Predicting discharge dates from the nicu using progress note data

Michael W. Temple, Christoph U. Lehmann, Daniel Fabbri

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

BACKGROUND AND OBJECTIVES: Discharging patients from the NICU may be delayed for nonmedical abstract reasons including the need for medical equipment, parental education, and children's services. We describe a method to predict which patients will be medically ready for discharge in the next 2 to 10 days, providing lead time to address nonmedical reasons for delayed discharge. METHODS: A retrospective study examined 26 features (17 extracted, 9 engineered) from daily progress notes of 4693 patients (103 206 patient-days) from the NICU of a large, academic children's hospital. These data were used to develop a supervised machine learning problem to predict days to discharge (DTD). Random forest classifiers were trained by using examined features and International Classification of Diseases, Ninth Revision-based subpopulations to determine the most important features. RESULTS: Three of the 4 subpopulations (premature, cardiac, gastrointestinal surgery) and all patients combined performed similarly at 2, 4, 7, and 10 DTD with area under the curve (AUC) ranging from 0.854 to 0.865 at 2 DTD and 0.723 to 0.729 at 10 DTD. Patients undergoing neurosurgery performed worse at every DTD measure, scoring 0.749 at 2 DTD and 0.614 at 10 DTD. This model was also able to identify important features and provide rule-of-thumb criteria for patients close to discharge. By using DTD equal to 4 and 2 features (oral percentage of feedings and weight), we constructed a model with an AUC of 0.843. CONCLUSIONS: Using clinical features from daily progress notes provides an accurate method to predict when patients in the NICU are nearing discharge.

Original languageEnglish (US)
Pages (from-to)e395-e405
JournalPediatrics
Volume136
Issue number2
DOIs
StatePublished - Aug 1 2015
Externally publishedYes

Fingerprint

Area Under Curve
Neurosurgery
International Classification of Diseases
Thoracic Surgery
Retrospective Studies
Education
Weights and Measures
Equipment and Supplies
Supervised Machine Learning

ASJC Scopus subject areas

  • Pediatrics, Perinatology, and Child Health

Cite this

Predicting discharge dates from the nicu using progress note data. / Temple, Michael W.; Lehmann, Christoph U.; Fabbri, Daniel.

In: Pediatrics, Vol. 136, No. 2, 01.08.2015, p. e395-e405.

Research output: Contribution to journalArticle

Temple, Michael W. ; Lehmann, Christoph U. ; Fabbri, Daniel. / Predicting discharge dates from the nicu using progress note data. In: Pediatrics. 2015 ; Vol. 136, No. 2. pp. e395-e405.
@article{a1979375343a495c84e8276857d231f4,
title = "Predicting discharge dates from the nicu using progress note data",
abstract = "BACKGROUND AND OBJECTIVES: Discharging patients from the NICU may be delayed for nonmedical abstract reasons including the need for medical equipment, parental education, and children's services. We describe a method to predict which patients will be medically ready for discharge in the next 2 to 10 days, providing lead time to address nonmedical reasons for delayed discharge. METHODS: A retrospective study examined 26 features (17 extracted, 9 engineered) from daily progress notes of 4693 patients (103 206 patient-days) from the NICU of a large, academic children's hospital. These data were used to develop a supervised machine learning problem to predict days to discharge (DTD). Random forest classifiers were trained by using examined features and International Classification of Diseases, Ninth Revision-based subpopulations to determine the most important features. RESULTS: Three of the 4 subpopulations (premature, cardiac, gastrointestinal surgery) and all patients combined performed similarly at 2, 4, 7, and 10 DTD with area under the curve (AUC) ranging from 0.854 to 0.865 at 2 DTD and 0.723 to 0.729 at 10 DTD. Patients undergoing neurosurgery performed worse at every DTD measure, scoring 0.749 at 2 DTD and 0.614 at 10 DTD. This model was also able to identify important features and provide rule-of-thumb criteria for patients close to discharge. By using DTD equal to 4 and 2 features (oral percentage of feedings and weight), we constructed a model with an AUC of 0.843. CONCLUSIONS: Using clinical features from daily progress notes provides an accurate method to predict when patients in the NICU are nearing discharge.",
author = "Temple, {Michael W.} and Lehmann, {Christoph U.} and Daniel Fabbri",
year = "2015",
month = "8",
day = "1",
doi = "10.1542/peds.2015-0456",
language = "English (US)",
volume = "136",
pages = "e395--e405",
journal = "Pediatrics",
issn = "0031-4005",
publisher = "American Academy of Pediatrics",
number = "2",

}

TY - JOUR

T1 - Predicting discharge dates from the nicu using progress note data

AU - Temple, Michael W.

