Pathologists and clinical laboratory scientists may find one hospital’s use of a machine-learning platform to help improve utilization of lab tests both an opportunity and a threat
Variation in how individual physicians order, interpret, and act upon clinical laboratory test results is regularly shown by studies in peer-reviewed medical journals to be one reason why some patients get great outcomes and other patients get less-than-desirable outcomes. That is why many healthcare providers are initiating efforts to improve how physicians utilize clinical laboratory tests and other diagnostic procedures.
This effort came about after clinical and administrative leadership at Flagler Hospital realized that only about one-third of its physicians regularly followed certain medical decision-making guidelines or clinical order sets. Armed with these insights, staff members decided to find a solution that reduced or removed variability from their healthcare delivery.
Reducing Variability Improves Care, Lowers Cost
Variability in physician care has been linked to increased healthcare costs and lower quality outcomes, as studies published in JAMA and JAMA Internal Medicine indicate. Such results do not bode well for healthcare providers in today’s value-based reimbursement system, which rewards increased performance and lowered costs.
Clinical order sets are designed to be used as part of clinical decision support systems (CDSS) installed by hospitals for physicians to standardize care and support sound clinical decision making and patient safety.
However, when doctors don’t adhere to those pre-defined standards, the results can be disadvantageous, ranging from unnecessary services and tests being performed to preventable complications for patients, which may increase treatment costs.
“Over the past few decades we’ve come to realize clinical variation plays an important part in the overuse of medical care and the waste that occurs in healthcare, making it more expensive than it should be,” Michael Sanders, MD (above) Flagler’s Chief Medical Information Officer, told Modern Healthcare. “Every time we’re adding something that adds cost, we have to make sure that we’re adding value.” (Photo copyright: Modern Healthcare.)
Flagler’s AI project involved uploading clinical,
demographic, billing, and surgical information to the AyasdiAI platform, which then
employed machine learning to analyze the data and identify trends. Flagler’s
physicians are now provided with a fuller picture of their patients’ conditions,
which helps identify patients at highest risk, ensuring timely interventions that
produce positive outcomes and lower costs.
How Symphony AyasdiAI Works
The AyasdiAI application utilizes a category of mathematics called topological data analysis (TDA) to cluster similar patients together and locate parallels between those groups. “We then have the AI tools generate a carepath from this group, showing all events which should occur in the emergency department, at admission, and throughout the hospital stay,” Sanders told Healthcare IT News. “These events include all medications, diagnostic tests, vital signs, IVs, procedures and meals, and the ideal timing for the occurrence of each so as to replicate the results of this group.”
Caregivers then examine the data to determine the optimal
plan of care for each patient. Cost savings are figured into the overall
equation when choosing a treatment plan.
Flagler first used the AI program to examine trends among their pneumonia patients. They determined that nebulizer treatments should be started as soon as possible with pneumonia patients who also have chronic obstructive pulmonary disease (COPD).
“Once we have the data loaded, we use [an] unsupervised
learning AI algorithm to generate treatment groups,” Sanders told Healthcare
IT News. “In the case of our pneumonia patient data, Ayasdi produced nine
treatments groups. Each group was treated similarly, and statistics were given
to us to understand that group and how it differed from the other groups.”
Armed with this information, the hospital achieved an 80% greater physician adherence to order sets for pneumonia patients. This resulted in a savings of $1,350 per patient and reduced the readmission rates for pneumonia patients from 2.9% to 0.4%, reported Modern Healthcare.
The development of a machine-learning platform designed to
reduce variation in care (by helping physicians become more consistent at
following accepted clinical care guidelines) can be considered a warning shot
across the bow of the pathology profession.
This is a system that has the potential to become interposed
between the pathologist in the medical laboratory and the physicians who refer
specimens to the lab. Were that to happen, the deep experience and knowledge
that have long made pathologists the “doctor’s doctor” will be bypassed.
Physicians will stop making that first call to their pathologists, clinical
chemists, and laboratory scientists to discuss a patient’s condition and
consult on which test to order, how to interpret the results, and get guidance
on selecting therapies and monitoring the patient’s progress.
