Browsing by Author "Pavon, Juliessa M"

Filter results by typing the first few letters
Now showing 1 - 4 of 4
  • Thumbnail Image
    ItemOpen Access
    Impact of Hearing Aid Use on Falls and Falls-Related Injury: Results From the Health and Retirement Study.
    (Ear and hearing, 2022-03) Riska, Kristal M; Peskoe, Sarah B; Kuchibhatla, Maragatha; Gordee, Alexander; Pavon, Juliessa M; Kim, Se Eun; West, Jessica S; Smith, Sherri L

    Objectives

    Falls are considered a significant public health issue and falls risk increases with age. There are many age-related physiologic changes that occur that increase postural instability and the risk for falls (i.e., age-related sensory declines in vision, vestibular, somatosensation, age-related orthopedic changes, and polypharmacy). Hearing loss has been shown to be an independent risk factor for falls. The primary objective of this study was to determine if hearing aid use modified (reduced) the association between self-reported hearing status and falls or falls-related injury. We hypothesized that hearing aid use would reduce the impact of hearing loss on the odds of falling and falls-related injury. If hearing aid users have reduced odds of falling compared with nonhearing aid users, then that would have an important implications for falls prevention healthcare.

    Design

    Data were drawn from the 2004-2016 surveys of the Health and Retirement Study (HRS). A generalized estimating equation approach was used to fit logistic regression models to determine whether or not hearing aid use modifies the odds of falling and falls injury associated with self-reported hearing status.

    Results

    A total of 17,923 individuals were grouped based on a self-reported history of falls. Self-reported hearing status was significantly associated with odds of falling and with falls-related injury when controlling for demographic factors and important health characteristics. Hearing aid use was included as an interaction in the fully-adjusted models and the results showed that there was no difference in the association between hearing aid users and nonusers for either falls or falls-related injury.

    Conclusions

    The results of the present study show that when examining self-reported hearing status in a longitudinal sample, hearing aid use does not impact the association between self-reported hearing status and the odds of falls or falls-related injury.
  • Thumbnail Image
    ItemOpen Access
    Machine learning functional impairment classification with electronic health record data.
    (Journal of the American Geriatrics Society, 2023-09) Pavon, Juliessa M; Previll, Laura; Woo, Myung; Henao, Ricardo; Solomon, Mary; Rogers, Ursula; Olson, Andrew; Fischer, Jonathan; Leo, Christopher; Fillenbaum, Gerda; Hoenig, Helen; Casarett, David

    Background

    Poor functional status is a key marker of morbidity, yet is not routinely captured in clinical encounters. We developed and evaluated the accuracy of a machine learning algorithm that leveraged electronic health record (EHR) data to provide a scalable process for identification of functional impairment.

    Methods

    We identified a cohort of patients with an electronically captured screening measure of functional status (Older Americans Resources and Services ADL/IADL) between 2018 and 2020 (N = 6484). Patients were classified using unsupervised learning K means and t-distributed Stochastic Neighbor Embedding into normal function (NF), mild to moderate functional impairment (MFI), and severe functional impairment (SFI) states. Using 11 EHR clinical variable domains (832 variable input features), we trained an Extreme Gradient Boosting supervised machine learning algorithm to distinguish functional status states, and measured prediction accuracies. Data were randomly split into training (80%) and test (20%) sets. The SHapley Additive Explanations (SHAP) feature importance analysis was used to list the EHR features in rank order of their contribution to the outcome.

    Results

    Median age was 75.3 years, 62% female, 60% White. Patients were classified as 53% NF (n = 3453), 30% MFI (n = 1947), and 17% SFI (n = 1084). Summary of model performance for identifying functional status state (NF, MFI, SFI) was AUROC (area under the receiving operating characteristic curve) 0.92, 0.89, and 0.87, respectively. Age, falls, hospitalization, home health use, labs (e.g., albumin), comorbidities (e.g., dementia, heart failure, chronic kidney disease, chronic pain), and social determinants of health (e.g., alcohol use) were highly ranked features in predicting functional status states.

    Conclusion

    A machine learning algorithm run on EHR clinical data has potential utility for differentiating functional status in the clinical setting. Through further validation and refinement, such algorithms can complement traditional screening methods and result in a population-based strategy for identifying patients with poor functional status who need additional health resources.
  • Thumbnail Image
    ItemOpen Access
    Poor Adherence to Risk Stratification Guidelines Results in Overuse of Venous Thromboembolism Prophylaxis in Hospitalized Older Adults.
    (Journal of hospital medicine, 2018-06) Pavon, Juliessa M; Sloane, Richard J; Pieper, Carl F; Colón-Emeric, Cathleen S; Cohen, Harvey J; Gallagher, David; Morey, Miriam C; McCarty, Midori; Ortel, Thomas L; Hastings, Susan N
  • Thumbnail Image
    ItemOpen Access
    Potential Targets for Deprescribing in Medically Complex Older Adults with Suspected Cognitive Impairment.
    (Geriatrics (Basel, Switzerland), 2022-05) Pavon, Juliessa M; Berkowitz, Theodore SZ; Smith, Valerie A; Hughes, Jaime M; Hung, Anna; Hastings, Susan N
    Deprescribing may be particularly beneficial in patients with medical complexity and suspected cognitive impairment (CI). We describe central nervous system (CNS) medication use and side effects in this population and explore the relationship between anticholinergic burden and sleep. We conducted a cross-sectional analysis of baseline data from a pilot randomized-controlled trial in older adult veterans with medical complexity (Care Assessment Need score > 90), and suspected CI (Telephone Interview for Cognitive Status score 20−31). CNS medication classes included antipsychotics, benzodiazepines, H2-receptor antagonists, hypnotics, opioids, and skeletal muscle relaxants. We also coded anticholinergic-active medications according to their Anticholinergic Cognitive Burden (ACB) score. Other measures included self-reported medication side effects and the Pittsburgh Sleep Quality Index (PSQI). ACB association with sleep (PSQI) was examined using adjusted linear regression. In this sample (N = 40), the mean number of prescribed CNS medications was 2.2 (SD 1.5), 65% experienced ≥ 1 side effect, and 50% had an ACB score ≥ 3 (high anticholinergic exposure). The ACB score ≥ 3 compared to ACB < 3 was not significantly associated with PSQI scores (avg diff in score = −0.1, 95% CI −2.1, 1.8). Although results did not demonstrate a clear relationship with worsened sleep, significant side effects and anticholinergic burden support the deprescribing need in this population.