News, Analysis, Trends, Management Innovations for
Clinical Laboratories and Pathology Groups

Hosted by Robert Michel

News, Analysis, Trends, Management Innovations for
Clinical Laboratories and Pathology Groups

Hosted by Robert Michel
Sign In

Harvard and Beth Israel Deaconess Researchers Use Machine Learning Software Plus Human Intelligence to Improve Accuracy and Speed of Cancer Diagnoses

Machine learning software may help pathologists make earlier and more accurate diagnoses

In Boston, two major academic centers are teaming up to apply big data and machine learning to the problem of diagnosing cancers earlier and with more accuracy. It is research that might have major implications for the anatomic pathology profession.

A collaborative effort between teams at Beth Israel Deaconess Medical Center (BIDMC) and Harvard Medical School (HMS) has resulted in an innovation that could result in more accurate diagnoses in the pathology laboratory. The teams have been working on a machine learning software program that will eventually function as an artificial intelligence (AI) to improve the accuracy of diagnostics. They hope to someday build AI-powered computer systems that can accurately and quickly interpret pathology images. (more…)

What is Swarm Learning and Might It Come to a Clinical Laboratory Near You?

International research team that developed swarm learning believe it could ‘significantly promote and accelerate collaboration and information exchange in research, especially in the field of medicine’

Swarm Learning” is a technology that enables cross-site analysis of population health data while maintaining patient privacy protocols to generate improvements in precision medicine. That’s the goal described by an international team of scientists who used this approach to develop artificial intelligence (AI) algorithms that seek out and identify lung disease, blood cancer, and COVID-19 data stored in disparate databases.

Since 80% of patient records feature clinical laboratory test results, there’s no doubt this protected health information (PHI) would be curated by the swarm learning algorithms. 

Researchers with DZNE (German Center for Neurodegenerative Diseases), the University of Bonn, and Hewlett Packard Enterprise (HPE) who developed the swarm learning algorithms published their findings in the journal Nature, titled, “Swarm Learning for Decentralized and Confidential Clinical Machine Learning.”

In their study they wrote, “Fast and reliable detection of patients with severe and heterogeneous illnesses is a major goal of precision medicine. … However, there is an increasing divide between what is technically possible and what is allowed, because of privacy legislation. Here, to facilitate the integration of any medical data from any data owner worldwide without violating privacy laws, we introduce Swarm Learning—a decentralized machine-learning approach that unites edge computing, blockchain-based peer-to-peer networking, and coordination while maintaining confidentiality without the need for a central coordinator, thereby going beyond federated learning.”

What is Swarm Learning?

Swarm Learning is a way to collaborate and share medical research toward a goal of advancing precision medicine, the researchers stated.

The technology blends AI with blockchain-based peer-to-peer networking to create information exchange across a network, the DZNE news release explained. The machine learning algorithms are “trained” to detect data patterns “and recognize the learned patterns in other data as well,” the news release noted. 

Joachim Schultze, MD

“Medical research data are a treasure. They can play a decisive role in developing personalized therapies that are tailored to each individual more precisely than conventional treatments,” said Joachim Schultze, MD (above), Director, Systems Medicine at DZNE and Professor, Life and Medical Sciences Institute at the University of Bonn, in the news release. “It’s critical for science to be able to use such data as comprehensively and from as many sources as possible,” he added. This, of course, would include clinical laboratory test results data. (Photo copyright: University of Bonn.)
 

Since, as Dark Daily has reported many times, clinical laboratory test data comprises as much as 80% of patients’ medical records, such a treasure trove of information will most likely include medical laboratory test data as well as reports on patient diagnoses, demographics, and medical history. Swarm learning incorporating laboratory test results may inform medical researchers in their population health analyses.

“The key is that all participants can learn from each other without the need of sharing confidential information,” said Eng Lim Goh, PhD, Senior Vice President and Chief Technology Officer for AI at Hewlett Packard Enterprise (HPE), which developed base technology for swarm learning, according to the news release.

An HPE blog post notes that “Using swarm learning, the hospital can combine its data with that of hospitals serving different demographics in other regions and then use a private blockchain to learn from a global average, or parameter, of results—without sharing actual patient information.

