Team’s Biosensor Technology May Lead to Breath Test for Lung Cancer

University of Texas at Dallas researchers have developed biosensor technology that when combined with artificial intelligence (AI) shows promise for detecting lung cancer through breath analysis.

The electrochemical biosensor identifies eight volatile organic compounds (VOCs) that are potential biomarkers for thoracic cancers, which include lung and esophageal cancers. AI then analyzes the biochemical characteristics of the compounds to determine whether they are a match to those linked to various thoracic cancers.

"We built a screening tool that could allow physicians to catch the disease in its early phases, which improves outcomes," said Dr. Shalini Prasad, professor and department head of bioengineering in the Erik Jonsson School of Engineering and Computer Science. "This technology offers a potentially affordable, quick and noninvasive breath analysis tool for cancer screening."

The project is a collaboration between UT Dallas bioengineering and computer science researchers and a clinical research team from UT Southwestern Medical Center. The researchers described the technology in the August issue of Sensing and Bio-Sensing Research.

The electrochemical device was tested on breath samples from 67 patients, including 30 with biopsy-confirmed thoracic cancer. The device accurately identified the VOCs in 90% of the confirmed cancer cases.

The inspiration for the device came about during the COVID-19 pandemic.

"There was a lot of interest at that time in noninvasive technologies that could rapidly allow us to screen and isolate the spread of COVID," said Prasad, corresponding author of the study and a Cecil H. and Ida Green Professor in Systems Biology Science. "The use of breath became very attractive because breath goes through our respiratory system and carries metabolites, which are indicators of disease."

Changes in metabolites in exhaled breath can occur early in the onset of a disease. This emerging field of breathomics has the potential to allow health care providers to analyze VOCs in exhaled breath to diagnose diseases and monitor health conditions, Prasad said. AI is an important component of the diagnostic capabilities of the UT Dallas team's device.

"There is a huge amount of data provided by the breath," Prasad said. "What is important? What is not? All of this information comes from the machine learning algorithm. That's why the partnership with computer science is critical. How meaningfully you integrate AI into a technology is important."

Prasad approached Dr. Ovidiu Daescu, professor and department head of computer science, a Jonsson School Chair and a co-author of the study, to fine-tune the machine learning models and validate the approach.

"The breath profiling device and associated machine learning model have great potential for making a difference in cancer detection while improving costs, assuming more cases are tested and validated over time in medical settings," Daescu said.

The researchers also partnered with Dr. Muhanned Abu-Hijleh, a professor of internal medicine in the division of pulmonary and critical care medicine at UT Southwestern.

"Lung cancer is the leading cause of cancer-related deaths in the U.S. and worldwide," said Abu-Hijleh, an interventional pulmonologist who is also the medical director of Respiratory Therapy and director of the Chronic Obstructive Pulmonary Disease Clinic and Program. "Using minimally invasive technologies like biomarkers and exhaled volatile-organic-compounds analysis can help in the early detection of thoracic malignancies with minimal burden on patients and the health care system, carrying less overall morbidity."

Prasad said the team will continue working on the device, including seeking further clinical validation.

"Eventually, this technology could be deployable in your primary care provider's office," she said. "So just as you go in for an annual physical and give an annual blood draw, you could do a breath test as well. Then the primary care provider could make recommendations to the patient if the indicators are elevated, such as a follow-up referral."

Other UT Dallas contributors to the paper include first author Dr. Anirban Paul, bioengineering research scientist; Kordel France, computer science doctoral student; and Avi Bhatia, neuroscience senior in the School of Behavioral and Brain Sciences.

Other collaborators from UT Southwestern include clinical research assistant Ruby Thapa and Dr. Rhoda Annoh Gordon, research programs manager in pulmonary and critical care medicine.

Media Contact: Jessica Good, UT Dallas, 972-883-4319, [email protected], or the Office of Media Relations, UT Dallas, (972) 883-2155, [email protected].