All Resources

2019 Nursing Knowledge: Big Data Science Conference Proceedings

The seventh-annual Nursing Knowledge: Big Data Science (NKBDS) Conference brought together professionals from academia, practice, research, information technology, health systems and standards organizations. Currently, there are 11 virtual workgroups, which shared their accomplishments to advance sharable and comparable nurse sensitive data integrated with patient, interprofessional and social determinants of health data to improve health and health care.

Conference Proceedings

Policy & Advocacy Workgroup

Ida Androwich, PhD, RN,FAAN & Joyce Sensmeier, MS, RN-BC, CPHIMS, FHIMSS, FAAN 

Dr. Androwich discussed the work of the Workgroup, including its collaboration with the other organizations such as the American Nurses Association and the American Council of State Boards of Nursing. She described the value of a unique nursing identifier and its importance as it pertains to big data initiatives namely to: 1) measure/quantify nursing care and impact on outcomes, 2) demonstrate nursing value/visibility, 3) empower organizations to track RNs for training and educational purposes; and 4) enable data analytics for  short and long-term impact.

Part of a panel presentation Nursing Knowledge Big Data Science: A National Collaborative to Achieve Sharable and Comparable Nurse-Sensitive Data. 

MedInfo 2019

August 28, 2019, Lyon France

erepository
MedInfo2019
Data Integration
Data standards
Health policy
Nursing value

Nursing Knowledge Big Data Science Initiative

Bonnie L. Westra, PhD, RN, FAAN, FACMI
westr006@umn.edu

The presentation was given at MedInfo 2019 in Lyon France is an overview of the Nursing Knowledge Big Data Science (NKBDS) initiative that describes the vision and management of the workgroups which engage  year-round to achieve planned goals and deliverables. The methodology was described, which includes an annual “think-tank” conference for discussing achievements and annual action plans ov 11 virtual workgroups to move an national agenda of implementing and successfully using standardized nurse-sensitive data.  The NKBDS initiative has been successful in connecting nurses, and interdisciplinary healthcare leaders. The overall resources, including university support, the website and LinkedIn infrastructure to support members and interested others to make connections was discussed. 

Part of a panel presentation Nursing Knowledge Big Data Science: A National Collaborative to Achieve Sharable and Comparable Nurse-Sensitive Data. 

August 28, 2019, Lyon France

erepository
Clinical data analytics
Data-driven research and discovery
Data mining and knowledge discovery
Precision health/ medicine
Secondary use of EHR data
Pain
MedInfo2019

Education Workgroup

Marisa L. Wilson DNSc MHSc RN-BC CPHIMS FAMIA FAAN
University of Alabama at Birmingham School of Nursing
mwilsoa@uab.edu

Dr. Wilson described the output of the NKBDS Education workgroup in building a collaborative process and multimodal method for developing a national response which seeks to address the significant informatics competency deficit of educators and faculty of nurses and nursing students. A plan of action has been created which includes informing and educating thought leaders and faculty alike and providing tools, resources, and hands-on assistance to faculty and educators in a broad-based dissemination plan of action while ensuring collaboration among professional organizations through a matrix approach overseen by the NKBDS Education Workgroup.     

Part of a panel presentation Nursing Knowledge Big Data Science: A National Collaborative to Achieve Sharable and Comparable Nurse-Sensitive Data. 

August 28, 2019, Lyon France

Encoding and Modeling
Education
erepository
Education and Training
MedInfo2019

Clinical Data Analytics Workgroup

Lisiane Pruinelli, PhD, MS, RN
pruin001@umn.edu

Dr. Pruinelli presented the purpose of the Clinical Data Analytics Workgroup with the emergence of objectives over the past 7 years.  She described the engagement of national participants in collaborative data science,  current nursing data science publications and population health informatics. She highlighted how healthcare organizations have collaborated on validation of information models to standardize flowsheet data for expanding common data models to support quality improvement and research.


Part of a panel presentation Nursing Knowledge Big Data Science: A National Collaborative to Achieve Sharable and Comparable Nurse-Sensitive Data. 

August 28, 2019, Lyon France

Clinical data analytics
Data-driven research and discovery
Data mining and knowledge discovery
Data standards
Machine learning and predictive modeling
Precision health/ medicine
Secondary use of EHR data
erepository
MedInfo2019

Nursing Value Workgroup A Structured Approach to Measuring Individual Nurse’s Contribution in Patient Outcomes

Ellen Harper, DNP, RN-BC, MBA, FAAN 
eharper3@kumc.edu

We will describe how researchers, nursing and information technology teams used large and complex data sets to identify, extract, anonymize patient and nurse information and transfer files for analysis while complying with security and confidentiality requirements. There is a growing need to devise methods to better understand how nursing costs and resources are expended for each patient and how these resources relate to quality and outcomes. Time-stamped data can provide useful information and several means to identify both the clinical trajectory as well as the sequence of nursing care and nurses’ engagement during a patient during hospitalization. Nurses are linked to individual patients in several ways e.g., the electronic capture of the nurse-patient assignment and data from barcoding technologies used for medication administration. Automatic capture of nurse-generated clinical observations and nursing interventions data for secondary use can provide new and unique opportunities to measure nursing care in several different dimensions. 

Part of a panel presentation Nursing Knowledge Big Data Science: A National Collaborative to Achieve Sharable and Comparable Nurse-Sensitive Data. 

August 28, 2019, Lyon France

erepository
MedInfo2019
Nursing Value
Data-driven research and discovery
Data Integration
Data mining and knowledge discovery
Data standards
Electronic health record
Machine learning and predictive modeling
Measuring outcomes
Precision health/ medicine
Secondary use of EHR data

Visualization Pain Related Factors from EHR Flowsheet Data

Bonnie L. Westra, PhD, RN, FAAN, FACMI

westr006@umn.edu

Part of a panel presentation Nursing Knowledge Big Data Science: A National Collaborative to Achieve Sharable and Comparable Nurse-Sensitive Data.

August 28, 2019, Lyon France
 

erepository
Unpublished resource
Clinical data analytics
Data-driven research and discovery
Data mining and knowledge discovery
Precision health/ medicine
Secondary use of EHR data
Pain

Pain Data Set (Not Real Patients)

Author(s): Bonnie Westra & Tristan Fin

A fake data set generated from 2 organizations, de-identified, duplicated to achieve 10,000 patients, massaged to calculate data elements i.e. age . This data set can be used for practicing data visualization skills.

Data mining and knowledge discovery
Visualization
Clinical Data Analytics
erepository
Fake Data Set