A Nomogram for Predicting the Mortality of Patients with Acute Respiratory Distress Syndrome

Wang, Zhenqing; Xing, Lihua; Cui, Hongwei; Fu, Guowei; Zhao, Hui; Huang, Mingjun; Zhao, Yangchao; Xu, Jing

doi:https://doi.org/10.1155/2022/5940900

Journal of Healthcare Engineering

On this page

Abstract Introduction Methods Results Discussion Conclusion Data Availability Conflicts of Interest References Copyright Related Articles

Research Article | Open Access

Volume 2022 | Article ID 5940900 | https://doi.org/10.1155/2022/5940900

A Nomogram for Predicting the Mortality of Patients with Acute Respiratory Distress Syndrome

Zhenqing Wang,¹Lihua Xing,²Hongwei Cui,³Guowei Fu,¹Hui Zhao,¹Mingjun Huang,¹Yangchao Zhao,¹and Jing Xu¹

Academic Editor: Emiliano Schena

Received22 Oct 2021

Accepted25 Feb 2022

Published07 Apr 2022

Abstract

Acute respiratory distress syndrome (ARDS) is an acute lung injury associated with high morbidity and mortality. This study aimed to establish an accurate prediction model for mortality risk in ARDS. 70% of patients from the Medical Information Mart for Intensive Care Database (MIMIC-III) were selected as the training group, and the remaining 30% as the testing group. Patients from a Chinese hospital were used for external validation. Univariate and multivariate regressions were used to screen the independent predictors. The receiver operating characteristic curve (ROC) analysis, the Hosmer–Lemeshow test, and the calibration curve were used for evaluating the performance of the model. Age, hemoglobin, heart failure, renal failure, Simplified Acute Physiology Score II (SAPS II), immune function impairment, total bilirubin (TBIL), and PaO₂/FiO₂ were identified as independent predictors. The algorithm of the prediction model was: ln (Pr/(1 + Pr)) = −3.147 + 0.037 ∗ age − 0.068 ∗ hemoglobin + 0.522 ∗ heart failure (yes) + 0.487 ∗ renal failure (yes) + 0.029 ∗ SAPS II + 0.697 ∗ immune function impairment (yes) + 0.280 ∗ TBIL (abnormal) − 0.006 ∗ PaO₂/FiO₂ (Pr represents the probability of death occurring). The AUC of the model was 0.791 (0.766–0.816), and the internal and the external validations both confirmed the good performance of the model. A nomogram for predicting the risk of death in ARDS patients was developed and validated. It may help clinicians early identify ARDS patients with high risk of death and thereby help reduce the mortality and improve the survival of ARDS.

1. Introduction

Acute respiratory distress syndrome (ARDS) is an acute lung injury characterized by progressive hypoxemia and respiratory distress and is associated with high morbidity and mortality [1–3]. In China, the incidence of ARDS was 27% in the ICU, and the mortality rate was as high as 25% to 75% [4]. The incidence is about 10.4% with the overall incidence of postoperative ARDS of about 3% [5]. Herein, it is of great significance to early identify ARDS patients with higher risk of death and to perform early intervention and treatment, which would help reduce the mortality risk of ARDS and improve the poor prognosis.

At present, many studies have extensively studied the risk factors for mortality of ARDS, including age [6–8], lower respiratory tract infection [8], immunosuppressive drugs [9, 10], multiple organ failures [8, 11], and some biomarkers [12, 13]. However, due to multiple factors that worked together to determine the final outcome of ARDS patients, developing an effective prediction model would be of great clinical use for risk assessment. Currently, most of the established prediction models were limited by the small sample size, single study population, or lacking external validation [14, 15]. Therefore, this study aims to establish an accurate prediction model for mortality risk in ARDS based on the Medical Information Mart for Intensive Care Database (MIMIC-III) and perform external validation in a Chinese population.

