Patterns of healthcare utilization according to health equity determinants during the first year of the pandemic at Johns Hopkins Medicine.

Objectives: Rapid telehealth adoption happened at the onset of the coronavirus disease 2019 (COVID-19) pandemic, resulting in a move from in-person predominant to telehealth predominant care delivery. Later, in person visits rebounded with telehealth options remaining. This study aimed to assess differences in healthcare utilization during this changing landscape in terms of health equity determinants. Materials and Methods: This was an observational cohort study of Johns Hopkins Medicine (JHM) patients. We analyzed utilization of video, telephone, and in-person patient-provider visits by eligible patients between March 16, 2019 and December 31, 2020. Percent changes in average weekly patient-provider visits from pre-pandemic (March 16, 2019-June 30, 2019) to early 2020 pandemic (March 16, 2020-June 30, 2020) and from pre-pandemic (July 1, 2019-December 31, 2019) to late 2020 pandemic (July 1, 2020-December 31, 2020). We used a quantile cut off technique to describe disproportionately smaller or greater drops in visits during the first year of the pandemic among health equity determinant groups and according to visit specialty, when compared to the total population. Results: There was a 39% drop in patient-provider visits from the pre-pandemic to the early 2020 pandemic period, and a 24% drop from pre-pandemic to the late 2020 pandemic period. We discovered 21 groups according to health equity determinates and visit departments with patterns of disproportionately smaller or greater drops in visits during the first year of the pandemic, when compared to the total population: Pattern 1 -smaller drop in visits early and late 2020 (age 45-64, Medicare insurance, high poverty and high unemployment; mental health and medical specialty visits -P < .001); Pattern 2 -greater drop in visits early 2020 only (age 65-84; OB/GYN and surgical specialty visits-P < .001); Pattern 3 -greater drop in visits early and late 2020 (age 0-5, age 6-17, age 85+, Asian race, Hispanic or Latino ethnicity, private insurance-P < .001); and Pattern 4-smaller drop in visits in early 2020 when compared to late 2020. The age 18-44 group showed a smaller drop in visits early 2020 and then visit levels similar to the total population late 2020. Primary care visits were similar to the total population early 2020 and then a smaller drop in visits late 2020 (P < .001). Discussion: Our study provides evidence of health equity determinant groups having disproportionally smaller or greater drops in visits during the first year of the pandemic. The observed differences may have been influenced by changing telehealth offerings during the first year of the pandemic. Groups with disproportionately smaller drops in visits early 2020 (Pattern #1 and age 18-44 group in Pattern #4), suggests more success with adopting telehealth among those groups. Whereas groups with disproportionately greater drops in visits early 2020 (Pattern #2 and Pattern #3), suggests less success with telehealth adoption. For Pattern #4, more clarification is needed on how changes in telehealth offerings contributed to the downward trend in visits observed from early to late 2020. Conclusion: We describe 4 main patterns to characterize groups with disproportionately smaller or greater drops in visits during the first year of the pandemic. While this work did not specifically study vulnerable populations, these patterns set the stage for further studies of such groups.

Incorporation of emergent symptoms and genetic covariates improves prediction of aromatase inhibitor therapy discontinuation.

Objectives: Early discontinuation is common among breast cancer patients taking aromatase inhibitors (AIs). Although several predictors have been identified, it is unclear how to simultaneously consider multiple risk factors for an individual. We sought to develop a tool for prediction of AI discontinuation and to explore how predictive value of risk factors changes with time. Materials and Methods: Survival machine learning was used to predict time-to-discontinuation of AIs in 181 women who enrolled in a prospective cohort. Models were evaluated via time-dependent area under the curve (AUC), c-index, and integrated Brier score. Feature importance was analysis was conducted via Shapley Additive Explanations (SHAP) and time-dependence of their predictive value was analyzed by time-dependent AUC. Personalized survival curves were constructed for risk communication. Results: The best-performing model incorporated genetic risk factors and changes in patient-reported outcomes, achieving mean time-dependent AUC of 0.66, and AUC of 0.72 and 0.67 at 6- and 12-month cutoffs, respectively. The most significant features included variants in ESR1 and emergent symptoms. Predictive value of genetic risk factors was highest in the first year of treatment. Decrease in physical function was the strongest independent predictor at follow-up. Discussion and Conclusion: Incorporation of genomic and 3-month follow-up data improved the ability of the models to identify the individuals at risk of AI discontinuation. Genetic risk factors were particularly important for predicting early discontinuers. This study provides insight into the complex nature of AI discontinuation and highlights the importance of incorporating genetic risk factors and emergent symptoms into prediction models.

Factors associated with resistance to SARS-CoV-2 infection discovered using large-scale medical record data and machine learning.

There have been over 621 million cases of COVID-19 worldwide with over 6.5 million deaths. Despite the high secondary attack rate of COVID-19 in shared households, some exposed individuals do not contract the virus. In addition, little is known about whether the occurrence of COVID-19 resistance differs among people by health characteristics as stored in the electronic health records (EHR). In this retrospective analysis, we develop a statistical model to predict COVID-19 resistance in 8,536 individuals with prior COVID-19 exposure using demographics, diagnostic codes, outpatient medication orders, and count of Elixhauser comorbidities in EHR data from the COVID-19 Precision Medicine Platform Registry. Cluster analyses identified 5 patterns of diagnostic codes that distinguished resistant from non-resistant patients in our study population. In addition, our models showed modest performance in predicting COVID-19 resistance (best performing model AUROC = 0.61). Monte Carlo simulations conducted indicated that the AUROC results are statistically significant (p < 0.001) for the testing set. We hope to validate the features found to be associated with resistance/non-resistance through more advanced association studies.

Recurrent preterm birth risk assessment for two delivery subtypes: A multivariable analysis.

OBJECTIVE: The study sought to develop and apply a framework that uses a clinical phenotyping tool to assess risk for recurrent preterm birth. MATERIALS AND METHODS: We extended an existing clinical phenotyping tool and applied a 4-step framework for our retrospective cohort study. The study was based on data collected in the Genomic and Proteomic Network for Preterm Birth Research Longitudinal Cohort Study (GPN-PBR LS). A total of 52 sociodemographic, clinical and obstetric history-related risk factors were selected for the analysis. Spontaneous and indicated delivery subtypes were analyzed both individually and in combination. Chi-square analysis and Kaplan-Meier estimate were used for univariate analysis. A Cox proportional hazards model was used for multivariable analysis. RESULTS: : A total of 428 women with a history of spontaneous preterm birth qualified for our analysis. The predictors of preterm delivery used in multivariable model were maternal age, maternal race, household income, marital status, previous caesarean section, number of previous deliveries, number of previous abortions, previous birth weight, cervical insufficiency, decidual hemorrhage, and placental dysfunction. The models stratified by delivery subtype performed better than the naïve model (concordance 0.76 for the spontaneous model, 0.87 for the indicated model, and 0.72 for the naïve model). DISCUSSION: The proposed 4-step framework is effective to analyze risk factors for recurrent preterm birth in a retrospective cohort and possesses practical features for future analyses with other data sources (eg, electronic health record data). CONCLUSIONS: We developed an analytical framework that utilizes a clinical phenotyping tool and performed a survival analysis to analyze risk for recurrent preterm birth.