Discriminating Acute Respiratory Distress Syndrome from other forms of respiratory failure via iterative machine learning

Chest radiographs in acute respiratory distress syndrome: an Achilles' heel of the Berlin criteria?

Background

Despite the high mortality and economic burden associated with the acute respiratory distress syndrome (ARDS), the role of chest radiograph (CXR) in ARDS diagnosis and prognosis remains uncertain. The purpose of this study is to elucidate clinical characteristics that distinguish ARDS patients from those without ARDS, especially in patients where CXRs are indicative of ARDS.

Methods

Secondary analysis of a prospective observational study with 454 postoperative septic patients under mechanical ventilation (MV). Patients were stratified in two groups depending on whether they met the Berlin criteria for ARDS. Primary outcome was identification of clinical characteristics differentiating patients with ARDS confirmed by CXR from non-ARDS patients. Secondary outcome was 60-day in-hospital mortality of postoperative sepsis-induced ARDS.

Results

One hundred thirty-nine patients (30.6%) had CXRs compatible with ARDS, although ARDS was confirmed in only 45 patients (9.9%). Emergency surgery (OR 6.6), abdominal source of infection (OR 6.0), pneumonia (OR 8.2), and higher lactate (OR 3.9) were clinical features associated with ARDS development confirmed by CXR. ARDS was an independent risk factor for 60-day mortality (OR 1.8).

Conclusion

Although CXR criteria for ARDS diagnosis could be replaced in future definitions, its importance for ARDS diagnosis should not be underestimated.

Machine Learning Tools for Acute Respiratory Distress Syndrome Detection and Prediction

Machine learning (ML) tools for acute respiratory distress syndrome (ARDS) detection and prediction are increasingly used. Therefore, understanding risks and benefits of such algorithms is relevant at the bedside. ARDS is a complex and severe lung condition that can be challenging to define precisely due to its multifactorial nature. It often arises as a response to various underlying medical conditions, such as pneumonia, sepsis, or trauma, leading to widespread inflammation in the lungs. ML has shown promising potential in supporting the recognition of ARDS in ICU patients. By analyzing a variety of clinical data, including vital signs, laboratory results, and imaging findings, ML models can identify patterns and risk factors associated with the development of ARDS. This detection and prediction could be crucial for timely interventions, diagnosis and treatment. In summary, leveraging ML for the early prediction and detection of ARDS in ICU patients holds great potential to enhance patient care, improve outcomes, and contribute to the evolving landscape of precision medicine in critical care settings. This article is a concise definitive review on artificial intelligence and ML tools for the prediction and detection of ARDS in critically ill patients.

A systematic review of machine learning models for management, prediction and classification of ARDS

AIM

Acute respiratory distress syndrome or ARDS is an acute, severe form of respiratory failure characterised by poor oxygenation and bilateral pulmonary infiltrates. Advancements in signal processing and machine learning have led to promising solutions for classification, event detection and predictive models in the management of ARDS.

METHOD

In this review, we provide systematic description of different studies in the application of Machine Learning (ML) and artificial intelligence for management, prediction, and classification of ARDS. We searched the following databases: Google Scholar, PubMed, and EBSCO from 2009 to 2023. A total of 243 studies was screened, in which, 52 studies were included for review and analysis. We integrated knowledge of previous work providing the state of art and overview of explainable decision models in machine learning and have identified areas for future research.

RESULTS

Gradient boosting is the most common and successful method utilised in 12 (23.1%) of the studies. Due to limitation of data size available, neural network and its variation is used by only 8 (15.4%) studies. Whilst all studies used cross validating technique or separated database for validation, only 1 study validated the model with clinician input. Explainability methods were presented in 15 (28.8%) of studies with the most common method is feature importance which used 14 times.

CONCLUSION

For databases of 5000 or fewer samples, extreme gradient boosting has the highest probability of success. A large, multi-region, multi centre database is required to reduce bias and take advantage of neural network method. A framework for validating with and explaining ML model to clinicians involved in the management of ARDS would be very helpful for development and deployment of the ML model.

Prone position in the mechanical ventilation of acute respiratory distress syndrome children: a systematic review and meta-analysis

Background

Prone position has been well recognized for the treatment of adult acute respiratory distress syndrome (ARDS). We aimed to evaluate the role of prone position in the mechanical ventilation in children with ARDS, to provide evidence to the treatment and care of children with ARDS.

Methods

We searched the Pubmed et al. databases by computer until January 23, 2024 for randomized controlled trials (RCTs) on the role of prone position in the mechanical ventilation in children with ARDS. We evaluated the quality of included studies according to the quality evaluation criteria recommended by the Cochrane library. RevMan 5.3 software was used for meta-analysis.

Results

7 RCTs involving 433 children with ARDS were included. Meta-analysis indicated that prone position is beneficial to improve the arterial oxygenation pressure [MD = 4.27 mmHg, 95% CI (3.49, 5.06)], PaO2/FiO2 [MD = 26.97, 95% CI (19.17, 34.77)], reduced the oxygenation index [MD = -3.52, 95% CI (-5.41, -1.64)], mean airway pressure [MD = -1.91 cmH2O, 95% CI (-2.27, -1.55)] and mortality [OR = 0.33, 95% CI (0.15, 0.73), all P < 0.05]. There were no statistical differences in the duration of mechanical ventilation between the prone position group and control group [MD = -17.01, 97.27, 95% CI (-38.28, 4.26), P = 0.12]. Egger test results showed that no significant publication bias was found (all P > 0.05).

Conclusions

Prone position ventilation has obvious advantages in improving oxygenation, but there is no significant improvement in the time of mechanical ventilation in the treatment of children with ARDS. In the future, more large-sample, high-quality RCTs are still needed to further analyze the role of prone position in the mechanical ventilation in children with ARDS.

Drivers of mortality in COVID ARDS depend on patient sub-type

The most common cause of death in people with COVID-19 is Acute Respiratory Distress Syndrome (ARDS). Prior studies have demonstrated that ARDS is a heterogeneous syndrome and have identified ARDS sub-types (phenoclusters). However, non-COVID-19 ARDS phenoclusters do not clearly apply to COVID-19 ARDS patients. In this retrospective cohort study, we implemented an iterative approach, combining supervised and unsupervised machine learning methodologies, to identify clinically relevant COVID-19 ARDS phenoclusters, as well as characteristics that are predictive of the outcome for each phenocluster. To this end, we applied a supervised model to identify risk factors for hospital mortality for each phenocluster and compared these between phenoclusters and the entire cohort. We trained the models using a comprehensive, preprocessed dataset of 2,864 hospitalized COVID-19 ARDS patients. Our research demonstrates that the risk factors predicting mortality in the overall cohort of COVID-19 ARDS may not necessarily apply to specific phenoclusters. Additionally, some risk factors increase the risk of hospital mortality in some phenoclusters but decrease mortality in others. These phenocluster-specific risk factors would not have been observed with a single predictive model. Heterogeneity in phenoclusters of COVID-19 ARDS as well as the drivers of mortality may partially explain challenges in finding effective treatments for all patients with ARDS.