Developing a computable phenotype for glioblastoma.

Sandra YanKaitlyn MelnickXing HeTianchen LyuRachel S F MoorMegan E H StillDuane A MitchellElizabeth A ShenkmanHan WangYi Guo Jiang Bian Ashley P Ghiaseddin

Published in: Neuro-oncology (2024)

We developed and validated a CP algorithm for identifying patients with GBM using both structured and unstructured EHR data from a large tertiary care center. The final algorithm achieved an F1-score of 0.817, indicating a high performance, which minimizes possible biases from misclassification errors.

Keyphrases

tertiary care
electronic health record
machine learning
deep learning
adverse drug
big data
neural network
emergency department
data analysis