Steve Rust

Dr. Steve Rust

orcid

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
7 March 2023 in JMIR Formative Research
Verified
Journal Article
Open access
ESEmre Sezgin
Emre Sezgin
SHSyed-Amad Hussain
Syed-Amad Hussain
SRSteve Rust
Steve Rust
YHYungui Huang
Yungui Huang
Background: Patient-generated health data (PGHD) captured via smart devices or digital health technologies can reflect an individual health journey. PGHD enables tracking and monitoring of personal health conditions, symptoms, and medications out of the clinic, which is crucial for self-care and shared clinical decisions. In addition to self-reported measures and structured PGHD (eg, self-screening, sensor-based biometric data), free-text and unstructured PGHD (eg, patient care note, medical diary) can provide a broader view of a patient’s journey and health condition. Natural language processing (NLP) is used to process and analyze unstructured data to create meaningful summaries and insights, showing promise to improve the utilization of PGHD. Objective: Our aim is to understand and demonstrate the feasibility of an NLP pipeline to extract medication and symptom information from real-world patient and caregiver data. Methods: We report a secondary data analysis, using a data set collected from 24 parents of children with special health care needs (CSHCN) who were recruited via a nonrandom sampling approach. Participants used a voice-interactive app for 2 weeks, generating free-text patient notes (audio transcription or text entry). We built an NLP pipeline using a zero-shot approach (adaptive to low-resource settings). We used named entity recognition (NER) and medical ontologies (RXNorm and SNOMED CT [Systematized Nomenclature of Medicine Clinical Terms]) to identify medication and symptoms. Sentence-level dependency parse trees and part-of-speech tags were used to extract additional entity information using the syntactic properties of a note. We assessed the data; evaluated the pipeline with the patient notes; and reported the precision, recall, and F1 scores. Results: In total, 87 patient notes are included (audio transcriptions n=78 and text entries n=9) from 24 parents who have at least one CSHCN. The participants were between the ages of 26 and 59 years. The majority were White (n=22, 92%), had more than one child (n=16, 67%), lived in Ohio (n=22, 92%), had mid- or upper-mid household income (n=15, 62.5%), and had higher level education (n=24, 58%). Out of 87 notes, 30 were drug and medication related, and 46 were symptom related. We captured medication instances (medication, unit, quantity, and date) and symptoms satisfactorily (precision >0.65, recall >0.77, F1>0.72). These results indicate the potential when using NER and dependency parsing through an NLP pipeline on information extraction from unstructured PGHD. Conclusions: The proposed NLP pipeline was found to be feasible for use with real-world unstructured PGHD to accomplish medication and symptom extraction. Unstructured PGHD can be leveraged to inform clinical decision-making, remote monitoring, and self-care including medical adherence and chronic disease management. With customizable information extraction methods using NER and medical ontologies, NLP models can feasibly extract a broad range of clinical information from unstructured PGHD in low-resource settings (eg, a limited number of patient notes or training data).

13 February 2020 in Journal of Medical Internet Research
Verified
Journal Article
Open access
ESEmre Sezgin
Emre Sezgin
GNGarey Noritz
Garey Noritz
AEAlexander Elek
Alexander Elek
KCKimberly Conkol
Kimberly Conkol
SRSteve Rust
Steve Rust
YHYungui Huang
Yungui Huang
Digital health tools and technologies are transforming health care and making significant impacts on how health and care information are collected, used, and shared to achieve best outcomes. As most of the efforts are still focused on clinical settings, the wealth of health information generated outside of clinical settings is not being fully tapped. This is especially true for children with medical complexity (CMC) and their families, as they frequently spend significant hours providing hands-on medical care within the home setting and coordinating activities among multiple providers and other caregivers. In this paper, a multidisciplinary team of stakeholders discusses the value of health information generated at home, how technology can enhance care coordination, and challenges of technology adoption from a patient-centered perspective. Voice interactive technology has been identified to have the potential to transform care coordination for CMC. This paper shares opinions on the promises, limitations, recommended approaches, and challenges of adopting voice technology in health care, especially for the targeted patient population of CMC.