“Under this model,” the blog continues, “‘each hospital is able to predict, with accuracy and with reduced bias, as though [it has] collected all the patient data globally in one place and learned from it,’ Goh says.”

Swarm Learning Applied in Study

The researchers studied four infectious and non-infectious diseases:

They used 16,400 transcriptomes from 127 clinical studies and assessed 95,000 X-ray images.

  • Data for transcriptomes were distributed over three to 32 blockchain nodes and across three nodes for X-rays.
  • The researchers “fed their algorithms with subsets of the respective data set” (such as those coming from people with disease versus healthy individuals), the news release noted.

Findings included:

  • 90% algorithm accuracy in reporting on healthy people versus those diagnosed with diseases for transcriptomes.
  • 76% to 86% algorithm accuracy in reporting of X-ray data.
  • Methodology worked best for leukemia.
  • Accuracy also was “very high” for tuberculosis and COVID-19.
  • X-ray data accuracy rate was lower, researchers said, due to less available data or image quality.

“Our study thus proves that swarm learning can be successfully applied to very different data. In principle, this applies to any type of information for which pattern recognition by means of artificial intelligence is useful. Be it genome data, X-ray images, data from brain imaging, or other complex data,” Schultze said in the DZNE news release.

The researchers plan to conduct additional studies aimed at exploring swarm learning’s implications to Alzheimer’s disease and other neurodegenerative diseases.

Is Swarm Learning Coming to Your Lab?

The scientists say hospitals as well as research institutions may join or form swarms. So, hospital-based medical laboratory leaders and pathology groups may have an opportunity to contribute to swarm learning. According to Schultze, sharing information can go a long way toward “making the wealth of experience in medicine more accessible worldwide.”

Donna Marie Pocius

Related Information:

AI With Swarm Intelligence: A Novel Technology for Cooperative Analysis of Big Data

Swarm Learning for Decentralized and Confidential Clinical Machine Learning

Swarm Learning

HPE’s Dr. Goh on Harnessing the Power of Swarm Learning

Swarm Learning: This Artificial Intelligence Can Detect COVID-19, Other Diseases

Researchers in Five Countries Use AI, Deep Learning to Analyze and Monitor the Quality of Donated Red Blood Cells Stored for Transfusions

By training a computer to analyze blood samples, and then automating the expert assessment process, the AI processed months’ worth of blood samples in a single day

New technologies and techniques for acquiring and transporting biological samples for clinical laboratory testing receive much attention. But what of the quality of the samples themselves? Blood products are expensive, as hospital medical laboratories that manage blood banks know all too well. Thus, any improvement to how labs store blood products and confidently determine their viability for transfusion is useful.

One such improvement is coming out of Canada. Researchers at the University of Alberta  (U of A) in collaboration with scientists and academic institutions in five countries are looking into ways artificial intelligence (AI) and deep learning can be used to efficiently and quickly analyze red blood cells (RBCs). The results of the study may alter the way donated blood is evaluated and selected for transfusion to patients, according to an article in Folio, a U of A publication, titled, “AI Could Lead to Faster, Better Analysis of Donated Blood, Study Shows.” 

The study, which uses AI and imaging flow cytometry (IFC) to scrutinize the shape of RBCs, assess the quality of the stored blood, and remove human subjectivity from the process, was published in Proceedings of the National Academy of Sciences (PNAS,) titled, “Objective Assessment of Stored Blood Quality by Deep Learning.”

Improving Blood Diagnostics through Precision Medicine and Deep Learning

“This project is an excellent example of how we are using our world-class expertise in precision health to contribute to the interdisciplinary work required to make fundamental changes in blood diagnostics,” said Jason Acker, PhD, a senior scientist at Canadian Blood Services’ Centre for Innovation, Professor of Laboratory Medicine and Pathology at the University of Alberta, and one of the lead authors of the study, in the Folio article.

The research took more than three years to complete and involved 19 experts from 12 academic institutions and blood collection facilities located in Canada, Germany, Switzerland, the United Kingdom, and the US.

