Technology could enable patients to monitor their own oxygen levels and transmit that data to healthcare providers, including clinical laboratories
Clinical laboratories may soon have a new data point to add to their laboratory information system (LIS) for doctors to review. Researchers have determined that smartphones can read blood-oxygen levels as accurately as purpose-built pulse oximeters.
Conducted by researchers at the University of Washington (UW) and University of California San Diego (UC San Diego), the proof-of-concept study found that an unmodified smartphone camera and flash along with an app is “capable of detecting blood oxygen saturation levels down to 70%. This is the lowest value that pulse oximeters should be able to measure, as recommended by the US Food and Drug Administration,” according to Digital Health News.
This could mean that patients at risk of hypoxemia, or who are suffering a respiratory illness such as COVID-19, could eventually add accurate blood-oxygen saturation (SpO2) readings to their lab test results at any time and from any location.
“In an ideal world, this information could be seamlessly transmitted to a doctor’s office. This would be really beneficial for telemedicine appointments or for triage nurses to be able to quickly determine whether patients need to go to the emergency department or if they can continue to rest at home and make an appointment with their primary care provider later,” Matthew Thompson, DPhil, Professor of Global Health and Family Medicine at University of Washington, told Digital Health News. Clinical laboratories may soon have a new data point for their laboratory information systems. (Photo copyright. University of Washington.)
UW/UC San Diego Study Details
The researchers studied three men and three women, ages 20-34. All were Caucasian except for one African American, Digital Health News reported. To conduct the study, a standard pulse oximeter was placed on a finger and, on the same hand, another of the participant’s fingers was placed over a smartphone camera.
“We performed the first clinical development validation on a smartphone camera-based SpO2 sensing system using a varied fraction of inspired oxygen (FiO2) protocol, creating a clinically relevant validation dataset for solely smartphone-based contact PPG [photoplethysmography] methods on a wider range of SpO2 values (70–100%) than prior studies (85–100%). We built a deep learning model using this data to demonstrate an overall MAE [Mean Absolute Error] = 5.00% SpO2 while identifying positive cases of low SpO2 < 90% with 81% sensitivity and 79% specificity,” the researchers wrote in NPJ Digital Medicine.
When the smartphone camera’s flash passes light through the finger, “a deep-learning algorithm deciphers the blood oxygen levels.” Participants were also breathing in “a controlled mixture of oxygen and nitrogen to slowly reduce oxygen levels,” Digital Health News reported.
“The camera is recording a video: Every time your heart beats, fresh blood flows through the part illuminated by the flash,” Edward Wang, PhD, Assistant Professor of Electrical and Computer Engineering at UC San Diego and senior author of the project, told Digital Health News. Wang started this project as a UW doctoral student studying electrical and computer engineering and now directs the UC San Diego DigiHealth Lab.
“The camera records how much that blood absorbs the light from the flash in each of the three color channels it measures: red, green, and blue. Then we can feed those intensity measurements into our deep-learning model,” he added.
The deep learning algorithm “pulled out the blood oxygen levels. The remainder of the data was used to validate the method and then test it to see how well it performed on new subjects,” Digital Health News reported.
“Smartphone light can get scattered by all these other components in your finger, which means there’s a lot of noise in the data that we’re looking at,” Varun Viswanath, co-lead author in the study, told Digital Health News. Viswanath is a UW alumnus who is now a doctoral student being advised by Wang at UC San Diego.
“Deep learning is a really helpful technique here because it can see these really complex and nuanced features and helps you find patterns that you wouldn’t otherwise be able to see,” he added.
Each round of testing took approximately 15 minutes. In total the researchers gathered more than 10,000 blood oxygen readings. Levels ranged from 61% to 100%.
“The smartphone correctly predicted whether the subject had low blood oxygen levels 80% of the time,” Digital Health News reported.
Smartphones Accurately Collecting Data
The UW/UC San Diego study is the first to show such precise results using a smartphone.
