First, pause and take a deep breath.

When we breathe in, our lungs fill with oxygen, which is distributed to our red blood cells for transportation throughout our bodies. Our bodies need a lot of oxygen to function, and healthy people have at least 95% oxygen saturation all the time.

Conditions like asthma or COVID-19 make it harder for bodies to absorb oxygen from the lungs. This leads to oxygen saturation percentages that drop to 90% or below, an indication that medical attention is needed.

In a clinic, doctors monitor oxygen saturation using pulse oximeters — those clips you put over your fingertip or ear. But monitoring oxygen saturation at home multiple times a day could , for example.

In a proof-of-principle study, 91̽�� and University of California San Diego researchers have shown that smartphones are 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 U.S. Food and Drug Administration.

The technique involves participants placing their finger over the camera and flash of a smartphone, which uses a deep-learning algorithm to decipher the blood oxygen levels. When the team delivered a controlled mixture of nitrogen and oxygen to six subjects to artificially bring their blood oxygen levels down, the smartphone correctly predicted whether the subject had low blood oxygen levels 80% of the time.

The team Sept. 19 in npj Digital Medicine.

“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 co-lead author , a 91̽��doctoral student in the Paul G. Allen School of Computer Science & Engineering. “With our test, we’re able to gather 15 minutes of data from each subject. Our data shows that smartphones could work well right in the critical threshold range.”

Another benefit of measuring blood oxygen levels on a smartphone is that almost everyone has one.

“This way you could have multiple measurements with your own device at either no cost or low cost,” said co-author , professor of family medicine in the 91̽��School of Medicine. “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.”

The team recruited six participants ranging in age from 20 to 34. Three identified as female, three identified as male. One participant identified as being African American, while the rest identified as being Caucasian.

To gather data to train and test the algorithm, the researchers had each participant wear a standard pulse oximeter on one finger and then place another finger on the same hand over a smartphone’s camera and flash. Each participant had this same set up on both hands simultaneously.

“The camera is recording a video: Every time your heart beats, fresh blood flows through the part illuminated by the flash,” said senior author , who started this project as a 91̽��doctoral student studying electrical and computer engineering and is now an assistant professor at UC San Diego’s and the Department of Electrical and Computer Engineering.

“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,” said Wang, who also directs the . “Then we can feed those intensity measurements into our deep-learning model.”

Each participant breathed in a controlled mixture of oxygen and nitrogen to slowly reduce oxygen levels. The process took about 15 minutes. For all six participants, the team acquired more than 10,000 blood oxygen level readings between 61% and 100%.

The researchers used data from four of the participants to train a deep learning algorithm to pull 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.

“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,” said co-lead author , a 91̽��alumnus who is now a doctoral student 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.”

The team hopes to continue this research by testing the algorithm on more people.

“One of our subjects had thick calluses on their fingers, which made it harder for our algorithm to accurately determine their blood oxygen levels,” Hoffman said. “If we were to expand this study to more subjects, we would likely see more people with calluses and more people with different skin tones. Then we could potentially have an algorithm with enough complexity to be able to better model all these differences.”

But, the researchers said, this is a good first step toward developing biomedical devices that are aided by machine learning.

“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.”

Additional co-authors are , a doctoral student at Southern Methodist University; , associate professor of computer science at Southern Methodist University; , who completed this research as a 91̽��undergraduate student; and , 91̽��professor in both the Allen School and the electrical and computer engineering department. This research was funded by the 91̽��. The researchers have applied for a patent that covers systems and methods for SpO2 classification using smartphones (application number: 17/164,745).

For more information, contact Hoffman at jasonhof@cs.washington.edu, Wang at ejaywang@eng.ucsd.edu and Viswanath at varunv9@eng.ucsd.edu. For questions specifically for Matthew Thompson, please contact Leila Gray at leilag@uw.edu.

