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.”
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.
“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.
Speedy DNA sequencing and on-the-spot digital imaging may change the future of anatomic pathology procedures during surgery
Researchers at the Center for Molecular Medicine (CMM) at UMC Utrecht, a leading international university medical center in the Netherlands, have paired artificial intelligence (AI) and machine learning with DNA sequencing to develop a diagnostic tool cancer surgeons can use during surgeries to determine in minutes—while the patient is still on the operating table—whether they have fully removed all the cancerous tissue.
The method, “involves a computer scanning segments of a tumor’s DNA and alighting on certain chemical modifications that can yield a detailed diagnosis of the type and even subtype of the brain tumor,” according to The New York Times, which added, “That diagnosis, generated during the early stages of an hours-long surgery, can help surgeons decide how aggressively to operate, … In the future, the method may also help steer doctors toward treatments tailored for a specific subtype of tumor.”
This technology has the potential to reduce the need for frozen sections, should additional development and studies confirm that it accurately and reliably shows surgeons that all cancerous cells were fully removed. Many anatomic pathologists would welcome such a development because of the time pressure and stress associated with this procedure. Pathologists know that the patient is still in surgery and the surgeons are waiting for the results of the frozen section. Most pathologists would consider fewer frozen sections—with better patient outcomes—to be an improvement in patient care.
“It’s imperative that the tumor subtype is known at the time of surgery,” Jeroen de Ridder, PhD (above), associate professor in the Center for Molecular Medicine at UMC Utrecht and one of the study leaders, told The New York Times. “What we have now uniquely enabled is to allow this very fine-grained, robust, detailed diagnosis to be performed already during the surgery. It can figure out itself what it’s looking at and make a robust classification,” he added. How this discovery affects the role of anatomic pathologists and pathology laboratories during cancer surgeries remains to be seen. (Photo copyright: UMC Utrecht.)
Rapid DNA Sequencing Impacts Brain Tumor Surgeries
The UMC Utrecht scientists employed Oxford Nanopore’s “real-time DNA sequencing technology to address the challenges posed by central nervous system (CNS) tumors, one of the most lethal type of tumor, especially among children,” according to an Oxford Nanopore news release.
The researchers called their new machine learning AI application the “Sturgeon.”
According to The New York Times, “The new method uses a faster genetic sequencing technique and applies it only to a small slice of the cellular genome, allowing it to return results before a surgeon has started operating on the edges of a tumor.”
Jeroen de Ridder, PhD, an associate professor in the Center for Molecular Medicine at UMC Utrecht, told The New York Times that Sturgeon is “powerful enough to deliver a diagnosis with sparse genetic data, akin to someone recognizing an image based on only 1% of its pixels, and from an unknown portion of the image.” Ridder is also a principal investigator at the Oncode Institute, an independent research center in the Netherlands.
The researchers tested Sturgeon during 25 live brain surgeries and compared the results to an anatomic pathologist’s standard method of microscope tissue examination. “The new approach delivered 18 correct diagnoses and failed to reach the needed confidence threshold in the other seven cases. It turned around its diagnoses in less than 90 minutes, the study reported—short enough for it to inform decisions during an operation,” The New York Times reported.
But there were issues. Where the minute samples contain healthy brain tissue, identifying an adequate number of tumor markers could become problematic. Under those conditions, surgeons can ask an anatomic pathologist to “flag the [tissue samples] with the most tumor for sequencing, said PhD candidate Marc Pagès-Gallego, a bioinformatician at UMC Utrecht and a co-author of the study,” The New York Times noted.
“Implementation itself is less straightforward than often suggested,” Sebastian Brandner, MD, a professor of neuropathology at University College London, told The Times. “Sequencing and classifying tumor cells often still required significant expertise in bioinformatics as well as workers who are able to run, troubleshoot, and repair the technology,” he added.
“Brain tumors are also the most well-suited to being classified by the chemical modifications that the new method analyzes; not all cancers can be diagnosed that way,” The Times pointed out.
