TY - JOUR
T1 - PATNet: Propensity-Adjusted Temporal Network for Joint Imputation and Prediction Using Binary EHRs With Observation Bias
AU - Yin, Kejing
AU - Qian, Dong
AU - Cheung, William K.
N1 - This work was supported in part by General Research Fund under Grant RGC/HKBU12201219 and Grant RGC/HKBU12202117 from the Research Grants Council of Hong Kong. Recommended for acceptance by E. Chen.
Publisher copyright:
© 2023 The Authors.
PY - 2024/6
Y1 - 2024/6
N2 - Predictive analysis of electronic health records (EHR) is a fundamental task that could provide actionable insights to help clinicians improve the efficiency and quality of care. EHR are commonly recorded in binary format and contain inevitable missing data. The nature of missingness may vary by patients, clinical features, and time, which incurs observation bias. It is essential to account for the binary missingness and observation bias or the predictive performance could be substantially compromised. In this paper, we develop a propensity-adjusted temporal network (PATNet) to conduct data imputation and predictive analysis simultaneously. PATNet contains three subnetworks: 1) an imputation subnetwork that generates the initial imputation based on historical observations, 2) a propensity subnetwork that infers the patient-, feature-, and time-dependent propensity scores, and 3) a prediction subnetwork that produces the missing-informative prediction using the propensity-adjusted imputations and the missing probabilities. To allow the propensity scores to be inferred from data, we use the expectation-maximization (EM) algorithm to learn the imputation and propensity subnetworks and incorporate a low-rank constraint via PARAFAC2 approximation. Extensive evaluation using the MIMIC-III and eICU datasets demonstrates that PATNet outperforms the state-of-the-art methods in terms of binary data imputation, disease progression modeling, and mortality prediction tasks.
AB - Predictive analysis of electronic health records (EHR) is a fundamental task that could provide actionable insights to help clinicians improve the efficiency and quality of care. EHR are commonly recorded in binary format and contain inevitable missing data. The nature of missingness may vary by patients, clinical features, and time, which incurs observation bias. It is essential to account for the binary missingness and observation bias or the predictive performance could be substantially compromised. In this paper, we develop a propensity-adjusted temporal network (PATNet) to conduct data imputation and predictive analysis simultaneously. PATNet contains three subnetworks: 1) an imputation subnetwork that generates the initial imputation based on historical observations, 2) a propensity subnetwork that infers the patient-, feature-, and time-dependent propensity scores, and 3) a prediction subnetwork that produces the missing-informative prediction using the propensity-adjusted imputations and the missing probabilities. To allow the propensity scores to be inferred from data, we use the expectation-maximization (EM) algorithm to learn the imputation and propensity subnetworks and incorporate a low-rank constraint via PARAFAC2 approximation. Extensive evaluation using the MIMIC-III and eICU datasets demonstrates that PATNet outperforms the state-of-the-art methods in terms of binary data imputation, disease progression modeling, and mortality prediction tasks.
KW - Binary data imputation
KW - Data models
KW - Diseases
KW - Medical diagnostic imaging
KW - Predictive analytics
KW - Predictive models
KW - Task analysis
KW - Time series analysis
KW - clinical risk prediction
KW - disease progression modeling
KW - electronic health records
KW - missing at random
KW - missing data
KW - propensity score
UR - http://www.scopus.com/inward/record.url?scp=85174831911&partnerID=8YFLogxK
U2 - 10.1109/TKDE.2023.3321738
DO - 10.1109/TKDE.2023.3321738
M3 - Journal article
SN - 1041-4347
VL - 36
SP - 2600
EP - 2613
JO - IEEE Transactions on Knowledge and Data Engineering
JF - IEEE Transactions on Knowledge and Data Engineering
IS - 6
ER -