celine Sportisse
When it comes to social media, the top sites that doctors do seem to use for work are LinkedIn, online physician communities, and Facebook (see chart below). The specialities that reported the most use of online physician communities were ophthalmology, geriatrics, psychiatry, otolaryngology, and oncology.
Via Andrew Spong
Eighty percent of smartphone users are interested in using their smartphones to interact with health care providers, according to a FICO survey of 2,239 adult smartphone users from the UK, Australia, Brazil, China, France, Germany, India, Italy, Japan, Korea, Mexico, Russia, Turkey, and the United States.
The survey analyzed how consumers prefer to interact with health care providers on mobile devices, online and in-person.
Via Alex Butler, Andrew Spong