Neural networks probe proteins

A machine learning method based on neural networks outperformed a mutational scanning model at identifying disease-causing mutations in an Alzheimer’s disease protein, suggesting the method could be useful for facilitating therapeutic design.

COVID on Twitter: town vs. country

A natural language processing analysis of 407 million tweets from May 2020 to January 2022 captures the rural-urban divide regarding COVID-19.

Machine learning aids injury prevention in cardiac cath labs

Machine learning predicts delirium

Using machine learning based on electronic health records of ICU patients predicted new-onset delirium with 82% sensitivity, Vanderbilt researchers found.

Suicide notes

Natural language processing of notes in electronic health records can identify suicidal behavior and could be used to directly improve real-time risk prediction algorithms.

Vanderbilt study uses AI to speed mpox drug trials

A machine learning algorithm developed by researchers at Vanderbilt performs as well as humans at identifying skin lesions in clinical photographs of people with monkeypox.