Skip to content
View lshpaner's full-sized avatar
😁
😁

Highlights

  • Pro

Organizations

@MSADS-Capstone

Block or report lshpaner

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.

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
lshpaner/README.md

Hi, I'm Leon Shpaner

Data Scientist at UCLA Health | Adjunct Instructor at UCLA Extension and University of San Diego | Co-founder of Data Science Dynamics

I build clinical machine learning systems across nephrology, oncology NLP, and urology, and develop open-source tools for reproducible data science.


Open-source libraries

Library Description
eda_toolkit Reproducible EDA framework; docs at datasciencedynamics.com/eda_toolkit_docs
model_tuner Streamlined ML model tuning and cross-validation
model_metrics ROC, DeLong tests, gain/lift, and residual diagnostics
EquiBoots Bootstrapped fairness and equity evaluation
kfre Kidney Failure Risk Equation implementation

Selected work

  • CircumScore: ML-based surgical outcome prediction tool; paper published in BMC Urology

Talks and publications

  • JupyterCon 2025: eda_toolkit and EquiBoots (co-presented with Oscar Gil)
  • Bio-IT World 2026, Boston
  • CHOC Research GoBEYOND 2026: reproducible EDA frameworks poster
  • Late-breaking abstract, JASN / Kidney Week 2025

Links

datasciencedynamics.com | LinkedIn | Google Scholar


Pinned Loading

  1. kfre kfre Public

    A Python library for kidney failure risk estimation using Tangri's KFRE model

    Python 5

  2. uclamii/model_tuner uclamii/model_tuner Public

    A library to tune the hyperparameters of common ML models. Supports calibration and custom pipelines.

    Python 8

  3. data_science_for_everyone data_science_for_everyone Public

    HTML 1

  4. datasciencedynamics/eda_toolkit datasciencedynamics/eda_toolkit Public

    A collection of utility functions designed to streamline your exploratory data analysis (EDA) tasks. This repository offers tools for directory management, some data preprocessing, reporting, visua…

    Python 9 1

  5. circ_milan circ_milan Public

    Machine-learning pipeline for the development and internal validation of postoperative complication prediction models in adult male circumcision, using de-identified single-center clinical data fro…

    Python

  6. litecoin-foundation/litecoin_forecasting litecoin-foundation/litecoin_forecasting Public

    Jupyter Notebook