As the worldwide demand for histopathology services increases faster than the increase in the number of anatomic pathologist and histopathologists, a DP platform that suggests courses of treatments may be a boon to cancer diagnostics
Europe may become Ground Zero for the widespread adoption of whole-slide imaging (WSI), digital pathology (DP) workflow, and the use of image-analysis algorithms to make primary diagnoses of cancer. Several forward-looking histopathology laboratories in different European countries are moving swiftly to adopt these innovative technologies.
Clinical laboratories and anatomic pathology groups worldwide have watched digital pathology tools evolve into powerful diagnostic aids. And though not yet employed for primary diagnoses, thanks to artificial intelligence (AI) and machine learning many DP platforms are moving closer to daily clinical use and new collaborations with pathologists who utilize the technology to confirm cancer and other chronic diseases.
Now, Swiss company Unilabs, one of the largest laboratory, imaging, and pathology diagnostic developers in Europe, and Israel-based Ibex Medical Analytics, developer of AI-based digital pathology and cancer diagnostics, have teamed together to deploy “Ibex’s multi-tissue AI-powered Galen platform” across 16 European nations, according to a Unilabs press release.
Though not cleared by the federal Food and Drug Administration (FDA) for clinical use in the US, the FDA recently granted Breakthrough Device Designation to Ibex’s Galen platform. This designation is part of the FDA’s Breakthrough Device Program which was created to help expedite the development, assessment, and review of certain medical devices and products that promise to provide for more effective treatment or diagnosis of life-threatening or irreversibly debilitating diseases or conditions.
Benefits of AI-Digital Pathology to Pathologists, Clinical Labs, and Patients
According to Ibex’s website, the Galen DP platform uses AI algorithms to analyze images from breast and prostate tissue biopsies and provide insights that help pathologists and physicians determine the best treatment options for cancer patients.
This will, Ibex says, give pathologists “More time to dedicate to complex cases and research,” and will make reading biopsies “Less tedious, tiring, and stressful.”
Patients, according to Ibex, benefit from “Increased diagnostic accuracy” and “More objective results.”
And pathology laboratories benefit from “Increased efficiency, decreased turnaround time, and improved quality of service,” Ibex claims.
According to the press release, AI-generated insights can include “case prioritization worklists, cancer heatmaps, tumor grading and measurements, streamlined reporting tools and more.”
This more collaborative approach between pathologists and AI is a somewhat different use of digital pathology, which primarily has been used to confirm pathologists’ diagnoses, rather than helping to identify cancer and suggest courses of treatment to pathologists.
AI-based First and Second Reads
The utilization of the Galen platform will first be rolled out nationally in Sweden and then deployed in sixteen other countries. The AI-based DP platform is CE marked in the European Union for breast and prostate cancer detection in multiple workflows.
“The partnership with Ibex underlines Unilabs’ pioneering role in Digital Pathology and represents yet another step in our ambition to become the most digitally-enabled provider of diagnostic services in Europe,” Rebhan stated.
The Ibex website explains that the Galen platform is divided into two parts—First Read and Second Read:
The First Read “is an AI-based diagnostics application that aims to help pathologists significantly reduce turnaround time and improve diagnostic accuracy. The application uses a highly accurate AI algorithm to analyze slides prior to the pathologist and provides decision support tools that enable focusing on cancerous slides and areas of interest, streamline reporting, improve lab efficiency, and increase diagnostic confidence.”
The Second Read “is an AI-based diagnostics and quality control application that helps pathologists enhance diagnostic accuracy with no impact on routine workflow. The application analyzes slides in parallel with the pathologist and alerts in case of discrepancies with high clinical significance (e.g., a missed cancer), thereby providing a safety net that reduces error rates and enables a more efficient workflow.”
“Ibex is transforming cancer diagnosis with innovative AI solutions across the diagnostic pathway,” said Joseph Mossel, Chief Executive Officer and co-founder of Ibex, in the press release. “We are excited to partner with Unilabs to deploy our AI solutions and empower their pathologists with faster turnaround times and quality diagnosis. This cooperation follows a thorough evaluation of our technology at Unilabs and demonstrates the robustness and utility of our platform for everyday clinical practice.”
