Literature DB >> 28495350

Decaying relevance of clinical data towards future decisions in data-driven inpatient clinical order sets.

Jonathan H Chen1, Muthuraman Alagappan2, Mary K Goldstein3, Steven M Asch4, Russ B Altman5.   

Abstract

OBJECTIVE: Determine how varying longitudinal historical training data can impact prediction of future clinical decisions. Estimate the "decay rate" of clinical data source relevance.
MATERIALS AND METHODS: We trained a clinical order recommender system, analogous to Netflix or Amazon's "Customers who bought A also bought B..." product recommenders, based on a tertiary academic hospital's structured electronic health record data. We used this system to predict future (2013) admission orders based on different subsets of historical training data (2009 through 2012), relative to existing human-authored order sets.
RESULTS: Predicting future (2013) inpatient orders is more accurate with models trained on just one month of recent (2012) data than with 12 months of older (2009) data (ROC AUC 0.91 vs. 0.88, precision 27% vs. 22%, recall 52% vs. 43%, all P<10-10). Algorithmically learned models from even the older (2009) data was still more effective than existing human-authored order sets (ROC AUC 0.81, precision 16% recall 35%). Training with more longitudinal data (2009-2012) was no better than using only the most recent (2012) data, unless applying a decaying weighting scheme with a "half-life" of data relevance about 4 months. DISCUSSION: Clinical practice patterns (automatically) learned from electronic health record data can vary substantially across years. Gold standards for clinical decision support are elusive moving targets, reinforcing the need for automated methods that can adapt to evolving information. CONCLUSIONS AND RELEVANCM: Prioritizing small amounts of recent data is more effective than using larger amounts of older data towards future clinical predictions.
Copyright © 2017 The Authors. Published by Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Collaborative filtering; Data mining; Electronic health records; Practice variability; Prediction models

Mesh:

Year:  2017        PMID: 28495350      PMCID: PMC5459355          DOI: 10.1016/j.ijmedinf.2017.03.006

Source DB:  PubMed          Journal:  Int J Med Inform        ISSN: 1386-5056            Impact factor:   4.046


  58 in total

1.  STRIDE--An integrated standards-based translational research informatics platform.

Authors:  Henry J Lowe; Todd A Ferris; Penni M Hernandez; Susan C Weber
Journal:  AMIA Annu Symp Proc       Date:  2009-11-14

2.  Before-after study of a standardized hospital order set for the management of septic shock.

Authors:  Scott T Micek; Nareg Roubinian; Tim Heuring; Meghan Bode; Jennifer Williams; Courtney Harrison; Theresa Murphy; Donna Prentice; Brent E Ruoff; Marin H Kollef
Journal:  Crit Care Med       Date:  2006-11       Impact factor: 7.598

3.  Big data meets the electronic medical record: a commentary on "identifying patients at increased risk for unplanned readmission".

Authors:  Greg de Lissovoy
Journal:  Med Care       Date:  2013-09       Impact factor: 2.983

4.  Health information technology: standards, implementation specifications, and certification criteria for electronic health record technology, 2014 edition; revisions to the permanent certification program for health information technology. Final rule.

Authors: 
Journal:  Fed Regist       Date:  2012-09-04

5.  The use of sequential pattern mining to predict next prescribed medications.

Authors:  Aileen P Wright; Adam T Wright; Allison B McCoy; Dean F Sittig
Journal:  J Biomed Inform       Date:  2014-09-16       Impact factor: 6.317

6.  Paving the COWpath: data-driven design of pediatric order sets.

Authors:  Yiye Zhang; Rema Padman; James E Levin
Journal:  J Am Med Inform Assoc       Date:  2014-03-27       Impact factor: 4.497

7.  Big data and new knowledge in medicine: the thinking, training, and tools needed for a learning health system.

Authors:  Harlan M Krumholz
Journal:  Health Aff (Millwood)       Date:  2014-07       Impact factor: 6.301

8.  Prognosis of Clinical Outcomes with Temporal Patterns and Experiences with One Class Feature Selection.

Authors:  Robert Moskovitch; Hyunmi Choi; George Hripcsak; Nicholas Tatonetti
Journal:  IEEE/ACM Trans Comput Biol Bioinform       Date:  2016-07-14       Impact factor: 3.710

9.  A targeted real-time early warning score (TREWScore) for septic shock.

Authors:  Katharine E Henry; David N Hager; Peter J Pronovost; Suchi Saria
Journal:  Sci Transl Med       Date:  2015-08-05       Impact factor: 17.956

10.  Mining for clinical expertise in (undocumented) order sets to power an order suggestion system.

Authors:  Jonathan H Chen; Russ B Altman
Journal:  AMIA Jt Summits Transl Sci Proc       Date:  2013-03-18
View more
  26 in total

1.  An evaluation of clinical order patterns machine-learned from clinician cohorts stratified by patient mortality outcomes.

