Health Life

An AI can determine your 12-year lung cancer risk by looking at a chest X-ray

Credit: Pixabay/CC0 Public Domain

A deep learning model—a form of artificial intelligence (AI)—was more accurate than the current clinical standard at predicting a person’s 12-year risk of developing lung cancer. The model’s predictions are based on chest radiograph images (CXRs) and basic demographic data (age, sex, and current smoking status) commonly available in electronic health records (EHRs). The findings are published in Annals of Internal Medicine.

Lung cancer screening with chest computed tomography (CT) scans can prevent death. However, Medicare’s current standard to determine who is eligible for cancer screening CT misses most lung cancers. Furthermore, lung cancer screening participation is poor, with an estimated less than 5 percent of screening-eligible persons being screened.

Researchers from Massachusetts General Hospital developed a convolutional neural network (CXR-LC) that predicts long-term incident lung cancer based on a chest X-ray image using 41,856 people from a large multicenter trial of lung cancer screening with chest X-rays (Prostate, Lung, Colorectal, and Ovarian (PLCO) cancer screening trial). The final model was validated in 5,615 additional PLCO participants and 5,493 persons from a second trial, the National Lung Screening Trial (NLST). The performed better than the Medicare lung cancer screening criteria, the current clinical standard, missing 31 percent fewer lung cancers while screening the same number of people.

The author of an accompanying editorial from the National Cancer Institute discusses the researchers’ findings and raises a number of issues associated with the use of AI and, more generally, data mining of EHRs to improve patient care.


Current lung cancer public health screening guidelines under count African Americans


More information:
Michael T. Lu et al. Deep Learning Using Chest Radiographs to Identify High-Risk Smokers for Lung Cancer Screening Computed Tomography: Development and Validation of a Prediction Model, Annals of Internal Medicine
Health article

If You Have Pets | COVID-19

Coronaviruses are a large family of viruses. Some coronaviruses cause cold-like illnesses in people, while others cause illness in certain types of animals, such as cattle, camels, and bats. Some coronaviruses, such as canine and feline coronaviruses, infect only animals and do not infect humans.

Risk of people spreading the virus that causes COVID-19 to pets

We are still learning about the virus that causes COVID-19, but it appears that it can spread from people to animals in some situations. A small number of pets worldwide, including cats and dogs, have been reportedexternal icon to be infected with the virus that causes COVID-19, mostly after close contact with people with COVID-19.

Infected pets might get sick or they might not have any symptoms. Of the pets that have gotten sick, most only had mild illness and fully recovered.

What to do if you own pets

Until we learn more about how this virus affects animals, treat pets as you would other human family members to protect them from a possible infection.

Because there is a risk that people with COVID-19 could spread the virus to animals, CDC recommends that pet owners limit their pet’s interaction with people outside their household.

  • Keep cats indoors when possible and do not let them roam freely outside.
  • Walk dogs on a leash at least 6 feet (2 meters) away from others.
  • Avoid public places where a large number of people gather.
  • Do not put a mask on pets. Masks could harm your pet.

There is no evidence that the virus can spread to people from the skin, fur, or hair of pets. Do not wipe or bathe your pet with chemical disinfectants, alcohol, hydrogen peroxide, or any other products not approved for animal use.

Talk to your veterinarian if your pet gets sick