Improving health outcomes and clinical translation

I develop quantitative ways to assess health and function from physiology and behavior. My aim is to complement clinical assessment with measurements that are reproducible, interpretable, and sensitive to change within an individual.

A difference between groups does not automatically make a reliable biomarker. I ask how a measurement depends on the person, task, and recording context, and whether it adds clinically meaningful information beyond conventional assessments. I address these questions across mental health, visual function, and sensing in daily life.

In PRECOG, I investigated eye movements during cognitive and affective tasks. The study identified patterns that distinguish participants with depressive symptoms and suicidal ideation from healthy controls, connecting visual attention to responses to emotional information. [1]

I pursue related questions in pediatric ophthalmology, using fundus images and gaze measurements with clinical collaborators. This work includes detecting papilledema, characterizing atypical gaze, and quantifying visual attention in children with cerebral/cortical visual impairment. [2] [3] [4]

Moving into daily life adds another source of variation: people’s activities and surroundings change alongside their physiology. Our ambulatory study of families examined personalized learning methods for sensing mental health symptoms in everyday life. It motivates my interest in measurements that account for a person’s activities and circumstances, rather than treating physiological variation in isolation. [5]

These studies motivate my interest in moving from group-level differences toward personalized, longitudinal assessment. This means separating stable individual characteristics from changing physiological states, accounting for sleep, activity, and social context, and testing whether measurements reliably capture meaningful changes in health over repeated observations.

References

1. Deep Learning Characterizes Depression and Suicidal Ideation in Young Adults From Eye Movements

Kleanthis Avramidis, Woojae Jeong, Aditya Kommineni, Sudarsana R Kadiri, Marcus Ma, Colin McDaniel, Myzelle Hughes, Thomas McGee, Elsi Kaiser, Dani Byrd, Assal Habibi, B Rael Cahn, Idan A Blank, Kristina Lerman, Takfarinas Medani, Richard M Leahy, Shrikanth Narayanan

npj Digital Medicine · 2026

Paper PDF Code

2. Automating Detection of Papilledema in Pediatric Fundus Images With Explainable Machine Learning

Kleanthis Avramidis, Mohammad Rostami, Melinda Chang, Shrikanth Narayanan

IEEE International Conference on Image Processing (ICIP) · 2022

Paper PDF Code

3. Evaluating Atypical Gaze Patterns Through Vision Models: The Case of Cortical Visual Impairment

Kleanthis Avramidis, Melinda Y Chang, Rahul Sharma, Mark S Borchert, Shrikanth Narayanan

IEEE Engineering in Medicine and Biology Society Conference (EMBC) · 2024

Paper PDF Code

4. Generative Artificial Intelligence (AI)-Enabled Saliency Analysis of Eye Tracking in Cerebral/Cortical Visual Impairment (SET-CVI)

Kate Matsunaga, Kleanthis Avramidis, Mark S Borchert, Shrikanth Narayanan, Melinda Y Chang

Ophthalmology Science · 2026

Paper

5. Developing Personalized Algorithms for Sensing Mental Health Symptoms in Daily Life

Adela C Timmons, Abdullah Aman Tutul, Kleanthis Avramidis, Jacqueline B Duong, Kayla E Carta, Sierra N Walters, Grace A Jumonville, Alyssa S Carrasco, Gabrielle F Freitag, Daniela N Romero, Matthew W Ahle, Jonathan S Comer, Shrikanth S Narayanan, Ishita P Khurd, Theodora Chaspari

npj Mental Health Research · 2025

Paper