Identification and Prediction of Novel Clinical Phenotypes for Intensive Care Patients With SARS-CoV-2 Pneumonia: An Observational Cohort Study

Background: Phenotypes have been identified within heterogeneous disease, such as acute respiratory distress syndrome and sepsis, which are associated with important prognostic and therapeutic implications. The present study sought to assess whether phenotypes can be derived from intensive care patients with coronavirus disease 2019 (COVID-19), to assess the correlation with prognosis, and to develop a parsimonious model for phenotype identification.Methods: Adult patients with COVID-19 from Tongji hospital between January 2020 and March 2020 were included. The consensus k means clustering and latent class analysis (LCA) were applied to identify phenotypes using 26 clinical variables. We then employed machine learning algorithms to select a maximum of five important classifier variables, which were further used to establish a nested logistic regression model for phenotype identification.Results: Both consensus k means clustering and LCA showed that a two-phenotype model was the best fit for the present cohort (N = 504). A total of 182 patients (36.1%) were classified as hyperactive phenotype, who exhibited a higher 28-day mortality and higher rates of organ dysfunction than did those in hypoactive phenotype. The top five variables used to assign phenotypes were neutrophil-to-lymphocyte ratio (NLR), ratio of pulse oxygen saturation to the fractional concentration of oxygen in inspired air (Spo2/Fio2) ratio, lactate dehydrogenase (LDH), tumor necrosis factor α (TNF-α), and urea nitrogen. From the nested logistic models, three-variable (NLR, Spo2/Fio2 ratio, and LDH) and four-variable (three-variable plus TNF-α) models were adjudicated to be the best performing, with the area under the curve of 0.95 [95% confidence interval (CI) = 0.94–0.97] and 0.97 (95% CI = 0.96–0.98), respectively.Conclusion: We identified two phenotypes within COVID-19, with different host responses and outcomes. The phenotypes can be accurately identified with parsimonious classifier models using three or four variables.

Download Full-text

Comparison of machine learning algorithms for mortality prediction in intensive care patients on multi-center critical care databases

IOP Conference Series Materials Science and Engineering ◽

10.1088/1757-899x/1163/1/012027 ◽

2021 ◽

Vol 1163 (1) ◽

pp. 012027 ◽

Cited By ~ 1

Author(s):

Thanakron Na Pattalung ◽

Sitthichok Chaichulee

Keyword(s):

Machine Learning ◽

Critical Care ◽

Intensive Care ◽

Learning Algorithms ◽

Mortality Prediction ◽

Machine Learning Algorithms ◽

Intensive Care Patients

Download Full-text

Patient Survival Prediction with Machine Learning Algorithms

Journal of Intelligent Systems with Applications ◽

10.54856/jiswa.202012126 ◽

2020 ◽

pp. 93-96

Author(s):

Mustafa Berkant Selek ◽

Saadet Sena Egeli ◽

Yalcin Isler

Keyword(s):

Machine Learning ◽

Intensive Care ◽

Cross Validation ◽

Patient Survival ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Survival Prediction ◽

Accuracy Rate ◽

Intensive Care Patients ◽

One Year

In this study, the intensive care unit patient survival is predicted by machine learning algorithms according to the examinations performed in the first 24 hours. The data of intensive care patients collected from approximately two hundred hospitals over a period of one year were used. Algorithms are run in Python environment. Machine learning models were compared with the Cross-Validation method, and the random forest algorithm is used. The model made the prediction with 92,53% accuracy rate.

Download Full-text

Delta Procalcitonin Is a Better Indicator of Infection Than Absolute Procalcitonin Values in Critically Ill Patients: A Prospective Observational Study

Journal of Immunology Research ◽

10.1155/2016/3530752 ◽

2016 ◽

Vol 2016 ◽

pp. 1-9 ◽

Cited By ~ 5

Author(s):

Domonkos Trásy ◽

Krisztián Tánczos ◽

Márton Németh ◽

Péter Hankovszky ◽

András Lovas ◽

...

