Nick Ma
Data Scientist, Cerner Intelligence
Actions
Nick Ma received a PhD from the University of Kansas in 2019 in Mathematics. His doctoral research was in stochastic analysis and stochastic PDEs. Since 2019, he has worked as a Data Scientist in Cerner Intelligence developing clinical and operations models.
Leveraging data, UX design, and scalable web tech to rapidly deploy the CV-19 Resurgence Risk Index
As COVID-19 cases were flattening, stakeholders within Cerner and at client facilities needed accurate and up to date estimations of COVID-19 growth in local metro areas. With existing models generally only providing state-level information, and with the need to take into account constantly shifting institutional and individual social distancing behavior, the process of building the Cerner COVID-19 Resurgence Risk Index (CCRI) model included navigating challenges not only in data and machine learning, but also in UX design and deployment.
In this talk, we discuss the story of how statistical and machine learning methods, UX design, scalable web hosting, and cloud computing platforms were used to rapidly prototype and deploy the CCRI model in weeks instead of months. The resulting model is leveraged across Cerner as part of Cerner’s COVID-19 “Recover” phase, including the COVID-19 Client Readiness Lights on Network Dashboard and the Real Time Health System Command Center Dashboard.
Using NLP Methods to Embed ICD-10 Diagnosis Codes
Traditional methods of processing diagnosis codes involve using CCS categories or one-hot encoding. We explore using NLP methods such as Word2Vec, FastText, and GloVe to create broadly applicable embeddings from diagnosis codes to real-valued vectors. We will also use UMAP to demonstrate how the embedding groups similar diagnoses together without any manual intervention, and explore the weird world of ICD-10 codes.
Maintenance of machine learning models often faces challenges from changing codesets, and we explore using existing embeddings on new codesets even with little data in the new codeset by using an auto-trained transformation.
Nick Ma
Data Scientist, Cerner Intelligence
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top