2. Methods

2.1. Study Population

In the retrospective study, we collected patient data from the Medical Information Mart for Intensive Care Database III version 1.3 (MIMIC-III v1.3) for the development of the prediction model. Inclusion criteria were as follows: (1) patients whose age ≥18 years and (2) patients who were diagnosed with ARDS according to the Berlin definition [1]. The MIMIC-III Database is a large, freely accessible database comprising information related to patients admitted to critical care unit at a large tertiary care hospital. It integrates deidentified, comprehensive clinical data of patients admitted to the Beth Israel Deaconess Medical Center in Boston, Massachusetts, and makes it widely accessible to researchers internationally under a data use agreement.

Also, ARDS patients in the First Affiliated Hospital of Zhengzhou University from June 2014 to December 2020 were enrolled in the study for external validation. Inclusion criteria were as follows: (1) patients whose age ≥18 years and (2) patients who were diagnosed with ARDS according to the Berlin definition [1]. The Ethics Committee of the First Affiliated Hospital of Zhengzhou University suggests that retrospective studies be exempted from ethical review. As the present study was a retrospective study, the Ethics Committee of the First Affiliated Hospital of Zhengzhou University exempted it from the requirement of the ethical review. All identifiable information about the patients has been stripped; the Ethics Committee of the First Affiliated Hospital of Zhengzhou University has waived the requirement for the informed consent in the study. Also, the study was conducted in line with the Declaration of Helsinki.

2.2. Data Extraction

In the present study, demographic data, laboratory indicators, and clinical data were collected. The following variables were extracted: age (years), sex, SaO₂, PaO₂/FiO₂, platelet (PLT, 109/L), pH, lactate (mmol/L), international normalized ratio (INR, %), creatinine (mg/dl), hematocrit (%), hemoglobin (g/dl), aspartate transaminase (AST, U/L), alanine transaminase (ALT, U/L), total bilirubin (TBIL, umol/L), blood urea nitrogen (BUN, mg/dl), white blood cell (WBC, 109/L), potassium (mmol/L), sodium (mmol/L), bicarbonate (mmol/L), mean arterial pressure (MAP, mm Hg), ICU type, causes of ARDS, bicarbonate input, ventilation, ventilation time, the Simplified Acute Physiology Score II (SAPS II), the Glasgow Coma Scale (GCS), the Sequential Organ Failure Assessment (SOFA) score, immune function impairment, heart failure, renal failure, respiratory rate (breaths/min), and heart rate (breaths/min). Immune function impairment was defined as patients with liver cirrhosis, acquired immune deficiency syndrome (AIDS), solid tumor, hematological malignancy, solid organ transplantation, or long-term use of corticosteroids. Multiple imputation was used to deal with missing data and sensitivity analysis was performed to evaluate the impact on the study after imputation (Table 1).

2.3. Development and Validation of the Prediction Model

Firstly, the 70% of the study patients from the MIMIC-III Database were randomly selected as the training group for the development of the prediction model, and the remaining 30% as the testing group for the internal validation. Data of patients from the hospital were used for external validation. After developing the prediction model, we adopted the receiver operating characteristic curve (ROC) analysis, the Hosmer–Lemeshow test, and the calibration curve to evaluate the performance of the model.

Univariate regression analysis was performed using the data of the training group from the MIMIC-III Database. Variables with statistical significance in the univariate analysis were included in the multivariate regression for stepwise screening, to screen the independent predictors and thereby to develop the model. The algorithm of the prediction model is as follows: the dependent variable y is 0 (represents survival) and 1 (represents death); the Pr value is the probability of death event.where .

Then we used the maximum likelihood estimation (MLE) to estimate the coefficients of each variable.

Finally, .

2.4. Statistical Analysis

Normally distributed measurement data were described as mean ± standard deviation (Mean ± SD), and the independent t-test was used for comparison between groups. Nonnormally distributed data were described as median and interquartile range M (Q1, Q3), and the Mann-Whitney U test was used for comparison. Besides, enumeration data were described as number of cases and constituent ratio N (%), and the chi-squared test or Fisher’s exact test was used for comparison.

We adopted the univariate and multivariate regression analysis to screen some independent predictors, and thereby these predictors were included in the prediction model to establish a prediction equation for assessing the risk of death in ARDS patients.