“Other smartphone apps that do this were developed by asking people to hold their breath. But people get very uncomfortable and have to breathe after a minute or so, and that’s before their blood-oxygen levels have gone down far enough to represent the full range of clinically relevant data,” said Jason Hoffman, a PhD student researcher at UW’s UbiComp Lab and co-lead author of the study.
The ability to track a full 15 minutes of data is a prime example of improvement. “Our data shows that smartphones could work well right in the critical threshold range,” Hoffman added.
“Smartphone-based SpO2 monitors, especially those that rely only on built-in hardware with no modifications, present an opportunity to detect and monitor respiratory conditions in contexts where pulse oximeters are less available,” the researchers wrote.
“This way you could have multiple measurements with your own device at either no cost or low cost,” Matthew Thompson, DPhil, Professor of Global Health and Family Medicine at University of Washington, told Digital Health News. Thompson is a professor of both family medicine and global health and an adjunct professor of pediatrics at the UW School of Medicine.
What Comes Next
The UW/UC San Diego research team plans to continue its research and gather more diversity among subjects.
“It’s so important to do a study like this,” Wang said. “Traditional medical devices go through rigorous testing. But computer science research is still just starting to dig its teeth into using machine learning for biomedical device development and we’re all still learning. By forcing ourselves to be rigorous, we’re forcing ourselves to learn how to do things right.”
Though no current clinical laboratory application is pending, smartphone use to capture biometrics for testing is increasing. Soon, labs may need a way to input all that data into their laboratory information systems. It’s something to consider.
Further development of this novel technology could result in new, more sensitive assays for clinical laboratories to use in the effort to improve antimicrobial stewardship in hospitals
Researchers at McMaster University in Ontario, Canada, have used artificial intelligence (AI) to identify a potential antibiotic that neutralizes the drug-resistant bacteria Acinetobacter baumannii, an antibiotic resistant pathogen commonly found in many hospitals. This will be of interest to clinical laboratory managers and microbiologists involved in identifying strains of bacteria to determine if they are antimicrobial-resistant (AMR) superbugs.
Using machine learning, the scientists screened thousands molecules to look for those that inhibited the growth of this specific pathogen. And they succeeded.
“We trained a neural network with this growth inhibition dataset and performed in silico predictions for structurally new molecules with activity against A. baumannii,” the researchers wrote in their published study.
They discovered that the molecule abaucin inhibited the growth of the antibiotic-resistant pathogen in vitro.
This shows how machine learning and AI technologies are giving biomedical researchers tools to identify new therapeutic drugs that are effective against drug-resistant strains of bacteria. This same research can be expected to lead to new clinical laboratory assays that determine if superbugs can be attacked by specific therapeutic drugs.
“When I think about AI in general, I think of these models as things that are just going to help us do the thing we’re going to do better,” Jonathan Stokes, PhD, Assistant Professor of Biomedicine and Biochemistry at McMaster University in Ontario, Canada, and lead author of the study, told USA Today. Clinical laboratory scientists and microbiologists will be encouraged by the McMaster University scientists’ findings. (Photo copyright: McMaster University.)
McMaster Study Details
Jonathan Stokes, PhD, head of the Stokes Laboratory at McMaster University, is Assistant Professor of Biomedicine/Biochemistry at McMaster and lead author of the study. Stokes’ team worked with researchers from the Broad Institute of MIT and Harvard to explore the effectiveness of AI in combating superbugs, USA Today reported.
“This work highlights the utility of machine learning in antibiotic discovery and describes a promising lead with targeted activity against a challenging Gram-negative pathogen,” the researchers wrote in Nature Chemical Biology.
Stokes Lab utilized the high-throughput drug screening technique, spending weeks growing and exposing Acinetobacter baumannii to more than 7,500 agents of drugs and active ingredients of drugs. When 480 compounds were uncovered that blocked the growth of bacteria, this information was then provided to a computer that was trained to run an AI algorithm, CNN reported.
“Once we had our [machine learning] model trained, what we could do then is start showing that model brand-new pictures of chemicals that it had never seen, right? And based on what it had learned during training, it would predict for us whether those molecules were antibacterial or not,” Stokes told CNN.
