Browsing by Author "Song, Yiqiang"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Development and validation of a pragmatic natural language processing approach to identifying falls in older adults in the emergency department
    (Biomed Central, 2019-07-22) Patterson, Brian W.; Jacobsohn, Gwen C.; Shah, Manish N.; Song, Yiqiang; Maru, Apoorva; Venkatesh, Arjun K.; Zhong, Monica; Taylor, Katherine; Hamedani, Azita G.; Mendonça, Eneida A.; Pediatrics, IU School of Medicine
    BACKGROUND: Falls among older adults are both a common reason for presentation to the emergency department, and a major source of morbidity and mortality. It is critical to identify fall patients quickly and reliably during, and immediately after, emergency department encounters in order to deliver appropriate care and referrals. Unfortunately, falls are difficult to identify without manual chart review, a time intensive process infeasible for many applications including surveillance and quality reporting. Here we describe a pragmatic NLP approach to automating fall identification. METHODS: In this single center retrospective review, 500 emergency department provider notes from older adult patients (age 65 and older) were randomly selected for analysis. A simple, rules-based NLP algorithm for fall identification was developed and evaluated on a development set of 1084 notes, then compared with identification by consensus of trained abstractors blinded to NLP results. RESULTS: The NLP pipeline demonstrated a recall (sensitivity) of 95.8%, specificity of 97.4%, precision of 92.0%, and F1 score of 0.939 for identifying fall events within emergency physician visit notes, as compared to gold standard manual abstraction by human coders. CONCLUSIONS: Our pragmatic NLP algorithm was able to identify falls in ED notes with excellent precision and recall, comparable to that of more labor-intensive manual abstraction. This finding offers promise not just for improving research methods, but as a potential for identifying patients for targeted interventions, quality measure development and epidemiologic surveillance.
  • Thumbnail Image
    Item
    Exploring Racial and Age Disproportionalities in COVID-19 Positive Pediatric Cohort
    (Indiana Medical Student Program for Research and Scholarship (IMPRS), 2020-12-15) Freeman, Emily; Song, Yiqiang; Allen, Katie; Hui, Siu; Mendonca, Eneida; Department of Pediatrics, IU School of Medicine
    Background: Social and health inequities place marginalized populations at increased risk of contracting the novel coronavirus 2019 (COVID-19). While COVID-19 literature continues to accumulate, there remains a lack of comprehensive epidemiological data on COVID-19 in children. The study aims to identify demographic trends in disease severity amongst COVID-19 positive pediatric patients. Methods: We analyzed the medical records of 2217 laboratory-confirmed COVID-19 pediatric patients, ages 0-18, across Indiana. Working with Regenstrief Institute Center of Biomedical Informatics, data was extracted from the databases of Indiana Network for Patient Care, Indiana University Health, and Eskenazi Health from February 28th, 2020 to July 13th, 2020. Factors of interest were age, race, and ethnicity. The study assessed the clinical outcome of disease severity which was defined by one of the following clinical designations: outpatient management exclusively, emergency care without hospital admission, non-pediatric intensive care unit (PICU) hospitalization, PICU hospitalization, and death. Results: The laboratory confirmed COVID-19 pediatric cohort was composed of 12.2% (N= 270) Black or African American, 49.3% (N=1094) white, and 3.2% (N= 71) American Indian/Alaska Native, Asian/Pacific Islander, and Multiracial combined group. 34.4% of Black or African American patients required emergency (12.2%) or inpatient care (22.2%) while 24.4% white patients required emergency (7.0%) or inpatient care (17.3%). 17.6% of the cohort was 0-5 years old, 24.8% was 6-12 years old, and 57.6% was 13-18 years old. 30.9% of the 0-5 age group required emergency or inpatient care while the percentages of the 6-12 age group and 13-18 age group requiring emergency or inpatient care were 20.6% and 18.9%, respectively. Conclusion: While our data is preliminary and requires additional validation, our exploration of racial and age disproportionalities in pediatric coronavirus severity serves to expand on the current COVID-19 literature and understanding of this virus.