Objectives: To explore whether machine learning applied to pediatric critical care data could discover medically pertinent information, we analyzed clinically collected electronic medical record data, after data extraction and preparation, using k-means clustering. Design: Retrospective analysis of electronic medical record ICU data. Setting: Tertiary Children’s Hospital PICU. Patients: Anonymized electronic medical record data from PICU admissions over 10 years. Interventions: None. Measurements and Main Results: Data from 11,384 PICU episodes were cleaned, and specific features were generated. A k-means clustering algorithm was applied, and the stability and medical validity of the resulting 10 clusters were determined. The distribution of mortality, length of stay, use of ventilation and pressors, and diagnostic categories among resulting clusters was analyzed. Clusters had significant prognostic information (p
from Emergency Medicine via xlomafota13 on Inoreader https://ift.tt/2I8phq3
Εγγραφή σε:
Σχόλια ανάρτησης (Atom)
Δημοφιλείς αναρτήσεις
-
[PDF] Καρκίνος του στομάχου -- Αλέξανδρος Γ. Σφακιανάκης Αναπαύσεως 5 Άγιος Νικόλαος Λασιθίου 72100 2841026182
-
Abstract Introduction In recent years, platelet-rich plasma (PRP) has emerged as a promising autologous biological treatment modality fo...
-
Rehab patients are friends and co-workers, which requires additional awareness for rehab medical personnel and preplanning to administer ove...
-
Tales from the Night:: Emergency MR Imaging in Pediatric Patients after Hours Publication date: May 2019 Source: Magnetic Resonance Imaging...
-
blood bank stuff: The basics of crit care transfusion medicine EMCrit by Scott Weingart . from Emergency Medicine via xlomafota13 on I...
-
DELAYED RESPONSE: It is yet another delayed ambulance response to an emergency in D.C. With no ambulance in sight, a man suffering from mult...
-
Fully-featured ICU ventilation for military patient transports under the world's toughest conditions Specially modified for military com...
Δεν υπάρχουν σχόλια:
Δημοσίευση σχολίου