Thus, the research continues. The new method is being applied to other surgical samples as well. The study authors said other facilities are utilizing the method on their own surgical tissue samples, “suggesting that it can work in other people’s hands.” But more work is needed, The Times reported.
UMC Utrecht Researchers Receive Hanarth Grant
To expand their research into the Sturgeon’s capabilities, the UMC Utrecht research team recently received funds from the Hanarth Fonds, which was founded in 2018 to “promote and enhance the use of artificial intelligence and machine learning to improve the diagnosis, treatment, and outcome of patients with cancer,” according to the organization’s website.
The researchers will investigate ways the Sturgeon AI algorithm can be used to identify tumors of the central nervous system during surgery, a UMC Utrecht news release states. These type of tumors, according to the researchers, are difficult to examine without surgery.
“This poses a challenge for neurosurgeons. They have to operate on a tumor without knowing what type of tumor it is. As a result, there is a chance that the patient will need another operation,” said de Ridder in the news release.
The Sturgeon application solves this problem. It identifies the “exact type of tumor during surgery. This allows the appropriate surgical strategy to be applied immediately,” the news release notes.
The Hanarth funds will enable Jeroen and his team to develop a variant of the Sturgeon that uses “cerebrospinal fluid instead of (part of) the tumor. This will allow the type of tumor to be determined already before surgery. The main challenge is that cerebrospinal fluid contains a mixture of tumor and normal DNA. AI models will be trained to take this into account.”
The UMC Utrecht scientists’ breakthrough is another example of how organizations and research groups are working to shorten time to answer, compared to standard anatomic pathology methods. They are combining developing technologies in ways that achieve these goals.
If validated, study findings may result in new biomarkers for clinical laboratory cholesterol tests and for diagnosing dementia
Researchers continue to find new associations between biomarkers commonly tested by clinical laboratories and certain health conditions and diseases. One recent example comes from research conducted by the University of California San Francisco. The UCSF study connected cholesterol biomarkers generally used for managing cardiovascular disease with an increased risk for dementia as well.
The researchers found that both high and low levels of high-density lipoprotein (HDL)—often referred to as “good” cholesterol—was associated with dementia in older adults, according to a news release from the American Academy of Neurology (AAN).
UCSF’s large, longitudinal study incorporated data from 184,367 people in the Kaiser Permanente Northern California health plan. How the findings may alter cholesterol biomarker use in future diagnostics has not been determined.
“The elevation in dementia risk with both high and low levels of HDL cholesterol was unexpected, but these increases are small, and their clinical significance is uncertain,” said epidemiologist Maria Glymour, ScD (above), study author and Professor of Epidemiology and Biostatistics at UCSF School of Medicine, in a news release. This is another example of how researchers are associating common biomarkers tested regularly by clinical laboratories with additional health conditions and disease states. (Photo copyright: University of California San Francisco.)
HDL Levels Link to Dementia Risk
The UCSF researchers used cholesterol measurements and health behavior questions as they tracked Kaiser Permanente Northern California health plan members who were at least 55 years old between 2002 and 2007, and who did not have dementia at the time of the study’s launch.
The researchers then followed up with the study participants through December 2020 to find out if they had developed dementia, Medical News Today reported.
“Previous studies on this topic have been inconclusive, and this study is especially informative because of the large number of participants and long follow-up,” said epidemiologist Maria Glymour, ScD, study author and Professor of Epidemiology and Biostatistics at UCSF School of Medicine, in the AAN news release. “This information allowed us to study the links with dementia across the range of cholesterol levels and achieve precise estimates even for people with cholesterol levels that are quite high or quite low.”
According to HealthDay, UCSF’s study findings included the following:
More than 25,000 people developed dementia over about nine years. They were divided into five groups.
53.7 milligrams per deciliter (mg/dL) was the average HDL cholesterol level, amid an optimal range of above 40 mg/dL for men and above 50 mg/dL for women.
