Mar 6, 2020 | Instruments & Equipment, Laboratory Instruments & Laboratory Equipment, Laboratory Management and Operations, Laboratory News, Laboratory Pathology, Laboratory Testing, Management & Operations
Researchers find a savings of more than one million dollars and prevention of hundreds, if not thousands, of adverse drug events could have been had with machine learning system
Support for artificial intelligence (AI) and machine learning (ML) in healthcare has been mixed among anatomic pathologists and clinical laboratory leaders. Nevertheless, there’s increasing evidence that diagnostic systems based on AI and ML can be as accurate or more accurate at detecting disease than systems without them.
Dark Daily has covered the development of artificial intelligence and machine learning systems and their ability to accurately detect disease in many e-briefings over the years. Now, a recent study conducted at Brigham and Women’s Hospital (BWH) and Massachusetts General Hospital (MGH) suggests machine learning can be more accurate than existing clinical decision support (CDS) systems at detecting prescription medication errors as well.
The researchers published their findings in the Joint Commission Journal on Quality and Patient Safety, titled, “Using a Machine Learning System to Identify and Prevent Medication Prescribing Errors: A Clinical and Cost Analysis Evaluation.”
A Retrospective Study
The study was partially retrospective in that the
researchers compiled past alerts generated by the CDS systems at BWH and MGH
between 2009-2011 and added them to alerts generated during the active part of
the study, which took place from January 1, 2012 to December 31, 2013, for a
total of five years’ worth of CDS alerts.
They then sent the same patient-encounter data that generated those CDS alerts to a machine learning platform called MedAware, an AI-enabled software system developed in Ra’anana, Israel.
MedAware was created for the “identification and prevention
of prescription errors and adverse drug effects,” notes the study, which goes
on to state, “This system identifies medication issues based on machine
learning using a set of algorithms with different complexity levels, ranging
from statistical analysis to deep learning with neural networks. Different
algorithms are used for different types of medication errors. The data elements
used by the algorithms include demographics, encounters, lab test results,
vital signs, medications, diagnosis, and procedures.”
The researchers then compared the alerts produced by
MedAware to the existing CDS alerts from that 5-year period. The results were
astonishing.
According to the study:
- “68.2% of the alerts generated were unique to
the MedAware system and not generated by the institutions’ CDS alerting system.
- “Clinical outlier alerts were the type least
likely to be generated by the institutions’ CDS—99.2% of these alerts were
unique to the MedAware system.
- “The largest overlap was with dosage alerts,
with only 10.6% unique to the MedAware system.
- “68% of the time-dependent alerts were unique to
the MedAware system.”
Perhaps even more important was the results of the cost
analysis, which found:
- “The average cost of an adverse event
potentially prevented by an alert was $60.67 (range: $5.95–$115.40).
- “The average adverse event cost per type of
alert varied from $14.58 (range: $2.99–$26.18) for dosage outliers to $19.14
(range: $1.86–$36.41) for clinical outliers and $66.47 (range: $6.47–$126.47)
for time-dependent alerts.”
The researchers concluded that, “Potential savings of $60.67 per alert was mainly derived from the prevention of ADEs [adverse drug events]. The prevention of ADEs could result in savings of $60.63 per alert, representing 99.93% of the total potential savings. Potential savings related to averted calls between pharmacists and clinicians could save an average of $0.047 per alert, representing 0.08% of the total potential savings.
“Extrapolating the results of the analysis to the 747,985
BWH and MGH patients who had at least one outpatient encounter during the
two-year study period from 2012 to 2013, the alerts that would have been fired
over five years of their clinical care by the machine learning medication
errors identification system could have resulted in potential savings of
$1,294,457.”
Savings of more than one million dollars plus the prevention
of potential patient harm or deaths caused by thousands of adverse drug events
is a strong argument for machine learning platforms in diagnostics and
prescription drug monitoring.
Researchers Say Current Clinical Decision Support Systems
are Limited
Machine learning is not the same as artificial intelligence. ML is a “discipline of AI” which aims for “enhancing accuracy,” while AI’s objective is “increasing probability of success,” explained Tech Differences.