The model spent hours screening more than 6,000 molecules. It then narrowed the search to 240 chemicals, which were tested in the lab. The scientists pared down the results to the nine most effective inhibitors of bacteria. They then eliminated those that were either related to existing antibiotics or might be considered dangerous.
The researchers found one compound—RS102895 (abaucin)—which, according to Stokes, was likely created to treat diabetes, CNN reported. The scientists discovered that the compound prevented bacterial components from making their way from inside a cell to the cell’s surface.
“It’s a rather interesting mechanism and one that is not observed amongst clinical antibiotics so far as I know,” Stokes told CNN.
Because of the effectiveness of the antibiotic during testing on mice skin, the researchers believe this method may be useful for creating antibiotics custom made to battle additional drug resistant pathogens, CNN noted.
Defeating a ‘Professional Pathogen’
Acinetobacter baumannii (A. baumannii)—the focus of Stoke’s study—is often found on hospital counters and doorknobs and has a sneaky way of using other organisms’ DNA to resist antibiotic treatment, according to CNN.
“It’s what we call in the laboratory a professional pathogen,” Stokes told CNN.
A. baumannii causes infections in the urinary tract, lungs, and blood and typically wreaks havoc to vulnerable patients on breathing machines, in intensive care units, or undergoing surgery, USA Today reported.
A. baumannii is resistant to carbapenem, a potent antibiotic. The Centers for Disease Control and Prevention (CDC) reported that in 2017 the bacteria infected 8,500 people in hospitals, 700 of those infections being fatal.
Further, in its 2019 “Antibiotic Resistance Threats in the United States” report, the CDC stated that one out of every four patients infected with the bacteria died within one month of their diagnosis. The federal agency deemed the bacteria “of greatest need” for new antibiotics.
Thus, finding a way to defeat this particularly nasty bacteria could save many lives.
Implications of Study Findings on Development of new Antibiotics
The Stokes Laboratory study findings show promise. If more antibiotics worked so precisely, it’s possible bacteria would not have a chance to become resistant in the first place, CNN reported.
Next steps in Stokes’ research include optimizing the chemical structure and testing in larger animals or humans, USA Today reported.
“It’s important to remember [that] when we’re trying to develop a drug, it doesn’t just have to kill the bacterium,” Stokes noted. “It also has to be well tolerated in humans and it has to get to the infection site and stay at the infection site long enough to elicit an effect,” USA Today reported.
Stokes’ study is a prime example of how AI can make a big impact in clinical laboratory diagnostics and treatment.
“We know broad-spectrum antibiotics are suboptimal and that pathogens have the ability to evolve and adjust to every trick we throw at them … AI methods afford us the opportunity to vastly increase the rate at which we discover new antibiotics, and we can do it at a reduced cost. This is an important avenue of exploration for new antibiotic drugs,” Stokes told CNN.
Clinical laboratory managers and microbiologists may want to keep an open-mind about the use of AI in drug development. More research is needed to give substance to the McMaster University study’s findings. But the positive results may lead to methods for fine tuning existing antibiotics to better combat antimicrobial-resistant bacteria, USA Today reported.
An assay using mass spectrometry could go to clinical trial within two years
Dark Daily has regularly observed that humans generate a variety of volatile substances—particularly in breath—which can be used for diagnostic purposes. But what if people, like certain trained animals, could smell the presence of disease before the onset of symptoms? What types of clinical laboratory testing biomarkers could be developed based on human-generated volatile organic compounds?
Researchers at the University of Manchester (UM) in the United Kingdom (UK) say their “breakthrough” test to diagnose Parkinson’s disease “can diagnose disease from skin swabs in three minutes,” according to a university press release.
Perdita Barran, PhD (right), head of the University of Manchester research team that developed the mass spectrometry Parkinson’s test, is shown above with Joy Milne (left), the retired nurse from Scotland who inspired Barran’s team to develop a new Parkinson’s biomarker and method for identifying it. “We are tremendously excited by these results which take us closer to making a diagnostic test for Parkinson’s Disease that could be used in clinic,” she said in a press release. A viable clinical laboratory test for Parkinson’s disease is greatly needed, as more than 10 million people worldwide currently live with the neurodegenerative disorder. (Photo copyright: University of Manchester.)