A 15% rate of dementia was found in participants with HDL of 65 mg/dL or above.
A 7% rate of dementia was found in participants with HDL of 11 mg/dL to 41 mg/dL.
“We found a U-shaped relationship between HDL and dementia risk, such that people with either lower or higher HDL had a slightly elevated risk of dementia,” Erin Ferguson, PhD student of Epidemiology at UCSF, the study’s lead study author, told Medical News Today.
What about LDL?
The UCSF researchers found no correlation between low-density lipoprotein (LDL)—often referred to as “bad” cholesterol”—and increased risk for dementia. But the risk did increase slightly when use of statin lipid-lowering medications were included in the analysis.
“Higher LDL was not associated with dementia risk overall, but statin use qualitatively modified the association. Higher LDL was associated with a slightly greater risk of Alzheimer’s disease-related dementia for statin users,” the researchers wrote in Neurology.
“We found no association between LDL cholesterol and dementia risk in the overall study cohort. Our results add to evidence that HDL cholesterol has similarly complex associations with dementia as with heart disease and cancer,” Glymour noted in the AAN news release.
Australian Study also Links High HDL to Dementia
A separate study from Monash University in Melbourne, Victoria, Australia, found that “abnormally high levels” of HDL was also associated with increased risk for dementia, according to a Monash news release.
The Monash study—which was part of the ASPREE (ASPpirin in Reducing Events in the Elderly) trial of people taking daily aspirin—involved 16,703 Australians and 2,411 Americans during the years 2010 to 2014. The researchers found:
850 participants had developed dementia over about six years.
A 27% increased risk of dementia among people with HDL above 80 mg/dL and a 42% higher dementia risk for people 75 years and older with high HDL levels.
These findings, Newsweek pointed out, do not necessarily mean that high levels of HDL cause dementia.
“There might be additional factors that affect both these findings, such as a genetic link that we are currently unaware of,” Andrew Doig, PhD, Professor, Division of Neuroscience at University of Manchester, told Newsweek. Doig was not involved in the in the Monash University research.
Follow-up research could explore the possibility of diagnosing dementia earlier using blood tests and new biomarkers, Newsweek noted.
Cholesterol Lab Test Results of Value to Clinical Labs
If further studies validate new biomarkers for testing and diagnosis, a medical laboratory’s longitudinal record of cholesterol test results over many years may be useful in identifying people with an increased risk for dementia.
Clinical pathologists and laboratory managers will want to stay tuned as additional study insights and findings are validated and published. Existing laboratory testing reference ranges may need to be revised as well.
As well, the findings of this UCSF research demonstrate that, in this age of information, there will be plenty of opportunities for clinical lab scientists and pathologists to take their labs’ patient data and combine it with other sets of data. Digital tools like artificial intelligence (AI) and machine learning would then be used to assess that large pool of data and produce clinically actionable insights. In turn, that positions labs to add more value and be paid for that value.
Collected data could give healthcare providers and clinical laboratories a practical view of individuals’ oral microbiota and lead to new diagnostic assays
When people hear about microbiome research, they usually think of the study of gut bacteria which Dark Daily has covered extensively. However, this type of research is now expanding to include more microbiomes within the human body, including the oral microbiome—the microbiota living in the human mouth.
One example is coming from Genefitletics, a biotech company based in New Delhi, India. It recently launched ORAHYG, the first and only (they claim) at-home oral microbiome functional activity test available in Asia. The company is targeting the direct-to-consumer (DTC) testing market.
According to the Genefitletics website, the ORAHYG test can decode the root causes of:
“Using oral microbial gene expression sequencing technology and its [machine learning] model, [Genefitletics] recently debuted its oral microbiome gene expression solution, which bridges the gap between dentistry and systemic inflammation,” ETHealthworld reported.
“The molecular insights from this test would give an unprecedented view of functions of the oral microbiome, their interaction with gut microbiome and impact on metabolic, cardiovascular, cognitive, skin, and autoimmune health,” BioSpectrum noted.