Jason Acker, PhD (above), Senior Research Scientist, Canadian Blood Services, and Professor of Laboratory Medicine and Pathology at the University of Alberta in a white lab jacket in a laboratory
“Our study shows that artificial intelligence gives us better information about the red blood cell morphology, which is the study of how these cells are shaped, much faster than human experts,” said Jason Acker, PhD (above), Senior Research Scientist, Canadian Blood Services, and Professor of Laboratory Medicine and Pathology at the University of Alberta, in an article published on the Canadian Blood Services website. “We anticipate this technology will improve diagnostics for clinicians as well as quality assurance for blood operators such as Canadian Blood Services in the coming years,” he added. Clinical laboratories in the US may also benefit from this new blood viability process. (Photo copyright: University of Alberta.)

To perform the study, the scientists first collected and manually categorized 52,000 red blood cell images. Those images were then used to train an algorithm that mimics the way a human mind works. The computer system was next tasked with analyzing the shape of RBCs for quality purposes. 

Removing Human Bias from RBC Classification

“I was happy to collaborate with a group of people with diverse backgrounds and expertise,” said Tracey Turner, a senior research assistant in Acker’s laboratory and one of the authors of the study, in a Canadian Blood Services (CBS) article. “Annotating and reviewing over 52,000 images took a long time, however, it allowed me to see firsthand how much bias there is in manual classification of cell shape by humans and the benefit machine classification could bring.”

According to the CBS article, a red blood cell lasts about 115 days in the human body and the shape of the RBC reveals its age. Newer, healthier RBCs are shaped like discs with smooth edges. As they age, those edges become jagged and the cell eventually transforms into a sphere and loses the ability to perform its duty of transporting oxygen throughout the body. 

Blood donations are processed, packed, and stored for later use. Once outside the body, the RBCs begin to change their shape and deteriorate. RBCs can only be stored for a maximum of 42 days before they lose the ability to function properly when transfused into a patient. 

Scientists routinely examine the shape of RBCs to assess the quality of the cell units for transfusion to patients and, in some cases, diagnose and assess individuals with certain disorders and diseases. Typically, microscope examinations of red blood cells are performed by experts in medical laboratories to determine the quality of the stored blood. The RBCs are classified by shape and then assigned a morphology index score. This can be a complex, time-consuming, and laborious process.

“One of the amazing things about machine learning is that it allows us to see relationships we wouldn’t otherwise be able to see,” Acker said. “We categorize the cells into the buckets we’ve identified, but when we categorize, we take away information.”

Human analysis, apparently, is subjective and different professionals can arrive at different results after examining the same blood samples. 

“Machines are naive of bias, and AI reveals some characteristics we wouldn’t have identified and is able to place red blood cells on a more nuanced spectrum of change in shape,” Acker explained.

The researchers discovered that the AI could accurately analyze and categorize the quality of the red blood cells. This ability to perform RBC morphology assessment could have critical implications for transfusion medicine.

“The computer actually did a better job than we could, and it was able to pick up subtle differences in a way that we can’t as humans,” Acker said.

“It’s not surprising that the red cells don’t just go from one shape to another. This computer showed that there’s actually a gradual progression of shape in samples from blood products, and it’s able to better classify these changes,” he added. “It radically changes the speed at which we can make these assessments of blood product quality.”

More Precision Matching Blood Donors to Recipients

According to the World Health Organization (WHO), approximately 118.5 million blood donations are collected globally each year. There is a considerable contrast in the level of access to blood products between high- and low-income nations, which makes accurate assessment of stored blood even more critical. About 40% of all blood donations are collected in high-income countries that home to only about 16% of the world’s population.

More studies and clinical trials will be necessary to determine if U of A’s approach to using AI to assess the quality of RBCs can safely transfer to clinical use. But these early results promise much in future precision medicine treatments.

“What this research is leading us to is the fact that we have the ability to be much more precise in how we match blood donors and recipients based on specific characteristics of blood cells,” Acker stated. “Through this study we have developed machine learning tools that are going to help inform how this change in clinical practice evolves.”

The AI tools being developed at the U of A could ultimately benefit patients as well as blood collection centers, and at hospitals where clinical laboratories typically manage the blood banking services, by making the process of matching transfusion recipients to donors more precise and ultimately safer.

