MS Biostatistician β’ Co-authored Healthcare Research β’ R, Python, SAS, SQL
Hello, I'm
I develop ILP/MIP optimization models for healthcare scheduling, codify clinical policies into reproducible constraints, and apply machine learning to broader research problems with measurable impact.
Open to: Biostatistician Β· Statistical Analyst Β· Research Data Analyst Β· Health Data Analyst
Looking to hire a Biostatistician or Statistical Analyst?
Manuscripts
Co-authored studies in the academic publication pipeline β both currently under peer review.
Authors: Sai Teja Kattiboyina, co-authored with UT Dallas faculty Β· 4-Week ILP/MIP Model Β· 10+ Operational Constraints Β· CBC Solver Β· 1% Gap Tolerance
Oct 2025 β Present
ORCID: 0009-0001-9656-0015
0
Baseline Staffing Pool
16 FT Β· 4 CQ Β· 4 PT
0
Scenarios Analyzed
5 birth volumes Β· 20 staffing combos
$0
Avg Weekly Cost
Zero shortage Β· All constraints met
0
Sensitivity Cases
Zero aggregate shortage in all cases
Problem
Labor and Delivery units face time-varying workload driven by birth timing, induction practices, and emergent obstetric events. Scheduling must satisfy shift coverage, control overtime, and distribute night/weekend shifts equitably β yet clinical policies are rarely codified in a rigorous, reproducible way that enables peer-reviewed research.
Solution
Built a 4-week ILP/MIP nurse scheduling model for a 24-nurse L&D unit (16 FT, 4 charge-qualified, 4 PT) using Python/PuLP/CBC. Workload derived from 2024 CDC/NCHS natality microdata. Implemented 10+ constraints across 5 constraint families including charge nurse coverage and a $3/hr charge-duty differential. Evaluated 100 scenarios across 5 annual birth volumes Γ 20 staffing configurations, with sensitivity analysis across 35 parameter cases.
Impact
Authors: Sai Teja Kattiboyina, co-authored with UT Dallas faculty Β· Relationship Quality Theory Β· AI Adoption Β· SEM
2026 β Present
Problem
Existing AI adoption frameworks (TAM, UTAUT) explain whether organisations start using AI β but not what happens after adoption. No published study examines whether the ongoing relationship quality between an organisation and its AI provider predicts how extensively that AI gets adopted across operations.
Approach
Applies the Crosby, Evans & Cowles (1990) relationship quality framework β trust, satisfaction, and commitment β to the novel context of organisationβAI provider partnerships. Survey-based methodology analysed with structural equation modelling (SEM).
Key Constructs
About
Healthcare-focused research collaborator bridging optimization, ML, and clinical operations.
I'm a research-driven analyst focused on applying quantitative methods to healthcare operations and scheduling. I currently collaborate with UT Dallas faculty on two co-authored manuscripts β a nurse scheduling ILP/MIP optimization study and an AI provider relationship quality & adoption study β both currently under peer review β codifying domain policies into model constraints and building reproducible data workflows.
My broader work spans applied machine learning, simulation, and operations research β from reinforcement-learning control to large-scale transit and BI systems at Samsung SDS. I bring this methodological breadth back to healthcare problems where modeling rigor, fairness, and reproducibility matter most.
π 2 co-authored manuscripts under peer review β nurse scheduling ILP/MIP model Β· AI provider relationship quality & adoption.
Master of Science in Business Analytics & Artificial Intelligence
The University of Texas at Dallas β’ Dallas, TX
Awarded May 23, 2026
Bachelor of Technology in Electronics & Communication
IIIT Nagpur β’ India
Graduated 2022
M.S. Business Analytics & Artificial Intelligence
The University of Texas at Dallas β’ Dallas, TX
Aug 2024 β May 2026
Key Coursework
Notable Project
Levi Strauss & Co. β $50M strategic investment recommendation (Analytics Practicum capstone).
B.Tech Electronics & Communication Engineering
Indian Institute of Information Technology, Nagpur β’ Nagpur, India
Aug 2018 β Jun 2022
Field
Electronics & Communication Engineering
Achievement
Selected for Samsung SDS internship directly from campus.
Foundation
Programming, data structures, algorithmic problem solving.
0
Manuscripts Under Review
Co-authored with UT Dallas faculty
0K+
Federal Records Analyzed
NCES/IPEDS big data pipeline
0
Research Datasets (IPEDS/NCES)
Joined via institutional + CIP codes
0%
Faster Reporting at Samsung SDS
BI dashboard automation
Toolbox
A breadth of tools across analytics, ML, and operations research. Hover any skill to see how it was applied.
