Asset Details
Do you wish to reserve the book?
Leveraging Hematologic Single-Cell Measurements for Patient Triage and Outcome Prediction
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
Leveraging Hematologic Single-Cell Measurements for Patient Triage and Outcome Prediction
Do you wish to request the book?
Leveraging Hematologic Single-Cell Measurements for Patient Triage and Outcome Prediction
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
Leveraging Hematologic Single-Cell Measurements for Patient Triage and Outcome Prediction
2025
Overview
Background The complete blood count (CBC) is widely used across nearly all areas of medicine. While standard CBC markers reflect basic summaries of the blood cells, modern hematology analyzers generate many additional markers from the underlying data distributions—collectively referred to as cell population data (CPD). While CPD markers have been studied in targeted clinical settings, their value for general prognostic tasks has not yet been established. In this brief report, we assess whether CPD markers can provide additional prognostic information beyond CBC markers in general patient cohorts. Methods We retrospectively analyzed CBC and CPD markers from over 10 000 patients at a large academic medical center between March 14, 2024, and October 23, 2024. Marker associations with general outcomes (inpatient admission from the emergency department, mortality, and length-of-stay) were analyzed in both univariate and multivariate models. Outcomes were also predicted using CBC- and CPD-based machine learning models. Results Many CPD markers were strongly associated with patient mortality, length-of-stay, and inpatient admission from the emergency department. CPD markers showed consistent outcome associations after stratification by patient demographics and medical specialties, and many retained statistical significance after controlling for commonly used CBC markers. In machine learning modelling, inclusion of CPD markers enhanced predictive performance for mortality [area under the curve (AUC): 0.79] and inpatient admission (AUC: 0.81). Analysis of CPD markers revealed 2 phenotypes: an inflammatory phenotype associated with inpatient admission and a dysregulatory phenotype associated with mortality. Conclusions These results highlight how routinely collected CPD markers may enhance the use of the CBC for evaluation of general patient cohorts.
Publisher
Oxford University Press
Subject