Dr. Douglas Paauw honored for teaching by American College of Physicians ��

, 91̽��professor of general internal medicine in the School of Medicine and director of the 91̽��Medical Student Program, has been awarded the by the , a national organization of internists.

The award, established in 1969 and renamed for its first woman , is given annually to a fellow or of the college “who has demonstrated the ennobling qualities of a great teacher.” Paauw was a master of the college in 2009.

He joined the School of Medicine faculty in 1988 and is a physician at the 91̽��Medical Center’s general internal medicine and virology clinics. Paauw also received distinguished teaching awards from the 91̽��in 1997 and from its School of Medicine four times. He is the UW’s Rathmann Family Foundation Endowed Chair in Patient Centered Clinical Education.

Paauw will receive the award at the college’s annual convocation ceremony in April 2020 at the Los Angeles Convention Center.

* * *

Dr. Joel Kaufman named new editor-in-chief of environmental health journal

, 91̽��professor of environmental and occupational health sciences, medicine and epidemiology, has been named the new editor-in-chief of the journal .

The journal is published by the National Institute of Environmental Health and Sciences, which is part of the National Institutes of Health.

Kaufman is a practicing physician who has published more than 200 research papers and review articles on environmental science. Since joining the 91̽��faculty more than two decades ago, he has maintained a research program that encompasses epidemiology, inhalation toxicology, clinical medicine and exposure sciences. He previously served as interim dean for the School of Public Health.

Day-to-day operations for the journal will be carried out by full-time staff under Kaufman’s direction. The journal now enables its editor-in-chief to continue conducting research and teaching at their home institution.��

Kaufman has served on editorial boards and peer review panels for many of the leading clinical medicine and environmental health journals. He previously served on the editorial review board, then as an associate editor, of Environmental Health Perspectives before taking over as interim dean of the School of Public Health in 2016. .

* * *

Allen School faculty members honored by Association for Computing Machinery, Institute of Electrical and Electronics Engineers ��

The , or ACM, has professors and of the Paul G. Allen School of Computer Science & Engineering as among 58 new , honored for their “far-reaching accomplishments that define the digital age.”

Also, the , or IEEE, has named Allen School professor as among its Smith also has an appointment with the Department of Electrical & Computer Engineering.

These announcements bring to 24 the number of current or former Allen School faculty members made an ACM Fellows, and 16 who have been named IEEE Fellows.

* * *

Sam Luboga of Department of Family Medicine to lead Ugandan education commission

, a 91̽��clinical associate professor in the Department of Family Medicine has been named to lead the of The Republic of Uganda. Luboga is also an associate professor of health sciences at , in Kampala, Uganda. The appointment calls for Luboga to lead the nation’s civil service teacher’s personnel board, responsible for ensuring the high caliber of Uganda’s teaching workforce.

“I will make sure that the reputation of the Education Service Commission remains high and grows more,” Luboga said in an about his appointment.

An Ethics Feature in the May-June issue of the Journal of the American Board of Family Medicine describes the lessons learned as the Madras Medical Group transformed itself into a pharma-free clinic.�� The small, private clinic of five physicians no longer has contact with detailers – representatives from the pharmaceutical industry who visit physicians to educate them about medications. The clinic also refuses drug samples, gifts and lunches from pharmaceutical companies.

The corresponding author of the paper, David V. Evans, practiced at the clinic and is now an assistant professor of family medicine at the 91̽��. He and his colleagues at the Oregon State University College of Pharmacy and at University of Oregon Health & Sciences University ��examined the clinic’s successful methods to change a culture ingrained in medicine.

“Detailing – selling drugs by educating physicians – ��was first reported as a problem in the late 1950’s,” Evans said. ��Since then, extensive research indicates that detailing can encourage physicians to prescribe medicines that may not be appropriate, necessary or cost-effective for patients, and that may pose safety concerns.

