Md Saiful Islam

Computer Science PhD Candidate University of Rochester

Google PhD Fellow Health Research, 2023–2026

Assistant Professor (on study leave), Department of CSE, BUET

I build machine learning and large language models to advance accessible healthcare -- focusing on digital biomarker extraction, video-based remote assessment, and LLM-driven clinical triage. Beyond research and teaching, I enjoy reading, traveling, and playing table tennis.


Full list of publications: Google Scholar

  • Digital Biomarkers
  • Remote Assessment
  • AI Assisted Clinical Triage
  • Multimodal ML
  • Human Computer Interaction

Latest News

  • Best paper nomination (AI in Healthcare)
    Sep 2025 — Our paper "Beyond Accuracy: Enhancing Parkinson's Diagnosis with Uncertainty Quantification of Machine Learning Models" was nominated for the best paper award in the International Conference on AI in Healthcare.

Research

Automated Video Analysis for Movement Disorder Screening and Progression Tracking

Tags: video analysis, digital biomarkers, Parkinson's disease, movement disorder, health AI, automated screening, progression tracking

Over 900,000 people in the U.S. live with Parkinson's disease, yet many -- especially those over 65 -- struggle to access neurologists for diagnosis and monitoring. PARK (Parkinson's Analysis with Remote Kinetic-tasks) offers an accessible telemedicine solution. Using only a webcam, it guides users through motor, speech, and facial tasks and analyzes performance with AI. Through various studies, we show that PARK can screen for PD and track symptom severity with accuracy comparable to expert neurologists. Try a live demo here.

Physiological Sensing and Digital Biomarkers

Tags: ballistocardiogram (BCG), photoplethysmography (PPG), heart rate monitoring, blood pressure, cardiac output, earbud sensors

I completed two internships with the Digital Health Team at Samsung Research America, where I developed algorithms for heart-rate and non-invasive blood pressure monitoring using next-generation earbuds with IMU and PPG sensors. My contributions included analyzing BCG signals, building machine learning models for automated signal quality assessment, integrating these models into downstream applications, and designing study protocols for data collection and validation.

Publications: CHI 2025; ICASSP 2025

NLP for Sustainability

Tags: Sustainability, environment, eco-friendly shopping, knowledge graph

As first author, I developed KnowUREnvironment, a large-scale knowledge graph on climate change and environmental issues, automatically extracting over 210K domain-specific concepts and 411K relationships from scientific literature to support tasks like information retrieval, QA, and recommendation. I also designed SEER (Sustainable E-commerce with Environmental-impact Rating), a concept for E-commerce platforms that displays products' environmental impact. In a user study, SEER significantly increased eco-friendly purchasing behavior and achieved high usability scores, showing its potential to reduce carbon emissions from online shopping.

Bangla Natural Language Processing

Tags: language model, bangla, text summarization

I co-developed XL-Sum, a large-scale multilingual summarization dataset with 1M article-summary pairs across 44 languages, including Bangla, enabling state-of-the-art results for low-resource summarization. I also helped create BanglaBERT, the first Bangla-specific BERT model, along with new benchmarks and datasets, establishing strong performance across multiple language understanding tasks.

Influential Community Search in Social Networks

Tags: influential community search, social networks, keyword similarity, academic graph

I introduced KICQ (Keyword-aware Influential Community Query), a framework for finding influential communities in large attributed graphs. KICQ combines semantic keyword matching with a novel influence measure that accounts for both cohesiveness and dominance, enabling more intuitive and effective community search. We further designed efficient algorithms to scale this approach and validated its performance through experiments and case studies.

Continuous Cardiovascular Monitoring

Tags: atrial fibrillation, PPG, cardiovascular monitoring, bayesian deep learning

The work explored the use of smartwatches and fitness trackers for real-time cardiovascular monitoring, with a focus on Atrial Fibrillation (AF) detection from noisy photoplethysmography (PPG) signals. Our team developed BayesBeat, a Bayesian deep learning model that not only improves AF risk prediction but also provides uncertainty estimates. BayesBeat outperforms existing methods while being 40-200x more parameter-efficient, making it practical for deployment on resource-constrained wearable devices. As a collaborator, I played a key role in preparing and presenting the grant proposal that secured 1.5 million BDT funding from the ICT Division, Bangladesh for this project.

