From Research Results to Prediction and Translation: A Decision Support System for Children, Parents, and Distraction During Healthcare Procedures

2.50
Hdl Handle:
http://hdl.handle.net/10755/243275
Category:
Abstract
Type:
Presentation
Title:
From Research Results to Prediction and Translation: A Decision Support System for Children, Parents, and Distraction During Healthcare Procedures
Author(s):
Hanrahan, Kirsten; Ersig, Anne L.; Street, W. Nick; Zimmerman, Miriam B.; Kleiber, Charmaine; McCarthy, Ann Marie
Author Details:
Hanrahan, Kirsten, DNP, ARNP, kirsten-hanrahan@uiowa.edu; Ersig, Anne L., PhD, RN; Street, W. Nick , PhD; Zimmerman, Miriam B. , PhD; Kleiber, Charmaine, RN, PhD, FAAN; McCarthy, Ann Marie, RN, PhD, FAAN;
Abstract:
Purpose: For many children, distress from healthcare procedures affects the success of the procedure, leads to additional child and parent distress, and impacts healthcare utilization and costs. Being able to predict which children are more likely to experience high distress during procedures could allow for targeted interventions for those children. The purpose of this presentation is to describe a decision support system developed from an initial intervention trial, validation in the next stage of the research program, and progress on translation of the research intervention into clinical practice.

Methods: Regression models and data mining identified predictors of procedural distress. Predictive models were built using support vector machine (SVM) regression and further improved by automatic feature selection. Each model was extensively evaluated using multiple cross-validation tests. These data were incorporated into a computerized decision support system in the next phase of study.

Results: In the initial study, measures of procedural distress for 542 children included child-report, parent-report, behavioral observation, and a biomarker. From 255 initial items, regression models identified 30 items explaining child distress, whereas data mining identified 44 predictive items. In multiple cross-validation tests, the predictive accuracy of data mining was superior to linear regression (p < 0.01). In the second phase of the trial, the model predicted level of distress for 582 children, and informed the level of intervention received. For each intervention group, there was a significant difference (p < 0.006) between dyads predicted to be low vs. high risk for distress, validating effective identification of risk assignment.

Conclusion: Findings from this multi-phase study resulted in the development of new tools to predict child procedural distress and ultimately inform clinical interventions to reduce distress. Current work includes re-training the predictive model using data from the second phase and refining the computer application for translation into clinical practice.

Keywords:
Predictive Models; Data mining; Translation
Repository Posting Date:
12-Sep-2012
Date of Publication:
12-Sep-2012
Conference Date:
2012
Conference Name:
23rd International Nursing Research Congress
Conference Host:
Sigma Theta Tau International, the Honor Society of Nursing
Conference Location:
Brisbane, Australia

Full metadata record

DC FieldValue Language
dc.type.categoryAbstracten_GB
dc.typePresentationen_GB
dc.titleFrom Research Results to Prediction and Translation: A Decision Support System for Children, Parents, and Distraction During Healthcare Proceduresen_GB
dc.contributor.authorHanrahan, Kirstenen_GB
dc.contributor.authorErsig, Anne L.en_GB
dc.contributor.authorStreet, W. Nicken_GB
dc.contributor.authorZimmerman, Miriam B.en_GB
dc.contributor.authorKleiber, Charmaineen_GB
dc.contributor.authorMcCarthy, Ann Marieen_GB
dc.author.detailsHanrahan, Kirsten, DNP, ARNP, kirsten-hanrahan@uiowa.edu; Ersig, Anne L., PhD, RN; Street, W. Nick , PhD; Zimmerman, Miriam B. , PhD; Kleiber, Charmaine, RN, PhD, FAAN; McCarthy, Ann Marie, RN, PhD, FAAN;en_GB
dc.identifier.urihttp://hdl.handle.net/10755/243275-
dc.description.abstract<b>Purpose: </b>For many children, distress from healthcare procedures affects the success of the procedure, leads to additional child and parent distress, and impacts healthcare utilization and costs. Being able to predict which children are more likely to experience high distress during procedures could allow for targeted interventions for those children. The purpose of this presentation is to describe a decision support system developed from an initial intervention trial, validation in the next stage of the research program, and progress on translation of the research intervention into clinical practice. <p><b>Methods: </b>Regression models and data mining identified predictors of procedural distress. Predictive models were built using support vector machine (SVM) regression and further improved by automatic feature selection. Each model was extensively evaluated using multiple cross-validation<b> </b>tests. These data were incorporated into a computerized decision support system in the next phase of study. <p><b>Results: </b>In the initial study, measures of procedural distress for 542 children included child-report, parent-report, behavioral observation, and a biomarker. From 255 initial items, regression models identified 30 items explaining child distress, whereas data mining identified 44 predictive items. In multiple cross-validation tests, the predictive accuracy of data mining was superior to linear regression (p &lt; 0.01). In the second phase of the trial, the model predicted level of distress for 582 children, and informed the level of intervention received. For each intervention group, there was a significant difference (p &lt; 0.006) between dyads predicted to be low vs. high risk for distress, validating effective identification of risk assignment. <p><b>Conclusion: </b>Findings from this multi-phase study resulted in the development of new tools to predict child procedural distress and ultimately inform clinical interventions to reduce distress. Current work includes re-training the predictive model using data from the second phase and refining the computer application for translation into clinical practice.en_GB
dc.subjectPredictive Modelsen_GB
dc.subjectData miningen_GB
dc.subjectTranslationen_GB
dc.date.available2012-09-12T09:19:58Z-
dc.date.issued2012-09-12-
dc.date.accessioned2012-09-12T09:19:58Z-
dc.conference.date2012en_GB
dc.conference.name23rd International Nursing Research Congressen_GB
dc.conference.hostSigma Theta Tau International, the Honor Society of Nursingen_GB
dc.conference.locationBrisbane, Australiaen_GB
All Items in this repository are protected by copyright, with all rights reserved, unless otherwise indicated.