Nav: Home

Artificial intelligence cuts lung cancer screening false positives

March 12, 2019

PITTSBURGH, March 12, 2019 - Lung cancer is the leading cause of cancer deaths worldwide. Screening is key for early detection and increased survival, but the current method has a 96 percent false positive rate. Using machine learning, researchers at the University of Pittsburgh and UPMC Hillman Cancer Center have found a way to substantially reduce false positives without missing a single case of cancer.

The study was published today in the journal Thorax. This is the first time artificial intelligence has been applied to the question of sorting out benign from cancerous nodules in lung cancer screening.

"We were able to rule out cancer in about a third of patients, so they wouldn't need biopsies, they wouldn't need PET scans or a short-interval CT scan. They just need to come back in a year," said senior author David Wilson, M.D., M.P.H., associate professor of medicine, cardiothoracic surgery and clinical and translational science at Pitt and co-director of the Lung Cancer Center at UPMC Hillman.

A low-dose CT scan is the standard diagnostic test for lung cancer for those at high risk. Nationwide, about a quarter of these scans turn up shadows indicating nodules in the lung - a positive result - but fewer than 4 percent of those patients actually have cancer.

Right now, it's impossible to know from the scan alone who those 4 percent are, Wilson said. Of course, physicians don't want to miss any real cases of cancer, but they're also trying to reduce the false positive rate, he noted.

"A positive test creates anxiety, increases health care costs, and the follow-up tests are not risk free," said study coauthor Panayiotis (Takis) Benos, Ph.D., professor and vice chair of computational and systems biology and associate director of the Integrative Systems Biology Program at Pitt. "For the 96 percent of people who have benign nodules, these procedures are unnecessary. So, we try to mine the data to tell which are benign and which are malignant."

Wilson, Benos and colleagues gathered low-dose CT scan data from 218 high-risk UPMC patients who were later confirmed to have either lung cancer or benign nodules. Then they fed the data into a machine learning algorithm - a form of artificial intelligence - to create a model that calculates the probability of cancer. If the probability falls below a certain threshold, the model rules out cancer.

Comparing the model's assessment against the actual diagnoses of these patients, the researchers found that they would have been able to save 30 percent of the people with benign nodules from undergoing additional testing, without missing a single case of cancer.

The three factors that were most important to the model, Benos said, are the number of blood vessels surrounding the nodule, the number of nodules and the number of years since the patient quit smoking.

"While it has been known for some time that tumors recruit more vascular support, this is the first time that we've been able to use computer technology to quantify their contribution and incorporate them into a predictive model that decides, with certainty, that some patients don't have cancer," Wilson said. "The next step is to evaluate this technique in a larger population, and actually it's started already, using about 6,000 scans from the National Lung Screening Trial."
-end-
Additional authors on the study include Vineet Raghu, Wei Zhao, M.D., Ph.D., Jiantao Pu, Ph.D., Joseph Leader, Ph.D., Jian-Min Yuan, M.D., Ph.D., of Pitt; James Herman, M.D., and Renwei Wang, M.D., of UPMC Hillman.

This work was supported by the National Institutes of Health (U01HL137159, R01LM012087), particularly the National Cancer Institute (P50CA90440, P30CA047904, R21CA197493 and T32CA082084).

To read this release online or share it, visit http://www.upmc.com/media/news/031219-lung-ca-machine-learning [when embargo lifts].

About the University of Pittsburgh Schools of the Health Sciences

The University of Pittsburgh Schools of the Health Sciences include the schools of Medicine, Nursing, Dental Medicine, Pharmacy, Health and Rehabilitation Sciences and the Graduate School of Public Health. The schools serve as the academic partner to the UPMC (University of Pittsburgh Medical Center). Together, their combined mission is to train tomorrow's health care specialists and biomedical scientists, engage in groundbreaking research that will advance understanding of the causes and treatments of disease and participate in the delivery of outstanding patient care. Since 1998, Pitt and its affiliated university faculty have ranked among the top 10 educational institutions in grant support from the National Institutes of Health. For additional information about the Schools of the Health Sciences, please visit http://www.health.pitt.edu.

