English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Patient monitoring is vital in all stages of care. We here report thedevelopment and validation of ICU length of stay and mortality predictionmodels. The models will be used in an intelligent ICU patient monitoring moduleof an Intelligent Remote Patient Monitoring (IRPM) framework that monitors thehealth status of patients, and generates timely alerts, maneuver guidance, orreports when adverse medical conditions are predicted. We utilized the publiclyavailable Medical Information Mart for Intensive Care (MIMIC) database toextract ICU stay data for adult patients to build two prediction models: onefor mortality prediction and another for ICU length of stay. For the mortalitymodel, we applied six commonly used machine learning (ML) binary classificationalgorithms for predicting the discharge status (survived or not). For thelength of stay model, we applied the same six ML algorithms for binaryclassification using the median patient population ICU stay of 2.64 days. Forthe regression-based classification, we used two ML algorithms for predictingthe number of days. We built two variations of each prediction model: one using12 baseline demographic and vital sign features, and the other based on ourproposed quantiles approach, in which we use 21 extra features engineered fromthe baseline vital sign features, including their modified means, standarddeviations, and quantile percentages. We could perform predictive modeling withminimal features while maintaining reasonable performance using the quantilesapproach. The best accuracy achieved in the mortality model was approximately89% using the random forest algorithm. The highest accuracy achieved in thelength of stay model, based on the population median ICU stay (2.64 days), wasapproximately 65% using the random forest algorithm.

Predicting Intensive Care Unit Length of Stay and Mortality Using Patient Vital Signs: Machine Learning Model Development and Validation