Using Machine Learning to Predict Early Onset Acute Organ Failure in Critically Ill Intensive Care Unit Patients With Sickle Cell Disease: Retrospective Study.
electronic medical record
hematology
machine learning
multiple organ failure
sickle cell disease
Journal
Journal of medical Internet research
ISSN: 1438-8871
Titre abrégé: J Med Internet Res
Pays: Canada
ID NLM: 100959882
Informations de publication
Date de publication:
13 05 2020
13 05 2020
Historique:
received:
13
05
2019
accepted:
28
01
2020
revised:
18
08
2019
entrez:
14
5
2020
pubmed:
14
5
2020
medline:
18
11
2020
Statut:
epublish
Résumé
Sickle cell disease (SCD) is a genetic disorder of the red blood cells, resulting in multiple acute and chronic complications, including pain episodes, stroke, and kidney disease. Patients with SCD develop chronic organ dysfunction, which may progress to organ failure during disease exacerbations. Early detection of acute physiological deterioration leading to organ failure is not always attainable. Machine learning techniques that allow for prediction of organ failure may enable early identification and treatment and potentially reduce mortality. The aim of this study was to test the hypothesis that machine learning physiomarkers can predict the development of organ dysfunction in a sample of adult patients with SCD admitted to intensive care units (ICUs). We applied diverse machine learning methods, statistical methods, and data visualization techniques to develop classification models to distinguish SCD from controls. We studied 63 sequential SCD patients admitted to ICUs with 163 patient encounters (mean age 30.7 years, SD 9.8 years). A subset of these patient encounters, 22.7% (37/163), met the sequential organ failure assessment criteria. The other 126 SCD patient encounters served as controls. A set of signal processing features (such as fast Fourier transform, energy, and continuous wavelet transform) derived from heart rate, blood pressure, and respiratory rate was identified to distinguish patients with SCD who developed acute physiological deterioration leading to organ failure from patients with SCD who did not meet the criteria. A multilayer perceptron model accurately predicted organ failure up to 6 hours before onset, with an average sensitivity and specificity of 96% and 98%, respectively. This retrospective study demonstrated the viability of using machine learning to predict acute organ failure among hospitalized adults with SCD. The discovery of salient physiomarkers through machine learning techniques has the potential to further accelerate the development and implementation of innovative care delivery protocols and strategies for medically vulnerable patients.
Sections du résumé
BACKGROUND
Sickle cell disease (SCD) is a genetic disorder of the red blood cells, resulting in multiple acute and chronic complications, including pain episodes, stroke, and kidney disease. Patients with SCD develop chronic organ dysfunction, which may progress to organ failure during disease exacerbations. Early detection of acute physiological deterioration leading to organ failure is not always attainable. Machine learning techniques that allow for prediction of organ failure may enable early identification and treatment and potentially reduce mortality.
OBJECTIVE
The aim of this study was to test the hypothesis that machine learning physiomarkers can predict the development of organ dysfunction in a sample of adult patients with SCD admitted to intensive care units (ICUs).
METHODS
We applied diverse machine learning methods, statistical methods, and data visualization techniques to develop classification models to distinguish SCD from controls.
RESULTS
We studied 63 sequential SCD patients admitted to ICUs with 163 patient encounters (mean age 30.7 years, SD 9.8 years). A subset of these patient encounters, 22.7% (37/163), met the sequential organ failure assessment criteria. The other 126 SCD patient encounters served as controls. A set of signal processing features (such as fast Fourier transform, energy, and continuous wavelet transform) derived from heart rate, blood pressure, and respiratory rate was identified to distinguish patients with SCD who developed acute physiological deterioration leading to organ failure from patients with SCD who did not meet the criteria. A multilayer perceptron model accurately predicted organ failure up to 6 hours before onset, with an average sensitivity and specificity of 96% and 98%, respectively.
CONCLUSIONS
This retrospective study demonstrated the viability of using machine learning to predict acute organ failure among hospitalized adults with SCD. The discovery of salient physiomarkers through machine learning techniques has the potential to further accelerate the development and implementation of innovative care delivery protocols and strategies for medically vulnerable patients.
Identifiants
pubmed: 32401216
pii: v22i5e14693
doi: 10.2196/14693
pmc: PMC7254279
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
e14693Informations de copyright
©Akram Mohammed, Pradeep S B Podila, Robert L Davis, Kenneth I Ataga, Jane S Hankins, Rishikesan Kamaleswaran. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 13.05.2020.
Références
Int J Med Inform. 2019 Feb;122:55-62
pubmed: 30623784
JAMA. 2016 Feb 23;315(8):801-10
pubmed: 26903338
Crit Care Med. 1995 Oct;23(10):1638-52
pubmed: 7587228
Pathology. 2017 Jan;49(1):1-9
pubmed: 27914684
Hemoglobin. 2016 Sep;40(5):295-299
pubmed: 27643740
Crit Care Med. 1985 Oct;13(10):818-29
pubmed: 3928249
BMC Bioinformatics. 2008 Jul 22;9:319
pubmed: 18647401
Medicine (Baltimore). 2005 Nov;84(6):363-76
pubmed: 16267411
J Crit Care. 2017 Dec;42:238-242
pubmed: 28797896
Intensive Care Med. 1996 Jul;22(7):707-10
pubmed: 8844239
Pediatr Crit Care Med. 2018 Oct;19(10):e495-e503
pubmed: 30052552
Artif Intell Med. 2003 Sep-Oct;29(1-2):39-60
pubmed: 12957780
Hemoglobin. 1990;14(6):573-98
pubmed: 2101835
J Biomed Inform. 2002 Oct-Dec;35(5-6):352-9
pubmed: 12968784
Proc IEEE Inst Electr Electron Eng. 2016 Feb;104(2):444-466
pubmed: 27765959
Bioinformatics. 2005 Mar 1;21(5):631-43
pubmed: 15374862