For visualizing the prediction model, we also plotted a nomogram. Then, the established model performed the internal and external validation, to assess the predicting performance of model. The receiver operating characteristic curve (ROC) analysis, the Hosmer–Lemeshow test, and the calibration curve were used for evaluating the performance of the model. The two-tailed test was carried out for all statistical tests, and was considered statistically significant. The SAS 9.4 software (SAS Institute Inc., Cary, NC, USA) was used for the screening of independent predictors and the development of the prediction model. R 4.0.2 was used to validate and visualize the model.

3. Results

3.1. Baseline Description

In the present study, 1,814 patients were randomly selected from the MIMIC-III Database with 1,230 in the training group and 584 in the testing group. The mean age was 62.16 ± 16.93 years. There were 1,048 (57.77%) males and 766 (42.23%) females. The ARDS of 150 (8.27%) patients was caused by pneumonia, the ARDS of 51 (2.81%) was by sepsis, and the ARDS of the remaining 1,613 (88.92%) was by other causes. Impaired immune function was reported in 544 (29.99%) patients, heart failure in 553 (30.49%) patients, and renal failure in 611 (33.69%) patients. 1,550 (85.45%) patients received ventilation and 264 (14.55%) did not, and the median ventilation time was 7.00 (3.00, 15.00) days. The median SAPS II was 38.00 (29.00, 48.00). The median GCS score was 9.00 (5.00, 14.00). The median SOFA score was 6.00 (4.00, 9.00). As shown in Table 2, there were no significant differences in baseline information and laboratory indicators between the randomly selected training group and the testing group (all ).

In the Chinese hospital, totally 168 eligible patients were included: 100 (59.52%) males and 68 (40.48%) females. The mean age was 61.43 ± 17.66 years.

The ARDS of 7 (4.17%) patients was caused by pneumonia, the ARDS of 2 (1.19%) was by sepsis, and the ARDS of the remaining 159 (94.64%) was by other causes. Among them, 41 (24.40%) patients reported immune function impairment, 52 (30.95%) reported heart failure, and 55 (32.74%) reported renal failure. 21 (12.5%) patients received ventilation and 147 (87.50%) did not, and the median ventilation time was 7.00 (2.50, 14.00) days. The median SAPS II was 36.00 (29.00, 47.00). The median GCS score was 9.00 (5.00, 13.00). The median SOFA score was 6.00 (4.00, 9.00) (Table 2).

3.2. Development of the Prediction Model

According to the clinical outcome, the training group was divided into the survival group (n = 628) and the death group (n = 602). As shown in Table 3, the univariate logistic regression analysis suggested that age (t = −14.790, ), the constituent ratios of immune function impairment (χ² = 30.088, ), heart failure (χ² = 69.255, ), renal failure (χ² = 76.323, ), INR (Z = 6.092, ), creatinine (Z = 5.050, ), abnormal TBIL (χ² = 14.059, ), input bicarbonate (χ² = 9.770, ), SAPS II (Z = 13.604, ), and SOFA score (Z = 6.820, ) in the death group were all significantly higher than those in the survival group. The constituent ratios of hematocrit (t = 3.440, ), hemoglobin (t = 4.470, ), abnormal BUN (χ² = 26.937, ), ventilation (χ² = 33.480, ), MAP (t = 2.720, = 0.007), and PaO₂/FiO₂ (Z = −5.321, ) were all significantly lower than those in the survival group.

