Free Hospital EMR and EHR 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 Hospital EMR and EHR for FREE!

Using Clinical Decision Support Can Decrease Care Costs

Posted on September 28, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

A study of clinical decision support system use has found that abiding by its recommendations can lower medical costs, adding weight to the notion that they might be worth deploying despite possible pushback from clinicians.

The study, which appeared in The American Journal of Managed Care, looked at the cost of care delivered by providers who adhered to CDS guidelines compared with care by nonadhering providers.

To conduct the study, researchers reviewed 26,424 patient encounters. In the treatment group, the provider adhered to all CDS recommendations, and in the control group, the provider did not do so. The encounters took place over three years.

The data they gathered regarding the encounters included alert status (adherence), provider type, patient demographics, clinical outcomes, Medicare status, and diagnosis information. The research team looked at the extent to which four outcome measures were associated with alert adherence, including encounter length of stay, odds of 30-day readmissions, odds of complications of care and total direct costs.

After conducting their analysis, the researchers found that the total encounter cost was 7.3% higher for nonadherent encounters than adherent ones, and that length of stay was 6.2% longer for nonadherent versus adherent encounters. They also found that the odds ratio for readmission within 30 days increased by 1.14, and the odds ratio for complications by 1.29, for nonadherent encounters versus adherent encounters.

Not surprisingly, given these results, the study’s authors suggest that provider organization should introduce real-time CDS support adherence to evidence-based guidelines.

It is worth noting, however, that the researchers inserted one caveat in their conclusion, warning that because they couldn’t tell what caused the association between CDS interventions and improved clinical and financial outcomes, it would be better to study the issue further.

Besides, getting clinicians on board can be painful, with many clicking through alerts without reading them and largely ignoring their content. In fact, another recent study found that almost 20% of CDS alert dismissals may be inappropriate.

Most of the inappropriate overrides were associated with an increased risk of adverse drug events. Overall, inappropriate overrides were six times as likely to be associated with potential and definite adverse drug events.

Hospitals Struggle To Get Users On Board With Mobile Policies

Posted on August 6, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

A new survey has found that hospitals are having a hard time managing and tracking user compliance with mobile communications policies.

The survey, which was conducted in early 2018 by communications vendor Spok, collected information on mobile device communications strategies from approximately 300 healthcare professionals. Forty-four percent of respondents were clinicians, 10% were IT and telecom staff, 6% were executive leaders, and another 40% had a wide variety of healthcare roles.

Spok found that hospitals who do have a mobile strategy in place have had one for a long time, with 42% having had such a strategy for either 3 to 5 years or more than five years. Another 46% have had a formal mobile strategy for one to three years. Only 12% have had a strategy in place for one year or less.

Reasons they cited for creating mobile device strategies included the launch of a communication initiative (46%); a clinical initiative (25%); or a technology initiative (24%). Five percent of responses were “other.” Top areas of focus for these strategies included mobile management and security (56%), mobile device selection (52%) and integration with the EHR (48%).

Other reasons for mobile initiatives included clinical workflow evaluation (43%), device ownership strategy/BYOD (34%), mobile apps strategy (29%), mobile app catalog (16%), mobile strategy governance (14%) and business intelligence and reporting strategy (12%).

However, there’s little agreement as to which hospital department should monitor compliance. Forty-three percent of respondents said the security team was monitoring policies for the hospital or system, 43% rely on a telecommunications team, 43% said a clinical informatics team played that role, and 26% had monitoring done by a mobile team. Twenty-one percent said individual departments enforce mobile policies and 9% said they don’t have an enforcement method in place. Another 9% of responses fell into the “other” category.

Given the degree to which monitoring varies between institutions, it’s little wonder to learn that policies aren’t enforced effectively in many cases. On the one hand, 39% respondents said the policies were enforced extremely well most of the time, and one-third said they were enforced well most the time. However, 4% said the policies were being enforced poorly and inconsistently, and 44% said they are not sure about how well the policies are being enforced.

Hospitals are aware of this problem, though, and many are taking steps to ensure that users understand and comply with mobile policies. According to the survey, 48% offer educational programs on the subject, 42% use technology or data gathered from devices to measure and track compliance, 37% leverage direct feedback from users and 23% use surveys.

Still, 21% said they don’t have a way to validate compliance — which suggests that hospitals have a lot more work to do.

Despite Risks, Hospitals Connecting A Growing Number Of Medical Devices

Posted on July 20, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

Over the past few years, hospitals have gotten closer and closer to connecting all of their medical devices to the Internet — and more importantly, connecting them to each other and to critical health IT systems.

