A U - Net Deep Learning Model for Infant Heart Rate Estimation from Ballistography.

Ballistography(BSG) is a non-intrusive and low- cost alternative to electrocardiography (ECG) for heart rate (HR) monitoring in infants. Due to the inter-patient variance and susceptibility to noise, heartbeat detection in the BSG waveform remains a challenge. The aim of this study was to estimate HR from a bed-based pressure mat BSG signal using a deep learning approach. We trained a U-Net deep neural network through supervised learning by deriving ground truth as the location of the heartbeats from simultaneously recorded ECG signals after peak matching. For improved generalization, we modified an existing U - Net to include an IC-layer. A predictive performance of 80% was achieved using the U-Net without the IC-layer. The inclusion of the IC-layer, while improving the generalization ability of the model to detect heartbeats, did not improve the HR estimation performance.

Improving adult immunization equity: Where do the published research literature and existing resources lead?

Evidence suggests that disparities in adult immunization (AI) rates are growing. Providers need adequate patient resources and information about successful interventions to help them engage in effective practices to reduce AI disparities. The primary purposes of this paper were to review and summarize the evidence base regarding interventions to reduce AI disparities and to scan for relevant resources that could support providers in their AI efforts to specifically target disparities. First, building on a literature review conducted by the U.S. Centers for Disease Control and Prevention, we searched the peer-reviewed literature to identify articles that either discussed interventions to reduce AI disparities or provided reasons and associations for disparities. We scanned the articles and conducted an internet search to identify tools and resources to support efforts to improve AI rates. We limited both searches to resources that addressed influenza, pneumococcal, hepatitis B, Tdap, and/or herpes zoster vaccinations. We found that most articles characterized AI disparities, but several discussed strategies for reducing AI disparities, including practice-based changes, communication and health literacy approaches, and partnering with community-based organizations. The resources we identified were largely fact sheets and handouts for patients and journal articles for providers. Most resources pertain to influenza vaccination and Spanish was the most prevalent language after English. More evaluation is needed to assess the health literacy levels of the materials. We conclude that additional research is needed to identify effective ways to reduce AI disparities and more resources are needed to support providers in their efforts. We recommend identifying best practices of high performers, further reviewing the appropriateness and usefulness of available resources, and prioritizing which gaps should be addressed.