Using Mass Spectrometry to Analyze Sebum
The UM scientists hypothesized that the smell could be due to sebum, a light oily substance on skin that was going through a chemical change due to the Parkinson’s disease, Hull Daily Mail explained.
Increased sebum, which is produced by the sebaceous glands, is a hallmark of Parkinson’s, the researchers noted.
Their new method involves analysis of sebum using mass spectrometry, according to the JACS AU paper. The method, the researchers claim, makes it possible to diagnose Parkinson’s disease from skin swabs in three minutes.
“There are no cures for Parkinson’s, but a confirmatory diagnosis would allow [Parkinson’s patients] to get the right treatment and get the drugs that will help to alleviate their symptoms,” Perdita Barran, PhD, told the Hull Daily Mail. Barran is Chair of Mass Spectrometry in the Department of Chemistry and Director of the Michael Barber Centre for Collaborative Mass Spectrometry at UM’s Manchester Institute of Biotechnology. “What we are now doing is seeing if (hospital laboratories) can do what we’ve done in a research lab in a hospital lab,” she added.
Sebum Analyzed with Mass Spectrometry
Parkinson’s disease—the world’s fastest growing neurodegenerative disorder—needs “robust biomarkers” that could advance detection and head off onset of motor symptoms such as tremor, rigidity, and postural instability, the researchers note in their paper.
Their recent study builds on earlier 2019 findings they published in ACS Central Science about volatile compounds in sebum possibly being used as Parkinson’s biomarkers.
“Sebum is an underexplored biofluid, which is readily obtained from non-invasive skin swabs, which primarily consists of a mixture of triglycerides, cholesterol, free fatty acids, waxy esters, and squalene,” the researchers explained in their JACS AU paper.
The scientists sought, “to develop a method to analyze sebum in its native state to facilitate rapid assessment of the Parkinson’s disease status. Paper spray ionization mass spectrometry, which allows the direct analysis of compounds from paper, has previously been demonstrated to detect small molecules from unprocessed biofluids, such as blood and urine, but not to date with sebum,” they wrote.
The UM researchers used mass spectrometry to analyze sebum collected on cotton swabs from the backs of 79 people with Parkinson’s and 71 healthy individuals, BBC Scotland News reported.
Depanjan Sarkar, PhD, Research Associate, University of Manchester, further explained the technique in the UM news release:
Sebum is taken from the swab to filter paper cut in a triangle.
Using a solvent and voltage, sebum compounds transfer into the mass spectrometer.
“When we did this, we found more than 4,000 unique compounds of which 500 are different between people with Parkinson’s compared to the control participants,” Sarkar said.
Fatty Acids Make Assay Possible
Could fatty acids pave the way to an assay? The UM researchers believe so.
“We have identified two classes of lipids, namely [triglycerides] and diglycerides, as components of human sebum that are significantly differentially expressed in PD,” the researchers wrote in JACS AU. “Non-invasive sampling followed by PS-IM-MS [paper spray-ion mobility–mass spectrometry] analysis targeting these compounds could provide an inexpensive assay to support clinical phenotyping for the confirmatory diagnosis of Parkinson’s disease.”
A clinical trial for their test, which costs about $20, may be done within two years in Manchester area, the Daily Mail reported.
When Dark Daily reported in 2020 on Joy Milne’s unique ability to smell her husband’s Parkinson’s disease before it was formally diagnosed, we predicted a diagnostic test for Parkinson’s may be years away. And here it is, albeit with regulatory clearance needed following clinical trials.
It may in fact be possible to leverage sebum analysis to detect other diseases, the UM researchers noted.
For diagnostics developers, this story of Joy Milne and her husband Les Milne is a useful example of how, in tracking the life of a specific patient with a specific disease and close family members, researchers were able to identify a new class of biomarkers that could be used in a diagnostic assay.
