Nagur Shareef Shaik, Ph.D.

Applied Scientist · Multimodal Medical AI & Agentic Systems

Machine Learning Engineer II
AI Center of Excellence (AI CoE), UST Global Inc.
Ph.D. in Computer Science
Georgia State University

I build medical AI that holds up on messy, incomplete patient data. My Ph.D. research at Georgia State targets what breaks multimodal models in practice: missing modalities, imbalanced classes, and predictions that ignore how a patient changes over time. At UST, I'm a Machine Learning Engineer II in the AI Center of Excellence, leading a 21-person team that ships agentic and RAG systems across healthcare, retail and finance.

At a glance

Citation metrics: Google Scholar, Nov 2026. Paper count includes workshops.

Published at

  • IEEE MLSP
  • AAAI
  • IEEE EMBC
  • Machine Vision and Applications
  • IEEE ICASSP
  • IEEE ISBI
  • NeurIPS (GenAI4Health)
  • IEEE ICIP
  • Image and Vision Computing
  • Applied Intelligence
  • J. Ambient Intelligence & Humanized Computing
  • Signal, Image and Video Processing
  • IJPRAI
  • Computers in Biology and Medicine
  • Electronics (MDPI)

Research program

Ph.D. dissertation, Georgia State University. Defended November 16, 2026 · Ph.D. conferral December 2026.

Reading a medical image involves five judgments: locating a finding, grading it, weighing it against clinical context, comparing it with earlier studies, and committing to a claim. This dissertation builds methods for each stage on two ideas: every stage carries a distribution rather than a point estimate, and evidence from different sources is represented separately so that losing one source does not corrupt the others. It is evaluated across endoscopy, whole-slide histology, retinal photography, brain MRI with genomics, and chest radiography.

About the dissertation

Selected publications

Recent papers presented orally at peer-reviewed venues.

C²A: Coupling Spatial Evidence with Clinical Priors via Co-occurrence Aware Class Attention for Multi-Label Chest X-Ray Classification

Gogineni, Akash; Shaik, Nagur Shareef; Mandava, Aasrith; Masood, Adnan; Ye, Dong Hye

Proceedings of the 36th IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2026), 2026

All publications

Selected projects

Systems built outside the dissertation, most of them open source.

AURA

Feb 2026

Multi-agent healthcare ecosystem where a master intent router hands off to specialist agents (diagnosis, CBT wellbeing, triage, nutrition, visualization), including IRIS, a Vision Transformer that predicts systemic risk from a mobile retinal image, and COMPASS, an Agentic RAG insurance guide. Benchmarked on mBRSET, MIMIC-CXR, DeepEyeNet and ROCO.

Stack: Python · FastAPI · React/TypeScript · Vision Transformers · Gemini · ChromaDB

AxisSQL

Aug 2026

Controlled study of inference-time scaling for Text-to-SQL: varies five scaling knobs of a multi-stage pipeline and measures where extra compute turns into execution accuracy. Developed in a research collaboration with Professor Tatsunori Hashimoto's group at Stanford; listed on the official BIRD-SQL leaderboard at 76.86% test execution accuracy.

Stack: Python · LLMs · Text-to-SQL · BIRD · Inference-time scaling

InsightRx

Sep 2026

Retinal screening and HCP collaboration workspace on a DINOv2-L/LoRA ensemble (0.980 patient-level AUROC for referable DR on 247 held-out mBRSET patients), with quality-gated two-eye assessment, attention maps, clinician-signed referrals, and traceable links to guideline therapy, protein targets and drug evidence.

Stack: DINOv2-L · LoRA · FastAPI · ONNX

All projects

News

  1. Nov 2026SC-CoMoE and Oculo-MoE submitted to IEEE ISBI 2027.
  2. Nov 2026Dist-RRG and Evidence That Can Contradict (ICLR 2027), STRIDE (AAAI 2027) and DELTA (CVPR 2027) under review.
  3. Nov 2026Successfully defended my Ph.D. dissertation, “From Perception to Clinical Reasoning,” at Georgia State University on November 16, 2026. Thank you to my advisor Dr. Dong Hye Ye and my committee, Dr. Vince D. Calhoun, Dr. Hemanth D. Venkateswara, Dr. Mario M. Kubek and Dr. Adnan Masood. The full dissertation is now available on the Research page.
  4. Aug 2026Attended the 2nd Agentic AI Summit at Berkeley RDI.
  5. Aug 2026Two oral papers at IEEE MLSP 2026: C²A and saliency-guided sparse expert routing.