Cognitive phenotypes 1 month after ICU discharge in mechanically ventilated patients: a prospective observational cohort study.
Cognition in ICU survivors
Critical illness
Neuropsychological profiles
Post-intensive care syndrome
Journal
Critical care (London, England)
ISSN: 1466-609X
Titre abrégé: Crit Care
Pays: England
ID NLM: 9801902
Informations de publication
Date de publication:
21 10 2020
21 10 2020
Historique:
received:
22
04
2020
accepted:
06
10
2020
entrez:
22
10
2020
pubmed:
23
10
2020
medline:
2
6
2021
Statut:
epublish
Résumé
ICU patients undergoing invasive mechanical ventilation experience cognitive decline associated with their critical illness and its management. The early detection of different cognitive phenotypes might reveal the involvement of diverse pathophysiological mechanisms and help to clarify the role of the precipitating and predisposing factors. Our main objective is to identify cognitive phenotypes in critically ill survivors 1 month after ICU discharge using an unsupervised machine learning method, and to contrast them with the classical approach of cognitive impairment assessment. For descriptive purposes, precipitating and predisposing factors for cognitive impairment were explored. A total of 156 mechanically ventilated critically ill patients from two medical/surgical ICUs were prospectively studied. Patients with previous cognitive impairment, neurological or psychiatric diagnosis were excluded. Clinical variables were registered during ICU stay, and 100 patients were cognitively assessed 1 month after ICU discharge. The unsupervised machine learning K-means clustering algorithm was applied to detect cognitive phenotypes. Exploratory analyses were used to study precipitating and predisposing factors for cognitive impairment. K-means testing identified three clusters (K) of patients with different cognitive phenotypes: K1 (n = 13), severe cognitive impairment in speed of processing (92%) and executive function (85%); K2 (n = 33), moderate-to-severe deficits in learning-memory (55%), memory retrieval (67%), speed of processing (36.4%) and executive function (33.3%); and K3 (n = 46), normal cognitive profile in 89% of patients. Using the classical approach, moderate-to-severe cognitive decline was recorded in 47% of patients, while the K-means method accurately classified 85.9%. The descriptive analysis showed significant differences in days (p = 0.016) and doses (p = 0.039) with opioid treatment in K1 vs. K2 and K3. In K2, there were more women, patients were older and had more comorbidities (p = 0.001) than in K1 or K3. Cognitive reserve was significantly (p = 0.001) higher in K3 than in K1 or K2. One month after ICU discharge, three groups of patients with different cognitive phenotypes were identified through an unsupervised machine learning method. This novel approach improved the classical classification of cognitive impairment in ICU survivors. In the exploratory analysis, gender, age and the level of cognitive reserve emerged as relevant predisposing factors for cognitive impairment in ICU patients. ClinicalTrials.gov Identifier:NCT02390024; March 17,2015.
Sections du résumé
BACKGROUND
ICU patients undergoing invasive mechanical ventilation experience cognitive decline associated with their critical illness and its management. The early detection of different cognitive phenotypes might reveal the involvement of diverse pathophysiological mechanisms and help to clarify the role of the precipitating and predisposing factors. Our main objective is to identify cognitive phenotypes in critically ill survivors 1 month after ICU discharge using an unsupervised machine learning method, and to contrast them with the classical approach of cognitive impairment assessment. For descriptive purposes, precipitating and predisposing factors for cognitive impairment were explored.
METHODS
A total of 156 mechanically ventilated critically ill patients from two medical/surgical ICUs were prospectively studied. Patients with previous cognitive impairment, neurological or psychiatric diagnosis were excluded. Clinical variables were registered during ICU stay, and 100 patients were cognitively assessed 1 month after ICU discharge. The unsupervised machine learning K-means clustering algorithm was applied to detect cognitive phenotypes. Exploratory analyses were used to study precipitating and predisposing factors for cognitive impairment.
RESULTS
K-means testing identified three clusters (K) of patients with different cognitive phenotypes: K1 (n = 13), severe cognitive impairment in speed of processing (92%) and executive function (85%); K2 (n = 33), moderate-to-severe deficits in learning-memory (55%), memory retrieval (67%), speed of processing (36.4%) and executive function (33.3%); and K3 (n = 46), normal cognitive profile in 89% of patients. Using the classical approach, moderate-to-severe cognitive decline was recorded in 47% of patients, while the K-means method accurately classified 85.9%. The descriptive analysis showed significant differences in days (p = 0.016) and doses (p = 0.039) with opioid treatment in K1 vs. K2 and K3. In K2, there were more women, patients were older and had more comorbidities (p = 0.001) than in K1 or K3. Cognitive reserve was significantly (p = 0.001) higher in K3 than in K1 or K2.