“Microbes, the planet Earth’s original inhabitants, have coevolved with humanity, carry out vital biological tasks inside the body, and fundamentally alter how we think about nutrition, medicine, cleanliness, and the environment,” Sushant Kumar (above), founder and CEO of Genefitletics, told the Economic Times. “This has sparked additional research over the past few years into the impact of the trillions of microorganisms that inhabit the human body on our health and diverted tons of funding into the microbiome field.” Clinical laboratories may eventually see an interest and demand for testing of the oral microbiome. (Photo copyright: ETHealthworld.)
Imbalanced Oral Microbiome Can Trigger Disease
The term microbiome refers to the tiny microorganisms that reside on and inside our bodies. A high colonization of these microorganisms—including bacteria, fungi, yeast, viruses, and protozoa—live in our mouths.
“Mouth is the second largest and second most diverse colonized site for microbiome with 770 species comprising 100 billion microbes residing there,” said Sushant Kumar, founder and CEO of Genefitletics, BioSpectrum reported. “Each place inside the mouth right from tongue, throat, saliva, and upper surface of mouth have a distinctive and unique microbiome ecosystem. An imbalanced oral microbiome is said to trigger onset and progression of type 2 diabetes, arthritis, heart diseases, and even dementia.”
The direct-to-consumer ORAHYG test uses a saliva sample taken either by a healthcare professional or an individual at home. That sample is then sequenced through Genefitletics’ gene sequencing platform and the resulting biological data set added to an informatics algorithm.
Genefitletics’ machine-learning platform next converts that information into a pre-symptomatic molecular signature that can predict whether an individual will develop a certain disease. Genefitletics then provides that person with therapeutic and nutritional solutions that can suppress the molecules that are causing the disease.
“The current industrial healthcare system is really a symptom care [system] and adopts a pharmaceutical approach to just make the symptoms more bearable,” Kumar told the Economic Times. “The system cannot decode the root cause to determine what makes people develop diseases.”
Helping People Better Understand their Health
Founded in 2019, Genefitletics was created to pioneer breakthrough discoveries in microbial science to promote better health and increase longevity in humans. The company hopes to unravel the potential of the oral microbiome to help people fend off illness and gain insight into their health.
“Microorganisms … perform critical biological functions inside the body and transform our approach towards nutrition, medicine, hygiene and environment,” Kumar told CNBC. “It is important to understand that an individual does not develop a chronic disease overnight.
“It starts with chronic inflammation which triggers pro-inflammatory molecular indications. Unfortunately, these molecular signatures are completely invisible and cannot be measured using traditional clinical grade tests or diagnostic investigations,” he added. “These molecular signatures occur due to alteration in gene expression of gut, oral, or vaginal microbiome and/or human genome. We have developed algorithms that help us in understanding these alterations way before the clinical symptoms kick in.”
Genefitletics plans to utilize individuals’ collected oral microbiome data to determine their specific nutritional shortcomings, and to develop personalized supplements to help people avoid disease.
The company also produces DTC kits that analyze gut and vaginal microbiomes as well as a test that is used to evaluate an infant’s microbiome.
“The startup wants to develop comparable models to forecast conditions like autism, PCOS [polycystic ovarian syndrome], IBD [Inflammatory bowel disease], Parkinson’s, chronic renal [kidney] disease, anxiety, depression, and obesity,” the Economic Times reported.
Time will tell whether the oral microbiome tests offered by this company prove to be clinically useful. Certainly Genefitletics hopes its ORAHYG test can eventually provide healthcare providers—including clinical laboratory professionals—with a useful view of the oral microbiome. The collected data might also help individuals become aware of pre-symptomatic conditions that make it possible for them to seek confirmation of the disease and early treatment by medical professionals.
Initial analyses also shows AI screening lowers associated radiologist image reading workload by half
Both radiologists and pathologists analyze images to make cancer diagnoses, although one works with radiological images and the other works with tissue biopsies as the source of information. Now, advances in artificial intelligence (AI) for cancer screenings means both radiologists and pathologists may soon be able to detect cancer more accurately and in significantly less time.