Keyword(s):

Intensive Care ◽

Observational Study ◽

Prospective Observational Study ◽

Area Under The Curve ◽

Absolute Value ◽

Intensive Care Patients ◽

Reactive Protein ◽

Post Hoc ◽

Microbiological Data ◽

New Onset

Purpose. To investigate whether absolute value of procalcitonin (PCT) or the change (delta-PCT) is better indicator of infection in intensive care patients.Materials and Methods.Post hocanalysis of a prospective observational study. Patients with suspected new-onset infection were included in whom PCT, C-reactive protein (CRP), temperature, and leukocyte (WBC) values were measured on inclusion (t0) and data were also available from the previous day (t-1). Based on clinical and microbiological data, patients were groupedpost hocinto infection- (I-) and noninfection- (NI-) groups.Results. Of the 114 patients, 85 (75%) had proven infection. PCT levels were similar att-1: I-group (median [interquartile range]): 1.04 [0.40–3.57] versus NI-group: 0.53 [0.16–1.68],p=0.444. Byt0PCT levels were significantly higher in the I-group: 4.62 [1.91–12.62] versus 1.12 [0.30–1.66],p=0.018. The area under the curve to predict infection for absolute values of PCT was 0.64 [95% CI = 0.52–0.76],p=0.022; for percentage change: 0.77 [0.66–0.87],p<0.001; and for delta-PCT: 0.85 [0.78–0.92],p<0.001. The optimal cut-off value for delta-PCT to indicate infection was 0.76 ng/mL (sensitivity 80 [70–88]%, specificity 86 [68-96]%). Neither absolute values nor changes in CRP, temperature, or WBC could predict infection.Conclusions. Our results suggest that delta-PCT values are superior to absolute values in indicating infection in intensive care patients. This trial is registered with ClinicalTrials.gov identifier:NCT02311816.

Download Full-text

Influence of the TNF-α and TNF-β Polymorphisms upon Infectious Risk and Outcome in Surgical Intensive Care Patients

Surgical Infections ◽

10.1089/109629603766956951 ◽

2003 ◽

Vol 4 (2) ◽

pp. 163-169 ◽

Cited By ~ 23

Author(s):

Jacqueline E. Calvano ◽

John Y. Um ◽

Doreen M. Agnese ◽

Sae J. Hahm ◽

Ashwini Kumar ◽

...

Keyword(s):

Intensive Care ◽

Surgical Intensive Care ◽

Intensive Care Patients ◽

Infectious Risk ◽

Tnf Α

Download Full-text

Fluid Overload Phenotypes in Critical Illness—A Machine Learning Approach

Journal of Clinical Medicine ◽

10.3390/jcm11020336 ◽

2022 ◽

Vol 11 (2) ◽

pp. 336

Author(s):

Anna S. Messmer ◽

Michel Moser ◽

Patrick Zuercher ◽

Joerg C. Schefold ◽

Martin Müller ◽

...

Keyword(s):

Machine Learning ◽

Septic Shock ◽

Logistic Regression ◽

Intensive Care ◽

Random Forest ◽

Fluid Overload ◽

Area Under The Curve ◽

Machine Learning Techniques ◽

Intensive Care Patients ◽

Multivariable Logistic Regression

Background: The detrimental impact of fluid overload (FO) on intensive care unit (ICU) morbidity and mortality is well known. However, research to identify subgroups of patients particularly prone to fluid overload is scarce. The aim of this cohort study was to derive “FO phenotypes” in the critically ill by using machine learning techniques. Methods: Retrospective single center study including adult intensive care patients with a length of stay of ≥3 days and sufficient data to compute FO. Data was analyzed by multivariable logistic regression, fast and frugal trees (FFT), classification decision trees (DT), and a random forest (RF) model. Results: Out of 1772 included patients, 387 (21.8%) met the FO definition. The random forest model had the highest area under the curve (AUC) (0.84, 95% CI 0.79–0.86), followed by multivariable logistic regression (0.81, 95% CI 0.77–0.86), FFT (0.75, 95% CI 0.69–0.79) and DT (0.73, 95% CI 0.68–0.78) to predict FO. The most important predictors identified in all models were lactate and bicarbonate at admission and postsurgical ICU admission. Sepsis/septic shock was identified as a risk factor in the MV and RF analysis. Conclusion: The FO phenotypes consist of patients admitted after surgery or with sepsis/septic shock with high lactate and low bicarbonate.

Download Full-text