Assessment of performance and utility of mortality prediction models in a single Indian mixed tertiary intensive care unit

Abstract Objectives: To develop prognosis prediction models for COVID-19 patients attending an emergency department (ED) based on initial chest X-ray (CXR), demographics, clinical and laboratory parameters. Methods: All symptomatic confirmed COVID-19 patients admitted to our hospital ED between February 24th and April 24th 2020 were recruited. CXR features, clinical and laboratory variables and CXR abnormality indices extracted by a convolutional neural network (CNN) diagnostic tool were considered potential predictors on this first visit. The most serious individual outcome defined the three severity level: 0) home discharge or hospitalization ≤ 3 days, 1) hospital stay >3 days and 2) intensive care requirement or death. Severity and in-hospital mortality multivariable prediction models were developed and internally validated. The Youden index was used for model selection.Results: A total of 440 patients were enrolled (median 64 years; 55.9% male); 13.6% patients were discharged, 64% hospitalized, 6.6% required intensive care and 15.7% died. The severity prediction model included oxygen saturation/inspired oxygen fraction (SatO2/FiO2), age, C-reactive protein (CRP), lymphocyte count, extent score of lung involvement on CXR (ExtScoreCXR), lactate dehydrogenase (LDH), D-dimer level and platelets count, with AUC-ROC=0.94 and AUC-PRC=0.88. The mortality prediction model included age, SatO2/FiO2, CRP, LDH, CXR extent score, lymphocyte count and D-dimer level, with AUC-ROC=0.97 and AUC-PRC=0.78. The addition of CXR CNN-based indices slightly improved the predictive metrics for mortality (AUC-ROC=0.97 and AUC-PRC=0.83).Conclusion: The developed and internally validated severity and mortality prediction models could be useful as triage tools for COVID-19 patients and they should be further validated at different ED.

Download Full-text

Mortality prediction models for pediatric intensive care: comparison of overall and subgroup specific performance

Intensive Care Medicine ◽

10.1007/s00134-013-2857-4 ◽

2013 ◽

Vol 39 (5) ◽

pp. 942-950 ◽

Cited By ~ 31

Author(s):

Idse H. E. Visser ◽

Jan A. Hazelzet ◽

Marcel J. I. J. Albers ◽

Carin W. M. Verlaat ◽

Karin Hogenbirk ◽

...

Keyword(s):

Intensive Care ◽

Prediction Models ◽

Pediatric Intensive Care ◽

Mortality Prediction ◽

Specific Performance ◽

Mortality Prediction Models

Download Full-text

Mortality prediction models in intensive care

Critical Care Medicine ◽

10.1097/00003246-199102000-00014 ◽

1991 ◽

Vol 19 (2) ◽

pp. 191-197 ◽

Cited By ~ 40

Author(s):

XAVIER CASTELLA ◽

JAUME GILABERT ◽

FRANCESC TORNER ◽

CARLES TORRES

Keyword(s):

Intensive Care ◽

Prediction Models ◽

Mortality Prediction ◽

Mortality Prediction Models

Download Full-text

Predicting mortality in intensive care patients with acute renal failure treated with dialysis.

Journal of the American Society of Nephrology ◽

10.1681/asn.v81111 ◽

1997 ◽

Vol 8 (1) ◽

pp. 111-117

Author(s):

C E Douma ◽

W K Redekop ◽

J H van der Meulen ◽

R W van Olden ◽

J Haeck ◽

...

Keyword(s):

Renal Failure ◽

Acute Renal Failure ◽

Intensive Care ◽

Mortality Rate ◽

Prediction Models ◽

Characteristic Curve ◽

Mortality Prediction ◽

Dialysis Treatment ◽

Apache Iii ◽

Mortality Prediction Models

Existing prognostic methods were compared in their ability to predict mortality in intensive care unit (ICU) patients on dialysis for acute renal failure (ARF). The clinical goal of this study was to determine whether these models could identify a group of patients where dialysis would provide no benefit because of a near 100% certainty of death even with dialysis treatment. This retrospective cohort study included 238 adult patients who received a first dialysis treatment for ARF in the ICU. This study examined the performance of seven general ICU mortality prediction models and four mortality prediction models developed for patients with ARF. These models were assessed for their ability to discriminate mortality form survival and for their ability to calibrate the observed mortality rate with the expected mortality rate. The observed in hospital mortality was 76% for our patient group. Areas under the receiver operating characteristic curve ranged from 0.50 to 0.78. With the Acute Physiology and Chronic Health Evaluation (APACHE) III and the Liano models, the observed mortality in the highest quintiles of risk were 97% and 98%. In conclusion, although none of the models examined in this study showed excellent discrimination between those patients who died in hospital and those who did not, some models (APACHE III, Liano) were able to identify a group of patients with a near 100% chance of mortality. This indicates that these models may have some use in supporting the decision not to initiate dialysis in a subgroup of patients.

Download Full-text

Development of a Machine Learning Model for the Prediction of the Real Time Mortality in Patients in the Intensive Care Unit

10.21203/rs.3.rs-1066192/v1 ◽

2021 ◽

Author(s):

Jaeyoung Yang ◽

Hong-Gook Lim ◽

Wonhyeong Park ◽

Dongseok Kim ◽

Jin Sun Yoon ◽

...

Keyword(s):

Machine Learning ◽

Intensive Care Unit ◽

Intensive Care ◽

Prediction Model ◽

Prediction Models ◽

External Validation ◽

Learning Model ◽

Mortality Prediction ◽

Machine Learning Model ◽

Mortality Prediction Model

Abstract BackgroundPrediction of mortality in intensive care units is very important. Thus, various mortality prediction models have been developed for this purpose. However, they do not accurately reflect the changing condition of the patient in real time. The aim of this study was to develop and evaluate a machine learning model that predicts short-term mortality in the intensive care unit using four easy-to-collect vital signs.MethodsTwo independent retrospective observational cohorts were included in this study. The primary training cohort included the data of 1968 patients admitted to the intensive care unit at the Veterans Health Service Medical Center, Seoul, South Korea, from January 2018 to March 2019. The external validation cohort comprised the records of 409 patients admitted to the medical intensive care unit at Seoul National University Hospital, Seoul, South Korea, from January 2019 to December 2019. Datasets of four vital signs (heart rate, systolic blood pressure, diastolic blood pressure, and peripheral capillary oxygen saturation [SpO2]) measured every hour for 10 h were used for the development of the machine learning model. The performances of mortality prediction models generated using five machine learning algorithms, Random Forest (RF), XGboost, perceptron, convolutional neural network, and Long Short-Term Memory, were calculated and compared using area under the receiver operating characteristic curve (AUROC) values and an external validation dataset.ResultsThe machine learning model generated using the RF algorithm showed the best performance. Its AUROC was 0.922, which is much better than the 0.8408 of the Acute Physiology and Chronic Health Evaluation II. Thus, to investigate the importance of variables that influence the performance of the machine learning model, machine learning models were generated for each observation time or vital sign using the RF algorithm. The machine learning model developed using SpO2 showed the best performance (AUROC, 0.89). ConclusionsThe mortality prediction model developed in this study using data from only four types of commonly recorded vital signs is simpler than any existing mortality prediction model. This simple yet powerful new mortality prediction model could be useful for early detection of probable mortality and appropriate medical intervention, especially in rapidly deteriorating patients.

Download Full-text