Kelly Peterson

Kelly Peterson

Auto-generated profile, based on publicly available information

Kelly Peterson

Veterans Health Administration, Office of Analytics and Performance Integration, Washington, District of Columbia, USA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
31 July 2019 in Nature
Verified
Journal Article
Closed access
PDF file
NTNenad Tomašev
Nenad Tomašev
XGXavier Glorot
Xavier Glorot
JRJack W. Rae
Jack W. Rae
MZMichal Zielinski
Michal Zielinski
HAHarry Askham
Harry Askham
SMShakir Mohamed
Shakir Mohamed

16 January 2019 in Drug Safety
Verified
Journal Article
Open access
PDF file
ACAlec B. Chapman
Alec B. Chapman
KPKelly S. Peterson
Kelly S. Peterson
PAPatrick Raymond Alba
Patrick Raymond Alba
SDScott L. DuVall
Scott L. DuVall
OPOlga V. Patterson
Olga V. Patterson
Introduction Identifying occurrences of medication side effects and adverse drug events (ADEs) is an important and challenging task because they are frequently only mentioned in clinical narrative and are not formally reported. Methods We developed a natural language processing (NLP) system that aims to identify mentions of symptoms and drugs in clinical notes and label the relationship between the mentions as indications or ADEs. The system leverages an existing word embeddings model with induced word clusters for dimensionality reduction. It employs a conditional random field (CRF) model for named entity recognition (NER) and a random forest model for relation extraction (RE). Results Final performance of each model was evaluated separately and then combined on a manually annotated evaluation set. The micro-averaged F1 score was 80.9% for NER, 88.1% for RE, and 61.2% for the integrated systems. Outputs from our systems were submitted to the NLP Challenges for Detecting Medication and Adverse Drug Events from Electronic Health Records (MADE 1.0) competition (Yu et al. in http://bio-nlp.org/index.php/projects/39-nlp-challenges, 2018). System performance was evaluated in three tasks (NER, RE, and complete system) with multiple teams submitting output from their systems for each task. Our RE system placed first in Task 2 of the challenge and our integrated system achieved third place in Task 3. Conclusion Adding to the growing number of publications that utilize NLP to detect occurrences of ADEs, our study illustrates the benefits of employing innovative feature engineering.

4 October 2022 in JAMIA Open
Verified
Journal Article
Open access
PDF file
ACAlec B Chapman
Alec B Chapman
KPKelly S Peterson
Kelly S Peterson
ERElizabeth Rutter
Elizabeth Rutter
MNMckenna Nevers
Mckenna Nevers
MZMingyuan Zhang
Mingyuan Zhang
BJBarbara E Jones
Barbara E Jones
Objective: To evaluate the feasibility, accuracy, and interoperability of a natural language processing (NLP) system that extracts diagnostic assertions of pneumonia in different clinical notes and institutions. Materials and Methods: A rule-based NLP system was designed to identify assertions of pneumonia in 3 types of clinical notes from electronic health records (EHRs): emergency department notes, radiology reports, and discharge summaries. The lexicon and classification logic were tailored for each note type. The system was first developed and evaluated using annotated notes from the Department of Veterans Affairs (VA). Interoperability was assessed using data from the University of Utah (UU). Results: The NLP system was comprised of 782 rules and achieved moderate-to-high performance in all 3 note types in VA (precision/recall/f1: emergency = 88.1/86.0/87.1; radiology = 71.4/96.2/82.0; discharge = 88.3/93.0/90.1). When applied to UU data, performance was maintained in emergency and radiology but decreased in discharge summaries (emergency = 84.7/94.3/89.3; radiology = 79.7/100.0/87.9; discharge = 65.5/92.7/76.8). Customization with 34 additional rules increased performance for all note types (emergency = 89.3/94.3/91.7; radiology = 87.0/100.0/93.1; discharge = 75.0/95.1/83.4). Conclusion: NLP can be used to accurately identify the diagnosis of pneumonia across different clinical settings and institutions. A limited amount of customization to account for differences in lexicon, clinical definition of pneumonia, and EHR structure can achieve high accuracy without substantial modification.

24 March 2021 in JMIR Public Health and Surveillance
Verified
Journal Article
Open access
KPKelly S Peterson
Kelly S Peterson
JLJulia Lewis
Julia Lewis
OPOlga V Patterson
Olga V Patterson
ACAlec B Chapman
Alec B Chapman
DDDaniel W Denhalter
Daniel W Denhalter
MJMakoto Jones
Makoto Jones
Background: Patient travel history can be crucial in evaluating evolving infectious disease events. Such information can be challenging to acquire in electronic health records, as it is often available only in unstructured text.Objective: This study aims to assess the feasibility of annotating and automatically extracting travel history mentions from unstructured clinical documents in the Department of Veterans Affairs across disparate health care facilities and among millions of patients. Information about travel exposure augments existing surveillance applications for increased preparedness in responding quickly to public health threats.Methods: Clinical documents related to arboviral disease were annotated following selection using a semiautomated bootstrapping process. Using annotated instances as training data, models were developed to extract from unstructured clinical text any mention of affirmed travel locations outside of the continental United States. Automated text processing models were evaluated, involving machine learning and neural language models for extraction accuracy.Results: Among 4584 annotated instances, 2659 (58%) contained an affirmed mention of travel history, while 347 (7.6%) were negated. Interannotator agreement resulted in a document-level Cohen kappa of 0.776. Automated text processing accuracy (F1 85.6, 95% CI 82.5-87.9) and computational burden were acceptable such that the system can provide a rapid screen for public health events.Conclusions: Automated extraction of patient travel history from clinical documents is feasible for enhanced passive surveillance public health systems. Without such a system, it would usually be necessary to manually review charts to identify recent travel or lack of travel, use an electronic health record that enforces travel history documentation, or ignore this potential source of information altogether. The development of this tool was initially motivated by emergent arboviral diseases. More recently, this system was used in the early phases of response to COVID-19 in the United States, although its utility was limited to a relatively brief window due to the rapid domestic spread of the virus. Such systems may aid future efforts to prevent and contain the spread of infectious diseases.

