ICU staffing feature phenotypes and their relationship with patients’ outcomes: an unsupervised machine learning analysis

Zampieri, Fernando Godinho; Salluh, Jorge I.; Azevedo, Luciano César Pontes; Kahn, Jeremy M.; Damiani, Lucas Petri; Borges, Lunna Perdigão; Viana, William N.; Costa, Roberto; Corrêa, Thiago Domingos; Araya, Dieter E S; Maia, Marcelo O.; Ferez, Marcus Antônio; Carvalho, Alexandre; Knibel, Marcos Freitas; Melo, Ulisses O.; Santino, Marcelo S.; Lisboa, Thiago; Caser, Eliana Bernadete; Besen, Bruno Adler Maccagnan Pinheiro; Bozza, Fernando A.; Angus, Derek C.; Soares, Márcio; Investigators, Orchestra Study

doi:10.1007/s00134-019-05790-z

Cited by 50 publications

(58 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In another study that analyzed 167 confirmed patients with severe COVID-19, the LDH concentration was higher and the albumin concentration was lower in these patients, with significant differences [ 34 ]. Recently, Liang et al [ 22 ] used Least Absolute Shrinkage and Selection Operator (LASSO) and logistic regression to construct a predictive risk score (COVID-GRAM), in which the AUC in the development cohort was 0.88 (95% CI 0.85-0.91) and the AUC in the validation cohort was 0.88 (95% CI 0.84-0.93) for predicting patients’ risk of developing critical illness. The results in that study coincide with our results to some extent, and the machine learning algorithm can identify potential indicators better than the conventional algorithm.…”

Section: Discussionmentioning

confidence: 99%

“…The theoretical core of machine learning analysis is the data mining algorithm. Various data mining algorithms based on different data types and formats can more scientifically represent the characteristics of the data and can better penetrate the data trends and recognized values [ 22 ]. On this basis, one of the most important application areas is predictive analysis, which involves identifying features (in machine learning, “features” refers to individual characteristics of the data) from mechanical learning, establishing models through science, and then running new data through the models to predict future data [ 23 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prognostic Assessment of COVID-19 in the Intensive Care Unit by Machine Learning Methods: Model Development and Validation

Pan¹,

Li²,

Xiao³

et al. 2020

J Med Internet Res

View full text Add to dashboard Cite

Background Patients with COVID-19 in the intensive care unit (ICU) have a high mortality rate, and methods to assess patients’ prognosis early and administer precise treatment are of great significance. Objective The aim of this study was to use machine learning to construct a model for the analysis of risk factors and prediction of mortality among ICU patients with COVID-19. Methods In this study, 123 patients with COVID-19 in the ICU of Vulcan Hill Hospital were retrospectively selected from the database, and the data were randomly divided into a training data set (n=98) and test data set (n=25) with a 4:1 ratio. Significance tests, correlation analysis, and factor analysis were used to screen 100 potential risk factors individually. Conventional logistic regression methods and four machine learning algorithms were used to construct the risk prediction model for the prognosis of patients with COVID-19 in the ICU. The performance of these machine learning models was measured by the area under the receiver operating characteristic curve (AUC). Interpretation and evaluation of the risk prediction model were performed using calibration curves, SHapley Additive exPlanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME), etc, to ensure its stability and reliability. The outcome was based on the ICU deaths recorded from the database. Results Layer-by-layer screening of 100 potential risk factors finally revealed 8 important risk factors that were included in the risk prediction model: lymphocyte percentage, prothrombin time, lactate dehydrogenase, total bilirubin, eosinophil percentage, creatinine, neutrophil percentage, and albumin level. Finally, an eXtreme Gradient Boosting (XGBoost) model established with the 8 important risk factors showed the best recognition ability in the training set of 5-fold cross validation (AUC=0.86) and the verification queue (AUC=0.92). The calibration curve showed that the risk predicted by the model was in good agreement with the actual risk. In addition, using the SHAP and LIME algorithms, feature interpretation and sample prediction interpretation algorithms of the XGBoost black box model were implemented. Additionally, the model was translated into a web-based risk calculator that is freely available for public usage. Conclusions The 8-factor XGBoost model predicts risk of death in ICU patients with COVID-19 well; it initially demonstrates stability and can be used effectively to predict COVID-19 prognosis in ICU patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Prognostic Assessment of COVID-19 in the Intensive Care Unit by Machine Learning Methods: Model Development and Validation