CONCLUSION
One month after ICU discharge, three groups of patients with different cognitive phenotypes were identified through an unsupervised machine learning method. This novel approach improved the classical classification of cognitive impairment in ICU survivors. In the exploratory analysis, gender, age and the level of cognitive reserve emerged as relevant predisposing factors for cognitive impairment in ICU patients.
TRIAL REGISTRATION
ClinicalTrials.gov Identifier:NCT02390024; March 17,2015.
Identifiants
pubmed: 33087171
doi: 10.1186/s13054-020-03334-2
pii: 10.1186/s13054-020-03334-2
pmc: PMC7579874
doi:
Banques de données
ClinicalTrials.gov
['NCT02390024']
Types de publication
Journal Article
Observational Study
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
618Subventions
Organisme : Instituto de Salud Carlos III
ID : PI13/02204
Pays : International
Organisme : Instituto de Salud Carlos III
ID : PI16/01606
Pays : International
Références
Intensive Care Med. 2006 Jun;32(6):923-6
pubmed: 16525845
PLoS Med. 2017 Mar 21;14(3):e1002259
pubmed: 28323829
J Trauma. 2011 Oct;71(4):860-6
pubmed: 21537211
Crit Care Med. 2010 Jul;38(7):1513-20
pubmed: 20473145
Intensive Care Med. 2013 Mar;39(3):376-86
pubmed: 23328935
Neurobiol Aging. 2017 Dec;60:164-172
pubmed: 28968586
Brain Inj. 2010;24(12):1478-84
pubmed: 20858026
Acta Anaesthesiol Scand. 2011 Oct;55(9):1044-51
pubmed: 22092200
Chest. 2018 Nov;154(5):1239-1248
pubmed: 29752973
Am J Respir Crit Care Med. 2005 Feb 15;171(4):340-7
pubmed: 15542793
Crit Care Med. 2012 Jul;40(7):2022-32
pubmed: 22710202
Am J Respir Crit Care Med. 2010 Jul 15;182(2):183-91
pubmed: 20299535
JAMA. 2010 Oct 27;304(16):1787-94
pubmed: 20978258
Crit Care Med. 2018 Dec;46(12):1977-1984
pubmed: 30222636
Med Intensiva. 2018 Mar;42(2):114-128
pubmed: 28851588
Lancet Neurol. 2012 Nov;11(11):1006-12
pubmed: 23079557
Mayo Clin Proc. 2018 Jan;93(1):68-82
pubmed: 29304923
Front Aging Neurosci. 2017 Oct 24;9:340
pubmed: 29118710
Neuropsychologia. 2017 Feb;96:19-28
pubmed: 28041947
J Gen Intern Med. 2001 Nov;16(11):770-8
pubmed: 11722692
Diabetes Care. 2010 Mar;33(3):639-44
pubmed: 20032274
Semin Respir Crit Care Med. 2012 Aug;33(4):327-38
pubmed: 22875378
Crit Care Med. 2003 Apr;31(4):1226-34
pubmed: 12682497
JAMA. 2010 Feb 24;303(8):763-70
pubmed: 20179286
J Am Geriatr Soc. 2016 Jun;64(6):1341-6
pubmed: 27321616
Ann Am Thorac Soc. 2013 Oct;10(5):450-7
pubmed: 23987665
Stroke. 2002 Jun;33(6):1605-9
pubmed: 12052999
J Coll Physicians Surg Pak. 2014 Aug;24(8):543-8
pubmed: 25149830
N Engl J Med. 2013 Oct 3;369(14):1306-16
pubmed: 24088092
Acta Psychiatr Scand. 2018 Nov;138(5):441-455
pubmed: 30105820
J Crit Care. 2019 Aug;52:166-171
pubmed: 31078997
Crit Care Med. 2013 Sep;41(9 Suppl 1):S81-98
pubmed: 23989098
Crit Care Med. 2019 Aug;47(8):1116-1124
pubmed: 31107280
Crit Care. 2012 Dec 17;16(6):R233
pubmed: 23245397
Parkinsonism Relat Disord. 2015 Aug;21(8):899-904
pubmed: 26037458
J Int Neuropsychol Soc. 2015 Feb;21(2):95-104
pubmed: 25665170
Crit Care Med. 2012 Jan;40(1):112-8
pubmed: 21926597
J Int Neuropsychol Soc. 2007 Jul;13(4):595-605
pubmed: 17521481
Neuropsychol Dev Cogn B Aging Neuropsychol Cogn. 2012 Nov;19(6):759-68
pubmed: 22670852
Crit Care. 2019 Jul 5;23(1):245
pubmed: 31277722
J Int Neuropsychol Soc. 2010 Jan;16(1):84-93
pubmed: 19887015
Am J Respir Crit Care Med. 2012 Jun 15;185(12):1307-15
pubmed: 22492988
Arch Neurobiol (Madr). 1992 Nov-Dec;55(6):262-6
pubmed: 1492780
Ann Am Thorac Soc. 2013 Aug;10(4):315-23
pubmed: 23952849