Please join us on Friday, April 3, 2026, from 12:30 to 1:30 p.m. for the in-person ISP Forum in SENSQ 5317.  We will be featuring two ISP students, Fengyi Gao & Nya Feinstein.

Fengyi Gao’s Presentation Information

Title: Explainable Contrastive Learning for KL Grading Classification in Knee Osteoarthritis

Abstract: Kellgren-Lawrence (KL) grading prediction plays an important role in the assessment of knee osteoarthritis (OA), aiding in early diagnosis and monitoring. This study aims to develop and validate an effective and explainable AI framework for automated KL grading using only plain knee radiographs. The proposed AI-powered framework combines a contrastive learning strategy with Grad-CAM++ visualization, thus offering enhanced feature representation along with AI model explainability. Experimental results indicate that the proposed model achieves promising classification accuracy. Furthermore, the explainability analysis, with domain experts involved, confirms that the AI model focuses on clinically relevant regions, aligning with domain-specific knowledge in orthopedics.

Bio: Fengyi Gao is a first-year PhD student in the Intelligent Systems Program. She is a researcher affiliated with the HexAI Research Laboratory and the Computational Pathology & AI Center of Excellence (CPACE). Her research focuses on advancing artificial intelligence to address real-world medical and scientific problems, with an emphasis on developing and validating data mining and machine learning models using structured and unstructured clinical data to support clinical decision-making and improve patient care.

Nya Feinstein’s Presentation Information

Title: Credibility as a Societal Construct: Cross-National Patterns of Information Perception in Public Discourse

Abstract: When presented with new information, media consumers assess its trustworthiness through prior knowledge and reasoning processes rooted in both personal and societal variables. In the context of social media, cues of credibility are easily obscured by platforms’ role in providing space for expression of both facts and opinions. This research examines how the same pieces of information can be perceived differently across cultural, linguistic, and socio-political contexts on social media. Using data from X (formerly Twitter) and methods of topic extraction, epistemic frame classification, and temporal analysis, credibility assessment variation is shown across diverse contexts. Future steps include implementation of a user study to clarify specific interpretations of information credibility. Overall, understanding how reactions to information intersect with cultural, societal, and political factors reveals how systemic differences shape accepted plausibility independently of factual accuracy.

Bio: Nya Feinstein is a first-year PhD student in Intelligent Systems at the University of Pittsburgh working within the Pitt Computational Social Dynamics Lab and advised by Prof. Yu-Ru Lin. With a focus on multilingual and international analysis, her research centers around how networks of communication reveal narratives which impact, shape, and explain socio-political landscapes and relations.