1 March 2019 in Epilepsy & Behavior
Verified
Journal Article
Closed access
SNSunjay Nunley
Sunjay Nunley
PGPeter Glynn
Peter Glynn
SRSteve Rust
Steve Rust
JVJorge Vidaurre
Jorge Vidaurre
DADara V.F. Albert
Dara V.F. Albert
APAnup D. Patel
Anup D. Patel

21 March 2024 in Cell Reports
Verified
Journal Article
Open access
LSLaura Schwartz
Laura Schwartz
KSKristin Salamon
Kristin Salamon
ASAaron Simoni
Aaron Simoni
TETad Eichler
Tad Eichler
AJAshley R. Jackson
Ashley R. Jackson
JSJohn Spencer
John Spencer
Urinary tract infections (UTIs) commonly afflict people with diabetes. To better understand the mechanisms that predispose diabetics to UTIs, we employ diabetic mouse models and altered insulin signaling to show that insulin receptor (IR) shapes UTI defenses. Our findings are validated in human biosamples. We report that diabetic mice have suppressed IR expression and are more susceptible to UTIs caused by uropathogenic Escherichia coli (UPEC). Systemic IR inhibition increases UPEC susceptibility, while IR activation reduces UTIs. Localized IR deletion in bladder urothelium promotes UTI by increasing barrier permeability and suppressing antimicrobial peptides. Mechanistically, IR deletion reduces nuclear factor κB (NF-κB)-dependent programming that co-regulates urothelial tight junction integrity and antimicrobial peptides. Exfoliated urothelial cells or urine samples from diabetic youths show suppressed expression of IR, barrier genes, and antimicrobial peptides. These observations demonstrate that urothelial insulin signaling has a role in UTI prevention and link IR to urothelial barrier maintenance and antimicrobial peptide expression.

30 September 2019 in JMIR Human Factors
Verified
Journal Article
Open access
SASelasi Attipoe
Selasi Attipoe
YHYungui Huang
Yungui Huang
SSSharon Schweikhart
Sharon Schweikhart
SRSteve Rust
Steve Rust
JHJeffrey Hoffman
Jeffrey Hoffman
SLSimon Lin
Simon Lin
Background: There is limited published data on variation in physician usage of electronic health records (EHRs), particularly after hours. Research in this area could provide insight into the effects of EHR-related workload on physicians. Objective: This study sought to examine factors associated with after-hours EHR usage among primary care physicians. Methods: Electronic health records usage information was collected from primary care pediatricians in a large United States hospital. Inclusion criteria consisted solely of being a primary care physician who started employment with the hospital before the study period, so all eligible primary care physicians were included without sampling. Mixed effects statistical modeling was used to investigate the effects of age, gender, workload, normal-hour usage, week to week variation, and provider-to-provider variation on the after-hour usage of EHRs. Results: There were a total of 3498 weekly records obtained on 50 physicians, of whom 22% were male and 78% were female. Overall, more EHR usage during normal work hours was associated with decreased usage after hours. The more work relative value units generated by physicians, the more time they spent interacting with EHRs after hours (β=.04, P<.001) and overall (ie, during normal hours and after hours) (β=.24, P<.001). Gender was associated with total usage time, with females spending more time than males (P=.03). However, this association was not observed with after-hours EHR usage. provider-to-provider variation was the largest and most dominant source of variation in after-hour EHR usage, which accounted for 52% of variance of total EHR usage. Conclusion: The present study found that there is a considerable amount of variability in EHR use among primary care physicians, which suggested that many factors influence after-hours EHR usage by physicians. However, provider-to-provider variation was the largest and most dominant source of variation in after-hours EHR usage. While the results are intuitive, future studies should consider the effect of EHR use variations on workload efficiency.

8 May 2017 in Journal of Digital Imaging
Verified
Journal Article
Closed access
PDF file
WCWei Chen
Wei Chen
CDClaire Durkin
Claire Durkin
YHYungui Huang
Yungui Huang
BABrent Adler
Brent Adler
SRSteve Rust
Steve Rust
SLSimon Lin
Simon Lin