TY - JOUR
T1 - Early Detection of Post-Surgical Complications using Time-series Electronic Health Records
AU - Chen, David
AU - Jiang, Jun
AU - Fu, Sunyang
AU - Demuth, Gabriel
AU - Liu, Sijia
AU - Schaeferle, Gavin M.
AU - Wilson, Patrick M.
AU - Habermann, Elizabeth
AU - Larson, David W.
AU - Storlie, Curtis
AU - Liu, Hongfang
N1 - Publisher Copyright:
©2021 AMIA - All rights reserved.
PY - 2021
Y1 - 2021
N2 - Models predicting health complications are increasingly attempting to reflect the temporally changing nature of patient status. However, both the practice of medicine and electronic health records (EHR) have yet to provide a true longitudinal representation of a patient's medical history as relevant data is often asynchronous and highly missing. To match the stringent requirements of many static time models, time-series data has to be truncated, and missing values in samples have to be filled heuristically. However, these data preprocessing procedures may unconsciously misinterpret real-world data, and eventually lead into failure in practice. In this work, we proposed an augmented gated recurrent unit (GRU), which formulate both missingness and timeline signals into GRU cells. Real patient data of post-operative bleeding (POB) after Colon and Rectal Surgery (CRS) was collected from Mayo Clinic EHR system to evaluate the effectiveness of proposed model. Conventional models were also trained with imputed dataset, in which event missingness or asynchronicity were approximated. The performance of proposed model surpassed current state-of-the-art methods in this POB detection task, indicating our model could be more eligible to handle EHR datasets.
AB - Models predicting health complications are increasingly attempting to reflect the temporally changing nature of patient status. However, both the practice of medicine and electronic health records (EHR) have yet to provide a true longitudinal representation of a patient's medical history as relevant data is often asynchronous and highly missing. To match the stringent requirements of many static time models, time-series data has to be truncated, and missing values in samples have to be filled heuristically. However, these data preprocessing procedures may unconsciously misinterpret real-world data, and eventually lead into failure in practice. In this work, we proposed an augmented gated recurrent unit (GRU), which formulate both missingness and timeline signals into GRU cells. Real patient data of post-operative bleeding (POB) after Colon and Rectal Surgery (CRS) was collected from Mayo Clinic EHR system to evaluate the effectiveness of proposed model. Conventional models were also trained with imputed dataset, in which event missingness or asynchronicity were approximated. The performance of proposed model surpassed current state-of-the-art methods in this POB detection task, indicating our model could be more eligible to handle EHR datasets.
UR - http://www.scopus.com/inward/record.url?scp=85115279214&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85115279214&partnerID=8YFLogxK
M3 - Article
C2 - 34457129
AN - SCOPUS:85115279214
SN - 1559-4076
VL - 2021
SP - 152
EP - 160
JO - AMIA ... Annual Symposium proceedings. AMIA Symposium
JF - AMIA ... Annual Symposium proceedings. AMIA Symposium
ER -