Skip to main content

Arpit Mathur

Ph.D. student at CMU

As a Ph.D. student at Carnegie Mellon University's Human-Computer Interaction Institute, I design and build human-centered AI systems for high-stakes domains, like healthcare. My work sits at the intersection of Human-AI Collaboration, Data Visualization, and Applied Machine Learning, with a strong emphasis on turning research ideas into working, usable tools.

I build end-to-end prototypes that help people reason with complex AI outputs, bridge expertise gaps between experts and non-experts, and support real decision-making. Across my projects, I work hands-on across the stack, from interaction design and front-end systems to model integration and evaluation with real users.

Before my Ph.D., I got my B.Des from the Indian Institute of Technology, Guwahati and earned an M.S. in HCI from the Georgia Institute of Technology. Through these experiences, I developed a strong foundation in applied HCI and systems thinking. I’ve also worked as a UX Designer at MathWorks, improving Model-Based Systems Engineering workflows for MATLAB and Simulink, which shaped how I think about designing tools for technical, expert users at scale.

Outside of academia, I enjoy video game design and development. You can find some of my Gamejam Submissions here. I love playing and watching football, and I'm an avid Arsenal fan.

• projects

PHORA: AI-CDSS for PAH project thumbnail

PHORA: AI-CDSS for PAH

An interactive clinical decision-support system that helps clinicians and patients collaboratively reason about AI-based survival predictions in Pulmonary Arterial Hypertension.

Clini-Compare: Interactive Patient Similarity for Clinical Decision Support project thumbnail

Clini-Compare: Interactive Patient Similarity for Clinical Decision Support

An interactive visualization tool that helps physicians reason about complex cases by comparing semantically similar patients using unstructured radiology notes. Designed to support clinical sensemaking, trust, and decision-making.

Text-to-CT Scan Generative AI project thumbnail

Text-to-CT Scan Generative AI

A system that integrates a text-to-CT scan generative AI model into a medical imaging interface. The system lets radiologists prompt a text-guided model to generate synthetic 3D CT scans and interact with outputs in context.

Design Cost Estimation: Visualizing Cost Metrics for MATLAB Projects project thumbnail

Design Cost Estimation: Visualizing Cost Metrics for MATLAB Projects

Profiling is a way to measure the time it takes to run your code and identify where MATLAB® spends the most time. After you identify which functions are consuming the most time, you can evaluate them for possible performance improvements.

TranscriptExplorer: A Dashboard for Interaction Analysis project thumbnail

TranscriptExplorer: A Dashboard for Interaction Analysis

A dashboard to amplify, not automate, transcription in qualitative research. Users can interactively visualize one video dataset in four different ways using contemporary interactive visualization techniques.

Visualizing Quantum Physics project thumbnail

Visualizing Quantum Physics

Interactive web based visualizations as course material for EC 3040 Semiconductor Devices. 4 interactive chapters were used by 100 students enrolled in EC 3040 over the fall semester 2020, to facilitate remote learning.

AGGIE: Tracking Hate Speech Online during the Myanmar General Elections 2020 project thumbnail

AGGIE: Tracking Hate Speech Online during the Myanmar General Elections 2020

A tool for tracking and classification of problematic posts related to the Myanmar General Elections 2020, using Tableau. The tool was used by 16 trackers in Myanmar and helped in the identification of over 20,000 problematic posts.

• publications

AIES 2025

A Human-Centered Approach to Identifying Promises, Risks, & Challenges of Text-to-Image Generative AI in Radiology

Katelyn Morrison, Arpit Mathur, Aidan Bradshaw, Tom Wartmann, Steven Lundi, Afrooz Zandifar, Weichang Dai, Kayhan Batmanghelich, Motahhare Eslami, Adam Perer

CHI 2025

Exploratory Visual Analysis of Transcripts for Interaction Analysis in Human-Computer Interaction

Ben Rydal Shapiro, Rogers Hall, Arpit Mathur, Edwin Zhao

CHI 2025 (WORKSHOP)

Clini-Compare: An Interactive Patient-Similarity Visualization Tool for Clinical Decision Support

Arpit Mathur, Adam Perer

Arxiv

Texture: Structured Exploration of Text Datasets

Will Epperson, Arpit Mathur, Adam Perer, Dominik Moritz

MIDL 2025

Toward Interpretable 3D Diffusion in Radiology: Token-Wise Attribution for Text-to-CT Synthesis

Aidan Bradshaw, Katelyn Morrison, Arpit Mathur, Weicheng Dai, Motahhare Eslami, Kayhan Batmanghelich, Adam Perer

ICLS 2024

Turn charts for interaction analysis: Visually mapping the conversation floor

Benjamin R. Shapiro, Rogers Hall, Arpit Mathur, Edwin Zhao

ICLS 2022

Interactive Transcription Techniques for Interaction Analysis

Arpit Mathur, Benjamin R. Shapiro

HCII 2021

A Study of Motivation, Preferences, and Pain Points Regarding Participation in Career Related Mentorship

Arpit Mathur, Carrie Bruce

ICoRD 2021

Development and Evaluation of Usability Heuristics for Voice User Interfaces

Lokesh Fulfagar, Anupriya Gupta, Arpit Mathur, Abhishek Shrivastava

INTERACT 2019

A Study of Outbound Automated Call Preferences for DOTS Adherence in Rural India.

Arpit Mathur, Shimmila Bhowmick, Keyur Sorathia

• experience

Carnegie Mellon University

Aug 24 - Present

Doctoral Research Assistant

Conducting research at the intersection of Human-Computer Interaction, Machine Learning, Healthcare, and Human-AI Collaboration, focusing on developing innovative solutions in healthcare using advanced data visualization techniques.

The MathWorks, Inc.

Jun 21 - Jun 24

UX Designer

Supporting multiple MATLAB and Simulink products, including MATLAB fixed-point workflows, Simulink Studio, and System Composer. Responsibilities include collaborative design events, wireframing, iterative prototyping and high-fidelity visual design.

Georgia Institute of Technology

Jan 20 - Jul 20

Graduate Research Assistant

Worked with the School of Electrical Engineering, to create course Material for EC 3040 Semiconductor Devices. Created interactive web based visualizations as course materials using D3.js and P5.js.

Aug 20 - May 21

Graduate Teaching Assistant

Served as a Teaching Assistant for CS 4460 Introduction to Information Visualization over Fall 2020 and Spring 2020. Major responsibilities included lecturing, grading, and assisting undergradute students with d3.js and Tableau.

SAS Research and Development

May 18 - Jul 18

UX Design Intern

Redesigned the SAS Analytics Credit Scoring Tool. Conducted Contextual Interviews with Risk Analysts in Indian banks, and used those insights to create high-fidelity sketch mockups.

Get in touch!