Robin Austin

Dr. Robin Austin


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 November 2023 in Journal of the American Medical Informatics Association
Verified
Journal Article
Open access
PDF file
HZHuixue Zhou
Huixue Zhou
RARobin Austin
Robin Austin
SLSheng-Chieh Lu
Sheng-Chieh Lu
GSGreg Marc Silverman
Greg Marc Silverman
YZYuqi Zhou
Yuqi Zhou
RZRui Zhang
Rui Zhang
Objective: To construct an exhaustive Complementary and Integrative Health (CIH) Lexicon (CIHLex) to help better represent the often underrepresented physical and psychological CIH approaches in standard terminologies, and to also apply state-of-the-art natural language processing (NLP) techniques to help recognize them in the biomedical literature. Materials and methods: We constructed the CIHLex by integrating various resources, compiling and integrating data from biomedical literature and relevant sources of knowledge. The Lexicon encompasses 724 unique concepts with 885 corresponding unique terms. We matched these concepts to the Unified Medical Language System (UMLS), and we developed and utilized BERT models comparing their efficiency in CIH named entity recognition to well-established models including MetaMap and CLAMP, as well as the large language model GPT3.5-turbo. Results: Of the 724 unique concepts in CIHLex, 27.2% could be matched to at least one term in the UMLS. About 74.9% of the mapped UMLS Concept Unique Identifiers were categorized as “Therapeutic or Preventive Procedure.” Among the models applied to CIH named entity recognition, BLUEBERT delivered the highest macro-average F1-score of 0.91, surpassing other models. Conclusion: Our CIHLex significantly augments representation of CIH approaches in biomedical literature. Demonstrating the utility of advanced NLP models, BERT notably excelled in CIH entity recognition. These results highlight promising strategies for enhancing standardization and recognition of CIH terminology in biomedical contexts.

3 April 2021 in Journal of Nursing Scholarship
Verified
Journal Article
Closed access
PDF file
Karen MonsenKaren Monsen
Karen Monsen
RARobin Austin
Robin Austin
BGBhavana Goparaju
Bhavana Goparaju
RJRobert Clarence Jones
Robert Clarence Jones
MMMichelle A. Mathiason
Michelle A. Mathiason
MEMilton Eder
Milton Eder

19 June 2022 in Research in Nursing & Health
Verified
Journal Article
Open access
RARobin Austin
Robin Austin
MMMichelle A. Mathiason
Michelle A. Mathiason
Karen MonsenKaren Monsen
Karen Monsen
Data visualization techniques are useful for examining large multidimensional data sets. In this exploratory data analysis (EDA) study, we applied a visualization pattern detection and testing process to deidentified data to discover patterns in whole‐person health for adults 65 and older. Whole‐person health examines a person's environmental, psychosocial, and physical health, as well as their health‐related behaviors; and assesses their strengths, challenges, and needs. Strengths are defined as assets and capabilities in the face of short‐or long‐term stressors. We collected data using a mobile application that delivers a comprehensive whole‐person assessment using a simplified version of a standardized instrument, the Omaha System. The visualization pattern detection process is iterative, includes various techniques, and requires visualization literacy. The data visualization techniques applied in this analysis included bubble charts, parallel coordinates line graphs, box plots, and alluvial flow diagrams. We discovered six patterns within the visualizations. We formulated and tested six hypotheses based on these six patterns, and all six hypotheses were supported. Adults 65 and older had more strengths than challenges and more challenges than needs (p < 0.001). Strengths and challenges were negatively correlated (p < 0.001). Unexpectedly, a subset of adults 65 and older who had many, but not all, strengths had significantly more needs (p = 0.04). The use of standardized terminology with its inherent data interrelationships was key to discovering patterns in whole‐person health. This methodology may be used in future EDA research using new data sets.

