Label-Free Identification of White Blood Cells Using Machine Learning.

White blood cell (WBC) differential counting is an established clinical routine to assess patient immune system status. Fluorescent markers and a flow cytometer are required for the current state-of-the-art method for determining WBC differential counts. However, this process requires several sample preparation steps and may adversely disturb the cells. We present a novel label-free approach using an imaging flow cytometer and machine learning algorithms, where live, unstained WBCs were classified. It achieved an average F1-score of 97% and two subtypes of WBCs, B and T lymphocytes, were distinguished from each other with an average F1-score of 78%, a task previously considered impossible for unlabeled samples. We provide an open-source workflow to carry out the procedure. We validated the WBC analysis with unstained samples from 85 donors. The presented method enables robust and highly accurate identification of WBCs, minimizing the disturbance to the cells and leaving marker channels free to answer other biological questions. It also opens the door to employing machine learning for liquid biopsy, here, using the rich information in cell morphology for a wide range of diagnostics of primary blood. © 2019 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

Feasibility of Implementing Group Well Baby/Well Woman Dyad Care at Federally Qualified Health Centers.

OBJECTIVE: Group care has been shown to be effective for delivery of infant well child care. Centering Parenting (CP) is a model of group dyad care for mothers and infants. CP might improve quality and efficiency of preventive care, particularly for low-income families. Federally qualified health centers (FQHCs) might be optimal sites for implementation, however, facilitators and barriers might be unique. The aim of this qualitative study was to assess stakeholder perspectives on the feasibility of implementing CP in FQHCs in Baltimore. METHODS: Semistructured interviews were conducted with mothers, clinicians, staff, and administrators recruited from 2 FQHCs using purposive sampling. Interviews were recorded, transcribed verbatim, and uploaded to Atlas.ti version 7.0 (Atlas.ti Scientific Software Development, GmbH Berlin, Germany) for analysis. Using an inductive thematic analysis approach, 2 investigators coded the transcripts. Matrices of key codes were developed to identify themes and patterns across stakeholder groups. RESULTS: Interviews were completed with 26 mothers and 16 clinicians, staff, and administrators. Most participants considered CP desirable. Facilitators included: peer support and education, emphasis on maternal wellness, and increased patient and clinician satisfaction. Barriers included: exposure to "others," scheduling and coordination of care, productivity, training requirements, and cost. Parenting experience did not appear to affect perspectives on CP. CONCLUSIONS: Perceptions regarding facilitators and barriers to CP implementation in FQHCs are similar to existing group well-child care literature. The benefit of emphasis on maternal wellness is a unique finding. Maternal wellness integration might make CP a particularly desirable model for implementation at FQHCs, but potential systems barriers must be addressed.