Research
I perform research to enhance AI in circumstances where data are limited, data are noisy, and humans are actively involved in sensitive decisions. Selected papers are grouped below by theme, and the full list is in my CV. The three main themes of my work are:
Data
Bringing data to a data-starved field
I helped build many of the most widely used datasets in clinical AI.
Read more
Models
Powerful models with limited data
I build models that learn from small, noisy data by starting from what experts already know.
Read more
Trust
Calibration and decision support
I build models that know when they are wrong, and decision support that people can act on.
Read moreFocus 1: Bringing data to a data-starved field
Open data, benchmarks, and tools for AI10 papers
-
Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments2025
-
Plant Science Knowledge Graph Corpus: A Gold Standard Entity and Relation Corpus for the Molecular Plant Sciences2024
-
The International Cardiac Arrest Research (I-CARE) Consortium Database2023
-
SPread: Automated Financial Metric Extraction and Spreading Tool from Earnings Reports2020
-
You Snooze, You Win: the PhysioNet/Computing in Cardiology Challenge2018
-
A Repository of Corpora for Summarization2018
-
An Open-Source Tool For The Automated Transcription of Paper-Spreadsheet Data2017
-
MIMIC-III, A Freely Accessible Critical Care Database2016
-
A Datathon Model to Support Cross-Disciplinary Collaboration2016
-
Management and Analysis of Biomedical Big Data with Cloud-based In-memory Database and Dynamic Querying: a Hands-on Experience with Real-world Data2014
AI that mines health records5 papers
-
Using a Data-Driven Approach to Define Post-COVID Conditions in US Electronic Health Record Data2024
-
One-year mortality after recovery from critical illness: A retrospective cohort study2018
-
How is the Doctor Feeling? ICU Provider Sentiment is Associated with Diagnostic Imaging Utilization2018
-
Management of Atrial Fibrillation with Rapid Ventricular Response in the Intensive Care Unit: A Secondary Analysis of Electronic Health Record Data2017
-
A Visualization of Evolving Clinical Sentiment Using Vector Representations of Clinical Notes2015
Focus 2: Reconciling powerful models with limited data
AI that starts from expert knowledge8 papers
-
An LSTM Feature Imitation Network for Hand Movement Recognition from sEMG Signals2025
-
GLoG-CSUnet: Enhancing Vision Transformers with Adaptable Radiomic Features for Medical Image Segmentation2025
-
Characterization of acute radiation induced vascular changes in animal model of brain tumors using time frequency analysis of DCE MRI information2025
-
Feature Imitating Networks Enhance Performance, Reliability and Speed of Deep Learning On Biomedical Image Processing Tasks2024
-
Probabilistic Nested Model Selection in Pharmacokinetic Analysis of DCE-MR Data in Animal Model of Cerebral Tumor2024
-
Radiomics Characterization of Tissues in an Animal Brain Tumor Model Imaged Using Dynamic Contrast Enhanced (DCE) MRI2023
-
Dynamic contrast enhanced (DCE) MRI estimation of vascular parameters using knowledge-based adaptive models2023
-
Feature Imitating Networks2022
AI that reads complex, noisy signals13 papers
-
Single-Channel EEG Sleep Stage Classification Using Synchrosqueezed Transform and Sequential Representation Learning2026
-
Neurophysiology State Dynamics Underlying Acute Neurological Recovery After Cardiac Arrest2023
-
Artifact Detection and Correction in EEG data: A Review2021
-
Unsupervised EEG Artifact Detection and Correction2021
-
Predicting Neurological Outcome in Comatose Patients after Cardiac Arrest with Multiscale Deep Neural Networks2021
-
Predicting Neurological Outcome from Electroencephalogram Dynamics in Comatose Patients after Cardiac Arrest with Deep Learning2021
-
EEG Channel Interpolation Using Deep Encoder-decoder Networks2020
-
Cost-effectiveness analysis of multimodal prognostication in cardiac arrest with EEG monitoring2020
-
Quantitative EEG Trends Predict Recovery in Hypoxic-Ischemic Encephalopathy2019
-
Estimating the False Positive Rate of Absent Somatosensory Evoked Potentials in Cardiac Arrest Prognostication2018
-
An Enhanced Cerebral Recovery Index2015
