Skip to content
View tat1a's full-sized avatar

Block or report tat1a

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
tat1a/README.md

Tatia Tsiklauri, MD

Physician-researcher building reproducible clinical and healthcare data analytics projects with Python, SQL, and Power BI.

My work focuses on clinical data quality, surgical outcomes, EHR-style cohort logic, public-health survey analysis, postmarket surveillance, and responsible interpretation of healthcare data.

Selected Clinical Analytics Portfolio

Project Data / Domain What it demonstrates
Metabolic Surgery Eligibility and Cardiometabolic Risk Analytics Public-use NHANES 2017-March 2020 data Survey-weighted cohort phenotyping, cardiometabolic risk engineering, missing-data sensitivity analysis, SQL validation, and Power BI
Breast Implant Postmarket Safety Analysis FDA MAUDE medical-device reports, 2020-2025 Python pipeline, data cleaning, complication taxonomy, reporting-pattern analysis, Power BI dashboard, 59 automated tests
EHR Readmission and Care Quality Analytics Synthetic EHR-style inpatient encounters EHR table modeling, index admission logic, 30-day readmission outcome, care-quality documentation checks, SQL validation, Power BI semantic model
Synthetic Surgical Outcomes Registry Synthetic surgical outcomes registry Data model design, validation logic, SQLite reconciliation, aggregate operational analytics

Technical Toolkit

Python · pandas · SQL · SQLite · Power BI · DAX · Power Query · Git · GitHub Actions

Clinical Analytics Focus

  • Cohort construction and denominator logic
  • Survey-weighted population-health analysis
  • EHR-style data modeling across patients, encounters, diagnoses, observations, and medications
  • Surgical outcomes and registry-style analytics
  • Healthcare data-quality checks and reconciliation
  • Dashboard-ready semantic models and KPI reporting
  • Transparent limitations for synthetic and observational data

Working Principles

  • Reproducible pipelines over one-off analysis
  • Explicit validation before visualization
  • Clear data dictionaries and methods documentation
  • Responsible interpretation without overstating clinical meaning
  • Portfolio work that can be defended in technical and clinical interviews

Current Direction

I am developing a clinical analytics portfolio focused on healthcare data, surgical outcomes, EHR workflows, and research-ready reporting. The goal is to combine medical training with practical data skills for clinical research, quality improvement, and healthcare analytics roles.

Connect

LinkedIn

Pinned Loading

  1. breast-implant-safety-analysis breast-implant-safety-analysis Public

    Reproducible Python and Power BI analysis of 237,194 FDA MAUDE breast implant reports, with validated quality controls and responsible postmarket interpretation.

    Python

  2. ehr-readmission-quality-analytics ehr-readmission-quality-analytics Public

    EHR-style readmission and care-quality analytics project with Python, SQL, validation tests, and Power BI

    Python

  3. synthetic-surgical-outcomes-registry synthetic-surgical-outcomes-registry Public

    Reproducible synthetic clinical registry: data model, validation, query reconciliation, and aggregate operational dashboard.

    Python

  4. nhanes-metabolic-surgery-risk-analytics nhanes-metabolic-surgery-risk-analytics Public

    Survey-weighted NHANES analysis of guideline-like metabolic surgery eligibility, cardiometabolic risk, and equity patterns using Python, SQL, and Power BI.

    Python