Hypertension, renin-angiotensin-aldosterone-system-blocking agents, and COVID-19.

BACKGROUND: There have been concerns regarding the safety of renin-angiotensin-aldosterone-system (RAAS)-blocking agents including angiotensin-converting enzyme inhibitors (ACEI) and angiotensin receptor blockers (ARB) during the coronavirus disease 2019 (COVID-19) pandemic. This study sought to evaluate the impact of hypertension and the use of ACEI/ARB on clinical severity in patients with COVID-19. METHODS: A total of 3,788 patients aged 30 years or older who were confirmed with COVID-19 with real time reverse transcription polymerase chain reaction were identified from a claims-based cohort in Korea. The primary study outcome was severe clinical events, a composite of intensive care unit admission, need for ventilator care, and death. RESULTS: Patients with hypertension (n = 1,190, 31.4 %) were older and had higher prevalence of comorbidities than those without hypertension. The risk of the primary study outcome was significantly higher in the hypertension group, even after multivariable adjustment (adjusted odds ratio [aOR], 1.67; 95 % confidence interval [CI], 1.04 to 2.69). Among 1,044 patients with hypertensive medical treatment, 782 (74.9 %) were on ACEI or ARB. The ACEI/ARB subgroup had a lower risk of severe clinical outcomes compared to the no ACEI/ARB group, but this did not remain significant after multivariable adjustment (aOR, 0.68; 95 % CI, 0.41 to 1.15). CONCLUSIONS: Patients with hypertension had worse COVID-19 outcomes than those without hypertension, while the use of RAAS-blocking agents was not associated with increased risk of any adverse study outcomes. The use of ACE inhibitors or ARBs did not increase the risk of adverse COVID-19 outcomes, supporting current guidance to continue these medications when indicated.

Predicting Inpatient Medication Orders From Electronic Health Record Data.

In a general inpatient population, we predicted patient-specific medication orders based on structured information in the electronic health record (EHR). Data on over three million medication orders from an academic medical center were used to train two machine-learning models: A deep learning sequence model and a logistic regression model. Both were compared with a baseline that ranked the most frequently ordered medications based on a patient's discharge hospital service and amount of time since admission. Models were trained to predict from 990 possible medications at the time of order entry. Fifty-five percent of medications ordered by physicians were ranked in the sequence model's top-10 predictions (logistic model: 49%) and 75% ranked in the top-25 (logistic model: 69%). Ninety-three percent of the sequence model's top-10 prediction sets contained at least one medication that physicians ordered within the next day. These findings demonstrate that medication orders can be predicted from information present in the EHR.

Scalable and accurate deep learning with electronic health records.

Predictive modeling with electronic health record (EHR) data is anticipated to drive personalized medicine and improve healthcare quality. Constructing predictive statistical models typically requires extraction of curated predictor variables from normalized EHR data, a labor-intensive process that discards the vast majority of information in each patient's record. We propose a representation of patients' entire raw EHR records based on the Fast Healthcare Interoperability Resources (FHIR) format. We demonstrate that deep learning methods using this representation are capable of accurately predicting multiple medical events from multiple centers without site-specific data harmonization. We validated our approach using de-identified EHR data from two US academic medical centers with 216,221 adult patients hospitalized for at least 24 h. In the sequential format we propose, this volume of EHR data unrolled into a total of 46,864,534,945 data points, including clinical notes. Deep learning models achieved high accuracy for tasks such as predicting: in-hospital mortality (area under the receiver operator curve [AUROC] across sites 0.93-0.94), 30-day unplanned readmission (AUROC 0.75-0.76), prolonged length of stay (AUROC 0.85-0.86), and all of a patient's final discharge diagnoses (frequency-weighted AUROC 0.90). These models outperformed traditional, clinically-used predictive models in all cases. We believe that this approach can be used to create accurate and scalable predictions for a variety of clinical scenarios. In a case study of a particular prediction, we demonstrate that neural networks can be used to identify relevant information from the patient's chart.

The Supervised Hierarchical Dirichlet Process.

We propose the supervised hierarchical Dirichlet process (sHDP), a nonparametric generative model for the joint distribution of a group of observations and a response variable directly associated with that whole group. We compare the sHDP with another leading method for regression on grouped data, the supervised latent Dirichlet allocation (sLDA) model. We evaluate our method on two real-world classification problems and two real-world regression problems. Bayesian nonparametric regression models based on the Dirichlet process, such as the Dirichlet process-generalised linear models (DP-GLM) have previously been explored; these models allow flexibility in modelling nonlinear relationships. However, until now, hierarchical Dirichlet process (HDP) mixtures have not seen significant use in supervised problems with grouped data since a straightforward application of the HDP on the grouped data results in learnt clusters that are not predictive of the responses. The sHDP solves this problem by allowing for clusters to be learnt jointly from the group structure and from the label assigned to each group.