Use of AI in Pathology Increases as Number of Actual Pathologists Declines
Developers like Unilabs and Ibex believe that DP platforms driven by AI image analysis algorithms can help pathologists be more productive and can shorten the time it takes for physicians to make diagnoses and issue reports to patients.
This may be coming at a critical time. As nations around the globe face increasing shortages of pathologists and histopathologists, the use of AI in digital pathology could become more critical for disease diagnosis and treatment.
A 2019 Medscape survey stated that “One-third of active pathologists are burned out,” and that many pathologists are on the road to retirement.
And in the same year, Fierce Healthcare noted that in a 2013 study, “researchers found that more than 40% of pathologists were 55 or older. They predicted that retirements would reach their apex in 2021. Consequently, by the end of next decade, the United States will be short more than 5,700 pathologists.”
Dark Daily previously reported on the growing global shortage of pathologists going back to 2011.
Even China is struggling to keep up with demand for anatomic pathologists. In 2017, Dark Daily wrote, “China is currently facing a severe shortage of anatomic pathologists, which blocks patients’ access to quality care. The relatively small number of pathologists are often overworked, even as more patients want access to specialty care for illnesses. Some hospitals in China do not even have pathologists on staff. Thus, they rely on understaffed anatomic pathology departments at other facilities, or they use imaging only for diagnoses.”
Thus, it may be time for an AI-driven digital platform to arrive that can speed up and increase the accuracy of the cancer diagnostics process for pathologists, clinical laboratories, and patients alike.
There are multiple companies rapidly developing AI, machine learning, and image analysis products for diagnosing diseases. Pathologists should expect progress in this field to be ongoing and new capabilities regularly introduced into the market.
Hello primary diagnosis of digital pathology images via artificial intelligence! Goodbye light microscopes!
Digital pathology is poised to take a great leap forward. Within as few as 12 months, image analysis algorithms may gain regulatory clearance in the United States for use in primary diagnosis of whole-slide images (WSIs) for certain types of cancer. Such a development will be a true revolution in surgical pathology and would signal the beginning of the end of the light microscope era.
A harbinger of this new age of digital pathology and automated image analysis is a press release issued last week by Ibex Medical Analytics of Tel Aviv, Israel. The company announced that its Galen artificial intelligence (AI)-powered platform for use in the primary diagnosis of specific cancers will undergo an accelerated review by the Food and Drug Administration (FDA).
FDA’s ‘Breakthrough Device Designation’ for Pathology AI Platform
Ibex stated that “The FDA’s Breakthrough Device Designation is granted to technologies that have the potential to provide more effective treatment or diagnosis of life-threatening diseases, such as cancer. The designation enables close collaboration with, and expedited review by, the FDA, and provides formal acknowledgement of the Galen platform’s utility and potential benefit as well as the robustness of Ibex’s clinical program.”
“All surgical pathologists should recognize that, once the FDA begins to review and clear algorithms capable of using digital pathology images to make an accurate primary diagnosis of cancer, their daily work routines will be forever changed,” stated Robert L. Michel, Editor-in-Chief of Dark Daily and its sister publication The Dark Report. “Essentially, as FDA clearance is for use in clinical care, pathology image analysis algorithms powered by AI will put anatomic pathology on the road to total automation.
“Clinical laboratories have seen the same dynamic, with CBCs (complete blood counts) being a prime example. Through the 1970s, clinical laboratories employed substantial numbers of hematechnologists [hematechs],” he continued. “Hematechs used a light microscope to look at a smear of whole blood that was on a glass slide with a grid. The hematechs would manually count and record the number of red and white blood cells.
“That changed when in vitro diagnostics (IVD) manufacturers used the Coulter Principle and the Coulter Counter to automate counting the red and white blood cells in a sample, along with automatically calculating the differentials,” Michel explained. “Today, only clinical lab old-timers remember hematechs. Yet, the automation of CBCs eventually created more employment for medical technologists (MTs). That’s because the automated instruments needed to be operated by someone trained to understand the science and medicine involved in performing the assay.”
