Supporting ColoREctal Equitable Navigation (SCREEN): a protocol for a stepped-wedge cluster randomized trial for patient navigation in primary care.

BACKGROUND: Black individuals in the United States (US) have a higher incidence of and mortality from colorectal cancer (CRC) compared to other racial groups, and CRC is the second leading cause of death among Hispanic/Latino populations in the US. Patient navigation is an evidence-based approach to narrow inequities in cancer screening among Black and Hispanic/Latino patients. Despite this, limited healthcare systems have implemented patient navigation for screening at scale. METHODS: We are conducting a stepped-wedge cluster randomized trial of 15 primary care clinics with six steps of six-month duration to scale a patient navigation program to improve screening rates among Black and Hispanic/Latino patients. After six months of baseline data collection with no intervention we will randomize clinics, whereby three clinics will join the intervention arm every six months until all clinics cross over to intervention. During the intervention roll out we will conduct training and education for clinics, change infrastructure in the electronic health record, create stakeholder relationships, assess readiness, and deliver iterative feedback. Framed by the Practical, Robust Implementation Sustainment Model (PRISM) we will focus on effectiveness, reach, provider adoption, and implementation. We will document adaptations to both the patient navigation intervention and to implementation strategies. To address health equity, we will engage multilevel stakeholder voices through interviews and a community advisory board to plan, deliver, adapt, measure, and disseminate study progress. Provider-level feedback will include updates on disparities in screening orders and completions. DISCUSSION: Primary care clinics are poised to close disparity gaps in CRC screening completion but may lack an understanding of the magnitude of these gaps and how to address them. We aim to understand how to tailor a patient navigation program for CRC screening to patients and providers across diverse clinics with wide variation in baseline screening rates, payor mix, proximity to specialty care, and patient volume. Findings from this study will inform other primary care practices and health systems on effective and sustainable strategies to deliver patient navigation for CRC screening among racial and ethnic minorities. TRIAL REGISTRATION: NCT06401174.

Protocol for Evaluating Remote Patient Blood Pressure Monitoring Adapted to Black Women and Birthing Persons.

Cardiovascular disease is the leading cause of maternal death among Black women in the United States. A large, urban hospital adopted remote patient blood pressure monitoring (RBPM) to increase blood pressure monitoring and improve the management of hypertensive disorders of pregnancy (HDP) by reducing the time to diagnosis of HDP. The digital platform integrates with the electronic health record (EHR), automatically inputting RBPM readings to the patients' chart; communicating elevated blood pressure values to the healthcare team; and offers a partial offset of the cost through insurance plans. It also allows for customization of the blood pressure values that prompt follow-up to the patient's risk category. This paper describes a protocol for evaluating its impact. Objective 1 is to measure the effect of the digitally supported RBPM on the time to diagnosis of HDP. Objective 2 is to test the effect of cultural tailoring to Black participants. The ability to tailor digital content provides the opportunity to test the added value of promoting social identification with the intervention, which may help achieve equity in severe maternal morbidity events related to HDP. Evaluation of this intervention will contribute to the growing literature on digital health interventions to improve maternity care in the United States.

Using Machine Learning to Capture Quality Metrics from Natural Language: A Case Study of Diabetic Eye Exams.

BACKGROUND AND OBJECTIVE: The prevalence of value-based payment models has led to an increased use of the electronic health record to capture quality measures, necessitating additional documentation requirements for providers. METHODS: This case study uses text mining and natural language processing techniques to identify the timely completion of diabetic eye exams (DEEs) from 26,203 unique clinician notes for reporting as an electronic clinical quality measure (eCQM). Logistic regression and support vector machine (SVM) using unbalanced and balanced datasets, using the synthetic minority over-sampling technique (SMOTE) algorithm, were evaluated on precision, recall, sensitivity, and f1-score for classifying records positive for DEE. We then integrate a high precision DEE model to evaluate free-text clinical narratives from our clinical EHR system. RESULTS: Logistic regression and SVM models had comparable f1-score and specificity metrics with models trained and validated with no oversampling favoring precision over recall. SVM with and without oversampling resulted in the best precision, 0.96, and recall, 0.85, respectively. These two SVM models were applied to the unannotated 31,585 text segments representing 24,823 unique records and 13,714 unique patients. The number of records classified as positive for DEE using the SVM models ranged from 667 to 8,935 (2.7-36% out of 24,823, respectively). Unique patients classified as positive for DEE ranged from 3.5 to 41.8% highlighting the potential utility of these models. DISCUSSION: We believe the impact of oversampling on SVM model performance to be caused by the potential of overfitting of the SVM SMOTE model on the synthesized data and the data synthesis process. However, the specificities of SVM with and without SMOTE were comparable, suggesting both models were confident in their negative predictions. By prioritizing to implement the SVM model with higher precision over sensitivity or recall in the categorization of DEEs, we can provide a highly reliable pool of results that can be documented through automation, reducing the burden of secondary review. Although the focus of this work was on completed DEEs, this method could be applied to completing other necessary documentation by extracting information from natural language in clinician notes. CONCLUSION: By enabling the capture of data for eCQMs from documentation generated by usual clinical practice, this work represents a case study in how such techniques can be leveraged to drive quality without increasing clinician work.

Modeling patient-related workload in the emergency department using electronic health record data.

INTRODUCTION: Understanding and managing clinician workload is important for clinician (nurses, physicians and advanced practice providers) occupational health as well as patient safety. Efforts have been made to develop strategies for managing clinician workload by improving patient assignment. The goal of the current study is to use electronic health record (EHR) data to predict the amount of work that individual patients contribute to clinician workload (patient-related workload). METHODS: One month of EHR data was retrieved from an emergency department (ED). A list of workload indicators and five potential workload proxies were extracted from the data. Linear regression and four machine learning classification algorithms were utilized to model the relationship between the indicators and the proxies. RESULTS: Linear regression proved that the indicators explained a substantial amount of variance of the proxies (four out of five proxies were modeled with R2 > 0.80). Classification algorithms also showed success in classifying a patient as having high or low task demand based on data from early in the ED visit (e.g. 80 % accurate binary classification with data from the first hour). CONCLUSION: The main contribution of this study is demonstrating the potential of using EHR data to predict patient-related workload automatically in the ED. The predicted workload can potentially help in managing clinician workload by supporting decisions around the assignment of new patients to providers. Future work should focus on identifying the relationship between workload proxies and actual workload, as well as improving prediction performance of regression and multi-class classification.