Browsing by Author "Fischer, Jonathan"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • 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
    Provider Interaction With an Electronic Health Record Notification to Identify Eligible Patients for a Cluster Randomized Trial of Advance Care Planning in Primary Care: Secondary Analysis.
    (Journal of medical Internet research, 2023-05) Ma, Jessica E; Lowe, Jared; Berkowitz, Callie; Kim, Azalea; Togo, Ira; Musser, R Clayton; Fischer, Jonathan; Shah, Kevin; Ibrahim, Salam; Bosworth, Hayden B; Totten, Annette M; Dolor, Rowena

    Background

    Advance care planning (ACP) improves patient-provider communication and aligns care to patient values, preferences, and goals. Within a multisite Meta-network Learning and Research Center ACP study, one health system deployed an electronic health record (EHR) notification and algorithm to alert providers about patients potentially appropriate for ACP and the clinical study.

    Objective

    The aim of the study is to describe the implementation and usage of an EHR notification for referring patients to an ACP study, evaluate the association of notifications with study referrals and engagement in ACP, and assess provider interactions with and perspectives on the notifications.

    Methods

    A secondary analysis assessed provider usage and their response to the notification (eg, acknowledge, dismiss, or engage patient in ACP conversation and refer patient to the clinical study). We evaluated all patients identified by the EHR algorithm during the Meta-network Learning and Research Center ACP study. Descriptive statistics compared patients referred to the study to those who were not referred to the study. Health care utilization, hospice referrals, and mortality as well as documentation and billing for ACP and related legal documents are reported. We evaluated associations between notifications with provider actions (ie, referral to study, ACP not documentation, and ACP billing). Provider free-text comments in the notifications were summarized qualitatively. Providers were surveyed on their satisfaction with the notification.

    Results

    Among the 2877 patients identified by the EHR algorithm over 20 months, 17,047 unique notifications were presented to 45 providers in 6 clinics, who then referred 290 (10%) patients. Providers had a median of 269 (IQR 65-552) total notifications, and patients had a median of 4 (IQR 2-8). Patients with more (over 5) notifications were less likely to be referred to the study than those with fewer notifications (57/1092, 5.2% vs 233/1785, 13.1%; P<.001). The most common free-text comment on the notification was lack of time. Providers who referred patients to the study were more likely to document ACP and submit ACP billing codes (P<.001). In the survey, 11 providers would recommend the notification (n=7, 64%); however, the notification impacted clinical workflow (n=9, 82%) and was difficult to navigate (n=6, 55%).

    Conclusions

    An EHR notification can be implemented to remind providers to both perform ACP conversations and refer patients to a clinical study. There were diminishing returns after the fifth EHR notification where additional notifications did not lead to more trial referrals, ACP documentation, or ACP billing. Creation and optimization of EHR notifications for study referrals and ACP should consider the provider user, their workflow, and alert fatigue to improve implementation and adoption.

    Trial registration

    ClinicalTrials.gov NCT03577002; https://clinicaltrials.gov/ct2/show/NCT03577002.