Primary Diagnosis of Cancer with an AI-Powered Algorithm
Surgical pathology is poised to go down a similar path. Use of a light microscope to conduct a manual review of glass slides will be supplanted by use of digital pathology images and the coming next generation of image analysis algorithms. Whether these algorithms are called machine learning, computational pathology, or artificial intelligence, the outcome is the same—eventually these algorithms will make an accurate primary diagnosis from a digital image, with comparable quality to a trained anatomic pathologist.
How much of a threat is automated analysis of digital pathology images? Computer scientist/engineer Ajit Singh, PhD, a partner at Artiman Ventures and an authority on digital pathology, believes that artificial intelligence is at the stage where it can be used for primary diagnosis for two types of common cancer: One is prostate cancer, and the other is dermatology.
“It is now possible to do a secondary read, and even a first read, in prostate cancer with an AI system alone. In cases where there may be uncertainty, a pathologist can review the images. Now, this is specifically for prostate cancer, and I think this is a tremendous positive development for diagnostic pathways,” he added.
Use of Digital Pathology with AI-Algorithms Changes Diagnostics
Pathologists who are wedded to their light microscopes will want to pay attention to the impending arrival of a fully digital pathology system, where glass slides are converted to whole-slide images and then digitized. From that point, the surgical pathologist becomes the coach and quarterback of an individual patient’s case. The pathologist guides the AI-powered image analysis algorithms. Based on the results, the pathologist then orders supplementary tests appropriate to developing a robust diagnosis and guiding therapeutic decisions for that patient’s cancer.
In his interview with The Dark Report, Singh explained that the first effective AI-powered algorithms in digital pathology will be developed for prostate cancer and skin cancer. Both types of cancer are much less complex than, say, breast cancer. Moreover, the AI developers have decades of prostate cancer and melanoma cases where the biopsies, diagnoses, and downstream patient outcomes create a rich data base from which the algorithms can be trained and tuned.
This webinar is organized as a roundtable discussion so participants can interact with the expert panelists. The Chair and Moderator is Ajit Singh, PhD, Adjunct Professor at the Stanford School of Medicine and Partner at Artiman Ventures.
The panelists (above) represent academic pathology, community hospital pathology, and the commercial sector. They are:
Because the arrival of automated analysis of digital pathology images will transform the daily routine of every surgical pathologist, it would be beneficial for all pathology groups to have one or more of their pathologists register and participate in this critical webinar.
The roundtable discussion will help them understand how quickly AI-powered image analysis is expected be cleared for use by the FDA in such diseases as prostate cancer and melanomas. Both types of cancers generate high volumes of case referrals to the nation’s pathologists, so potential for disruption to long-standing client relationships, and the possible loss of revenue for pathology groups that delay their adoption of digital pathology, can be significant.
On the flip side, community pathology groups that jump on the digital pathology bandwagon early and with the right preparation will be positioned to build stronger client relationships, increase subspecialty case referrals, and generate additional streams of revenue that boost partner compensation within their group.
Also, because so many pathologists are working remotely, Dark Daily has arranged special group rates for pathology practices that would like their surgical pathologists to participate in this important webinar and roundtable discussion on AI-powered primary diagnosis of pathology images. Inquire at info@darkreport.com or call 512-264-7103.
Physicians and clinical laboratories that do business with other healthcare providers who have been denied enrollment in Medicare or had their enrollment revoked are under increased scrutiny
Efforts by the Centers for Medicare and Medicaid Services
(CMS) to crack down on fraud could soon be bolstered by artificial
intelligence (AI) tools, placing new pressure on medical
laboratories and anatomic pathology groups to ensure that their billing
practices are fully compliant with current federal “affiliations” regulations.
This is why, last October, CMS issued a Request
for Information (RFI) seeking feedback from vendors, providers, and
suppliers about the potential use of AI tools to identify cases of fraud,
waste, and abuse in billing for healthcare services. Statements from CMS
indicate that the agency plans to deepen its investigation into the affiliations
physicians and clinical laboratories have with healthcare providers that been
involved in fraudulent behavior within the Medicare program.