According to a new study by research firm Frost & Sullivan, most hospitals are working to foster interoperability between medical devices and EHRs. By doing so, they can gather, analyze and present data important to care in a more sophisticated way.

“Hospitals are developing connectivity strategies based on early warning scores, automated electronic charting, emergency alert and response, virtual intensive care units, medical device asset management and real-time location solutions,” Frost analysts said in a prepared statement.

Connecting medical devices to other hospital infrastructure has become so important to the future of healthcare that the FDA has taken notice. The agency recently issued guidance on how healthcare organizations can foster interoperability between the devices and other information systems.

Of course, while hospitals would like to see medical devices chat with their EHRs and other health IT systems, it’s just one of many important goals hospitals have for data collection and analysis. Health IT executives are up to the eyebrows supporting big data transformation, predictive analytics and ongoing EHR management, not to mention trying out soon-to-be standard technologies such as blockchain.

More importantly, few medical devices are as secure as they should be. While the average hospital room contains 15 to 20 connected devices, many of them are frighteningly vulnerable. Some of them are still running on obsolete operating systems, many of which haven’t been patched in years, or roughly 1,000 years in IT time. Other systems have embedded passwords in their code, which is one heck of a problem.

While the press plays up the possibility of a hacker stopping someone’s connected pacemaker, the reality is that an EHR hack using a hacked medical device is far more likely. When these devices are vulnerable to outside attacks, attackers are far more likely to tunnel into EHRs and steal patient health data. After all, while playing with a pacemaker might be satisfying to really mean people, thieves can get really good money for patient records on the dark web.

All this being said, connected medical devices are likely to become a key part of hospital IT infrastructure in hospitals over time as the industry solves these problems, Frost predicts that the global market for such devices will climb from $233 million to almost $1 billion by 2022.

It looks like hospital IT executives will have some hard choices to make here. Ignoring the benefits of connecting all medical devices with other data sources just won’t work, but creating thousands of security vulnerabilities isn’t wise either. Ultimately, hospital leaders must find a way to secure these devices ASAP without cratering their budget, and it won’t be easy.

Pager Breach Exposes Patient Data From Six Hospitals

Posted on July 6, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

The IT worker was shocked. All he had done was buy an antenna and try to get TV channels on his laptop computer, but to his amazement, he inadvertently intercepted a flood of unencrypted pager messages chock full of private patient data.

The pager messages flooded in from six Kansas City area hospitals, including the University of Kansas Hospital, Cass County Regional, Liberty Hospital, Children’s Mercy Hospital, St. Mary’s Medical Center and Wesley Medical Center.  All told, the man had gotten access to information on hundreds of patients, in a fusillade of potential HIPAA violations.

According to an article in the Kansas City Star, patients who learned about the breach were horrified. “Who knows what else is going on, if it’s that easy for that information to get out there?” one woman told the newspaper. “There’s a big security breach there that needs to be stopped.”

When the paper spoke to the hospitals involved, some punted and didn’t respond to questions. Others shrugged off the problem or suggested that the breach was not a big deal.

For example, the University of Kansas told the reporter that the pager vulnerability was due to “a specific vulnerability in our paging system that may allow access to certain personal health information in limited circumstances.” It seems that an apology was not forthcoming.

Another hospital, Children’s Mercy, told the Star that the IT worker was to blame for the problem, contending that the pager data was only accessible to “local hackers with specific scanning and decoding equipment —- and technical knowledge of how to use it for this specific purpose.” In other words, the breach wasn’t really its fault.

As the article points out, the IT worker could be accused of violating the Electronic Communications Protection Act, which restricts the interception of electronic communications. For that reason, the paper never identifies him. But the article strongly suggests that he was surprised to see the messages and operated in good faith.

The worker, for his part, sensibly argues that the hospitals should have realized that the messages were in the clear. “It’s security by obscurity at this point —- and that’s scary,” he told the paper. “In my line of work you see a lot of ‘Let’s hope nobody finds it,’ [or] ‘It’s hard to find, so it’s pretty secure.’ That’s not enough. We can’t just trust people won’t stumble upon it. We have to assume that they do.”

Financial Perspectives from the HFMA Annual Conference

Posted on June 26, 2018 I Written By

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

I always enjoy attending the HFMA Annual Conference (Formerly known as ANI) which brings together healthcare CFOs and others in the healthcare financial management community. Or as someone once told me, this use to be a conference of CPAs. In spite of its roots, there was an interesting mix of people at HFMA including health IT professionals, HIM professionals, and of course CFOs at the conference.

