Clinical pathway discovery from electronic health record data

Groups related to this event

Centre for Health Informatics

Event date

Tuesday, 25 October 2016

Speaker

Professor Rema Padman

Abstract

Clinical pathways translate the best available evidence to local practice workflows, reflecting patients’ co-progression of disease with treatments and related interventions in a given clinical setting. They aim to reduce variations in treatments and support clinical decision making when faced with multiple or ambiguous care options, thus improving care quality and controlling costs. However, efficient, automated methods to create actual care delivery pathways for identifying best practices and targeting practice change is limited. In this study, we propose a data-driven, practice-based, clinical pathway development process where candidate clinical pathways are discovered for Chronic Kidney Disease (CKD) using detailed demographic and treatment data on more than 1,000 patients captured in electronic health records (EHR) as part of routine outpatient care delivery. We model each patient’s multidimensional clinical records into one-dimensional sequences using novel constructs designed to capture and collate information on each visit’s purpose, procedures, medications and diagnoses. Analysis and clustering on visit sequences identify distinct types of patient subgroups. Characterizing visit sequences as Markov chains, significant transitions are extracted and visualized into clinical pathways across subgroups. Results indicate, among others, (1) common pathways within each subgroup that show typical disease progression; (2) practices that are consistent/inconsistent with CKD guidelines; and, (3) pathways that illustrate sustainable improvements in patients’ health conditions. Insights from this study may result in evidence to support patient-centered treatment approaches that empower patients to better manage their chronic health conditions. For healthcare providers and organizations, the generalizable clinical pathway learning approach may provide a mechanism for efficient medical practice review and develop innovations in care delivery models with the potential for improved care quality and future cost reductions.

Speaker profile

Rema Padman is Professor of Management Science and Healthcare Informatics in the H. John Heinz III College at Carnegie Mellon University in Pittsburgh. She is also Thrust Leader of Healthcare Informatics Research at iLab and Research Area Director for Operations and Informatics at the Center for Health Analytics at the Heinz College, Adjunct Professor in the Department of Biomedical Informatics at the University of Pittsburgh School of Medicine, and Honorary Professor in the School of Health Sciences at the University of Salford in UK. She received B.Tech. in Chemical Engineering from the Indian Institute of Technology, Kanpur, India, PhD in Operations Research from the University of Texas at Austin and National Library of Medicine Senior Fellowship in Applied Informatics from The University of Pittsburgh School of Medicine.

Professor Padman’s current research examines healthcare operations, data-driven decision support and process modeling and risk analysis in the context of clinical (using Electronic Health Record) and consumer-facing IT interventions in healthcare delivery and management such as e-health, m-health, chronic disease management, and workflow analysis. She has developed, applied, and evaluated models and methods drawn from optimization, machine learning, econometrics, statistics and behavioral science for designing and investigating these IT interventions in the inpatient, ambulatory, and consumer self-health management settings. She has published extensively, served on editorial boards of major academic journals, and has been funded by the US Veterans Administration, National Institutes of Health, National Science Foundation, National Library of Medicine, and the Centers for Disease Control, among others. She has received several Best Paper and Best Poster awards at conferences, the IBM Faculty Award, and CMU Teaching Excellence awards. She has been a visiting professor at universities in UK, Germany, Singapore and India, and a keynote speaker at several conferences, including the First International Association for Computing Machinery (ACM) Conference on Women in Computing in 2010.

Professor Padman has served on proposal review panels for US and international funding agencies, including the National Institutes of Health, National Science Foundation, Agency for Healthcare Research and Quality and the American Association for Advancement of Science in the US, the Medical Research Council in the UK, and the Swiss National Science Foundation. She has advised healthcare informatics projects for organizations such as IBM Research, Johnson Johnson, Deloitte Consulting, Central Blood Bank, Veterans Administration Health System, GlaxoSmithKline, Jewish Healthcare Foundation, Ernst Young, and major Pittsburgh hospitals. She is a member of the American Medical Informatics Association, The Institute for Operations Research and Management Science, and the Association for Computing Machinery.

Seminar details

Date: Tuesday 25th October 2016

Time: 12pm - 1pm

Venue: Seminar room, Level 1, 75 Talavera Road, Macquarie University

Chair: Associate Professor Farah Magrabi, Centre for Health Informatics, AIHI

To register for this seminar please click here