At present, CMS uses a variety of approaches to spot
improper claims, the RFI notes, including the use of human medical reviewers.
However, this is a costly process that allows review of less than 1% of claims.
AI tools would increase the speed and accuracy of those investigations
exponentially.
The RFI notes that AI technology could “help CMS identify
potentially problematic affiliations upon initial screening and through continuous
monitoring. One example would be a new tool or technology that would allow
easy, seamless access to state and local business ownership and registration
information that could improve CMS’ line-of-sight to potentially problematic
business relationships.”
CMS’ New Affiliations Rule Affects Clinical Laboratories
Our sister publication, The Dark Report (TDR),
provided in-depth coverage of this rule, which allows CMS “to revoke or deny
enrollment if it finds that a provider’s or supplier’s current or previous
affiliations pose an undue risk of fraud.” (See TDR, “Labs
Must Respond to New CMS Anti-Fraud Rule,” October 14, 2019.)
“For too many years, we have played an expensive and
inefficient game of ‘whack-a-mole’ with criminals—going after them one at a
time—as they steal from our programs,” CMS Administrator Seema Verma
said in a
statement about the new rule. “These fraudsters temporarily disappear into
complex, hard-to-track webs of criminal entities, and then re-emerge under
different corporate names. These criminals engage in the same behaviors again
and again.”
As TDR reported, the rule defines four “disclosable
events” that trigger the disclosure requirements:
Uncollected debt to Medicare, Medicaid, or CHIP;
Payment suspension under a federal healthcare program;
Exclusion by the Office of Inspector General from participation in Medicare, Medicaid, or CHIP; and
Termination, revocation, or denial of Medicare, Medicaid, or CHIP enrollment.
If disclosure is required, CMS described five definitions of
an affiliation, using a five-year look-back:
Direct or indirect ownership of 5% or more in another organization;
A general or limited partnership interest, regardless of the percentage;
An interest in which an individual or entity “exercises operational or managerial control over, or directly conducts” the daily operations of another organization, “either under direct contract or through some other arrangement;”
When an individual is acting as an officer or director of a corporation; and
Any reassignment relationship.
One interesting consequence of these definitions is that
individuals or companies that invest and own an interest in a provider
organization that has one or more “disclosable events” would be flagged by the
provider at time of enrollment or re-enrollment in the Medicare program. Over
the years, some very prominent private equity companies have been investors and
owners of medical laboratory companies that owed money to Medicare or entered
into civil settlements with the federal government where the full amount of the
alleged overpayments was not recovered and the provider neither admitted nor
denied guilt. These affiliations would need to be disclosed and could be used
by CMS to deny enrollment in the Medicare program.
“Lab companies that engage in fraud and abuse—often paying illegal inducements to physicians to encourage them to order medically-unnecessary tests—distort the lab testing marketplace and capture lab test referrals that would otherwise go to compliant clinical labs and pathology groups,” stated Robert Michel, Editor-In-Chief of The Dark Report. “So, honest labs will recognize how the new rule can help suppress various types of fraud that constantly plague the clinical lab industry.” (See TDR, “Is New Medicare Affiliation Rule Good, Bad, or Ugly?” November 4, 2019.)
Other AI Applications in Healthcare
The CMS RFI also suggests other areas in which artificial
intelligence could help identify fraudulent activity, including real-time monitoring
of electronic
health records (EHR), risk
adjustment data validation (RADV) audits, and value-based payment systems.
“These tools hold the promise of more expeditious, seamless
and accurate review of chart documentation during medical review to ensure that
we are paying for what we get and getting what we pay for,” the RFI states.
“However, concerns about potential improper payments and bad actors remain. We
need to determine whether innovative new strategies, tools, and technologies
presently exist that can increase data accuracy and integrity and consequently
reduce improper payments.”
Clinical laboratories should not be surprised by any of this.
Artificial intelligence and machine learning are increasingly becoming vital
tools in today’s modern healthcare system. Nevertheless, lab leaders should
closely monitor CMS’ use of these technologies to root out fraud, as labs are
often caught up in their investigations.
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.
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.
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 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.”
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.