Article

Temporal disease trajectories condensed from population-wide registry data covering 6.2 million patients

Nature Communications (Impact Factor: 11.47). 06/2014; 5:4022. DOI: 10.1038/ncomms5022
Source: PubMed

ABSTRACT

A key prerequisite for precision medicine is the estimation of disease progression from the current patient state. Disease correlations and temporal disease progression (trajectories) have mainly been analysed with focus on a small number of diseases or using large-scale approaches without time consideration, exceeding a few years. So far, no large-scale studies have focused on defining a comprehensive set of disease trajectories. Here we present a discovery-driven analysis of temporal disease progression patterns using data from an electronic health registry covering the whole population of Denmark. We use the entire spectrum of diseases and convert 14.9 years of registry data on 6.2 million patients into 1,171 significant trajectories. We group these into patterns centred on a small number of key diagnoses such as chronic obstructive pulmonary disease (COPD) and gout, which are central to disease progression and hence important to diagnose early to mitigate the risk of adverse outcomes. We suggest such trajectory analyses may be useful for predicting and preventing future diseases of individual patients.

Download full-text

Full-text

Available from: Anders Boeck Jensen, Mar 15, 2015
  • Source
    • "Thus its predictive power is very limited. Capturing disease progression has been of great interest [10,14], and much effort has been spent on Markov models [8,22]. However, healthcare is inherently non-Markovian due to the long-term dependencies. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Personalized predictive medicine necessitates modeling of patient illness and care processes, which inherently have long-term temporal dependencies. Healthcare observations, recorded in electronic medical records, are episodic and irregular in time. We introduce DeepCare, a deep dynamic neural network that reads medical records and predicts future medical outcomes. At the data level, DeepCare models patient health state trajectories with explicit memory of illness. Built on Long Short-Term Memory (LSTM), DeepCare introduces time parameterizations to handle irregular timing by moderating the forgetting and consolidation of illness memory. DeepCare also incorporates medical interventions that change the course of illness and shape future medical risk. Moving up to the health state level, historical and present health states are then aggregated through multiscale temporal pooling, before passing through a neural network that estimates future outcomes. We demonstrate the efficacy of DeepCare for disease progression modeling and readmission prediction in diabetes, a chronic disease with large economic burden. The results show improved modeling and risk prediction accuracy.
    Full-text · Conference Paper · Apr 2016
  • Source
    • "Existing work that handles such irregularities includes interval-based extraction [4], but this method is rather coarse and does not explicitly model the illness dynamics. Capturing disease progression has been of great interest [27, 28], and much effort has been spent on Markov models [7, 29] and dynamic Bayesian networks [30]. However, healthcare is inherently non-Markovian due to the long-term dependencies. "
    [Show description] [Hide description]
    DESCRIPTION: Personalized predictive medicine necessitates the modeling of patient illness and care processes, which inherently have long-term temporal dependencies. Healthcare observations, recorded in electronic medical records, are episodic and irregular in time. We introduce DeepCare, an end-to-end deep dynamic neural network that reads medical records, stores previous illness history, infers current illness states and predicts future medical outcomes. At the data level, DeepCare represents care episodes as vectors in space, models patient health state trajectories through explicit memory of historical records. Built on Long Short-Term Memory (LSTM), DeepCare introduces time parameterizations to handle irregular timed events by moderating the forgetting and consolidation of memory cells. DeepCare also incorporates medical interventions that change the course of illness and shape future medical risk. Moving up to the health state level, historical and present health states are then aggregated through multiscale temporal pooling, before passing through a neural network that estimates future outcomes. We demonstrate the efficacy of DeepCare for disease progression modeling, intervention recommendation, and future risk prediction. On two important cohorts with heavy social and economic burden -- diabetes and mental health -- the results show improved modeling and risk prediction accuracy.
    Full-text · Research · Feb 2016
  • Source
    • "It is difficult to find the trajectory of conditions that may be correlated. Research has been carried out on predicting incidence [2] [3] [4] [5] and progression trajectories [6] [7] from EHR data. However, EHR datasets are usually limited to one medical site or network and have limited coverage of population and time period. "
    [Show abstract] [Hide abstract]
    ABSTRACT: In the U.S., 80% of Medicare spending is for managing patients with multiple coexisting conditions. Predicting potentially correlated diseases for an individual patient and correlated disease progression paths are both important research tasks. For example, obese patients are at an increased risk for developing type-2 diabetes and hypertension. This correlation is called comorbidity relationship. Discovering the comorbidity relationships is complex and difficult due to the limited access to Electronic Health Records by privacy laws. In this paper, we present a framework called Social Data-based Prediction of Incidence and Trajectory to predict potential risks for medical conditions as well as its progression trajectory to identify the comorbidity path. The framework utilizes patients’ publicly available social media data and presents a collaborative prediction model to predict the ranked list of potential comorbidity incidences, and a trajectory prediction model to reveal different paths of condition progression. The experimental results show that our framework is able to predict future conditions for online patients with a coverage value of 48% and 75% for a top-20 and a top-100 ranked list, respectively. For risk trajectory prediction, our framework is able to reveal each potential progression trajectory between any two conditions and infer the confidence of the future trajectory, given any observed condition. The predicted trajectories are validated with existing comorbidity relations from the medical literature.
    Full-text · Conference Paper · Nov 2015
Show more