Instead, a “smart software solution” will be inserted into
the clinical workflow of physicians. This solution will automatically guide the
physician to follow the established care protocol. In turn, this will give the
medical laboratory the simple role of accepting a lab test order, performing
the analysis, and reporting the results.
If this were true, then it could be argued that a laboratory
test is a commodity and hospitals, physicians, and payers would argue that they
should buy these commodity lab tests at the cheapest price.
Sale of respected laboratory information system company may be an early sign that investors believe clinical laboratories and pathology groups are ready to upgrade their LISs and add needed capabilities
In the past 10 years there has been little disruption to the
laboratory
information systems (LIS) market that clinical
laboratories and anatomic
pathology groups use. Yet, over that same 10-year period, almost every
hospital and physician group practice adopted an electronic
health system (EHR), primarily because of federal financial incentives that
encouraged such adoption.
For medical
laboratories and pathology groups, this widespread—nearly
universal—adoption of EHRs by the nation’s hospitals and physicians was
disruptive. Labs were required to expend resources building digital interfaces
to the EHRs of their parent hospitals and client physicians to support
electronic test ordering and test reporting.
However, because that wave of EHR adoption is now over,
clinical labs and pathology groups have an opportunity to assess the current
state of the health
information technology (HIT) that they use daily, primarily in the form of
the classic laboratory information system that handles nearly all the primary
functions needed to support testing and other operational needs.
This opportunity to help medical laboratories enhance and/or
upgrade the capabilities of their laboratory information systems may be one
motivation behind the recent sale of a well-known LIS company.
Private Equity Firm Buys Orchard Software
On Oct. 7, 2019, Orchard Software Corporation of Carmel,
Ind., announced its acquisition by Franciscan Partners, a private equity firm
based in San Francisco.
Orchard Software, founded in 1993, has grown steadily over
the past 20 years, primarily by serving physician office laboratories,
community hospital labs, and independent clinical laboratory companies. With each
stage of growth, Orchard added functionality to its LIS and related software
offerings and moved up-market to serve larger hospitals and larger labs.
The purchase price and the terms of the sale were not
announced. Orchard’s Founder, President and CEO, Rob Bush, will retire. The new
CEO is Billie Whitehurst, who came to Orchard from Netsmart Technologies, where she was Senior
Vice President. The remainder of Orchard’s management team will be kept in
place.
“Francisco Partners will provide capital and expertise to enable Orchard to grow at a faster pace and continue to develop its newer web-based products in an industry that has lagged behind in adoption of cloud-based software,” says Rob Bush (above), Orchard Software’s Founder and exiting CEO, in a press release. (Photo copyright: Twitter.)
Is the LIS Market Heating Up?
What makes the purchase of Orchard by a multi-billion-dollar
private equity company noteworthy is the fact that it is the first significant
transaction in the LIS sector probably since the mid-2000s, which saw several
significant mergers and acquisitions.
Other acquisitions or investments involving LIS companies
need to happen before it would be appropriate to say that investor interest in
the LIS sector is heating up. However, it is accurate to say that many
professional investors will be watching to see whether Franciscan Partners
succeeds with its investment in Orchard Software. If Orchard’s revenue and
operating profits increase substantially in the next few years, that may
encourage other investors to look for LIS companies and products that they can
buy.
If this were to happen, that would be a positive development
for both clinical laboratories and anatomic pathology groups, because these
investors would have a motive to add new functions and capabilities to their
LIS products. It would also wake up a sector of lab information technology that
has been relatively quiet for several years.
Another push for price transparency steps up pressure on medical laboratories and anatomic pathology groups to develop compliance strategies
Clinical
laboratories and anatomic
pathology groups are under increasing pressure to develop strategies for
making their test prices more accessible to patients. Those pressures are
likely to grow due to newly proposed federal regulations that aim to allow
patients to compare prices for healthcare services on their smartphones.
This new proposed rule comes less than a year after a rule
involving hospital prices was implemented. As of January 1, 2019, the federal
Centers for Medicare and Medicaid Services (CMS) required
US hospitals to post their prices online. Dark
Daily reported last year about the risks and opportunities posed by
that move.