R
Proficient1+ yr experience
Statistical analysis, visualization, mixed-effects & panel models
Applied in: Hospital Operating Margins panel analysis Β· MS Coursework: Statistical Modeling
Python
Expert1.5 yrs experience
Data analysis, ML, automation, ILP/MIP optimization
Applied in: Healthcare Scheduling Research (ILP/MIP) Β· Brain Tumor Detection project
Machine Learning
Advanced1+ yr experience
Predictive models, classification, healthcare AI
Applied in: AI-provider relationship manuscript Β· Brain Tumor Detection project
SQL
Expert1.5 yrs experience
Schema design, complex joins, ETL
Applied in: NCES/IPEDS federal analytics Β· Samsung SDS β BI Developer role
SAS
ProficientFoundational experience
Statistical analysis, clinical & health data
Applied in: MS Coursework: Statistical Programming
Prompt Engineering
Advanced2026 experience
LLM prompting, chain-of-thought, evaluation, model limits
Applied in: AI-provider relationship manuscript Β· Clinical literature synthesis
Responsible AI
Proficient2026 experience
AI governance, risk, capability & limitation assessment
Applied in: AI-provider relationship manuscript
Credentials
Foundational training supporting work in healthcare analytics, clinical data, and operations research.
Anthropic
AI Fluency: Framework & Foundations
Date: 2026
Detail: Certificate of Completion
Credential: CERT-26001
Anthropic
AI Fluency: AI Capabilities & Limitations
Date: 2026
Detail: Certificate of Completion
Credential: CERT-26002
University of Cape Town
Understanding Clinical Research: Behind the Statistics
Date: 2026
Detail: Coursera Certificate
Credential: CERT-26003
Johns Hopkins Medicine
Data and Electronic Health Records
Date: 2026
Detail: Coursera Certificate
Credential: CERT-26004
UT Dallas β Naveen Jindal School of Management
Graduate Certificate in Business Decision Analytics
Date: 2026
Detail: Awarded May 23, 2026 Β· Digitally certified
Credential: CERT-26005
Work
Selected statistical, ML, and data engineering work across healthcare, education, and enterprise BI.
Built a 29,670-record hospital-year panel from raw CMS Medicare Cost Reports and modeled ruralβurban margin differences using mixed-effects models, GEE, and logistic mixed models in R.
Big data pipeline analyzing federal U.S. Department of Education datasets to quantify the relationship between online distance enrollment and program completion outcomes across 5,824 institutions.
Key Tools
Processed 307,707+ federal administrative records across 3 official NCES/IPEDS datasets
View on GitHubHealthcare AI project applying R-based preprocessing and segmentation workflows to identify tumor regions in brain MRI scans.
Key Tools
Processed 500+ MRI scans through a fully reproducible segmentation pipeline
View on GitHubReal-time BI dashboards connecting 16+ data sources for Samsung SDS, processing 1M+ records daily.
Key Tools
30% faster reporting efficiency
View on GitHubMachine learning model to predict loan defaults for the Small Business Administration loan program.
Key Tools
AUCPR of 0.472 achieved on imbalanced loan data
View on GitHubSwipe β β Β· 1 of 5
Built a 29,670-record hospital-year panel from raw CMS Medicare Cost Reports and modeled ruralβurban margin differences using mixed-effects models, GEE, and logistic mixed models in R.
Big data pipeline analyzing federal U.S. Department of Education datasets to quantify the relationship between online distance enrollment and program completion outcomes across 5,824 institutions.
Key Tools
Processed 307,707+ federal administrative records across 3 official NCES/IPEDS datasets
View on GitHubHealthcare AI project applying R-based preprocessing and segmentation workflows to identify tumor regions in brain MRI scans.
Key Tools
Processed 500+ MRI scans through a fully reproducible segmentation pipeline
View on GitHubReal-time BI dashboards connecting 16+ data sources for Samsung SDS, processing 1M+ records daily.
Key Tools
30% faster reporting efficiency
View on GitHubMachine learning model to predict loan defaults for the Small Business Administration loan program.
Key Tools
AUCPR of 0.472 achieved on imbalanced loan data
View on GitHubJourney
Click any role to expand the full bullet points.
Feb 2022
Samsung SDS Intern
Jul 2022
BI Developer β SAMS
Oct 2025
Healthcare Research β UT Dallas
May 2026
MS Graduating β Available
Value
Three reasons I am ready to contribute on day one.
2 co-authored manuscripts under peer review with UT Dallas faculty β a nurse scheduling ILP/MIP optimization study and an AI provider relationship quality & adoption study.
2 Manuscripts Under ReviewNearly 2 years of BI development experience at Samsung SDS including internship, delivering SQL pipelines, QlikView data models, ETL workflows, and KPI dashboards on the Sales Analytics Management System (SAMS).
SAMSUNG SDS22 months total experience
MS graduating May 2026 Β· F-1 OPT from July 2026 Β· Open to relocation.
Contact
Open to full-time Healthcare Research and Biostatistician roles in healthcare scheduling, informatics, and clinical analytics.
Mohan Venkata Pavan Sai Teja Kattiboyina
MS Business Analytics & AI Β· Healthcare Research
mvpk240054@gmail.com
Location
Dallas, TX
saitejakmvp
GitHub
SaiTejaPortfolioDS
ORCID
0009-0001-9656-0015
Follow
Follow on LinkedIn for research updates
Authorized to work in the U.S. starting July 2026, with up to 3 years of eligibility under F-1 STEM OPT β no immediate sponsorship required.
The fastest ways to reach me or learn more about my work.