In one of my interviews at the conference, I sat down with Dan Berger, Director of Healthcare at AxiaMed. We had a wide-ranging conversation about healthcare payments and payment processing, but he struck me pretty hard when he talked about what would happen if a hospital or health systems payment processing went down. We talk a lot about EHR downtime and encourage healthcare organizations to have downtime procedures, but we don’t talk about payment downtime.

In some ways, this may be an appropriate response to downtime. If the EHR is down, that could impact patient care and literally patients lives. So, EHR downtime should be important. However, from a financial perspective payment processing downtime is a really big deal for healthcare organizations as well. The problem is that no patient will complain if you can’t collect their payment. The patients won’t go to the news with stories of payment processing issues. However, your business office will definitely feel it if the cash stops flowing.

This example is a simple reminder of how healthcare is a business. You see that in full view when you’re at a conference like HFMA’s annual conference. In some ways that’s a good thing since healthcare organizations have to be financially sound if they want to fulfill their missions. However, sometimes that can be taken too far as some people treat patients as a number on a spreadsheet.

I have seen some hope here at the conference. There are quite a few companies working hard to personalize the payment experience, to make pricing and payment information available to patients in ways it hasn’t been available before, and efforts to improve things like legible bills. These are small things, but they make a big difference to a patient.

I was also impressed with a number of companies that were using financial data to understand the patients better and when combined with other data can really personalize the care a patient is provided. A great example of this is Clarify Health Solutions which is making patient financial data useful and optimizing the patient journey. This is challenging stuff, but the data is getting there and companies are starting to see success and build up data that can be used by any healthcare organization.

What’s become more and more apparent to me is how challenging all of these healthcare problems are and how many people have to be influenced for change to happen. The wide variety of stakeholders that can hijack a great project is amazing. Dan Berger from AxiaMed who I mention at the start of this article commented on how payment processing used to be largely owned by the business office. He went on to share that now he’s seeing the CISO get involved and even the CIO. In many cases the CISO has veto power over vendors that don’t meet a healthcare organization’s security needs. Given all the security issues healthcare faces that’s generally a good thing. However, these types of group decision making do make the process of adding new innovations to your organization more complicated.

Mayo Clinic EMR Install Goes Poorly For Nurses

Posted on June 1, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

Ordinarily, snagging a contract to help with an Epic install is a prized opportunity. Anyone involved with this kind of project makes very good money, and the experience burnishes their resume too.

In this case, though, a group of nurse contractors says that the assignment was a nightmare. After being recruited and traveling across the US to work, they say, they were treated horribly by the contractor overseeing the Mayo Clinic’s go-live of its Epic EMR.

According to a recent news story, the Clinic hired a team of seven nurses to help with the final stages of the rollout. The nurses, all of whom were familiar with Epic, were recruited by Mayo vendor the HCI Group. One nurse, Angela Coffaro, was offered $15,000 for her work. However, she found the way she was treated to be so offensive that she quit after only days on the job. Working conditions were “horrendous,” she told the reporter.

Nurse.org reported that another nurse said the contract nurses were verbally abused, intimidated, and even threatened that they would lose their jobs on an “hourly” basis. They also noted being assigned to positions well outside the skill set. For example, Coffaro said, she was sent to the outpatient eye clinic instead of the OR, and an OR nurse to radiology.

What’s more, the HCI Group executives apparently treated the nurses brutally during training sessions. According to some, they were not permitted to leave the training room even to use the restroom during 6 to 8-hour orientation sessions.

Adding insult to injury, the contractor allegedly failed to provide adequate housing. For example, Nurse.org tells the story of Cleveland-based nurse practitioner Kumbi Madiye, who arrived at 9 AM the day before her training was scheduled to begin and found only chaos. Madiye told the publication that she waited 14 hours without a room, only to find out at 11 PM that her assigned room was an hour and a half away.

The story stresses that while the nurses said they were astonished by HCI Group’s attitude and performance, they had no problem with the way they were treated by Mayo Clinic personnel.

That being said, if even half of the allegations are true, Mayo would certainly bear some responsibility for failing to supervise their vendor adequately. Also, my instinct is that one or more of the nurses must have told Mayo what was going on and if the Clinic’s leaders did anything about the problem the nurses never mentioned it.

I’m also very surprised any vendor might have abused IT-savvy nurses with precious Epic experience. As sprawling as the health IT world is, word gets around, and I doubt anyone can afford to alienate a bunch of Epic experts.

In The Aftermath Of Sutter Health EMR Crash, Nurses Raise Safety Questions

Posted on May 24, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

In mid-May, Sutter Health’s Epic EMR crashed, accompanied by other technical problems. Officials said the system failures were caused by the activation of the fire suppression system in one of their IT buildings.