“In our current health system, there is an asymmetry of information for patients. They have few ways if any to anticipate or plan for costs, lower or compare costs, and, importantly, measure their quality of care or coverage relative to the price they pay. Transparency in the price and cost of healthcare could help address some of those concerns by empowering patients with information they need to make informed decisions,” said Donald Rucker, MD (above), National Coordinator for Health Information Technology (ONC), in remarks delivered to the US Senate. (Photo copyright: ONC.)
Giving Patients Access to Their Health Information
In May, officials with those agencies discussed the
regulations in prepared remarks for a hearing of the HELP committee.
“A central purpose of the proposed [ONC] rule is to
facilitate patient access to their EHI on their smartphone, growing a nascent
patient- and provider-facing app economy,” he said, noting that this access is
impeded by a lack of interoperability between health information systems, as
well as restrictions on information exchange imposed by health IT developers.
The proposed rule will mandate use of common software
standards so that app developers can access health information systems from
different vendors. As a result, patients could choose their own apps to view
their data regardless of which electronic
health records (EHR) system their provider uses. The rule also includes
provisions for dealing with so-called “information blocking”
by vendors, Rucker noted.
If the proposed rule is implemented as currently written,
there would be a need for clinical laboratories and pathology groups to ensure
that their laboratory
information systems (LIS) meet the specifications of the new rule. This may
mean that, along with enabling two-way digital interfaces with physicians’
EHRs, labs also would need to be able to pass data to the apps and mobile
devices used by patients that are covered by the proposed new rule.
“ONC’s proposed rule primarily focuses on clinical data,” he
said. “However, advances in computer science and the maturity of data standards
are accelerating the convergence of medical data with billing and price data.
As such, the rule proposes to include such information as part of a patient’s
EHI that should be available for access, exchange, and use.”
Enabling cost comparisons will allow patients to make
more-informed decisions about their healthcare, Rucker added. But he
acknowledged that implementing this vision won’t be easy.
“Unfortunately, the complex and decentralized nature of how
payment information for healthcare services is currently created, structured,
and stored presents many challenges to achieving price transparency,” he said.
“This entire information chain is geared to retrospective payments rather than
prices.”
Rucker told the HELP committee that the [ONC] will be
seeking public input about how to capture price information and enable price
transparency. Once the rule is finalized and published, providers will have two
years to comply.
Medical Laboratories Need a Strategy for Providing Access
to Patient Records
The proposed CMS rule imposes requirements on payers to
provide electronic access to health claims and other information for their
enrollees.
In her prepared remarks
for the Senate HELP hearing, Kate Goodrich,
MD, Director of the Center for Clinical Standards and Quality (CCSQ) and
CMS Chief Medical Officer, said, “A core policy principle underlying our
proposals is that every American should be able, without special effort or
advanced technical skills, to see, obtain, and use all electronically available
information that is relevant to their health, care, and choices—of plans,
providers, and specific treatment options.”
That’s all well and good, however, as Fred Schulte, a senior
correspondent for Kaiser
Health News, wrote in his coverage of the two proposed rules, “Meeting
these goals could prove to be a tall order.”
He continued, “For well over a decade, federal officials
have struggled to set up a digital records network capable of widespread
sharing of medical data and patient records.” Not to mention the billions of
dollars already spent by the CMS and ONC incentivizing providers to implement
truly interoperable health
information exchange (HIE) systems nationwide.
Nevertheless, pressure for greater consumer data access and
price transparency will likely continue to build across the healthcare
industry, including on medical laboratories. Price transparency as a trend is
making steady forward progress, despite resistance by hospitals, physicians,
medical associations, and others.
All clinical laboratories should have a strategy to make lab
test prices readily available to patients. It is something that will become
common at some future point.
EMPIs may help clinical laboratories ensure their patients and medical records are properly matched with medical laboratory test results and specimens
Mix-ups between patients and their medical records, known in
the healthcare industry as “patient mismatching,” happen far too frequently in
hospitals and clinics worldwide. When surgery is involved, such mismatches can lead
to deadly errors. However, clinical
laboratories and pathology
groups also must take steps to ensure patients, their medical records, and their
biological specimens remain properly matched.
