A Comprehensive Approach to Community Recruitment for Clinical and Translational Research

Stacked machine learning models to classify atrial disorders based on clinical ECG features: a method to predict early atrial fibrillation

OBJECTIVES

Atrial Tachycardia (AT) and Left Atrial Enlargement (LAE) are atrial diseases that are significant precursors to Atrial Fibrillation (AF). There are ML models for ECG classification; clinical features-based classification is required. The suggested work aims to create stacked ML models that categorize Sinus Rhythm (SR), Sinus Tachycardia (ST), AT, and LAE signals based on clinical parameters for AF prognosis.

METHODS

The classification was based on thirteen clinical parameters, such as amplitude, time domain ECG aspects, and P-Wave Indices (PWI), such as the ratio of P-wave length and amplitude ((P (ms)/P (µV)), P-wave area (µV*ms), and P-wave terminal force (PTFV1(µV*ms). Apart from classifying the ECG signals, the stacked ML models prioritized the clinical features using a pie formula-based technique.

RESULTS

The Stack 1 model achieves 99% accuracy, sensitivity, precision, and F1 score, while the Stack 2 model achieves 91%, 91%, 94%, and 92% for identifying SR, ST, LAE, and AT, respectively. Both stack models obtained a computational time of 0.06 seconds. PTFV1 (µV*ms), P (ms)/P (µV)), and P-wave area (µV*ms) were ranked as crucial clinical features.

CONCLUSION

Clinical feature-based stacking ML models may help doctors obtain insight into important clinical ECG aspects for early AF prediction.

Use of a Community Engagement and Research Core model to enhance primary care provider recruitment: A case example

Persistent barriers exist to engage rural providers in research and training. Provider shortages exacerbate these challenges, leading to a scarcity of time and limiting motivation to participate in research. We present application of an innovative engagement model to increase rural primary care provider participation in research. Using our Community Engagement and Research Core, we demonstrate that fundamental principles of training and expertise, attention to efficiency and multitasking, and commitment to community are important for addressing provider recruitment barriers. We encourage other Clinical and Translational Science Centers to provide similar services to their local investigators to enhance provider engagement in research.

Community health worker insights on promoting research engagement with diverse populations

Representation of diverse populations in health research enhances our ability to understand the factors that impact health, generalize results, implement findings, and promote social justice. The primary objective of the study was to understand the unique perspectives of frontline community health workers (CHWs) to identify actionable barriers and facilitators that may impact representation of diverse groups in health research. Focus groups with CHWs were conducted followed by thematic analysis. Results revealed five main themes: barriers/risks to research participation, facilitation of research, CHW roles, recommendations, and transparency. A novel finding was that some CHWs see themselves as both facilitators and gatekeepers. As facilitators, CHWs ensure their patient populations receive resources and benefit from being involved in research; as gatekeepers CHWs feel that they protect patient populations from experiencing further trauma, especially when engaging in research. Recognizing that in many communities there is a high reliance and trust with CHWs, can promote genuine and informed participation at all stages of research.

Guidelines for Evaluating the Feasibility of Recruitment in Pilot Studies of Diverse Populations: An Overlooked but Important Component

Background

In health disparities research, studies often fall short of their recruitment goals. Conducting a pilot feasibility study of recruitment in which data are collected systematically on recruitment processes can help investigators refine methods for the larger study. However, there are few guidelines for conducting pilot feasibility studies, and recruitment methods are seldom the focus. Feasibility indicators differ from traditional reports of recruitment results by focusing on the extent to which recruitment goals are met.

Methods

We present an organizing framework for assessing the feasibility of recruitment that includes eight steps, briefly: 1) specify recruitment goals; 2) specify recruitment processes; 3) establish a tracking system for each individual; 4) establish a tracking database for monitoring processes and results; 5) implement recruitment and track each individual's progress; 6) summarize recruitment results; 7) calculate and interpret feasibility measures - were goals met; and 8) if goals were not met, utilize tracking data to modify methods for the larger study. We describe methods within each step, with added details for steps 2-5 (the specific processes). The framework draws from a small literature on recruitment feasibility with a focus on health disparities populations. The guidelines blend well-known methods of recruitment with additional information on calculating feasibility indicators.

Conclusions

These guidelines provide a first step in thinking systematically about recruitment feasibility, to advance the field of measuring feasibility. Feasibility indicators also can be used to track the effectiveness of innovative recruitment strategies as part of building the science of recruitment, especially in disparities populations.

Training needs of investigators and research team members to improve inclusivity in clinical and translational research participation

Despite increasing attention to the importance of diverse research participants, success across the translational research spectrum remains limited. To assess investigator and research team training needs, we conducted a web-based survey exploring barriers in knowledge and practice. Respondents (n = 279) included those affiliated with the University of Wisconsin Institute for Clinical and Translational Research (ICTR). Although all respondents reported an abstract belief in the importance of diversity, factors associated with higher levels of best practices knowledge and implementation included: (1) use of federal funding; (2) having fewer years of experience; (3) recruiting healthy participants; and (4) having recruitment training.