18 July 2023 in Military Medicine
Verified
Journal Article
Open access
PDF file
AKAndrea Kalvesmaki
Andrea Kalvesmaki
ATAmira Y Trevino
Amira Y Trevino
ECElizabeth Charron
Elizabeth Charron
AKAimee Kroll-Desrosiers
Aimee Kroll-Desrosiers
KPKelly Peterson
Kelly Peterson
MPMary Jo Pugh
Mary Jo Pugh
Successful employment is a functional outcome of high importance for veterans after military discharge. There is a significant rising concern regarding exposure to military sexual trauma (MST) and related mental health outcomes that can impair functional outcomes, such as employment. Although resilience training is a key component of preparing for military service, to date the impact of resilience on employment outcomes for veterans with exposure to MST has yet to be examined. We sought to examine the relationship between resilience and employment in a national sample of post-9/11 veterans with and without MST exposure. A national survey was conducted between October 2021 and January 2022 to respond to the 2021 National Defense Authorization Act mandate to identify factors affecting post-9/11 women veteran’s unemployment. Of veterans, 1,185 completed the survey. Of these, 565 (47.6%) were post-9/11 veterans. The survey collected data on demographics and employment; MST, adult sexual trauma (AST, outside of military), and childhood sexual trauma (CST) exposure; resilience (Response to Stressful Experiences Scale); Post Traumatic Stress Disorder (PTSD) Checklist (PCL-5); and depression (Patient Health Questionnaire-2). Multivariable logistic regression models identified gender-specific associations of resilience with employment among those exposed and not exposed to MST, adjusting for AST, CST, PTSD, and depression. Significance was set at P < .05. Of 322 women and 243 men post-9/11 veterans, 86.5% were employed. MST exposure (MST[+]) was reported by 31.4% (n = 101) of women and 16.9% (n = 41) of men. MST(+) women veterans were more likely to report CST (35.6% vs. 14.5%; P < .001), AST (68.3% vs. 17.2%; P < .001), and both CST and AST (19.8% vs. 7.2%; P < .001) than MST(−) women. MST(+) men were more likely to report AST (65.9% vs. 7.9%; P < .001), and both CST and AST (14.6% vs. 1.0%; P < .001) than MST(−) men. Levels of self-reported resilience were similar for MST(+) women and men and their MST(−) counterparts (women: 11.1 vs. 11.0; men: 11.5 vs. 12.0). For MST(+) women, each unit increase in resilience was associated with a 36% increase in odds of employment (OR: 1.36, 95% CI, 1.08-1.71); resilience was not associated with increased odds of employment among MST(−) women. Among MST(+) men veterans, each unit increase in resilience was associated with an 83% increase in odds of employment (aOR: 1.83, 95% CI, 1.13-2.98), and like women veterans, resilience was not associated with employment among MST(−) men. Among MST(+) women and men post-9/11 veterans, higher resilience was associated with increased odds of employment, whereas resilience was not associated with employment in MST(−) veterans. These findings suggest that resiliency during and after military service is a key component for potentially improving long-term outcomes. Improving resilience using evidence-based approaches among post-9/11 veterans exposed to MST may be an important avenue for increasing successful functional outcomes such as employment. Moreover, MST(+) women and men veterans may benefit from trauma-informed care as a substantial proportion of these individuals also report exposure to CST, AST, PTSD, and depression.

7 June 2024 in PLOS Digital Health
Verified
Journal Article
Open access
PDF file
KPKelly S. Peterson
Kelly S. Peterson
ACAlec B. Chapman
Alec B. Chapman
WWWathsala Widanagamaachchi
Wathsala Widanagamaachchi
JSJesse Sutton
Jesse Sutton
BOBrennan Ochoa
Brennan Ochoa
MJMakoto M. Jones
Makoto M. Jones
Diagnostic error, a cause of substantial morbidity and mortality, is largely discovered and evaluated through self-report and manual review, which is costly and not suitable to real-time intervention. Opportunities exist to leverage electronic health record data for automated detection of potential misdiagnosis, executed at scale and generalized across diseases. We propose a novel automated approach to identifying diagnostic divergence considering both diagnosis and risk of mortality. Our objective was to identify cases of emergency department infectious disease misdiagnoses by measuring the deviation between predicted diagnosis and documented diagnosis, weighted by mortality. Two machine learning models were trained for prediction of infectious disease and mortality using the first 24h of data. Charts were manually reviewed by clinicians to determine whether there could have been a more correct or timely diagnosis. The proposed approach was validated against manual reviews and compared using the Spearman rank correlation. We analyzed 6.5 million ED visits and over 700 million associated clinical features from over one hundred emergency departments. The testing set performances of the infectious disease (Macro F1 = 86.7, AUROC 90.6 to 94.7) and mortality model (Macro F1 = 97.6, AUROC 89.1 to 89.1) were in expected ranges. Human reviews and the proposed automated metric demonstrated positive correlations ranging from 0.231 to 0.358. The proposed approach for diagnostic deviation shows promise as a potential tool for clinicians to find diagnostic errors. Given the vast number of clinical features used in this analysis, further improvements likely need to either take greater account of data structure (what occurs before when) or involve natural language processing. Further work is needed to explain the potential reasons for divergence and to refine and validate the approach for implementation in real-world settings.