PARAMO: A PARAllel predictive MOdeling platform for healthcare analytic research using electronic health records

Abstract

Objective Healthcare analytics research increasingly involves the construction of predictive models for disease targets across varying patient cohorts using electronic health records (EHRs). To facilitate this process, it is critical to support a pipeline of tasks: 1) cohort construction, 2) feature construction, 3) cross-validation, 4) feature selection, and 5) classification. To develop an appropriate model, it is necessary to compare and refine models derived from a diversity of cohorts, patient-specific features, and statistical frameworks. The goal of this work is to develop and evaluate a predictive modeling platform that can be used to simplify and expedite this process for health data. Methods To support this goal, we developed a PARAllel predictive MOdeling (PARAMO) platform which 1) constructs a dependency graph of tasks from specifications of predictive modeling pipelines, 2) schedules the tasks in a topological ordering of the graph, and 3) executes those tasks in parallel. We implemented this platform using Map-Reduce to enable independent tasks to run in parallel in a cluster computing environment. Different task scheduling preferences are also supported. Results We assess the performance of PARAMO on various workloads using three datasets derived from the EHR systems in place at Geisinger Health System and Vanderbilt University Medical Center and an anonymous longitudinal claims database. We demonstrate significant gains in computational efficiency against a standard approach. In particular, PARAMO can build 800 different models on a 300,000 patient data set in 3 hours in parallel compared to 9 days if running sequentially. Conclusion This work demonstrates that an efficient parallel predictive modeling platform can be developed for EHR data. This platform can facilitate large-scale modeling endeavors and speed-up the research workflow and reuse of health information. This platform is only a first step and provides the foundation for our ultimate goal of building analytic pipelines that are specialized for health data researchers.

ScaDiPaSi: An Effective Scalable and Distributable MapReduce-Based Method to Find Patient Similarity on Huge Healthcare Networks

“…PARAMO [38] is a method which uses MapReduce to develop a predictive modeling platform in the healthcare analytics domain. Some methods used LSH [42] (Locality-Sensitive Hashing) for finding similarities [33].…”

“…One of the methods which can be used for scalable and distributable solutions for big data is MapReduce [31]. MapReduce is used to solve healthcare problems [2,38,40]. But MapReduce and other distributable solutions have problems such as data locality, network bottlenecks, hardware inefficiency etc.…”

Technical Challenges for Big Data in Biomedicine and Health: Data Sources, Infrastructure, and Analytics

“…Many research have started using such infrastructure in various biomedical applications such as bioinformatics and genomic analysis [10], image informatics [11], and clinical informatics [12,13]. In particular, researchers can consider moving large research datasets into NOSQL paradigm instead managing traditional file system on a single machine.…”

“…Similar to Oozie, Cascading is another popular high-level abstraction on Hadoop that handles dependency among tasks. For example, the PARAMO system [20] provides a scalable system for computing a large number of clinical predictive modeling pipelines using electronic health records, which can be implemented in either Oozie or Cascading. Pig is a high-level data processing tool that also runs on top of Hadoop.…”

Research on the Modern Intelligent Healthcare Platform from the Perspectives of Grid based Cloud Computing and Information Management System Assisted Internet of Things Technology

“…Mobile computing technology refers to the mobile terminal through wireless communications and other mobile terminal information interaction or fixed computing devices have a purpose. Mobile computing to the far of moving objects detection and early warning and support the rapid transmission of data, for the medical staff of first aid to win time [8][9][10][11][12][13][14][15]. (4) The Internet of things technology.…”