Variables with statistical significance in the univariate analysis and the factors in the literature that have an impact on the prognosis of ARDS patients (ARDS causes and ventilation time [16]) were further included in the multivariate logistic regression. As shown in Table 4, the results showed that age, hemoglobin, heart failure, renal failure, SAPS II, immune function impairment, TBIL, and PaO₂/FiO₂ were identified as independent predictors of death in ARDS patients. For every one-year increase in age, the mortality risk in ARDS patients increased by 0.037 times (OR = 1.037, 95% CI: 1.028–1.047). For every 1 g/dl increase in hemoglobin, the mortality risk was reduced by 0.066 times (OR = 0.934, 95% CI: 0.877–0.995). The mortality risk of patients with heart failure increased by 0.686 times (OR = 1.686, 95% CI: 1.258–2.258), and the risk increased by 0.628 times (OR = 1.628, 95% CI: 1.217–2.178) for those with renal failure. For every one-point increase in SAPS II, the mortality risk increased by 0.029 times (OR = 1.029, 95% CI: 1.020–1.039). The risk increased by 1.007 times (OR = 2.007, 95% CI: 1.498–2.689) in patients with immune function impairment and 0.322 times (OR = 1.322, 95% CI: 1.013–1.727) in those with abnormal TBIL. For every unit increase in PaO₂/FiO₂, the risk was reduced by 0.005 times (OR = 0.995, 95% CI: 0.990–0.999).

Then we used the MLE to estimate the coefficients of each variable, and the algorithm of the prediction model was as follows: ln (Pr/(1 + Pr)) = −3.147 + 0.037 ∗ age − 0.068 ∗ hemoglobin + 0.522 ∗ heart failure (yes) + 0.487 ∗ renal failure (yes) + 0.029 ∗ SAPS II + 0.697 ∗ immune function impairment (yes) + 0.280 ∗ TBIL (abnormal) − 0.006 ∗ PaO₂/FiO₂ (Pr represents the probability of death occurring). For visualizing the prediction model, we also plotted a nomogram (Figure 1). For example, as shown in Figure 2, the patient was 67.2 years old with normal TBIL. The hemoglobin was 7.4 g/dL and PaO₂/FiO₂ was 22.2. SAPS II was 38. The patient was complicated with renal failure and immune function impairment, but no heart failure was reported. According to the nomogram, the total number of points was 373 and the corresponding predicted probability was 0.728, which indicated a high risk of death and was in line with the actual outcome of the patient.

3.3. Assessment and Validation of the Prediction Model

According to the ROC analysis, the AUC value of the training group was 0.791 (0.766–0.816), and the AUC was 0.780 (0.743–0.816) in the testing group (Table 5), all suggesting the good discrimination of the model. The Hosmer–Lemeshow test (χ² = 49.123, = 0.107), the ROC curves, and the calibration curves all indicated the good discrimination and calibration of the model (Figure 3). The Youden index suggested the cutoff value of 0.458. In the external validation, the AUC was 0.758 (0.756–0.761) (Table 5). The Hosmer–Lemeshow test (χ² = 7.256, = 0.509) and the calibration curves both suggested the good performance of the model in Chinese patients (Figure 3).

(a)

(b)

(c)

(d)

(e)

(f)

4. Discussion

In the present study, the prediction model based on eight predictors, age, heart failure, renal failure, immune function impairment, hemoglobin, TBIL, PaO₂/FiO₂, and SAPS II, was developed with good discrimination and calibration. The internal validation and external validation both confirmed the good performance of the model as reflected by the ROC analysis, the Hosmer–Lemeshow test, and the calibration curve. This may help clinicians predict the individual risk of death in ARDS patients.

Respiratory system dysfunction is often characterized by hypoxemia and impairment of gas exchange with the most developed form as ARDS [17, 18]. In the model, with the increase of hemoglobin and the oxygenation index of PaO₂/FiO₂, the risk of death was decreased. Villar et al. reported similar findings that patients with more severe lung disease tend to have lower PaO₂/FiO₂ [15]. Our model also found that an older age was associated with an increased risk of death in ARDS patients. This was consistent with previous studies [6, 7, 12]. The body may experience functional degeneration such as immune function impairment with the increase of age, leading to the decline of respiratory capacity and antibacterial capacity. In addition, older patients with ARDS may be complicated by other systemic diseases. The results of this study showed that both heart failure and renal failure independently increased the risk of death from ARDS. This was consistent with previous findings that multiple organ failures were responsible for death in ARDS patients [18, 19]. Moran et al. found that although the proportion of severe ARDS patients who died of respiratory failure alone decreased, the number of deaths from multiple organ failures increased year by year [20]. Herein, in clinical treatment, attention should be paid not only to the elderly patients but also to the deterioration of ARDS caused by other systemic failures.