It will be interesting to follow the University of Manchester researchers in their quest for a diagnostic mass spectrometry clinical laboratory test for Parkinson’s disease. According to Parkinson’s Foundation statistics, about 10 million people worldwide live with the neurodegenerative disorder. Such a new diagnostic test could be vitally important to medical laboratory care, and to patients and their families.
Japanese scientists who developed the detection method hope to use it to create ‘easy testing kits that anyone can use’
What do ostriches and humans have in common during the current COVID-19 pandemic? The unexpected answer is that ostrich antibodies can be used to identify humans infected with COVID-19. If proven viable in healthcare settings, the possibility exists that new clinical laboratory tests could be developed based on wearable diagnostics technologies that pathologists would interpret for doctors and patients.
The KPU scientists conducted a small study with 32 COVID-19 patients over a 10-day span. The surgical-style masks they wore later glowed around the nose and mouth areas but became dimmer over time as their viral load decreased.
“The ostrich antibody for corona placed on the mouth filter of the mask captures the coronavirus in coughing, sneezing, and water,” the researchers explained in Study Finds.
Tsukamoto himself learned he had contracted COVID-19 after wearing a prototype mask and noticing it glowed under UV light. A PCR test later confirmed his diagnosis, Kyodo News reported.
The KPU team “hopes to further develop the masks so they will glow automatically, without special lighting, if the [COVID-19] virus is detected.” Reuters noted in its coverage of the ostrich-antibody masks.
Making Medicine from Ostrich Antibodies
A profile in Audubon noted that Tsukamoto, who also serves as a veterinary medicine professor at Kyoto Prefectural University, made ostriches the focus of his research since the 1990s as he looked for ways to harness the dinosaur-like bird’s properties to fight human infections. He maintains a flock of 500 captive ostriches. Each female ostrich can produce 50 to 100 eggs/year over a 50-year life span.
Tsukamoto’s research focuses on customizing the antibodies in ostrich eggs by injecting females with inactive viruses, allergens, and bacteria, and then extracting the antibodies to develop medicines for humans. Antibodies form in the egg yolks in about six weeks and can be collected without harming the parent or young.
“The idea of using ostrich antibodies for therapeutics in general is a very interesting concept, particularly because of the advantages of producing the antibodies from eggs,” Ashley St. John, PhD, an Associate Professor in Immunology, at Duke-NUS Medical School in Singapore, told Audubon.
While more clinical studies will be needed before ostrich-antibody masks reach the commercial marketplace, Tsukamoto’s team is planning to expand their experiment to 150 participants with a goal of receiving Japanese government approval to begin selling the glowing COVID-detection masks as early as 2022. But they believe the ostrich-antibody technique ultimately may lead to development of an inexpensive COVID-19 testing kit.
“We can mass-produce antibodies from ostriches at a low cost. In the future, I want to make this into an easy testing kit that anyone can use,” Tsukamoto told Kyodo News.
Harvard, MIT Also Working on COVID-19 Detecting Facemask
According to Fast Company, the MIT/Harvard COVID-19-detecting masks use the same core technology as previous paper tests for Ebola and Zika that utilize proteins and nucleic acids embedded in paper that react to target molecules.
“They would especially be useful in situations where local variant outbreaks are occurring, allowing people to conveniently test themselves at home multiple times a day,” he told Fast Company.
“It’s on par specificity and sensitivity that you will get in a state-of-the-art [medical] laboratory, but with no one there,” Luis Ruben Soenksen, PhD, Venture Builder in Artificial Intelligence and Healthcare at MIT and one of the co-authors of the Nature Biotechnology study, told Fast Company.
As the definition of “wearable diagnostic technology” broadens, pathologists and clinical laboratory scientists may see their roles expand to include helping consumers interpret data collected by point-of-care testing technology as well as performing, evaluating, and interpreting laboratory test results that come from non-traditional sources.
Skin patch technologies could enable clinical laboratories to monitor patients’ vitals and report to medical professionals in real time
Pathologists and clinical laboratory leaders have read many Dark Daily ebriefings on the development of skin patches over the years that do everything from monitoring fatigue in the military to being a complete lab-on-skin technology. Now, researchers at the University of California San Diego (UCSD) have developed a wearable patch that can monitor cardiovascular signals and other various biochemical levels in the body simultaneously.
