A Hierarchical-Based Learning Approach for Multi-Action Intent Recognition.

Recent applications of wearable inertial measurement units (IMUs) for predicting human movement have often entailed estimating action-level (e.g., walking, running, jumping) and joint-level (e.

Evaluating Quality of Cancer Care in Delaware using Commission on Cancer (CoC) Quality Measures, 2018-2019.

Introduction: American College of Surgeons Commission on Cancer (CoC) quality measures are used to monitor and evaluate metrics among their CoC-accredited programs, which include seven of Delaware's hospitals. The Delaware Department of Health and Social Services, Division of Public Health (DPH) also utilizes these metrics to monitor and evaluate Delaware's overall performance on these standards of care as it relates to the health care provided to cancer patients.

Methods: Delaware Cancer Registry (DCR) cases diagnosed in 2018 and 2019 were selected and were analyzed separately to calculate results for each selected measure by year: HT, nBX, LNoSurg, and RECRTCT.

Sustaining Improvements in Colorectal Cancer Across Delaware:: A Look at Racial Disparities a Decade Later.

A previously initiated statewide effort in Delaware improved outcomes in colorectal cancer (CRC) racial disparities. To examine whether improvements in racial disparities for CRC have been sustained a decade later and the status of Delaware's current cancer burden. Cancer incidence data from the Delaware Cancer Registry, mortality data from the Centers for Disease and Control and Prevention (CDC)'s National Center for Health Statistics, and cancer screening data from CDC's Behavioral Risk Factor Surveillance System were analyzed.

Development of Sub-County Cancer Reporting Zones in Delaware and Example Use Case for Targeted Interventions.

Objective: To describe the Delaware Cancer Registry (DCR)'s participation in the National Cancer Institute (NCI)/North American Association of Central Cancer Registries (NAACCR) Zone Design Project to create sub-county geographic areas ("zones") for use in cancer reporting and geospatial analysis.

Methods: DCR and other stakeholders reviewed up to ten unique zone configurations for each of Delaware's three counties. The zone configurations were created using AZTool and were set to optimize three objectives: create zones that have a minimum and target population of 50,000; are homogenous based on the variables of percent minority, percent below poverty, and percent urban; and are as compact as possible.

The Effect of Sensor Feature Inputs on Joint Angle Prediction across Simple Movements.

The use of wearable sensors, such as inertial measurement units (IMUs), and machine learning for human intent recognition in health-related areas has grown considerably. However, there is limited research exploring how IMU quantity and placement affect human movement intent prediction (HMIP) at the joint level. The objective of this study was to analyze various combinations of IMU input signals to maximize the machine learning prediction accuracy for multiple simple movements.