To our knowledge, there are few studies that have established prediction models for assessing the risk of death in ARDS patients [14, 15, 21]. The model developed by Gajic O et al. was well calibrated, but it required data of organ functions three days after intubation [21]. Villar et al. developed a risk model categorizing continuous variables into tertiles [15]. However, tertiles may not be appropriate for some variables have intricate dependencies and associations with outcome. In the study, based on a relatively large sample size, we incorporated demographic, clinical, and laboratory variables that were available in clinical use and all collected at the admission, allowing for early recognition of ARDS patients at a high risk of death. After univariate and multivariate logistic regressions, eight predictors were finally included in the model. The model was well discriminated as reflected by an AUC of 0.791 in the training set and 0.780 in the testing set and as confirmed by the Hosmer–Lemeshow test and the calibration curve. Also, we performed an external validation using data from a Chinese hospital, and the results indicated the good predictive ability of the model in Chinese patients. In addition, we plotted a nomogram for visualizing the model, which was more convenient for clinicians to predict the mortality risk of individual patients.

Several limitations should be considered in the study. First of all, data in our study were collected from the MIMIC-III Database and our hospital. To keep the uniformity of the variables in the datasets, the selection of variables was limited in some way. Also, the accuracy and the specificity were relatively poor and the sample size in the external validation set was relatively small. In the future, a prospective study with a larger sample size is preferred for validating our model.

5. Conclusion

In the present study, a nomogram for predicting the risk of death in ARDS patients was developed and validated. The model incorporated eight predictors that were available in clinical use. It may help clinicians early identify ARDS patients with high risk of death, which could make timely treatment therapies and interventions for reducing the mortality and improving the survival of ARDS patients.

Data Availability

The data used to support the findings of this study are available from the corresponding author upon request.

Conflicts of Interest

The authors declare no conflicts of interest.