The researchers believe there is enormous potential for such a patch in helping patients monitor conditions such as hypertension or diabetes. They also foresee a scenario where the patch could be used in settings where vitals must be constantly monitored. They hope to develop future versions of the patch that can detect more biomarkers within the body.
“This type of wearable would be very helpful for people with underlying medical conditions to monitor their own health on a regular basis,” Lu Yin, a PhD student and co-first author of the study, told New Atlas. “It would also serve as a great tool for remote patient monitoring, especially during the COVID-19 pandemic when people are minimizing in-person visits to the clinic,” she added.
Combining Precision Medicine with Telehealth and the Internet of Things
About the size of a postage stamp and consisting of stretchy polymers that conform to the skin, the UCSD patch monitors blood pressure and contains sensors that measure different biochemical levels in the body, such as:
The sensors are carefully arranged on the patch to eliminate interference between the signals, noted a UCSD press release.
“Each sensor provides a separate picture of a physical or chemical change. Integrating them all in one wearable patch allows us to stitch those different pictures together to get a more comprehensive overview of what’s going on in our bodies,” said Sheng Xu, PhD, Principle Investigator, Xu Research Group at UCSD, Assistant Professor in the Department of NanoEngineering Department, and a co-first author of the study, in the press release.
The UCSD researchers developed their skin patch to monitor specific biomarkers that can affect blood pressure.
“Let’s say you are monitoring your blood pressure and you see spikes during the day and think that something is wrong,” co-first author Juliane Sempionatto, PhD, a postdoctoral researcher at California Institute of Technology (Caltech) and co-first author of the study, told New Atlas. “But a biomarker reading could tell you if those spikes were due to an intake of alcohol or caffeine. This combination of sensors can give you that type of information,” she added.
The blood pressure sensor sits near the center of the patch and consists of a set of small transducers welded to the patch via a conductive link. Voltage applied to the transducers send ultrasound waves through the body which bounce off arteries and create echoes that are detected by the sensor and converted into an accurate blood pressure reading.
The chemical sensor releases the drug pilocarpine into the skin to induce sweat and then measures the chemicals contained in the sweat to provide readings of certain biochemical levels.
The glucose sensor located in the patch emits a mild electrical current to the body that stimulates the release of interstitial fluid and then reads the glucose level in that fluid.
Skin Patch Measurements Closely Match Those of Traditional Devices
Test subjects wore the patch on their neck while performing various combinations of the following tasks:
exercising on a stationary bicycle,
eating a high-sugar meal,
drinking an alcoholic beverage, and
drinking a caffeinated beverage.
The results of the measurements taken from the patch closely matched measurements collected by traditional monitoring devices such as a:
For now, the patch must be connected to an external power source which transmits the reading to a counter-top machine, but the researchers hope to create a wireless version in the future.
“There are opportunities to monitor other biomarkers associated with various diseases,” Sempionatto said in the UCSD press release. “We are looking to add more clinical value to this device.”
Other Similar Skin Patch Monitoring Technologies
Though an important breakthrough, the UCSD’s device is not the first skin patch monitor to be developed.
Multiple research and clinical studies are underway that hope to prove the accuracy and safety of wearable devices at detecting and monitoring certain health conditions. It’s a worthy goal.
Skin patches, such as the one created at UCSD, could enable clinical laboratories to provide value-added service to medical professionals and patients alike. Medical labs could potentially monitor skin patch readings in real-time and notify physicians and patients of changes in biomarkers that require attention.
Further, as this technology is developed, it will likely find a ready market with the latest generation of consumers who are more willing than previous generations to buy their own diagnostic tests for home use. These “next-generation” healthcare consumers have demonstrated their willingness to use Apple watches, Fitbits, and similar wearable devices to monitor their condition during exercise and other health metrics.
Pathologists and clinical laboratory managers should not overlook the potential for robust consumer demand to accelerate development and market adoption of such skin patches.