Pathologists may find it instructive to learn more about how use of this technology shortened the time for the radiologist to sign out the case without compromising accuracy and quality.
Even better, AI screenings reduced doctors’ workload in interpreting mammography images by nearly 50%, the news release states. Such an improvement would also be a boon to busy pathology practices were this technology to become available for tissue biopsy screenings as well.
“The greatest potential of AI right now is that it could allow radiologists to be less burdened by the excessive amount of reading,” said breast radiologist Kristina Lång, MD, PhD, Associate Professor in Diagnostic Radiology at Lund University. Pathologists working with clinical laboratories in cancer diagnosis could benefit from similar AI advancements. (Photo copyright: Lund University.)
Can AI Save Time and Improve Diagnoses?
One motivation for conducting this study is that Sweden, like other nations, has a shortage of radiologists. Given ongoing advances in machine learning and AI, researchers launched the study to assess the accuracy of AI in diagnosing images, as well as its ability to make radiologists more productive.
The MASAI trial was the first to demonstrate the effectiveness of AI-supported screening, the Lund news release noted.
“We found that using AI results in the detection of 20% (41) more cancers compared with standard screening, without affecting false positives. A false positive in screening occurs when a woman is recalled but cleared of suspicion of cancer after workup,” said breast radiologist Kristina Lång, MD, PhD, clinical researcher and associate professor in diagnostic radiology at Lund University, and consultant at Skåne University Hospital, in the news release.
Not only did the researchers explore the accuracy of AI-supported mammography compared with radiologists’ standard screen reading, they also looked into AI’s effect on radiologists’ screen-reading workload, the Lancet paper states.
Impetus for the research was the shortage of radiologists in Sweden and other countries. A Lancet news release noted that “there is a shortage of breast radiologists in many countries, including a shortfall of around 41 (8%) in the UK in 2020 and about 50 in Sweden, and it takes over a decade to train a radiologist capable of interpreting mammograms.”
More Breast Cancer Identified with Lower Radiologist Workload When Using AI Screening
Here are study findings, according to the Lancet paper:
AI-supported screening resulted in 244 cancers of 861 women recalled.
Standard screening found 203 screen-detected cancers among 817 women who were recalled.
The false positive rate of 1.5% was the same in both groups.
41 (20%) more cancers were detected in the AI-enabled screening group.
Screen readings by radiologists in the AI-supported group totaled 46,345, as compared to 83,231 in the standard screening group.
Workload dropped by 44% for physicians using screen-reading with AI.
“We need to see whether these promising results hold up under other conditions—with other radiologists or other algorithms,” Lang said in the Lund news release.
“The results from our first analysis show that AI-supported screening is safe since the cancer detection rate did not decline despite a reduction in the screen-reading workload,” she added.
Is AI a Threat to Radiologists?
The use of AI in the Swedish study is an early indication that the technology is advancing in ways that may contribute to increased diagnostic accuracy for radiologists. But could AI replace human radiologists’ readings. Not anytime soon.
“These promising interim safety results should be used to inform new trials and program-based evaluations to address the pronounced radiologist shortage in many countries. But they are not enough on their own to confirm that AI is ready to be implemented in mammography screening,” Lång cautioned. “We still need to understand the implications on patients’ outcomes, especially whether combining radiologists’ expertise with AI can help detect interval cancers that are often missed by traditional screening, as well as the cost-effectiveness of the technology.”
“These tools work best when paired with highly trained radiologists who make the final call on your mammogram. Think of it as a tool like a stethoscope for a cardiologist,” she added.
Whether a simple tool or an industry-changing breakthrough, pathology groups and clinical laboratories that work with oncologists can safely assume that AI advances will lead to more cancer research and diagnostic tools that enable earlier and more accurate diagnoses from tissue biopsies and better guidance on therapies for patients.