16 May 2021 in Journal of Nursing Scholarship
Verified
Journal Article
Closed access
PDF file
RARobin Austin
Robin Austin
MMMichelle A. Mathiason
Michelle A. Mathiason
RLRuth A. Lindquist
Ruth A. Lindquist
SMSiobhan K. McMahon
Siobhan K. McMahon
DPDavid S. Pieczkiewicz
David S. Pieczkiewicz
Karen MonsenKaren Monsen
Karen Monsen

17 November 2025 in JMIR Nursing
Verified
Journal Article
Open access
CKChanhee Kim
Chanhee Kim
RARobin Austin
Robin Austin
RWRebecca M. Wurtz
Rebecca M. Wurtz
CDConnie White Delaney
Connie White Delaney
SRSripriya Rajamani
Sripriya Rajamani
Background: The COVID-19 pandemic exposed systemic vulnerabilities in public health infrastructure, underscoring the urgency for innovation in disease surveillance and emergency response. Artificial intelligence (AI) has emerged as a promising tool to enhance the accuracy, efficiency, and scalability of public health interventions. Yet, there remains a limited understanding of how AI has been applied in real-world infectious disease control and who is contributing to its development and implementation. Objective: This scoping review aimed to map current applications of AI in public health practice for infectious disease control since 2020. Specifically, it examined (1) the types of AI tools in use, (2) their purposes and implementation contexts, and (3) the professional and institutional actors leading these efforts, including the role of nurses. Methods: Using the Joanna Briggs Institute’s population, concept, and context framework, a structured search in Ovid MEDLINE was conducted, which was guided by the “5Cs” framework for health emergency preparedness from the World Health Organization (WHO). The search focused on English-language, peer-reviewed studies from 2020 that used AI tools for infectious disease control within real-world public health practice. Nonoriginal articles, simulation-only studies, and studies that lacked real-world implementation were excluded. Results: Out of 600 screened studies in Ovid MEDLINE, 10 met the inclusion criteria. Two major AI types were identified: machine learning (ML) algorithms and language-based tools such as chatbots and large language models. ML tools supported outbreak detection, risk stratification, and resource allocation, while language-based tools promoted health communication, particularly around immunization and HIV prevention. Studies were conducted in a diverse range of countries, including several low- and middle-income countries, and used national datasets or surveillance systems. Despite nurses comprising half of the global health workforce, no nursing-affiliated authors were found among first or corresponding authors, and no nurses were represented in the broader authorship of the included studies. Conclusions: AI technologies are being increasingly applied to support public health responses to infectious diseases, with applications ranging from predictive analytics to real-time public engagement. However, adoption remains limited in scale, scope, and professional diversity. The near-total absence of nursing participation in AI-related public health research is particularly striking and represents a missed opportunity for inclusive innovation. Strengthening implementation research and advancing informatics education among nursing professionals are critical next steps to ensure that AI tools reflect the realities of public health practice and promote equitable outcomes.

6 October 2017 in Journal of Innovation in Health Informatics
Verified
Journal Article
Open access
PDF file
RARobin Austin
Robin Austin
Karen MonsenKaren Monsen
Karen Monsen
CSCraig Schulz
Craig Schulz
Background: Low back pain (LBP) is a complex health care issue that often involves multiple providers across various care settings. Health information technology (HIT) holds promise to improve care delivery by providing infrastructure for communication, clinical documentation, and management of patient data. Standardized terminology is essential for interoperability and enables evaluation of clinical data generated by documentation in an electronic health record (EHR).Objective: The purpose of this study was to demonstrate the feasibility of mapping evidence-based practice for conservative management of low back pain to the Omaha System and foster inter-professional communication and collaboration among diverse practitioners and patients.Methods: Evidence-based practice (EBP) guidelines for non-invasive treatment of low back pain were mapped to the Omaha System using a clinical expert approach with attention to content feasibility, linguistic validity, and granularity of terms. Results: A clinical guideline for low back pain management was developed consisting of 13 interventions for Pain and Neuro-musculo-skeletal problems. The most common intervention categories were Case management followed by Treatments and procedures, Teaching, guidance, and counseling and Surveillance. Scope of practice overlap was identified between primary care, chiropractic, and physical therapy practice.Conclusion: Use of the guideline may facilitate clinical documentation using the Omaha System for low back pain management, and has potential to generate meaningful data to evaluate clinical effectiveness and promote quality research. The use of encoded EBP evidence within an EHR can increase use of available evidence, enable interprofessional communication, improve quality of care, and enhance usability of data across care settings.