Once horrific incident in 2016 involved Saint Vincent Hospital in
Worcester, Mass. Believing they were operating on a patient with a kidney
tumor, surgeons mistakenly removed a healthy kidney from the wrong patient. The
cause of the patient mismatch was a mix-up with CT scans. The two patients
shared similar names, Managed
Care reported.
Sadly, patient mismatching is not a new or rare problem. Patient
mismatches often lead to delays, extra costs to fix duplicate information, and
tragically, unnecessary surgery and inappropriate care, Healthcare
Dive noted.
According to Managed Care, organizations working on
solutions include:
“Incorrect matches could result in patients getting the
wrong medicine, and failure to link records could lead to treatment decisions
made without access to up-to-date laboratory test results,” Pew noted in an issues
brief.
Pew and the MAeHC interviewed 18 hospital, medical practice,
and health information technology exchange leaders. The respondents admitted
that they are uncertain about the extent of the matching problem.
“They don’t know all the records that should be related and
thus cannot understand what percentage of those are unlinked,” the researchers
wrote.
Nonetheless, the researchers found that patient/record match
rates fall “far below the desired level” for effective data exchange among
organizations, Healthcare Dive reported.
For pathologists and clinical laboratory managers, the
Pew/MAeHC study had several key takeaways, such as:
“Match rates are far below the desired level for
effective data exchange.
“An increased demand for interoperability—the
exchange of electronic data among different systems—is fueling the desire for
improvements.
“Match rates are difficult to measure.
“The methods in which records are received can
affect match results.
“Different types of healthcare providers vary in
their perspectives on the extent of the problem.
“Effective opportunities exist for organizations
to more accurately link individuals’ health records.”
About $1,950 in medical care costs per patient during a
hospital stay, and $1.5 million annually in denied claims per hospital, are
associated with inaccurate patient identification, reported a survey conducted
by Black
Book Research.
“Patient matching is a fundamental function of being able to get the right records, for the right person, at the right time, so that timely decisions can be made about his or her health. There has to be a mechanism to ensure that you’re actually getting a copy of the records for the right person,” Mariann Yeager (above), CEO of the Sequoia Project told Modern Healthcare. The Sequoia Project advocates for nationwide health information exchange (HIE). (Photo copyright: Value-based Care Summit.)
Why Patient-Matching is Difficult
Respondents to the Pew study reported that challenges to
correctly matching patients with their records include:
Receiving patient records that an organization
did not expect;
Urban health systems serving patients through
multiple sites;
High costs associated with matching solutions;
and
Differences in how organizations capture, use,
and link medical records.
When humans manually input patient data, Mary Elizabeth
Smith could be listed as M.E. Smith or Mary E. Smith or even Liz Smith. Such
data, when filed differently, can result in duplicate records for the same person,
or, as St. Vincent’s found out, patient mismatches that have dire consequences,
Managed Care noted.
“If there’s some kind of error in entering fields (name,
address, date of birth), either when the patient’s coming in or in a previous
entry, the matching can go awry,” Brendan Watkins,
Administrative Director of Enterprise Analytics at Stanford Children’s Health,
told Modern Healthcare.
Patient-Matching Solutions at Clinical Laboratories
Clinical laboratories also have tackled patient-mismatching
and have devised processing software solutions that ensure patients are
correctly identified and matched with the appropriate records and specimens.
Other solutions suggested by respondents to a previous 2018
Pew survey include:
Unique patient
identifier: Adoption of a patient identification number could help matching
efforts, though patients have expressed privacy concerns. The idea is to use
smartphones to validate patient data using digit codes. However, respondents
told Pew, not everyone has a smartphone.
Data
standardization: Respondents said standardization of data elements and
formatting could impact match rates. But agreement on which elements to use for
the match would be needed.
Referential
matching: Healthcare providers could follow the banking industry and use
outside sources, such as credit bureaus, to verify addresses and other data.
Respondents to the Pew survey balked at the cost.
With advancements in technology and interoperability,
medical laboratory leaders and other healthcare leaders may soon be expected to
achieve patient and record match rates of 100%. Pathology laboratories with
EMPIs and other solutions may be well prepared to meet those challenges.
