News

​Stony Brook University has received Graduate Assistance in Areas of National Need (GAANN) fellowships for six departments: psychology, civil engineering, computer science, biomedical engineering, materials science and chemical engineering, and electrical and computer engineering. Each department offers five fellowships annually, totaling 30 graduate student fellowships per year across the university. These fellowships provide tuition scholarships, fee waivers, and stipends, amounting to $3.6 million over three years. This initiative enhances Stony Brook's capacity to attract and support graduate students in critical research areas

​A study published on Hospimedica highlights the effectiveness of artificial intelligence (AI) in detecting fractures on X-rays. The research demonstrated that AI assistance reduced missed fractures by 29% and increased diagnostic sensitivity by 16% for single fractures, and by 30% for cases involving multiple fractures. Additionally, AI improved specificity by 5% and shortened X-ray reading time by an average of 6.3 seconds per patient. The enhancements were particularly notable in detecting fractures in the shoulder, clavicle, and thoracolumbar spine regions

​Ramana Davuluri, a professor in the Department of Biomedical Informatics and Director of the Bioinformatics Shared Resource at Stony Brook Cancer Center, is leveraging artificial intelligence to enhance cancer research. His work focuses on analyzing genomic and molecular data to better understand cancer biology and improve treatment specificity. By applying machine learning algorithms to gene expression data, Davuluri aims to identify precise drug targets and predict cancer subtypes, such as glioblastoma and high-grade ovarian cancer. His research has revealed that many existing drugs may not effectively target the most relevant protein isoforms, highlighting the importance of considering genetic variability in drug development. Through these efforts, Davuluri seeks to advance personalized medicine by improving the accuracy and effectiveness of cancer therapies

​A study by Stony Brook University and the University of Pennsylvania, published in the Findings of the Association for Computational Linguistics on November 29, 2021, analyzed over three million tweets from 3,000 social bot accounts and an equal number of genuine accounts. The research estimated 17 human attributes—such as age, gender, five personality traits, eight emotions, and sentiment—for each account. While individual bots appeared human-like, their uniformity across these attributes revealed their artificial nature, suggesting a new method for detecting bots based solely on linguistic patterns.