Pairwise-Ranking based Collaborative Recurrent Neural Networks for Clinical Event Prediction

Abstract

Patient Electronic Health Records (EHR) data consist of sequences of patient visits over time. Sequential prediction of patients' future clinical events (e.g., diagnoses) from their historical EHR data is a core research task and motives a series of predictive models including deep learning. The existing research mainly adopts a classification framework, which treats the observed and unobserved events as positive and negative classes. However, this may not be true in real clinical setting considering the high rate of missed diagnoses and human errors. In this paper, we propose to formulate the clinical event prediction problem as an events recommendation problem. An end-to-end pairwise-ranking based collaborative recurrent neural networks (PacRNN) is proposed to solve it, which firstly embeds patient clinical contexts with attention RNN, then uses Bayesian Personalized Ranking (BPR) regularized by disease co-occurrence to rank probabilities of patient-specific diseases, as well as use point process to provide simultaneous prediction of the occurring time of these diagnoses. Experimental results on two real world EHR datasets demonstrate the robust performance, interpretability, and efficacy of PacRNN.

Event Prediction in Big Data Era: A Systematic Survey

“…Not every event prediction method necessarily focuses on predicting all three domains of time, location, and semantics simultaneously, but may instead predict any part of them. For example, when predicting a clinical event such as the recurrence of disease in a patient, the event location might not always be meaningful [167], but when predicting outbreaks of seasonal flu, the semantic meaning is already known and the focus is the location and time [27] and when predicting political events, sometimes the location, time, and semantics (e.g., event type, participant population type, and event scale) are all necessary [171]. Moreover, due to the intrinsic nature of time, location, and semantic data, the prediction techniques and evaluation metrics of them are necessarily different, as described in the following.…”

“…Point Processes. As they allow more flexibility in fitting true event time distributions, point process methods [167,219] are widely leveraged and have demonstrated their effectiveness for continuous time event prediction tasks. They require a conditional intensity function, defined as follows:…”

Event Prediction in Big Data Era: A Systematic Survey

“…Unlike retrospective analyses such as event summarization and detection [38], event prediction focuses on anticipating events in the future and is the focus of this survey. Accurate anticipation of future events enables one to maximize the benefits and minimize the losses associated with some event in the future, bringing huge benefits for both society as a whole and individual members of society in key domains such as disease prevention [167], disaster management [140], business intelligence [226], and economics stability [24].…”

Attentive Dual Embedding for Understanding Medical Concepts in Electronic Health Records

“…In EHR dataset, there are many complicated co-occurrence relationship among medical concepts that includes much richer information than tree-based taxonomy. Therefore, the code derived from EHR data will provide more information for further healthcare analytics, for example, diagnoses prediction [1], [22], [25], predicting inpatient mortality [9] and length of stay after admission [9]. The EHR data is used to be a multi-level structure including three layers: patient, visit and medical concept.…”

“…The Fig. 1 shows an example segment of one patient journey EHR [5], [25] in EHRs, and each visit has a set of medical concepts, e.g. International Classification of Diseases (ICD).…”