References

V. M. Ranieri, G. D. Rubenfeld, B. T. Thompson et al., “Acute respiratory distress syndrome,” JAMA, vol. 307, no. 23, pp. 2526–2533, 2012.
View at: Publisher Site | Google Scholar
M. Confalonieri, F. Salton, and F. Fabiano, “Acute respiratory distress syndrome,” European Respiratory Review, vol. 26, no. 144, Article ID 160116, 2017.
View at: Publisher Site | Google Scholar
G. Bellani, J. G. Laffey, T. Pham et al., “Epidemiology, patterns of care, and mortality for patients with acute respiratory distress syndrome in intensive care units in 50 countries,” JAMA, vol. 315, no. 8, pp. 788–800, 2016.
View at: Publisher Site | Google Scholar
B. Du, Y. An, Y. Kang et al., “Characteristics of critically ill patients in ICUs in mainland China,” Critical Care Medicine, vol. 41, no. 1, pp. 84–92, 2013.
View at: Publisher Site | Google Scholar
B. J. Wright, “Lung-protective ventilation strategies and adjunctive treatments for the emergency medicine patient with acute respiratory failure,” Emergency Medicine Clinics of North America, vol. 32, no. 4, pp. 871–887, 2014.
View at: Publisher Site | Google Scholar
M. R. Baldwin, W. R. Narain, H. Wunsch et al., “A prognostic model for 6-month mortality in elderly survivors of critical illness,” Chest, vol. 143, no. 4, pp. 910–919, 2013.
View at: Publisher Site | Google Scholar
Y.-Z. Hsieh, M.-C. Su, C.-H. Wang, and P.-C. Wang, “Prediction of survival of ICU patients using computational intelligence,” Computers in Biology and Medicine, vol. 47, pp. 13–19, 2014.
View at: Publisher Site | Google Scholar
M. Schmidt, M. Bailey, J. Sheldrake et al., “Predicting survival after extracorporeal membrane oxygenation for severe acute respiratory failure. The Respiratory Extracorporeal Membrane Oxygenation Survival Prediction (RESP) score,” American Journal of Respiratory and Critical Care Medicine, vol. 189, no. 11, pp. 1374–1382, 2014.
View at: Publisher Site | Google Scholar
T. Enger, A. Philipp, V. Videm et al., “Prediction of mortality in adult patients with severe acute lung failure receiving veno-venous extracorporeal membrane oxygenation: a prospective observational study,” Critical Care, vol. 18, no. 2, p. R67, 2014.
View at: Publisher Site | Google Scholar
J. Villar, C. Ferrando, D. Martínez et al., “Dexamethasone treatment for the acute respiratory distress syndrome: a multicentre, randomised controlled trial,” The Lancet Respiratory Medicine, vol. 8, no. 3, pp. 267–276, 2020.
View at: Publisher Site | Google Scholar
C. Schmid, A. Philipp, M. Hilker et al., “Venovenous extracorporeal membrane oxygenation for acute lung failure in adults,” The Journal of Heart and Lung Transplantation, vol. 31, no. 1, pp. 9–15, 2012.
View at: Publisher Site | Google Scholar
E. Loekito, J. Bailey, R. Bellomo et al., “Common laboratory tests predict imminent death in ward patients,” Resuscitation, vol. 84, no. 3, pp. 280–285, 2013.
View at: Publisher Site | Google Scholar
A. A. Fowler, J. D. Truwit, R. D. Hite et al., “Effect of vitamin C infusion on organ failure and biomarkers of inflammation and vascular injury in patients with sepsis and severe acute respiratory failure: the CITRIS-ALI randomized clinical trial,” JAMA, vol. 322, no. 13, pp. 1261–1270, 2019.
View at: Publisher Site | Google Scholar
Z. Zhang and H. Ni, “Prediction model for critically ill patients with acute respiratory distress syndrome,” PLoS One, vol. 10, no. 3, Article ID e0120641, 2015.
View at: Publisher Site | Google Scholar
J. Villar, L. Perez-Mendez, S. Basaldua et al., “A risk tertiles model for predicting mortality in patients with acute respiratory distress syndrome: age, plateau pressure, and PaO2/FIO2 at ARDS onset can predict mortality,” Respiratory Care, vol. 56, no. 4, pp. 420–428, 2011.
View at: Publisher Site | Google Scholar
W. Chen and L. B. Ware, “Prognostic factors in the acute respiratory distress syndrome,” Clinical and Translational Medicine, vol. 4, no. 1, p. 65, 2015.
View at: Publisher Site | Google Scholar
A. L. Beal and F. B. Cerra, “Multiple organ failure syndrome in the 1990s. Systemic inflammatory response and organ dysfunction,” JAMA, vol. 271, no. 3, pp. 226–233, 1994.
View at: Google Scholar
M. T. Ziesmann and J. C. Marshall, “Multiple organ dysfunction: the defining syndrome of sepsis,” Surgical Infections, vol. 19, no. 2, pp. 184–190, 2018.
View at: Publisher Site | Google Scholar
J.-L. Vincent and M. Zambon, “Why do patients who have acute lung injury/acute respiratory distress syndrome die from multiple organ dysfunction syndrome? Implications for management,” Clinics in Chest Medicine, vol. 27, no. 4, pp. 725–731, 2006.
View at: Publisher Site | Google Scholar
J. L. Moran, A. D. Bersten, and P. J. Solomon, “Meta-analysis of controlled trials of ventilator therapy in acute lung injury and acute respiratory distress syndrome: an alternative perspective,” Intensive Care Medicine, vol. 31, no. 2, pp. 227–235, 2005.
View at: Publisher Site | Google Scholar
O. Gajic, B. Afessa, B. T. Thompson et al., “Prediction of death and prolonged mechanical ventilation in acute lung injury,” Critical Care, vol. 11, no. 3, p. R53, 2007.
View at: Publisher Site | Google Scholar

Copyright

Copyright © 2022 Zhenqing Wang et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

PDF Download Citation

Download other formats

Order printed copies

Views

298

Downloads

559

Citations