Aligning prediction models with clinical information needs: infant sepsis case study.

Objective: Sepsis recognition among infants in the Neonatal Intensive Care Unit (NICU) is challenging and delays in recognition can result in devastating consequences. Although predictive models may improve sepsis outcomes, clinical adoption has been limited. Our focus was to align model behavior with clinician information needs by developing a machine learning (ML) pipeline with two components: (1) a model to predict baseline sepsis risk and (2) a model to detect evolving (dynamic) sepsis risk due to physiologic changes.

Intervention, individual, and contextual determinants to high adherence to structured family-centered rounds: a national multi-site mixed methods study.

Background: Effective communication in transitions between healthcare team members is associated with improved patient safety and experience through a clinically meaningful reduction in serious safety events. Family-centered rounds (FCR) can serve a critical role in interprofessional and patient-family communication. Despite widespread support, FCRs are not utilized consistently in many institutions.

Getting to Complete and Accurate Medication Lists During the Transition to Home Health Care.

Objectives: Characterize the work that home health care (HHC) admission nurses complete as part of the medication reconciliation tasks, explore the impact of shared electronic medication data (interoperability) from the referral source on medication reconciliation, and highlight opportunities to enhance medication reconciliation with respect to transition in care to HHC agencies.

Design: Observational field study.

Settings And Participants: Three diverse Pennsylvania HHC agencies; each used different electronic health record systems with different interoperability characteristics.

Using Topic Modeling to Develop Multi-level Descriptions of Naturalistic Driving Data from Drivers with and without Sleep Apnea.

One challenge in using naturalistic driving data is producing a holistic analysis of these highly variable datasets. Typical analyses focus on isolated events, such as large g-force accelerations indicating a possible near-crash. Examining isolated events is ill-suited for identifying patterns in continuous activities such as maintaining vehicle control.

Variations on a theme: Topic modeling of naturalistic driving data.

This paper introduces Probabilistic Topic Modeling (PTM) as a promising approach to naturalistic driving data analyses. Naturalistic driving data present an unprecedented opportunity to understand driver behavior. Novel strategies are needed to achieve a more complete picture of these datasets than is provided by the local event-based analytic strategy that currently dominates the field.