Publications: IMWUT 2022

Automated Detection of NoSQL Injection

Collaborators: Anindya Iqbal, Rifat Shahriyar
Tags: NoSQL injection, database security, automatic detection, machine learning, supervised learning

We developed the first supervised learning-based tool for detecting NoSQL injections, supported by a novel training dataset that I specifically designed for this task. The tool achieved a 0.93 F2-score through cross-validation and outperformed the existing solution (Sqreen) by 36% in detection rate. It is also database-agnostic, demonstrating consistent performance across MongoDB and CouchDB.

Publications: COMPSAC 2019

Teaching Experiences

Role: Graduate Teaching Assistant

University of Rochester, New York, United States

Fall 2021


  • CSC280/480 Computer Models and Limitations
  • Course Instructor: Eustrat Zhupa

Spring 2022



Fall 2022


  • CSC 281 Introduction to Cryptography
  • Course Instructor: Eustrat Zhupa
August 2021 - December 2022

Role: Assistant Professor

Bangladesh University of Engineering and Technology (BUET), Bangladesh

January 2020


November 2020 - January 2021

Role: Lecturer

Bangladesh University of Engineering and Technology (BUET), Bangladesh

January 2019



July 2018



January 2018



July 2017



January 2017


February 2017 - November 2020

Role: AI Trainer

Hiperdyne Corporation, Japan

Theoretical and hands-on expertise on traditional machine learning and deep learning with Python.
November 2018 - March 2019

Awards & Honors

  • Best Engineering Poster, Graduate Research Day 2025, University of Rochester
  • Invited "Trainee" Speaker, NINDS Udall Centers Meeting, 2023
  • Google PhD Fellowship (Health Research), 2023
  • Travel grant to attend the Conference on Health, Inference and Learning (CHIL), 2023
  • University Merit Scholarship (8 times)
  • Dean's List Scholarship (4 times)
  • Champion in "Crowdsourcing information for city roads improvement" category in BRACathon 2015.
  • External judge of the ICPC Asia Kolkata-Kanpur Onsite Regional Contest 2018.
  • Supervisor of Bangladesh site, Asia-Pacific Informatics Olympiad.
  • Chief Judge, Bangladesh Olympiad in Informatics 2018.

Other Projects

Result Processing for Online College Admission System of Bangladesh

Tools : JAVA, Oracle

Result processing of about 1.5 million applicants for admission into 7,447 colleges of Bangladesh. This was a government-funded project to automate the entire higher secondary admission system. I designed and implemented the core algorithms for result processing using JAVA and Oracle database.

Project code is confidential and a property of Bangladesh Education Board.

Bangladesh e-Government Enterprise Resource Planning

A government-funded project for the office automation of ICT Division and Planning Commission of the Peoples' Republic of Bangladesh. I actively contributed as a technical consultant toward designing and developing the "meeting and event management" and "accounting" modules.

Project code is confidential.

Spatial Event Organizer

Tools : PHP, Google Map API, Android

There are multiple customers and multiple workers in a system. A customer can order something online, then a worker needs to go to the task location from his current location, pick the order, then deliver this to the home address of the customer. Google map API was used to estimate the duration of such travels. The spatial organizer distributes tasks among the employees so that the throughput is nearly optimal and all the employees are fairly loaded. The project was an android application of which, I designed and implemented the back-end algorithms in PHP.

Project code is available here.

Fix My Street

Tools : PHP, Codeigniter Framework, MySQL

An android application developed for Dhaka City Corporation. The citizens can report road and transportation-related issues to authority using this app. This project was initially developed for BRACathon 2015, a software development contest. After being the champion, this project was funded by BRAC. I designed and implemented the back-end using the PHP Codeigniter framework.

Project code is available here.

Fantasy Cricket

Tools : PHP, MySQL

Fantasy cricket is a game where a user forms a virtual team consisting of the players from the real game and receives points based on the performance of those players in the actual game. I designed the database and implemented the back-end using the PHP Codeigniter framework.

Project code is available here.

Resume/CV

Click here to download.


Miscellaneous

I am an avid reader and I love to collect quotes. Here are some of my favorites.