Healthcare needs the help. Prescription medication errors cause patient harm or deaths that cost more than $20 billion annually, states a Joint Commission news release.
CDS alerting systems are widely used to improve patient
safety and quality of care. However, the BWH-MGH researchers say the current
CDS systems “have a variety of limitations.” According to the study:
- “One limitation is that current CDS systems are rule-based and can thus identify only the medication errors that have been previously identified and programmed into their alerting logic.
- “Further, most have high alerting rates with many false positives, resulting in alert fatigue.”
Alert fatigue leads to physician burnout, which is a big problem in large healthcare systems using multiple health information technology (HIT) systems that generate large amounts of alerts, such as: electronic health record (EHR) systems, hospital information systems (HIS), laboratory information systems (LIS), and others.
Commenting on the value of adding machine learning
medication alerts software to existing CDS hospital systems, the BWH-MGH
researchers wrote, “This kind of approach can complement traditional rule-based
decision support, because it is likely to find additional errors that would not
be identified by usual rule-based approaches.”
However, they concluded, “The true value of such alerts is
highly contingent on whether and how clinicians respond to such alerts and
their potential to prevent actual patient harm.”
Future research based on real-time data is needed before machine
learning systems will be ready for use in clinical settings, HealthITAnalytics
noted.
However, medical laboratory leaders and pathologists will
want to keep an eye on developments in machine learning and artificial
intelligence that help physicians reduce medication errors and adverse drug
events. Implementation of AI-ML systems in healthcare will certainly affect
clinical laboratory workflows.
—Donna Marie Pocius
Related Information:
AI and Healthcare: A Giant Opportunity
Using a Machine Learning System to Identify and Prevent Medication Prescribing Errors: A Clinical and Cost Analysis Evaluation
Machine Learning System Accurately Identifies Medication Errors
Journal Study Evaluates Success of Automated Machine Learning System to Prevent Medication Prescribing Errors
Differences Between Machine Learning and Artificial Intelligence
Machining a New Layer of Drug Safety
Harvard and Beth Israel Deaconess Researchers Use Machine Learning Software Plus Human Intelligence to Improve Accuracy and Speed of Cancer Diagnoses
XPRIZE Founder Diamandis Predicts Tech Giants Amazon, Apple, and Google Will Be Doctors of The Future
Hospitals Worldwide Are Deploying Artificial Intelligence and Predictive Analytics Systems for Early Detection of Sepsis in a Trend That Could Help Clinical Laboratories, Microbiologists
Feb 7, 2018 | Digital Pathology, Laboratory Management and Operations, Laboratory News, Laboratory Operations, Laboratory Pathology, Laboratory Testing, Management & Operations
Federal agency receives input on eight focus areas as it looks for ways to enable providers ‘to design and offer new approaches to delivering care’
Medical laboratories and anatomic pathology groups preparing for the transition from fee-for-service healthcare will want to keep a close eye on the Centers for Medicare and Medicaid Services (CMS). The federal agency’s administrator plans to set a “new direction” for CMS as it shifts to value-based reimbursement models for Medicare services that could impact clinical laboratory revenues.
In an informal Request for Information (RFI), the Center for Medicare and Medicaid Innovation (CMMI) sought feedback on a “new direction to promote patient-centered care and test market-driven reforms that empower beneficiaries as consumers, provide price transparency, increase choices and competition to drive quality, reduce costs, and improve outcomes.”
CMS to ‘Move Away’ from Engineering Healthcare ‘From Afar’
The agency requested input on eight focus areas:
1. Increased participation in Advanced Alternative Payment Models (APMs);
2. Consumer-directed care and market-based innovation models;
3. Physician specialty models;
4. Prescription drug models;
5. Medicare Advantage innovation models;
6. State-based and local innovation;
7. Mental and behavioral health models; and,
8. Program integrity.
Comments from healthcare providers, clinicians, states, payers, and stakeholders were accepted through November 20, 2017.