AU - Lehmann, Christoph U.

AU - Fabbri, Daniel

PY - 2015/8/1

Y1 - 2015/8/1

N2 - BACKGROUND AND OBJECTIVES: Discharging patients from the NICU may be delayed for nonmedical abstract reasons including the need for medical equipment, parental education, and children's services. We describe a method to predict which patients will be medically ready for discharge in the next 2 to 10 days, providing lead time to address nonmedical reasons for delayed discharge. METHODS: A retrospective study examined 26 features (17 extracted, 9 engineered) from daily progress notes of 4693 patients (103 206 patient-days) from the NICU of a large, academic children's hospital. These data were used to develop a supervised machine learning problem to predict days to discharge (DTD). Random forest classifiers were trained by using examined features and International Classification of Diseases, Ninth Revision-based subpopulations to determine the most important features. RESULTS: Three of the 4 subpopulations (premature, cardiac, gastrointestinal surgery) and all patients combined performed similarly at 2, 4, 7, and 10 DTD with area under the curve (AUC) ranging from 0.854 to 0.865 at 2 DTD and 0.723 to 0.729 at 10 DTD. Patients undergoing neurosurgery performed worse at every DTD measure, scoring 0.749 at 2 DTD and 0.614 at 10 DTD. This model was also able to identify important features and provide rule-of-thumb criteria for patients close to discharge. By using DTD equal to 4 and 2 features (oral percentage of feedings and weight), we constructed a model with an AUC of 0.843. CONCLUSIONS: Using clinical features from daily progress notes provides an accurate method to predict when patients in the NICU are nearing discharge.

AB - BACKGROUND AND OBJECTIVES: Discharging patients from the NICU may be delayed for nonmedical abstract reasons including the need for medical equipment, parental education, and children's services. We describe a method to predict which patients will be medically ready for discharge in the next 2 to 10 days, providing lead time to address nonmedical reasons for delayed discharge. METHODS: A retrospective study examined 26 features (17 extracted, 9 engineered) from daily progress notes of 4693 patients (103 206 patient-days) from the NICU of a large, academic children's hospital. These data were used to develop a supervised machine learning problem to predict days to discharge (DTD). Random forest classifiers were trained by using examined features and International Classification of Diseases, Ninth Revision-based subpopulations to determine the most important features. RESULTS: Three of the 4 subpopulations (premature, cardiac, gastrointestinal surgery) and all patients combined performed similarly at 2, 4, 7, and 10 DTD with area under the curve (AUC) ranging from 0.854 to 0.865 at 2 DTD and 0.723 to 0.729 at 10 DTD. Patients undergoing neurosurgery performed worse at every DTD measure, scoring 0.749 at 2 DTD and 0.614 at 10 DTD. This model was also able to identify important features and provide rule-of-thumb criteria for patients close to discharge. By using DTD equal to 4 and 2 features (oral percentage of feedings and weight), we constructed a model with an AUC of 0.843. CONCLUSIONS: Using clinical features from daily progress notes provides an accurate method to predict when patients in the NICU are nearing discharge.

UR - http://www.scopus.com/inward/record.url?scp=84938840267&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938840267&partnerID=8YFLogxK

U2 - 10.1542/peds.2015-0456

DO - 10.1542/peds.2015-0456

M3 - Article

C2 - 26216319

AN - SCOPUS:84938840267

VL - 136

SP - e395-e405

JO - Pediatrics

JF - Pediatrics

SN - 0031-4005

IS - 2

ER -