Pan¹,

Li²,

Xiao³

et al. 2020

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…In Brazil, ICU nurse staffing varies considerably depending on local regulations. However, a study in 93 Brazilian ICUs showed that ICUs where nurses have higher autonomy, including start of weaning from ventilation and the titrating FiO 2 , have better outcomes compared to ICUs where there is less nurse autonomy [36]. After implementation of the structured checklist in the second phase of the CHECKLIST-ICU study, the positive effect of one nurse for every 10 patients in all shifts on the use of LTVV was no longer associated with compliance with LTVV.…”

Section: Discussionmentioning

confidence: 99%

Organizational factors associated with adherence to low tidal volume ventilation: a secondary analysis of the CHECKLIST-ICU database

Midega

Bozza

Machado

et al. 2020

Ann. Intensive Care

Self Cite

View full text Add to dashboard Cite

Background: Survival benefit from low tidal volume (V T) ventilation (LTVV) has been demonstrated for patients with acute respiratory distress syndrome (ARDS), and patients not having ARDS could also benefit from this strategy. Organizational factors may play a role on adherence to LTVV. The present study aimed to identify organizational factors with an independent association with adherence to LTVV. Methods: Secondary analysis of the database of a multicenter two-phase study (prospective cohort followed by a cluster-randomized trial) performed in 118 Brazilian intensive care units. Patients under mechanical ventilation at day 2 were included. LTVV was defined as a V T ≤ 8 ml/kg PBW on the second day of ventilation. Data on the type and number of beds of the hospital, teaching status, nursing, respiratory therapists and physician staffing, use of structured checklist, and presence of protocols were tested. A multivariable mixed-effect model was used to assess the association between organizational factors and adherence to LTVV. Results: The study included 5719 patients; 3340 (58%) patients received LTVV. A greater number of hospital beds (absolute difference 7.43% [95% confidence interval 0.61-14.24%]; p = 0.038), use of structured checklist during multidisciplinary rounds (5.10% [0.55-9.81%]; p = 0.030), and presence of at least one nurse per 10 patients during all shifts (17.24% [0.85-33.60%]; p = 0.045) were the only three factors that had an independent association with adherence to LTVV. Conclusions: Number of hospital beds, use of a structured checklist during multidisciplinary rounds, and nurse staffing are organizational factors associated with adherence to LTVV. These findings shed light on organizational factors that may improve ventilation in critically ill patients.

show abstract

“…This was a retrospective study on prospectively collected data from two databases. The first is from the Orchestra study [15], a multicenter study performed in 93 ICUs from 55 hospitals in several Brazilian states from January 2014 to December 2015, and the second, from the A.C. Camargo Cancer Center, a dedicated cancer center in São Paulo Brazil, with 50 ICU beds, from January 2011 to December 2017. A.C. Camargo Cancer Center Local Ethics Committees (CAAE: 86761718.0.0000.5432) and the Brazilian National Ethics Committee (CAAE: 19687113.8.1001.5249) approved the study without the need for informed consent, since all data were fully anonymized before researches could access them.…”

Section: Design and Settingmentioning

confidence: 99%

Elderly patients with cancer admitted to intensive care unit: A multicenter study in a middle-income country

et al. 2020

Self Cite

View full text Add to dashboard Cite

Background Very elderly critically ill patients (ie, those older than 75 or 80 years) are an increasing population in intensive care units. However, patients with cancer have encompassed only a minority in epidemiological studies of very old critically-ill patients. We aimed to describe clinical characteristics and identify factors associated with hospital mortality in a cohort of patients aged 80 or older with cancer admitted to intensive care units (ICUs). Methods This was a retrospective cohort study in 94 ICUs in Brazil. We included patients aged 80 years or older with active cancer who had an unplanned admission. We performed a mixed effect logistic regression model to identify variables independently associated with hospital mortality. Results Of 4604 included patients, 1807 (39.2%) died in hospital. Solid metastatic (OR = 2.46; CI 95%, 2.01-3.00), hematological cancer (OR = 2.32; CI 95%, 1.75-3.09), moderate/severe

show abstract

ICU staffing feature phenotypes and their relationship with patients’ outcomes: an unsupervised machine learning analysis

Cited by 50 publications

References 28 publications

Prognostic Assessment of COVID-19 in the Intensive Care Unit by Machine Learning Methods: Model Development and Validation

Prognostic Assessment of COVID-19 in the Intensive Care Unit by Machine Learning Methods: Model Development and Validation

Organizational factors associated with adherence to low tidal volume ventilation: a secondary analysis of the CHECKLIST-ICU database

Elderly patients with cancer admitted to intensive care unit: A multicenter study in a middle-income country

Contact Info

Product

Resources

About