—JP Schlingman

Related Information:

Objective Assessment of Stored Blood Quality by Deep Learning

Machines Rival Expert Analysis of Stored Red Blood Cell Quality

Breakthrough Study Uses AI to Analyze Red Blood Cells

Machine Learning Opens New Frontiers in Red Blood Cell Research

AI Could Lead to Faster, Better Analysis of Donated Blood, Study Shows

Blood Safety and Availability

FDA Grants Marketing Authorization to First Ever AI-Powered SaMD Diagnostic Tool for Sepsis That Shares Patient’s Risk within 24 Hours and Works with EHRs

Infection control teams and clinical laboratory managers may want to look at this new product designed to improve the diagnosis and treatment of sepsis

Accurate and fast diagnosis of sepsis for patients arriving in emergency departments is the goal of a new product that was just cleared by the federal Food and Drug Administration (FDA). It is also the newest example of how artificial intelligence (AI) continues to find its way into pathology and clinical laboratory medicine.

Sepsis is one of the deadliest killers in US hospitals. That is why there is interest in the recent action by the FDA to grant marketing authorization for an AI-powered sepsis detection software through the agency’s De Novo Classification Request. The DNCR “provides a marketing pathway to classify novel medical devices for which general controls alone, or general and special controls, provide reasonable assurance of safety and effectiveness for the intended use, but for which there is no legally marketed predicate device,” the FDA’s website states.

Developed by Chicago-based Prenosis, the Sepsis ImmunoScore is an AI and machine learning (ML) Software as a Medical Device (SaMD) used to “guide rapid diagnosis and prediction of sepsis” within 24 hours of the patient’s presentation in an emergency department or hospital, according to a company news release.

In a separate statement, Prenosis announced a commercial distribution deal with Roche, Basel, Switzerland, as well as the SaMD’s availability on Roche’s navify Algorithm Suite (a digital library of medical algorithms).

Unlike a single analyte assay that is run in a clinical laboratory, Prenosis’ AI/ML software uses 22 diagnostic and predictive parameters, along with ML algorithms, to analyze data and produce a clinically actionable answer on sepsis.

It is important for clinical laboratory managers and pathologists to recognize that this diagnostic approach to sepsis brings together a number of data points commonly found in a patient’s electronic health record (EHR), some of which the lab generated and others the lab did not generate.

“Sepsis is a serious and sometimes deadly complication. Technologies developed to help prevent this condition have the potential to provide a significant benefit to patients,” said Jeff Shuren, MD, JD, Director of the FDA’s Center for Devices and Radiological Health, in a statement. “The FDA’s authorization of the Prenosis Sepsis ImmunoScore software establishes specific premarket and post-market requirements for this device type.” Clinical laboratory EHRs contain some of the data points Prenosis’ diagnostic software uses. (Photo copyright: US Food and Drug Administration.)  

How it Works

To assist doctors diagnose sepsis, the ImmunoScore software is first integrated into the patient’s hospital EHR. From there, it leverages 22 parameters including:

Instead of requiring a doctor or nurse to look at each parameter separately, the SaMD tool uses AI “to evaluate all those markers at once”, CNBC noted. It then produces a risk score and four discrete risk stratification categories (low, medium, high, and very high) which correlate to “a patient’s risk of deterioration” represented by:

  • Hospital length of stay.
  • In-hospital mortality.
  • Intensive care unit transfer within 24 hours.
  • Vasopressor use within 24 hours.
  • Need for mechanical ventilation within 24 hours.

By sharing these details—a number from one to 100 for each of the 22 diagnostic and predictive parameters—Sepsis ImmunoScore helps doctors determine which will likely contribute most to the patient’s risk for developing sepsis, MedTech Dive reported.

“A lot of clinicians don’t trust AI products for multiple reasons. We are trying very hard to counter that skepticism by making a tool that was validated by the FDA first, and then the second piece is we’re not trying to replace the clinician,” Bobby Reddy Jr., PhD, Prenosis co-founder and CEO, told MedTech Dive.

Big Biobank and Blood Sample Data

Prenosis, which says its goal is the “enabling [of] precision medicine in acute care” developed Sepsis ImmunoScore using the company’s own biobank and a dataset of more than 100,000 blood samples from more than 25,000 patients.