Cerner and Epic are the industry’s revenue leaders, though smaller vendors remain popular with physician groups
Sales of electronic health record (EHR) systems and related hardware and services reached $31.5 billion in 2018. And those sales will increase, according to a 2019 market analysis from Kalorama Information. This is important information for clinical laboratories and anatomic pathology groups that must interface with the EHRs of their physician clients to enable electronic transmission of lab orders and test results between doctor and lab.
Kalorama’s ranking includes familiar big EHR manufacturer names—Cerner (NASDAQ:CERN) and Epic—and includes a new name, Change Healthcare, which was born out of Change Healthcare Holding’s merger with McKesson. However, smaller EHR vendors remain popular with many independent physicians.
“We estimate that 40% of the market is not in the top 15 [in total revenue rankings],” said Bruce Carlson, Kalorama’s publisher, in an exclusive interview with Dark Daily. “There’s a lot of room. There are small vendors out there—Amazing Charts, e-MDs, Greenway, NextGen, Athena Health—that show up on a lot of physician surveys.”
“The EHR is really important,” noted Bruce Carlson (above), Publisher at Kalorama. “Since there are a variety of systems—sometimes different from the LIS [laboratory information management system]—you want to make sure you know the vendors and the space.” Carlson says opportunities remain for new entrants in the 700-plus competitor space, which is expected to see continued mergers and acquisitions that will affect clinical laboratories and their client physicians. (Photo copyright: Twitter.)
Interoperability a Key Challenge, as Most Medical
Laboratories Know
Interoperability—or the lack thereof—remains one of the
industry’s biggest challenges. For pathologists, that means seamless electronic
communication between medical laboratories and provider hospitals can be
elusive and can create a backlash against EHR vendors.
Kalorama notes a joint investigation by Fortune and Kaiser Health News (KHN), titled, “Death by a Thousand Clicks: Where Electronic Health Records Went Wrong.” The report details the growing number of medical errors tied to EHRs. One instance involved a California lawyer with herpes encephalitis who allegedly suffered irreversible brain damage due to a treatment delay caused by the failure of a critical lab test order to reach the hospital laboratory. The order was typed into the EHR, but the hospital’s software did not fully interface with the clinical laboratory’s software, so the lab did not receive the order.
“Many software vendors and LIS systems were in use prior to
the real launching of EHRs—the [federal government] stimulus programs,” Carlson
told Dark Daily. “There are a lot of legacy systems that aren’t
compatible and don’t feed right into the EHR. It’s a work in progress.”
Though true interoperability isn’t on the immediate horizon, Carlson expects its arrival within the next five years as the U.S. Department of Health and Human Services ramps up pressure on vendors.
“I think it is going to be a simple matter eventually,” he
said. “There’s going to be much more pressure from the federal government on
this. They want patients to have access to their medical records. They want one
record. That’s not going to happen without interoperability.”
Other common criticisms of EHRs include:
Wasted provider time: a recent study published in JAMA Internal Medicine notes providers now spend more time in indirect patient care than interacting with patients.
Physician burnout: EHRs have been shown to increase physician stress and burnout.
Not worth the trouble: The debate continues over whether EHRs are improving the quality of care.
Negative patient outcomes: Fortune’s investigation outlines patient safety risks tied to software glitches, user errors, or other flaws.
There’s No Going Back
Regardless of the challenges—and potential dangers—it appears EHRs are here to stay. “Any vendor resistance of a spirited nature is gone. Everyone is part of the CommonWell Health Alliance now,” noted Carlson.
Clinical laboratories and pathology groups should expect
hospitals and health networks to continue moving forward with expansion of
their EHRs and LIS integrations.
“Despite the intensity of attacks on EHRs, very few health systems are going back to paper,” Carlson said in a news release. “Hospital EHR systems are largely in place, and upgrades, consulting, and vendor switches will fuel the market.”
Thus, it behooves clinical laboratory managers and
stakeholders to anticipate increased demand for interfaces to hospital-based
healthcare providers, and even off-site medical settings, such as urgent care
centers and retail health clinics.
