Novel criteria to classify ARDS severity using a machine learning approach

Sayed, Mohammed E.; Riaño, David; Villar, Jesús

doi:10.1186/s13054-021-03566-w

Cited by 25 publications

(22 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…More specifically, ARDS diagnosis increases total ICU and hospital costs for mechanically ventilated ICU patients, suggesting higher total costs due to more days on a ventilator, although there is no clear severity-dependent relationship between ARDS severity and incurred costs [35]. The benchmarking of ML algorithms is possible through publicly available databases such as MIMIC-III [19,27] or eICU [19,36].…”

Section: Discussionmentioning

confidence: 99%

“…Data extraction from both datasets was performed using Python 3.7. The selection of clinical variables was based on prior studies [9,19,[25][26][27]. All extracted patients from both datasets fulfilled the Berlin definition for ARDS [6].…”

Section: Study Design and Patient Populationmentioning

confidence: 99%

“…Supervised learning algorithms, the ones used in our study, detect relationships between potential explanatory features and a known target outcome [16]. They are commonly used in ICUs to predict clinical outcomes [16][17][18][19][20][21]. Troché and Moine addressed the critical question on whether MV duration is predictable [22].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predicting Duration of Mechanical Ventilation in Acute Respiratory Distress Syndrome Using Supervised Machine Learning

Sayed

Riaño

Villar

2021

JCM

Self Cite

View full text Add to dashboard Cite

Background: Acute respiratory distress syndrome (ARDS) is an intense inflammatory process of the lungs. Most ARDS patients require mechanical ventilation (MV). Few studies have investigated the prediction of MV duration over time. We aimed at characterizing the best early scenario during the first two days in the intensive care unit (ICU) to predict MV duration after ARDS onset using supervised machine learning (ML) approaches. Methods: For model description, we extracted data from the first 3 ICU days after ARDS diagnosis from patients included in the publicly available MIMIC-III database. Disease progression was tracked along those 3 ICU days to assess lung severity according to Berlin criteria. Three robust supervised ML techniques were implemented using Python 3.7 (Light Gradient Boosting Machine (LightGBM); Random Forest (RF); and eXtreme Gradient Boosting (XGBoost)) for predicting MV duration. For external validation, we used the publicly available multicenter database eICU. Results: A total of 2466 and 5153 patients in MIMIC-III and eICU databases, respectively, received MV for >48 h. Median MV duration of extracted patients was 6.5 days (IQR 4.4–9.8 days) in MIMIC-III and 5.0 days (IQR 3.0–9.0 days) in eICU. LightGBM was the best model in predicting MV duration after ARDS onset in MIMIC-III with a root mean square error (RMSE) of 6.10–6.41 days, and it was externally validated in eICU with RMSE of 5.87–6.08 days. The best early prediction model was obtained with data captured in the 2nd day. Conclusions: Supervised ML can make early and accurate predictions of MV duration in ARDS after onset over time across ICUs. Supervised ML models might have important implications for optimizing ICU resource utilization and high acute cost reduction of MV.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Study Design and Patient Populationmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Duration of Mechanical Ventilation in Acute Respiratory Distress Syndrome Using Supervised Machine Learning

Sayed

Riaño

Villar

2021

JCM

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, the Berlin definition does not consider the nonlinear relationship between PaO 2 and FiO 2 [ 67 ] and its prediction accuracy is limited [ [68] , [69] , [70] ]. Compared with the AECC diagnosis criteria, the minimum PEEP of 5 cmH 2 O did not significantly improve prediction for the Berlin definition [ 71 ]. Although, our results were similar to previous meta-analyses with respect to the reduction in ARDS [ 17 ], four of five eligible studies in this endpoint were published before 2011, which might cause risk of bias due to the different diagnostic criteria used in each study.…”

Section: Discussionmentioning

confidence: 99%

Effect of different levels of PEEP on mortality in ICU patients without acute respiratory distress syndrome: systematic review and meta-analysis with trial sequential analysis