About UPMC

A $19 billion world-renowned health care provider and insurer, Pittsburgh-based UPMC is inventing new models of patient-centered, cost-effective, accountable care. UPMC provides more than $900 million a year in benefits to its communities, including more care to the region's most vulnerable citizens than any other health care institution. The largest nongovernmental employer in Pennsylvania, UPMC integrates 87,000 employees, 40 hospitals, 700 doctors' offices and outpatient sites, and a 3.5 million-member Insurance Services Division, the largest medical insurer in western Pennsylvania. As UPMC works in close collaboration with the University of Pittsburgh Schools of the Health Sciences, U.S. News & World Report consistently ranks UPMC Presbyterian Shadyside on its annual Honor Roll of America's Best Hospitals. UPMC Enterprises functions as the innovation and commercialization arm of UPMC, and UPMC International provides hands-on health care and management services with partners around the world. For more information, go to UPMC.com.

http://www.upmc.com/media

Contact: Erin Hare
Office: 412-864-7194
Mobile: 412-738-1097
E-mail: HareE@upmc.edu

Contact: Madison Brunner
Office: 412-578-9193
Mobile: 412-432-8390
E-mail: BrunnerM@upmc.edu

University of Pittsburgh

Related Lung Cancer Articles:

Cancer-sniffing dogs 97% accurate in identifying lung cancer, according to study in JAOA
The next step will be to further fractionate the samples based on chemical and physical properties, presenting them back to the dogs until the specific biomarkers for each cancer are identified.
Lung transplant patients face elevated lung cancer risk
In an American Journal of Transplantation study, lung cancer risk was increased after lung transplantation, especially in the native (non-transplanted) lung of single lung transplant recipients.
Proposed cancer treatment may boost lung cancer stem cells, study warns
Epigenetic therapies -- targeting enzymes that alter what genes are turned on or off in a cell -- are of growing interest in the cancer field as a way of making a cancer less aggressive or less malignant.
Are you at risk for lung cancer?
This question isn't only for people who've smoked a lot.
Better equipped in the fight against lung cancer
Lung cancer is the third most common type of cancer in Germany and the disease affects both men and women.
New liquid biopsy-based cancer model reveals data on deadly lung cancer
Small cell lung cancer (SCLC) accounts for 14 percent of all lung cancers and is often rapidly resistant to chemotherapy resulting in poor clinical outcomes.
Cancer drug leads to 'drastic decrease' in HIV infection in lung cancer patient
Doctors in France have found the first evidence that a cancer drug may be able to eradicate HIV-infected cells in humans.
Air pollution is associated with cancer mortality beyond lung cancer
A large scale epidemiological study associates some air pollutants with kidney, bladder and colorectal cancer death.
Free lung-cancer screening in the Augusta area finds more than double the cancer rate of previous screenings
The first year of free lung cancer screening in the Augusta, Ga., area found more than double the rate seen in a previous large, national study as well as a Massachusetts-based screening for this No.
Lung cancer may go undetected in kidney cancer patients
Could lung cancer be hiding in kidney cancer patients? Researchers with the Harold C.
More Lung Cancer News and Lung Cancer Current Events

Top Science Podcasts

We have hand picked the top science podcasts of 2019.
Now Playing: TED Radio Hour

In & Out Of Love
We think of love as a mysterious, unknowable force. Something that happens to us. But what if we could control it? This hour, TED speakers on whether we can decide to fall in — and out of — love. Guests include writer Mandy Len Catron, biological anthropologist Helen Fisher, musician Dessa, One Love CEO Katie Hood, and psychologist Guy Winch.
Now Playing: Science for the People

#543 Give a Nerd a Gift
Yup, you guessed it... it's Science for the People's annual holiday episode that helps you figure out what sciency books and gifts to get that special nerd on your list. Or maybe you're looking to build up your reading list for the holiday break and a geeky Christmas sweater to wear to an upcoming party. Returning are pop-science power-readers John Dupuis and Joanne Manaster to dish on the best science books they read this past year. And Rachelle Saunders and Bethany Brookshire squee in delight over some truly delightful science-themed non-book objects for those whose bookshelves are already full. Since...
Now Playing: Radiolab

An Announcement from Radiolab