AI algorithms drew on this biological/clinical dataset—the largest in the world for acute care patients suspected of having serious infections, according to Prenosis—to “elucidate patterns in rapid immune response.”

Carle Foundation Hospital, Urbana, Ill., is one of three Illinois hospitals that helped build the biobank and dataset used by Prenosis, according to a Carle news release.

“It does not work without data, and the data started at Carle,” said critical care specialist Karen White, MD, PhD, Carle Foundation Hospital, St. Louis, MO, in the news release.  “The project involved a large number of physicians, research staff, and internal medicine residents at Carle who helped recruit patients, collect data, and samples,” she said.

Opportunity for Clinical Laboratories

Sepsis is a life-threatening condition based on an “extreme response to an infection” that affects nearly 1.7 million adults in the US each year and is responsible for 350,000 deaths, according to US Centers for Disease Control and Prevention (CDC) data. 

A non-invasive diagnostic tool like Sepsis ImmunoScore will be a boon to emergency physicians and the patients they treat. Now that the FDA has authorized the SaMD diagnostic tool to go to market, it may not be long before physicians can use the information it produces to save lives.

Clinical laboratory managers inspired by the development of Sepsis ImmunoScore may want to look for similar ways they can take certain lab test results and combine them with other data in an EHR to create intelligence that physicians can use to better treat their patients. The way forward in laboratory medicine will be combining lab test results with other relevant sets of data to create clinically actionable intelligence for physicians, patients, and payers.

—Donna Marie Pocius

Related Information:

Prenosis Announces FDA De Novo Marketing Authorization of the Sepsis ImmunoScore  

Prenosis Announces Commercial Distribution Collaboration with Roche for Sepsis ImmunoScore

FDA Authorizes Prenosis Software as First AI Tool That Can Diagnose Sepsis

FDA Round-Up April 5, 2024

FDA Grants De Novo Clearance to AI Tool for Detecting Sepsis

New AI Tool for Sepsis Diagnosis Gets its Start to Research at Carle

An AI Tool to Stop Sepsis

UK’s National Health Service Tests AI Tool That Can Spot Cancer in Mammograms Missed by Doctors

This AI platform has the potential to also reduce workload of radiologists, but also of anatomic pathologists and oncologists allowing them to be more productive

When the UK’s National Health Service (NHS) recently tested an artificial intelligence (AI) platform’s ability to analyze mammograms, the AI found early signs of breast cancer that “human doctors” had previously missed, the BBC reported. This level of ability by AI might soon be adapted to aid overworked anatomic pathologists and cancer doctors in the United Kingdom.

The pilot program, which was conducted at NHS Grampian Aberdeen in Scotland, tested the Mammography Intelligent Assessment (MIA) AI platform for breast screening developed by Kheiron Medical Technologies and Imperial College London

Out of 10,000 mammograms MIA analyzed, the AI platform found “tiny signs of breast cancer in 11 women” which had not been spotted during earlier examinations, the BBC noted, adding that the cancers “were practically invisible to the human eye.”

This is a significant development in AI’s role in healthcare. Anatomic pathologists and clinical laboratory leaders will note that ongoing advancements in AI are enabling technology developers to apply their solutions to assessing radiology images, as well as in whole slide imaging used in digital pathology. In the UK, use of AI, the BBC noted, may also help ease doctor’s workloads.

“This is just the beginning of our work with Kheiron,” said Ben Glocker, PhD (above), Professor in Machine Learning for Imaging at Imperial College London and Head of ML Research at Kheiron Medical, in a news release. “We are actively working on new methodologies for the safe deployment and continuous monitoring of MIA to support a US and UK rollout. We are working hard to make sure that as many women as possible will benefit from the use of this new technology within the next year.” AI tools such as MIA may soon take much of the load from anatomic pathologists and radiologists. (Photo copyright: Imperial College London.)

MIA Cloud-based AI Platform

Kheiron was founded in 2016 and MIA was named one of the seven biggest medical breakthroughs in 2023 by ABC News. A study conducted by Imperial College London in 2023 found that MIA “could significantly increase the early detection of breast cancers in a European healthcare setting by up to 13%,” according to an Imperial news release.