In a Wall Street Journal (WSJ) op-ed, CMS Administrator Seema Verma explained the agency’s process moving forward. “We will move away from the assumption that Washington can engineer a more efficient healthcare system from afar—that we should specify the processes healthcare providers are required to follow,” she wrote.
CMS Administrator Seema Verma (above) plans to lead the Center for Medicare and Medicaid Innovation “in a new direction” and may be signaling a willingness to give providers more flexibility with value-based care payment models for Medicare services. (Photo copyright: Healthcare Dive.)
The RFI states the new model design will follow six guiding principles:
1. Choice and competition in the market;
2. Provider choice and incentives;
3. Patient-centered care;
4. Benefit design and price transparency;
5. Transparent model design and evaluation; and,
6. Small scale testing.
Providers Need Freedom to Design New Approaches to Healthcare
Verma said CMS plans to review all Innovation Center models to determine “what is working and should continue, and what isn’t and shouldn’t.” She voiced concern that the complexity of some of the current models may have encouraged consolidation in the healthcare system, resulting in fewer choices for patients.
“We must shift away from a fee-for-service system that reimburses only on volume and move toward a system that holds providers accountable for outcomes and allows them to innovate,” Verma wrote in the WSJ op-ed. “Providers need the freedom to design and offer new approaches to delivering care. Our goal is to increase flexibility by providing more waivers from current requirements.”
Actual Progress of Value-based Healthcare ‘Herky-Jerky’
In its reporting on the recent CMS announcements, Healthcare DIVE suggested that the U.S. Department of Health and Human Services (HHS) “is looking to make some potentially major changes” in value-based payment models.
However, Neil Smiley, CEO of Loopback Analytics, which assists healthcare organizations with managing outcome-based care, believes the transition to value-based care may face stiffer headwinds under the new administration. He points to an August CMS proposal that canceled some mandatory bundled payment programs and scaled back others as an indication that healthcare transformation could be slowing.
“The pace at which CMS committed to rolling out value-based care is fundamentally different from the pace we’re currently seeing,” he told Health IT. “The progress toward value-based care, instead of this steady momentum they expected, is more of a herky-jerky fashion.”
Modify, Don’t Abandon Existing Payment Models, suggests HCTTF
The Health Care Transformation Task Force (HCTTF), a 42-member industry consortium, was among the stakeholders who responded to CMS’ RFI. In a 22-page letter, the task force reiterated its support for the healthcare system’s transformation to value-based payment and care delivery, while outlining areas for improvements. The group urged CMS to continue to develop new models while modifying, rather than abandoning, existing models that show promise and need time to achieve a lasting return.
“We would like CMS to continue support for promising models while balancing the current portfolio with new, innovative payment models,” Clare Wrobel, Director of Payment Reform Models at HCTTF, told Home Health Care News. “[But] it would be a mistake to discard current models that providers have already invested in and are showing real promise.”
Smiley, meanwhile, suggests clinical laboratory managers, pathologists, and other healthcare providers keep watch as healthcare transformation continues to evolve.
“The fee-for-service model, love it or hate it, is not dying. The organism has adapted,” he told Health IT. “For those that were aggressive early adopters of value-based care and really believed what they were hearing, and have gone fully after value-based care, some of them may feel a little exposed. If they go too hard too fast, they may suffer economically if they misjudge the pace at which this moves.”
—Andrea Downing Peck
Related Information:
Centers for Medicare and Medicaid Services: Innovation Center New Direction
Medicare and Medicaid Need Innovation
CMS Seeks ‘New Direction’ for Innovation Center
Comprehensive Care for Joint Replacement Payment Model
Task Force Calls on CMS to Encourage Alternative Payment Models
CMS Request for Information: Innovation Center New Direction
Task Force Urges CMS to Preserve Value Based Payment Models
Jun 23, 2017 | Laboratory Management and Operations, Laboratory News, Laboratory Operations, Laboratory Pathology, Management & Operations
Medical laboratory inpatient test volume may continue to decline as the Medicare hospital readmission reduction program expands in 2017 and state population health programs garner funding
We are now several years into the Medicare program that is designed to reduce hospital readmissions. Statistics from these years show encouraging progress in reducing the readmission rate of Medicare patients. This is a trend that has important implications for all hospital-based clinical laboratories.