As you might expect, employees at locations affected by the downtime weren’t able to access patient medical records. On top of that, they didn’t have access to email or even use their phones. In addition, the system had to contact some patients to reschedule appointments.

On the whole, this sounds like the kind of routine issue which, though embarrassing, can be brought to heel if an organization does the disaster planning and employee training on how to react to the situations.

According to some nurses, however, Sutter Medical Center may not have handled things so well. The nurses, who spoke on condition of anonymity with The Sacrament Bee, told the newspaper that the hospital moved ahead with some forms of care before the outage was completely resolved.

The nurses told that when some patients were admitted after the systems failure, clinicians still didn’t have access to critical patient information. For example, a surgical nurse noted that the surgical team relies upon EMR access to review patient histories and physicals performed within the previous 30 days. According to Sutter protocols, these results need to be certified by the physician as still being valid on the date of surgery.

Instead, patients were arriving with their histories and physical exam records on paper, and those documents didn’t include the doctor’s certification that the patient’s condition hadn’t changed. If something went wrong during elective surgery, the team would’ve had to rely on paper documents to determine the cause, the nurses said.

They argue that Sutter Medical Center shouldn’t have taken those cases until the EMR was fully online. “Other Sutter hospitals canceled elective surgeries,” one nurse told a reporter. “Why did Sutter Medical Center feel like they needed to do elective surgeries?”

Also, they say that at least one surgical procedure was affected by the outage, when a surgeon needed a particular instrument to proceed. Normally, they said, operating room telephones display a directory of numbers to supply rooms or nurse stations, but these weren’t available and it forced the surgical team to break its process. Under standard conditions, the team tries not to leave the operating room because a patient’s condition can deteriorate in seconds. In this case, however, a nurse had to hurry out of the room to get instruments the surgeon needed.

While it’s hard to tell from the outside, this sounds a bit, well, unseemly at best. Let’s hope Sutter’s decision-making in this case was based on thoughtful decisions rather than a need to maintain cash flow.

Let this also be an important reminder to every healthcare organization to make sure you have well thought out disaster plans that have been communicated to everyone in your organization. You don’t want to be caught liable when disaster strikes and your staff start free wheeling without having thought through all of the potential consequences.

Hospitals Still Grappling With RCM Tech Infrastructure

Posted on May 18, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

While revenue cycle management isn’t the sexiest topic on the block, hospitals need to get it right or they won’t be able to pay their bills. One key element needed to accomplish this goal is a robust tech infrastructure that helps RCM specialists get their job done.

However, it seems that many hospitals are struggling to manage RCM data and pick out the right vendors to support their efforts, according to a report published by Dimensional Insight in collaboration with HIMSS Analytics. To conduct the research, the two organizations reached out to 117 senior-level decision-makers in hospitals and health systems.

According to the survey, more than two-thirds of health systems use more than one vendor for RCM. But that might be a bad idea. The research also found that organizations using more than one RCM vendor seem to face bigger issues with denials than those using only one RCM solution. Regardless, the execs said that denials were the biggest RCM challenge for health systems today.

Pulling together RCM data is a struggle too, respondents said. More than 95% of health systems reported that the way data is collected is a challenge. Also, nearly all respondents said that collecting RCM data from disparate sources is also difficult.

One reason why it’s tough for hospitals to put effective RCM technology in place may be that health information management directors and managers aren’t at the top of the influencer list when it comes to making these decisions.

When asked who the key stakeholders were in RCM. 91.5% said that the CFO was the most important, followed by the head of revenue cycle, who was ranked as important by 62.4% of respondents. Meanwhile, only 48.7% of respondents saw the health IT leaders as key stakeholders in the RCM environment. In other words, it looks like tech leaders aren’t given much clout.

When it came to technical infrastructure for RCM, respondents were all over the map. For example, 34.5% were working with an EMR and 3+ vendors. Another 12.1% used in EMR with one vendor, followed by 11.2% with 3+ vendor solutions, 6.9% using an EMR plus two vendors and 4.3% using two to vendor solutions. Clearly, there’s no single best practice for managing RCM technology in hospitals.

Not only that, some hospitals aren’t doing much to analyze the RCM data they’ve got. According to the survey, 23.9% said that 51 to 75% of the RCM process was automated, which isn’t too bad. However, 36.8% of hospitals reported that less than 25% of the revenue cycle process was driven by analytics. Also, roughly a third of respondents said that collecting data from diverse sources was extremely challenging, which can cripple an analytics initiative.

