TY - JOUR
T1 - Medical concept embedding of real-valued electronic health records with application to inflammatory bowel disease
AU - Mann, Hanan
AU - Bar Hillel, Aharon
AU - Lev-Tzion, Raffi
AU - Greenfeld, Shira
AU - Kariv, Revital
AU - Lederman, Natan
AU - Matz, Eran
AU - Dotan, Iris
AU - Turner, Dan
AU - Lerner, Boaz
N1 - Publisher Copyright:
© 2023 Elsevier B.V.
PY - 2023/11/1
Y1 - 2023/11/1
N2 - Deep learning approaches are gradually being applied to electronic health record (EHR) data, but they fail to incorporate medical diagnosis codes and real-valued laboratory tests into a single input sequence for temporal modeling. Therefore, the modeling misses the existing medical interrelations among codes and lab test results that should be exploited to promote early disease detection. To find connections between past diagnoses, represented by medical codes, and real-valued laboratory tests, in order to exploit the full potential of the EHR in medical diagnosis, we present a novel method to embed the two sources of data into a recurrent neural network. Experimenting with a database of Crohn's disease (CD), a type of inflammatory bowel disease, patients and their controls (~1:2.2), we show that the introduction of lab test results improves the network's predictive performance more than the introduction of past diagnoses but also, surprisingly, more than when both are combined. In addition, using bootstrapping, we generalize the analysis of the imbalanced database to a medical condition that simulates real-life prevalence of a high-risk CD group of first-degree relatives with results that make our embedding method ready to screen this group in the population.
AB - Deep learning approaches are gradually being applied to electronic health record (EHR) data, but they fail to incorporate medical diagnosis codes and real-valued laboratory tests into a single input sequence for temporal modeling. Therefore, the modeling misses the existing medical interrelations among codes and lab test results that should be exploited to promote early disease detection. To find connections between past diagnoses, represented by medical codes, and real-valued laboratory tests, in order to exploit the full potential of the EHR in medical diagnosis, we present a novel method to embed the two sources of data into a recurrent neural network. Experimenting with a database of Crohn's disease (CD), a type of inflammatory bowel disease, patients and their controls (~1:2.2), we show that the introduction of lab test results improves the network's predictive performance more than the introduction of past diagnoses but also, surprisingly, more than when both are combined. In addition, using bootstrapping, we generalize the analysis of the imbalanced database to a medical condition that simulates real-life prevalence of a high-risk CD group of first-degree relatives with results that make our embedding method ready to screen this group in the population.
KW - Crohn's disease
KW - Electronic health record (EHR)
KW - Embedding
KW - Gated recurrent unit (GRU)
KW - Lab test result
KW - Medical concept
UR - http://www.scopus.com/inward/record.url?scp=85173282459&partnerID=8YFLogxK
U2 - 10.1016/j.artmed.2023.102684
DO - 10.1016/j.artmed.2023.102684
M3 - Article
C2 - 37925213
AN - SCOPUS:85173282459
SN - 0933-3657
VL - 145
JO - Artificial Intelligence in Medicine
JF - Artificial Intelligence in Medicine
M1 - 102684
ER -