“The study was conducted over three phases (two pilot phases and a live roll-out). Overall across the three phases, the AI reader found 24 more cancers than the standard human reading—a 7% relative increase—and resulted in 70 more women recalled (0.28% relative increase),” the news release reported. “Of the additional recalls, six (initial pilot), 13 (extended pilot), and 11 (live use) additional cancers were found, increasing relative cancer detection rate by 13%, 10%, and 5% respectively. [The researchers] found that 83% of the additional cancers detected using MIA in real clinical practice were invasive, showing that MIA can detect cancers where early detection is particularly vital.”

Supported by Microsoft’s Azure Cloud, MIA came together over six years based on training encompassing millions of mammograms worldwide, Healthcare Digital reported.

“AI tools are generally pretty good at spotting symptoms of a specific disease if they are trained on enough data to enable them to be identified. This means feeding the program with as many different anonymized images of those symptoms as possible, from as diverse a range of people as possible,” Sarah Kerruish, Chief Strategy Officer, Kheiron, told Healthcare Digital.

MIA has been trained to “recognize subtle patterns and anomalies” that can point to “cancerous cells even in their earliest stages of development,” Dataconomy reported.

MIA Finds Early Cancer Signs

In the pilot study, MIA examined mammograms from 10,889 women. Each image had previously been reviewed by two radiologists, the BBC reported.

Findings include the following according to Healthcare Digital:

  • MIA “flagged” all people the physicians previously identified with symptoms.
  • The AI platform discovered 11 people with cancer the doctors did not identify.
  • The cancer MIA discovered—and the doctors did not—suggested cancer in early stages.

So, how did the doctors miss the cancer that MIA spotted? Gerald Lip, MD, Clinical Director for Breast Screening in North East Scotland who led the pilot study for the NHS, told Healthcare Digital, “part of the power of AI is it’s not prone to exhaustion or distraction.

“There is an element of fatigue,” he said. “You get disruptions, someone’s coming in, someone’s chatting in the background. There are lots of things that can probably throw you off your regular routine as well. And in those days when you have been distracted, you go, ‘how on earth did I miss that?’ It does happen.”

Lip is also the Chief Investigator in the Mammography Artificial Intelligence Project in the Industrial Center for Artificial Intelligence and Digital Diagnostics in Scotland.  

“I see MIA as a friend and an augmentation to my practice,” he told Healthcare Digital. “MIA isn’t perfect. It had no access to patient history so [it] would flag cysts that had already been identified by previous scans and designated harmless.”

AI as a Safety Net

In the 2023 study, researchers from Imperial College London deployed MIA as an extra reader for mammograms of 25,065 women who visited screening sites in Hungary between April 2021 and January 2023, according to a news release.

“Our prospective real-world usage data in Hungary provides evidence for a significant, measurable increase of early breast cancer detection when MIA is used in clinical practice,” said Peter Kecskemethy, PhD, CEO and co-founder of Kheiron Medical, in the news release.

“Our study shows that AI can act as an effective safety net—a tool to prevent subtler signs of cancer from falling through the cracks,” said Ben Glocker, PhD, Professor in Machine Learning for Imaging at Imperial College London and Head of ML Research at Kheiron Medical, in the news release.

More studies are needed before MIA can be used in clinical settings. Nevertheless, use of AI in radiology—specifically mammograms—where the AI tool can identify very small cancers typically undetectable by radiologists, would be a boon to cancer doctors and the patients they treat.

So far, the research suggests that the AI-powered MIA has benefits to deployment in breast cancer screening. Eventually, it may also make impressive contributions to medical diagnosis and patient care, particularly if MIA eventually proves to be effective at analyzing the whole slide images used by anatomic pathologists. 

—Donna Marie Pocius

Related Information:

NHS AI Test Spots Tiny Cancers Missed by Doctors

Seven Biggest Medical Breakthroughs of 2023

AI Tool Picks up Early-Stage Breast Cancers Doctors Missed

AI Tool MIA Accurately Detects Subtle Breast Cancers

Meet MIA/Introducing Kheiron Medical Technologies

New AI Tool Detects up to 13% More Breast Cancers than Human Clinicians Can

Prospective Implementation of AI-assisted Screen Reading to Improve Early Detection of Breast Cancer

;