Hospitals are the most expensive site of care in the entire healthcare system. In its ongoing battle to reduce healthcare costs, the Centers for Medicare and Medicaid Services (CMS) implemented a carrot-and-stick program called the Hospital Readmission Reduction Program (HRRP) aimed at lowering hospital readmission rates nationwide.
Established in 2013 by the Affordable Care Act (also known as Obamacare), the HRRP lowers reimbursements to acute care hospitals that have high rates of Medicare readmissions within 30 days of initial discharge, and increases reimbursements to hospitals that lower their readmission rates, a March 2017 Kaiser Family Foundation (KFF) Issue Brief explained.
And, according to the KFF, these programs are having an impact. Readmission rates dropped by 8% nationwide as hospitals found ways to avoid the stiff financial penalties and earn the financial rewards. Additionally, patients are increasingly choosing ambulatory care settings, or to receive care at home, rather than re-entering hospitals. This has lowered states’ readmission rates even further.
From a healthcare cost perspective, this is good news. However, these programs have had unintentional consequences as well. The federal initiatives and state population health programs responsible for lowering readmission rates also directly impact medical laboratories by simultaneously reducing the flow of inpatient testing volume.
At the same time, clinicians at the nation’s hospitals—in their efforts to avoid readmissions—have a motive to become more effective at ordering the right medical laboratory test at the right time, and to use the lab test results to more effectively treat the patient. Thus, for the nation’s hospital labs, the Medicare program to reduce readmissions has both an upside and a downside.
Programs, Data Mining That Help Providers Avoid Readmissions
Hospitals nationwide are operating programs aimed at attracting federal financial rewards for keeping people healthy, and from being admitted to hospitals due to conditions that could have been prevented, USA Today reported.
One such program involves Christiana Care Health System (Christiana Care) of Wilmington, DE. Christiana Care implemented CMS’ Care Link transitions program through the Center for Medicare and Medicaid Innovation (CMMI), also known as The Innovation Center, which, “supports the development and testing of innovative healthcare payment and service delivery models.”
The provider experienced a 20% drop in patients being readmitted within 30 days of surgery, due to its “bundled payment” plan for heart failure, the USA Today article noted. Hip and knee replacement readmissions were down 25% 30 days after discharge as well.
“Without the funding we got through CMMI, it’s hard to imagine we’d be in the position we’re in today,” stated Janice Nevin, MD, CEO of Christiana Care.
Janice Nevin, MD (above), CEO of Christiana Care Health System, Wilmington, DE, is concerned that the upcoming changes to the ACA will affect the funding the healthcare provider has received from the CMS Innovation Center. “I would strongly urge that we keep the commitment to CMMI (because) you have to innovate to learn,” she told USA Today. (Photo copyright: Christiana Care Health System.)
Changes to HRRP for Dual-Eligibles Could Affect Penalties
Some patients are more expensive than others. Patients who draw both Medicare and Medicaid funding simultaneously, for example. These “dual-eligibles” are disproportionately expensive for hospitals to treat, reported Modern Healthcare.
In fact, they are just 18% of CMS beneficiaries, but accounted for one-third of all Medicare fee-for-service (FFS) spending in 2013, according to a Medicare Payment Advisory Commission June 2016 demographic report.
CMS is proposing to adjust penalties in the HRRP to reflect the proportion of patients who are dual-eligible, presumably hoping the change will both lower costs and reduce penalties on healthcare providers.
Hospital Readmissions Data from 49 States
CMS data show that between 2010 and 2015 hospital readmission rates fell by 8%, reported Healthcare Finance News. Other key data recently released by CMS and reported by Healthcare Finance News:
· 49 states reduced avoidable hospital readmission rates since 2010;
· Vermont’s readmission rate rose slightly from 15.3% in 2010 to 15.4% in 2015;
· In 43 states, readmission rates fell by more than 5%;
· 11 states had a more than 10% drop in readmission rates;
· The fall in readmission rate translates to about 104,000 hospital readmissions avoided for Medicare beneficiaries in 2015 and 565,000 readmissions averted since 2010; and
· Avoidable admissions, occurring within 30 days of initial discharges, account for more than $17 billion in Medicare annual expenditures.
