Philadelphia, Pennsylvania, United States
Contact Info
463 followers
458 connections
About
Activity
-
One year ago today, I quit my law firm job to find a better, happier career. 🎉 I knew I needed to find a new path, one that didn’t require my job…
One year ago today, I quit my law firm job to find a better, happier career. 🎉 I knew I needed to find a new path, one that didn’t require my job…
Liked by Lev Zadvinskiy
-
We’re excited to welcome 101 summer associates from across 10 of our offices joining us in Chicago today for our Summer Kickoff Program! We look…
We’re excited to welcome 101 summer associates from across 10 of our offices joining us in Chicago today for our Summer Kickoff Program! We look…
Liked by Lev Zadvinskiy
Experience & Education
Licenses & Certifications
Publications
-
Using abrupt change detection to categorize glucose variability of Type 1 diabetes patients
IEEE
According to the American Diabetes Association, Type 1 diabetes affects approximately three million Americans. This disease is characterized by an inability to regulate blood glucose, caused by diminished function of the pancreas to produce insulin. One current method of monitoring blood glucose is through continuous glucose monitoring, which measures patients' blood glucose levels at regular five-minute intervals via a skin patch sensor. Patients have an increased risk of mortality caused by…
According to the American Diabetes Association, Type 1 diabetes affects approximately three million Americans. This disease is characterized by an inability to regulate blood glucose, caused by diminished function of the pancreas to produce insulin. One current method of monitoring blood glucose is through continuous glucose monitoring, which measures patients' blood glucose levels at regular five-minute intervals via a skin patch sensor. Patients have an increased risk of mortality caused by dipping into the hypoglycemic (<; 70 mg/dL) range, so careful accurate monitoring is critical to the well-being of Type 1 diabetes patients. Analysis of the continuous glucose monitoring signal can be challenging, as it is difficult to separate behavioral changes from purely physiological changes in the signal. In this study, individual patients' glucose variability was analyzed based on features created from the signal including glycemic state, risk index calculations, and blood glucose rate of change. Primarily the signal was analyzed for any abrupt changes in the variability following an inpatient glycemic trial designed to test the patient's physiological response to insulin. Results show that a known change-point caused by an inpatient study could be identified in 7 out of 15 patients. This is important as glucose variability is reflective of a patient's physiological state, and an understanding of changes in glucose variability can lead to increased ability to maintain optimal euglycemic levels.
Courses
-
Actuarial Mathematics II
MATH 442
-
Applied Time Series Analysis
MATH 447
-
Data Mining
SYS 6018
-
Data Visualization
SARC 5400
-
Financial Statement Analysis
FIN 403
-
Linear Models for Data Science
STAT 6021
-
Machine Learning
SYS 6016
-
Options and Futures Markets
FIN 430
-
Regression Analysis
MATH 344
-
Reinforcement Learning
SYS 6582
-
Statistical Computing for Data Science
STAT 6430
-
Stochastic Processes
MATH 477
-
Stochastic Simulation
MATH 448
Projects
-
Presidential Approval Ratings Based on Twitter
-
Created a framework for approval rating calculations based on sentiment analysis of word embeddings from Word2Vec model using Twitter data collected via AWS EC2 and RDS instances
-
Using abrupt change detection to categorize glucose variability of Type 1 diabetes patients (Capstone Project)
-
- Managed a team of data science students and lead client negotiations with the Center for Diabetes Technology, at University of Virginia Hospital
- Applied Relative Unconstrained Least-Squares Importance Fitting algorithm for abrupt change detection in continuous glucose monitor data to boost glucose variability classification accuracy in patients with type I diabetes
Other creatorsSee project -
Florida Real Estate Pricing
-
Developed Naïve Bayes and Random Forest models to classify fairness of residential housing market in Florida based on Department of Revenue and Census data
Honors & Awards
-
Outstanding Performer Award 2013
TD Bank
An award given to the most valuable partner within service team at TD Bank.
Test Scores
-
SOA/CAS Exam FM/2
Score: Pass
-
SOA/CAS Exam P/1
Score: Pass
Languages
-
English
Full professional proficiency
-
Russian
Native or bilingual proficiency
More activity by Lev
-
Major personal news: Today was my last day of practicing law! A week from Monday, I'll start as a Legal Engineer at Ironclad, the leading digital…
Major personal news: Today was my last day of practicing law! A week from Monday, I'll start as a Legal Engineer at Ironclad, the leading digital…
Liked by Lev Zadvinskiy
-
I stand with Ukraine 🇺🇦 against Putin's unprovoked invasion.
I stand with Ukraine 🇺🇦 against Putin's unprovoked invasion.
Liked by Lev Zadvinskiy
-
There is no data science hype -- only poor application and execution of data science and data strategy. I've been doing this for over 10 years in…
There is no data science hype -- only poor application and execution of data science and data strategy. I've been doing this for over 10 years in…
Liked by Lev Zadvinskiy
-
Wahoowa to the Hoos of U.S. Soccer, and congratulations to the World Cup champions! 🏆https://lnkd.in/eix9A83
Wahoowa to the Hoos of U.S. Soccer, and congratulations to the World Cup champions! 🏆https://lnkd.in/eix9A83
Liked by Lev Zadvinskiy
-
Historic. President Jim Ryan’s announcement of the establishment of the nation’s first School of Data Science, thanks to the incredible vision and…
Historic. President Jim Ryan’s announcement of the establishment of the nation’s first School of Data Science, thanks to the incredible vision and…
Liked by Lev Zadvinskiy
-
An historic day at UVa today. So proud to be faculty with this growing department!
An historic day at UVa today. So proud to be faculty with this growing department!
Liked by Lev Zadvinskiy
-
Had a great time “trekking” around NYC last week with this amazing crew of MS in Data Science students. We visited 8 companies in two days, and…
Had a great time “trekking” around NYC last week with this amazing crew of MS in Data Science students. We visited 8 companies in two days, and…
Liked by Lev Zadvinskiy
-
How to get started with Apache Spark for Data Science? If you follow me you know I'm a Spark lover. For me it was an inspiration to go into the…
How to get started with Apache Spark for Data Science? If you follow me you know I'm a Spark lover. For me it was an inspiration to go into the…
Liked by Lev Zadvinskiy
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More