-
Global Optimization Approaches for Parameter Tuning in Biomedical Signal Processing: A Focus of Multi-scale Entropy2014
-
Accumulated Deep Sleep is a Powerful Predictor of LH Pulse Onset in Pubertal Children2014
AI that senses health and mood7 papers
-
Two-step Imputation and AdaBoost based Classification for Early Prediction of Sepsis on Imbalanced Clinical Data2020
-
Detecting Depression with Audio/Text Sequence Modeling of Interviews2018
-
Predicting Latent Narrative Mood using Audio and Physiologic Data2017
-
The Effects of Deep Network Topology on Mortality Prediction2016
-
Monitoring and Detecting Atrial Fibrillation using Wearable Technology2016
-
Patient Prognosis from Vital Sign Time Series: Combining Convolutional Neural Networks with a Dynamical Systems Approach2015
-
A Fast and Memory-Efficient Algorithm for Learning and Retrieval of Phenotypic Dynamics in Multivariate Cohort Time Series2014
Focus 3: Calibration, trust, and decision support
AI that knows when it is wrong5 papers
-
How Reliable are Confidence Estimators for Large Reasoning Models? A Systematic Benchmark on High-Stakes Domains2026
-
Calibrating LLM Confidence by Probing Perturbed Representation Stability2025
-
Do Explanations Improve the Quality of AI-assisted Human Decisions? An Algorithm-in-the-Loop Analysis of Factual & Counterfactual Explanations2023
-
Bayesian Networks Improve Out-of-Distribution Calibration for Agribusiness Delinquency Risk Assessment2023
-
Enhancing Credit Risk Reports Generation using LLMs: An Integration of Bayesian Networks and Labeled Guide Prompting2023
AI for high-stakes decisions8 papers
-
Distribution-Free Uncertainty Quantification in Mechanical Ventilation Treatment: A Conformal Deep Q-Learning Framework2025
-
Reinforcement Learning approach to Sedation and Delirium Management in the Intensive Care Unit2023
-
Patient-Specific Sedation Management via Deep Reinforcement Learning2021
-
Personalized Medication Dosing Using Volatile Data Streams2018
-
A Deep Deterministic Policy Gradient Approach to Medication Dosing and Surveillance in the ICU2018
-
Optimal Medication Dosing from Suboptimal Clinical Examples: A Deep Reinforcement Learning Approach2016
-
Machine Learning and Decision Support in Critical Care2016
-
A Data-Driven Approach to Optimized Medication Dosing: A Focus on Heparin2014
AI inside oncology and radiology clinics10 papers
-
Automated Stereotactic Radiosurgery Planning Using a Human-in-the-Loop Reasoning Large Language Model Agent2026
-
Hybrid Student-Teacher Large Language Model Refinement for Cancer Toxicity Symptom Extraction2025
-
Enhancing Radiology Clinical Histories Through Transformer-Based Automated Clinical Note Summarization2025
-
Integrating Natural Language Processing Into Radiation Oncology: A Practical Guide to Transformer Architecture and Large Language Models2025
-
Efficient CTCAE Grading for Post-Radiotherapy Toxicities Using Large Language Models: A Privacy-Preserving Approach Using Instruction Fine-Tuning2025
-
Advancing Post-Radiotherapy Toxicity Extraction: A Novel Privacy-Preserving, Parameter-Efficient Language Model Fine-Tuning2025
-
Iterative Prompt Refinement for Radiation Oncology Symptom Extraction Using Teacher-Student Large Language Models2024
-
Improving Automating Quality Control in Radiology: Leveraging Large Language Models to Extract Correlative Findings in Radiology and Operative Reports2024
-
A Novel Localized Student-Teacher LLM for Enhanced Toxicity Extraction in Radiation Oncology2024
-
Automation of Protocoling Advanced MSK Examinations Using Natural Language Processing Techniques2023
Trainees
Doctoral Students
-
Niloufar Eghbali Zarch2021 – Present
-
Reza Khanmohammadi2022 – Present
-
Sara Rezaeimanesh2025 – Present
Alumni13 people
-
Serena Lotreck2020 – 2024
-
Sari Saba-Sadiya2020 – 2022
-
Jeeva Bhavanandam2020 – 2024
-
Norah Alfadhli2021 – 2022
-
Shahaab Ali2024 – 2025
-
Navya Singh2022 – 2024
-
Minh Pham2022 – 2024
-
Sampan Chaudhuri2023 – 2024
-
Shangyang Min2022 – 2023
-
Anvita Gollu2022 – 2023
-
David Lingan2022
-
Abhinav Thirupathi2020 – 2022
-
Aven Zitzelberger2020 – 2021
Collaborators and Support
The organizations that have supported my research as sponsors or collaborators.