Action Steps for Clinical Laboratories
Pathologists and lab leaders need to efficiently work with colleagues, especially when caring for hospitalized patients with conditions relative to the HRRP. Clear and patient-friendly discharge instructions for diagnostics are important. And, the lab’s coordination with post-acute-care providers, such as skilled nursing facilities, on follow-up testing is key to avoiding unnecessary readmissions.
Regardless, medical laboratory inpatient test volume will likely continue to decline. As Dark Daily readers know, the decline in inpatient testing is associated with more than just the HRRP. The transition to new models of integrated care that has taken place over the last few years is also a factor, as Dark Daily reported in “Falling Inpatient Revenues at Many Hospitals is Sign of Healthcare’s Transition to New Models of Integrated Care and Changes in Medical Laboratory Test Utilization.”
Medical laboratory directors and sales teams are advised to continue their efforts at boosting outpatient volume to fill the inpatient void.
—Donna Marie Pocius
Related Information:
Hospitals Work to Keep Patients from Being Admitted
Aiming for Fewer Hospital U-Turns: The Medicare Hospital Readmission Reduction Program
49 States, DC Reduce Avoidable Hospital Readmissions
Dual-eligibles: The Next Target in Hospital Readmissions Penalties
June 2016 Data Book, Section 2: Medicare Beneficiary Demographics
Hospitals Mine Clinical Data to Help Reduce Costs and Avoid Readmissions, Creating Opportunities for Clinical Laboratories and Pathologists to Contribute to Improved Patient Outcomes
Falling Inpatient Revenues at Many Hospitals is Sign of Healthcare’s Transition to New Models of Integrated Care and Changes in Medical Laboratory Test Utilization
Jul 10, 2015 | Instruments & Equipment, Laboratory Instruments & Laboratory Equipment, Laboratory Management and Operations, Laboratory Pathology, Laboratory Testing
This innovative technology platform is newest effort to measure biomarkers without the need for the invasive specimen collection techniques used in medical laboratory testing
Pathologists and clinical laboratory managers interested in how new technologies are transforming certain well-established clinical practices will be interested to learn about the latest research breakthroughs in pulse oximetry, a common procedure used to measure the oxygen level (or oxygen saturation) in the blood.
Pulse oximetry is considered to be a noninvasive, painless, general indicator of oxygen delivery to the peripheral tissues (such as the finger, earlobe, or nose). For decades, PO has been ubiquitous in the hospital. Now, because of recent advance, this field is poised for a paradigm shift away from simple monitoring devices to advanced products capable of connecting patients to electronic systems that continuously gather data and notify caregivers when values become critical.
A group of bioengineering doctoral students at the University of California Berkeley (UC Berkeley) have invented an inexpensive Band-Aid-style oximeter that uses red and green light to non-invasively monitor pulse rate and oxygen level in blood. While this device could revolutionize pulse oximetry monitoring in healthcare settings, the technology might also be applied to measuring other useful biomarkers as one approach to eliminate invasive specimen collection. (more…)
Jul 11, 2014 | Compliance, Legal, and Malpractice, Digital Pathology, Instruments & Equipment, Laboratory Management and Operations, Laboratory News, Laboratory Operations, Laboratory Pathology
The majority of the nation’s hospitals and physicians now use electronic health records and most of these EHR users are already exchanging clinical data with regional HIEs
Pathologists tracking the adoption of EHR systems by hospitals and physicians will be interested to learn that, according to the federal government, more than 80% of hospitals and 50% of physicians now use these products. It is also reported that growing numbers of providers are exchanging data with health information exchanges.
Clinical laboratories and anatomic pathology groups have a big stake in these developments. Medical laboratory test data is an essential component to every patient’s permanent health record, which is why it is important for every lab to have interfaces with the HIEs serving their communities and regions.
(more…)
