With the help of AI, an inexpensive test found in many doctors’ offices may soon be used to screen for hidden structural heart disease. 

Living near Coldwater Creek—a Missouri River tributary north of St. Louis that was polluted by nuclear waste from the development of the first atomic bomb—in childhood in the 1940s, ’50s, and ’60s was associated with an elevated risk of cancer, according to a new study led by Harvard T.H. Chan School of Public Health. The researchers say the findings corroborate health concerns long held by community members.

The development, which enables researchers to see how neuron-specific waves travel through the brains of mice in real time, led to the discovery of three types of brain waves that move in directions never previously seen. The work holds promise for understanding diseases such as epilepsy, Alzheimer’s, and Parkinson’s, as well as developing artificial intelligence.

Cells and tissues surrounding a breast cancer tumor may hold critical information about how patients will respond to treatment. After looking for patterns in images of tissue and biopsy samples, a newly developed AI tool sorted breast cancer patients patients into seven groups. Some of the groups had better survival outcomes than others, suggesting there may be information in the microenvironments that oncologists could use for prognoses. 

Developed by researchers at Oregon Health & Science University’s Knight Cancer Institute, the tool, dubbed OmicsTweezer, uses advanced machine learning techniques to analyze biological data at a scale large enough to estimate the composition of cell types in a sample of tissue that may be taken from a biopsy. This process allows scientists to map the cellular makeup of tumors and surrounding tissues — an area known as the tumor microenvironment.