Shao

Kang

Qian

et al. 2021

Journal of Critical Care

View full text Add to dashboard Cite

Objective To determine whether higher positive end- expiratory pressure (PEEP) could provide a survival advantage for patients without acute respiratory distress syndrome (ARDS) compared with lower PEEP. Methods Eligible studies were identified through searches of Embase, Cochrane Library, Web of Science, Medline, and Wanfang database from inception up to 1 June 2021. Trial sequential analysis (TSA) was used in this meta-analysis. Data synthesis Twenty-seven randomized controlled trials (RCTs) were identified for further evaluation. Higher and lower PEEP arms included 1330 patients and 1650 patients, respectively. A mean level of 9.6±3.4 cmH 2 O was applied in the higher PEEP groups and 1.9±2.6 cmH 2 O was used in the lower PEEP groups. Higher PEEP, compared with lower PEEP, was not associated with reduction of all-cause mortality (RR 1.03; 95% CI 0.91–1.18; P =0.627), and 28-day mortality (RR 1.07 ; 95% CI 0.92–1.24; P =0.365). In terms of risk of ARDS (RR 0.43; 95% CI 0.24–0.78; P =0.005), duration of intensive care unit (MD -1.04; 95%CI-1.36 to −0.73; P < 0.00001), and oxygenation (MD 40.30; 95%CI 0.94 to 79.65; P = 0.045), higher PEEP was superior to lower PEEP. Besides, the pooled analysis showed no significant differences between groups both in the duration of mechanical ventilation (MD 0.00; 95%CI-0.13 to 0.13; P = 0.996) and hospital stay (MD -0.66; 95%CI-1.94 to 0.61; P = 0.309). More importantly, lower PEEP did not increase the risk of pneumonia, atelectasis, barotrauma, hypoxemia, or hypotension among patients compared with higher PEEP. The TSA analysis showed that the results of all-cause mortality and 28-day mortality might be false-negative results. Conclusions Our results suggest that a lower PEEP ventilation strategy was non-inferior to a higher PEEP ventilation strategy in ICU patients without ARDS, with no increased risk of all-cause mortality and 28-day mortality. Further high-quality RCTs should be performed to confirm these findings.

show abstract

“…Most studies have attempted to identify ARDS based on clinical data, including vital signs, laboratory tests, ventilator-derived parameters, etc. 10 – 12 For example, two studies developed prediction models for ARDS severity using machine models based on the Light Gradient Boosting Machine (LightGBM), random forest (RF), and eXtreme Gradient Boosting (XGBoost). 10 , 12 Le et al also developed a model for the early prediction of ARDS using XGBoost.…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence–aided diagnosis model for acute respiratory distress syndrome combining clinical data and chest radiographs

et al. 2022

View full text Add to dashboard Cite

Objective The aim of this study was to develop an artificial intelligence–based model to detect the presence of acute respiratory distress syndrome (ARDS) using clinical data and chest X-ray (CXR) data. Method The transfer learning method was used to train a convolutional neural network (CNN) model with an external image dataset to extract the image features. Then, the last layer of the model was fine-tuned to determine the probability of ARDS. The clinical data were trained using three machine learning algorithms—eXtreme Gradient Boosting (XGB), random forest (RF), and logistic regression (LR)—to estimate the probability of ARDS. Finally, ensemble-weighted methods were proposed that combined the image model and the clinical data model to estimate the probability of ARDS. An analysis of the importance of clinical features was performed to explore the most important features in detecting ARDS. A gradient-weighted class activation mapping (Grad-CAM) model was used to explain what our CNN sees and understands when making a decision. Results The proposed ensemble-weighted methods improved the performances of the ARDS classifiers (XGB + CNN, area under the curve [AUC] = 0.916; RF + CNN, AUC = 0.920; LR + CNN, AUC = 0.920; XGB + RF + LR + CNN, AUC = 0.925). In addition, the ML model using clinical data to present the top 15 important features to identify the risk factors of ARDS. Conclusion This study developed combined machine learning models with clinical data and CXR images to detect ARDS. According to the results of the Shapley Additive exPlanations values and the Grad-CAM techniques, an explicable ARDS diagnosis model is suitable for a real-life scenario.

show abstract

Novel criteria to classify ARDS severity using a machine learning approach

Cited by 25 publications

References 43 publications

Predicting Duration of Mechanical Ventilation in Acute Respiratory Distress Syndrome Using Supervised Machine Learning

Predicting Duration of Mechanical Ventilation in Acute Respiratory Distress Syndrome Using Supervised Machine Learning

Effect of different levels of PEEP on mortality in ICU patients without acute respiratory distress syndrome: systematic review and meta-analysis with trial sequential analysis

Artificial intelligence–aided diagnosis model for acute respiratory distress syndrome combining clinical data and chest radiographs

Contact Info

Product

Resources

About