Interpretable and Federated Tensor Factorization for Computational Phenotyping

Abstract

Phenotyping based on machine learning has been proposed to facilitate extraction of meaningful phenotypes automatically from electronic health records (EHRs) without human supervision through a process called computational phenotyping. Phenotyping by nonnegative tensor factorization (NTF) is becoming particularly popular due to its ability to capture high dimensional EHRs data. In this study, we developed a supervised NTF that derives discriminative and distinct phenotypes. We represented co-occurrence of diagnoses and prescriptions in EHRs as a third-order tensor, and decomposed it using the CP algorithm. We evaluated discriminative power of our models with an Intensive Care Unit database (MIMIC-III) and demonstrated superior performance than state-of-the-art ICU mortality calculators (e.g., APACHE II, SAPS II). Example of the resulted phenotypes are sepsis with acute kidney injury, cardiac surgery, anemia, respiratory failure, heart failure, cardiac arrest, metastatic cancer (requiring ICU), end-stage dementia (requiring ICU and transitioned to comfort-care), intraabdominal conditions, and alcohol abuse/withdrawal.

Meanwhile, these models need a large amount of diverse EHRs to avoid population bias. An open challenge is how to derive phenotypes jointly across multiple institutions, in which direct patient-level data sharing is not possible (e.g., due to institutional policies). Thus, we developed a novel solution to enable federated tensor factorization for computational phenotyping without sharing patient-level data. We developed secure data harmonization and federated computation procedures based on alternating direction method of multipliers (ADMM). Using this method, the multiple institutions iteratively update tensors and transfer secure summarized information to a central server, and the server aggregates the information to generate phenotypes. We demonstrated with real medical datasets that our method resembles the centralized training model (based on combined datasets) in terms of accuracy and phenotypes discovery while respecting privacy.