Taken as a whole, the report data suggests that hospitals need to improve their RCM game dramatically, which includes getting a lot smarter about RCM technology. Unfortunately, it looks like it could be a long time before this happens.

Despite EMR, Revenue Cycle Management Costs Were Still Substantial

Posted on April 26, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

While they may not say so out loud, most healthcare organizations bought EMRs largely because they believed they could use them to lower revenue cycle management expenses. If so, they may be somewhat disappointed. A new study has concluded that at least in one case, the presence of a certified EMR didn’t make much of a dent in these costs.

­To conduct the study, researchers conducted interviews with 27 health system administrators and 34 physicians at a large academic medical center. The interviews took place in 2016 and 2017. The research team used the feedback to create a process map charting the path of an insurance claim through the RCM process.

Using this data, the researchers calculated the cost of each major billing and insurance-related activity, as well as a total cost of processing a claim from end to end. The data included costs for five types of patient encounters, including primary care visits, discharge ED visits, general medicine inpatient stays, ambulatory surgical procedures and inpatient surgical procedures.

The team concluded that estimated processing times and total costs for billing and insurance-related activities were 13 minutes and $20.49 for a primary care visit, 32 minutes and $61.54 for a discharged ED visit, 73 minutes and $124.26 for a general inpatient stay, 75 minutes and $170.40 for an ambulatory surgical procedure and 100 minutes and $215.10 for an inpatient surgical procedure.

To put these numbers in perspective, the research team noted that billing costs represented an estimated 14.5% of professional revenue for primary care visits, 25.2% for emergency department visits, 8% for general medicine inpatient stays, 13.4% for ambulatory surgical procedures and 3.1% for inpatient surgical procedures.

There are more than a few unfortunate things to be seen in these numbers.

One is that primary care practices spent a very high percentage of revenue on RCM, which could be crushing given their typically low margins. Given that PCPs are already being squeezed by patients who can’t afford to meet their high deductibles, this is a recipe for financial disaster.

It’s also troubling to see that that the academic medical center in question was spending more than 25% of its ED revenue chasing insurance payments. I found myself wondering whether ED prices might drop to a reasonable level if it was easier for these departments to collect from insurers.

It’s scary to think that these numbers might’ve been higher before the academic medical center installed its EMR. As things stand, if the EMR is lowering RCM costs, it doesn’t seem to be having a major impact. But I’m just guessing here — what do you think?

Are We Going About Population Health The Wrong Way?

Posted on March 29, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

For most of us, the essence population health management is focusing on patients who have already experienced serious adverse health events. But what if that doesn’t work? At least one writer suggests that though it may seem counterintuitive, the best way to reduce needless admissions and other costly problems is to focus on patients identified by predictive health data rather than “gut feelings” or chasing frequent flyers.

Shantanu Phatakwala, managing director of research and development for Evolent Health, argues that focusing on particularly sick patients won’t reduce costs nearly as much as hospital leaders expect, as their assumptions don’t withstand statistical scrutiny.

Today, physicians and care management teams typically target patients with a standard set of characteristics, including recent acute events, signs of health and stability such as recent inpatient admissions and chronic conditions such as diabetes, COPD and heart disease. These metrics come from a treatment mindset rather than a predictive one, according to Phatakwala.

This approach may make sense intellectually, but in reality, it may not have the desired effect. “The reality is that patients who have already had major acute events tend to stabilize, and their future utilization is not as high,” he writes. Meanwhile, health leaders are missing the chance to prevent serious illness in an almost completely different cohort of patients.

To illustrate his point, he tells the story of a commercial entity managing 19,000 lives which began a population health management project. In the beginning, health leaders worked with the data science team, which identified 353 people whose behavior suggested that they were headed for trouble.

The entity then focused its efforts on 253 of the targeted cohort for short-term personal attention, including both personal goals (such as walking their daughter down the aisle at her wedding later that year) and health goals (such as losing 25 pounds). Care managers and nurses helped them develop plans to achieve these goals through self-management.

Meanwhile, the care team overrode data analytics recommendations regarding the remaining 100 patients and did not offer them specialized care interventions during the six-month program.  Lo and behold, care for the patients who didn’t get enrolled in health management programs cost 75% more than for patients who were targeted, at a total cost of $1.4 million. Whew!

None of this is to suggest that intuition is useless. However, this case illustrates the need for trusting data over intuition in some situations. As Phatakwala notes, this can call for a leap of faith, as on the surface it makes more sense to focus on patients who are already sick. But until clinicians feel comfortable working with predictive analytics data, health systems may never achieve the population health management results they seek, he contends. And he seems to have a good point.