Authors:  Jason K Wang; Jason Hom; Santhosh Balasubramanian; Alejandro Schuler; Nigam H Shah; Mary K Goldstein; Michael T M Baiocchi; Jonathan H Chen
Journal:  J Biomed Inform       Date:  2018-09-07       Impact factor: 6.317

2.  CORR Insights®: External Validation and Optimization of the SPRING Model for Prediction of Survival After Surgical Treatment of Bone Metastases of the Extremities.

Authors:  Benjamin K Potter
Journal:  Clin Orthop Relat Res       Date:  2018-08       Impact factor: 4.176

Review 3.  Artificial Intelligence and Orthopaedics: An Introduction for Clinicians.

Authors:  Thomas G Myers; Prem N Ramkumar; Benjamin F Ricciardi; Kenneth L Urish; Jens Kipper; Constantinos Ketonis
Journal:  J Bone Joint Surg Am       Date:  2020-05-06       Impact factor: 5.284

4.  Longitudinal analysis of social and behavioral determinants of health in the EHR: exploring the impact of patient trajectories and documentation practices.

Authors:  Daniel J Feller; Jason Zucker; Oliver Bear Don't Walk; Michael T Yin; Peter Gordon; Noémie Elhadad
Journal:  AMIA Annu Symp Proc       Date:  2020-03-04

5.  External Validation and Optimization of the SPRING Model for Prediction of Survival After Surgical Treatment of Bone Metastases of the Extremities.

Authors:  Michala Skovlund Sørensen; Thomas Alexander Gerds; Klaus Hindsø; Michael Mørk Petersen
Journal:  Clin Orthop Relat Res       Date:  2018-08       Impact factor: 4.176

6.  Machine Learning and Prediction in Medicine - Beyond the Peak of Inflated Expectations.

Authors:  Jonathan H Chen; Steven M Asch
Journal:  N Engl J Med       Date:  2017-06-29       Impact factor: 91.245

7.  Bayesian logistic regression for online recalibration and revision of risk prediction models with performance guarantees.

Authors:  Jean Feng; Alexej Gossmann; Berkman Sahiner; Romain Pirracchio
Journal:  J Am Med Inform Assoc       Date:  2022-04-13       Impact factor: 4.497

Review 8.  Clinical artificial intelligence quality improvement: towards continual monitoring and updating of AI algorithms in healthcare.

Authors:  Jean Feng; Rachael V Phillips; Ivana Malenica; Andrew Bishara; Alan E Hubbard; Leo A Celi; Romain Pirracchio
Journal:  NPJ Digit Med       Date:  2022-05-31

9.  Pharmacists' perceptions of a machine learning model for the identification of atypical medication orders.

Authors:  Sophie-Camille Hogue; Flora Chen; Geneviève Brassard; Denis Lebel; Jean-François Bussières; Audrey Durand; Maxime Thibault
Journal:  J Am Med Inform Assoc       Date:  2021-07-30       Impact factor: 4.497

10.  Why Is the Electronic Health Record So Challenging for Research and Clinical Care?

Authors:  John H Holmes; James Beinlich; Mary R Boland; Kathryn H Bowles; Yong Chen; Tessa S Cook; George Demiris; Michael Draugelis; Laura Fluharty; Peter E Gabriel; Robert Grundmeier; C William Hanson; Daniel S Herman; Blanca E Himes; Rebecca A Hubbard; Charles E Kahn; Dokyoon Kim; Ross Koppel; Qi Long; Nebojsa Mirkovic; Jeffrey S Morris; Danielle L Mowery; Marylyn D Ritchie; Ryan Urbanowicz; Jason H Moore
Journal:  Methods Inf Med       Date:  2021-07-19       Impact factor: 1.800

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.