Academic medical centers, such as medical schools and teaching hospitals,�� Evans noted, have critically looked at detailing,�� have advocated against it nationally, and have set institutional policies prohibiting or limiting student, resident and faculty contact with detailers .

However, he added, three-fourths of the country’s physicians practice in the community, where interactions between physicians and pharmaceutical representatives are still commonplace.�� Although some states have curbed contact between drug reps and physicians, most physicians in small, independent practices have little guidance on how to become pharma-free, the authors of the paper observed.

“Changing this situation is not easy, but with a deliberate and thoughtful approach it can occur,” Evans said. ��Although his clinic’s personnel were not unanimous in wanting to go pharma-free, approaching it in smaller steps helped to decrease dissent.

First, those championing a pharma-free clinic quantified the presence of detailers and their marketing strategies.�� This data helped convince the physicians and staff that a problem existed.�� The staff and physicians then voiced their concerns. These included doing without prescription samples for patients.

The clinic then scheduled sessions for their health professionals to keep current about medications by reviewing rigorous scientific studies. To replace the pharma-sponsored lunches, the clinic held its own regular lunches for their clinicians and staff.�� Clinic staff told patients about the change, and news media in the local area informed the nearby public. ��The clinic also created a chart comparing average monthly costs of many heavily marketed drugs with first-line, less-expensive or generic drugs, if such alternatives were available.

“Becoming pharma-free at our clinic was not an overnight thing,” said Evans. “Cultural change takes time.�� Eventually even the initial dissenters in the clinic came to feel good about the change, and it became a point of pride.”

Now, as a 91̽��medical school faculty member who teaches medical students and residents, Evans, along with colleague Pam Pentin, educate future physicians on effectively managing drug detailers, including how to turn all of them away.

“One of the concerns,” Evans said, “is that medical students and residents may come up through their education without ever having interacted with a drug representative.�� It’s important to teach medical students and residents how detailers operate in the real world. At the UW, family medicine residents learn about detailer strategies during their third-year practice management curriculum.�� This year’s graduating residents will be the first to have taken the training.”

As of 2009, there was one drug sales representative for every eight physicians. ��Despite increased scrutiny and regulation, Evans and his colleagues noted that the percentage of primary care physicians with industrial relationships remains high at 84 percent.�� Evans explained that most drug reps are well trained and personable. They use marketing strategies time-tested in the social sciences.

“It’s a sophisticated operation. For example, before they go in to see physicians,” he said, “detailers sit in their cars data-mining on their electronic devices. They find out the physicians’ prescribing patterns from databases in which the patients’ names and other identifying information have been removed. They know how much a doctor has prescribed of drug A, and will either thank the doctor or encourage him or her to prescribe drug B instead.”

Beginning in August 2013, as part of the Affordable Care Act of 2013, a national web site will contain information for patients on the monetary value of what individual physicians accept from pharmaceutical firms.�� The Physician Payment Sunshine Act will require manufacturers of drugs, devices and biologics to report all payments to physicians and teaching hospitals to a public web database.

What else can patients do to mitigate undesirable effects of drug marketing?�� Evans advises asking their physicians about the issue. He suggests refusing drug samples if they are offered. Patients can also become aware of the effects of drug advertising on their own treatment choices.

The authors of the paper, “Breaking Up is Hard to Do: Lessons Learned from a Pharma-Free Practice Transformation,” wrote that they hope their description of how a clinic changed its practice “contributes to the ongoing discussion of the potential clinical influences and the ethics of the relationship between practicing physicians and pharmaceutical marketing.”

The other authors were Daniel M. Hartung and Denise Beasley of the Department of Pharmacy Practice, Oregon State University College of Pharmacy in Portland. The senior author was Lyle J. Fagnan, a physician in the Oregon Rural Practice-based Research Network in the Department of Family Practice, Oregon Health & Science University School of Medicine.

###

The externally peer-reviewed analysis of the clinic transformation received no funding and the researchers declared no conflicts of interest.