Utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome

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.

Automatic ARDS surveillance with chest X-ray recognition using convolutional neural networks

OBJECTIVE

This study aims to design, validate and assess the accuracy a deep learning model capable of differentiation Chest X-Rays between pneumonia, acute respiratory distress syndrome (ARDS) and normal lungs.

MATERIALS AND METHODS

A diagnostic performance study was conducted using Chest X-Ray images from adult patients admitted to a medical intensive care unit between January 2003 and November 2014. X-ray images from 15,899 patients were assigned one of three prespecified categories: "ARDS", "Pneumonia", or "Normal".

RESULTS

A two-step convolutional neural network (CNN) pipeline was developed and tested to distinguish between the three patterns with sensitivity ranging from 91.8% to 97.8% and specificity ranging from 96.6% to 98.8%. The CNN model was validated with a sensitivity of 96.3% and specificity of 96.6% using a previous dataset of patients with Acute Lung Injury (ALI)/ARDS.

DISCUSSION

The results suggest that a deep learning model based on chest x-ray pattern recognition can be a useful tool in distinguishing patients with ARDS from patients with normal lungs, providing faster results than digital surveillance tools based on text reports.

CONCLUSION

A CNN-based deep learning model showed clinically significant performance, providing potential for faster ARDS identification. Future research should prospectively evaluate these tools in a clinical setting.

ARDSFlag: an NLP/machine learning algorithm to visualize and detect high-probability ARDS admissions independent of provider recognition and billing codes

BACKGROUND

Despite the significance and prevalence of acute respiratory distress syndrome (ARDS), its detection remains highly variable and inconsistent. In this work, we aim to develop an algorithm (ARDSFlag) to automate the diagnosis of ARDS based on the Berlin definition. We also aim to develop a visualization tool that helps clinicians efficiently assess ARDS criteria.

METHODS

ARDSFlag applies machine learning (ML) and natural language processing (NLP) techniques to evaluate Berlin criteria by incorporating structured and unstructured data in an electronic health record (EHR) system. The study cohort includes 19,534 ICU admissions in the Medical Information Mart for Intensive Care III (MIMIC-III) database. The output is the ARDS diagnosis, onset time, and severity.

RESULTS

ARDSFlag includes separate text classifiers trained using large training sets to find evidence of bilateral infiltrates in radiology reports (accuracy of 91.9%±0.5%) and heart failure/fluid overload in radiology reports (accuracy 86.1%±0.5%) and echocardiogram notes (accuracy 98.4%±0.3%). A test set of 300 cases, which was blindly and independently labeled for ARDS by two groups of clinicians, shows that ARDSFlag generates an overall accuracy of 89.0% (specificity = 91.7%, recall = 80.3%, and precision = 75.0%) in detecting ARDS cases.

CONCLUSION

To our best knowledge, this is the first study to focus on developing a method to automate the detection of ARDS. Some studies have developed and used other methods to answer other research questions. Expectedly, ARDSFlag generates a significantly higher performance in all accuracy measures compared to those methods.

Steroids in acute respiratory distress syndrome: A panacea or still a puzzle?

Acute respiratory distress syndrome (ARDS) is a unique entity marked by various etiologies and heterogenous pathophysiologies. There remain concerns regarding the efficacy of particular medications for each severity level apart from respiratory support. Among several pharmacotherapies which have been examined in the treatment of ARDS, corticosteroids, in particular, have demonstrated potential for improving the resolution of ARDS. Nevertheless, it is imperative to consider the potential adverse effects of hyperglycemia, susceptibility to hospital-acquired infections, and the development of intensive care unit acquired weakness when administering corticosteroids. Thus far, a multitude of trials spanning several decades have investigated the role of corticosteroids in ARDS. Further stringent trials are necessary to identify particular subgroups before implementing corticosteroids more widely in the treatment of ARDS. This review article provides a concise overview of the most recent evidence regarding the role and impact of corticosteroids in the management of ARDS.

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.

A pretrain-finetune approach for improving model generalizability in outcome prediction of acute respiratory distress syndrome patients

BACKGROUND

Early prediction of acute respiratory distress syndrome (ARDS) of critically ill patients in intensive care units (ICUs) has been intensively studied in the past years. Yet a prediction model trained on data from one hospital might not be well generalized to other hospitals. It is therefore essential to develop an accurate and generalizable ARDS prediction model adaptive to different hospital or medical centers.

METHODS

We analyzed electronic medical records of 200,859 and 50,920 hospitalized patients within 24 h after being diagnosed with ARDS from the Philips eICU Institute (eICU-CRD) and the Medical Information Mart for Intensive Care (MIMIC-IV) dataset, respectively. Patients were sorted into three groups, including rapid death, long stay, and recovery, based on their condition or outcome between 24 and 72 h after ARDS diagnosis. To improve prediction performance and generalizability, a "pretrain-finetune" approach was applied, where we pretrained models on the eICU-CRD dataset and performed model finetuning using only a part (35%) of the MIMIC-IV dataset, and then tested the finetuned models on the remaining data from the MIMIC-IV dataset. Well-known machine-learning algorithms, including logistic regression, random forest, extreme gradient boosting, and multilayer perceptron neural networks, were employed to predict ARDS outcomes. Prediction performance was evaluated using the area under the receiver-operating characteristic curve (AUC).

RESULTS

Results show that, in general, multilayer perceptron neural networks outperformed the other models. The use of pretrain-finetune yielded improved performance in predicting ARDS outcomes achieving a micro-AUC of 0.870 for the MIMIC-IV dataset, an improvement of 0.046 over the pretrain model.

CONCLUSIONS

The proposed pretrain-finetune approach can effectively improve model generalizability from one to another dataset in ARDS prediction.

Predicting Phase 1 Lymphoma Clinical Trial Durations Using Machine Learning: An In-Depth Analysis and Broad Application Insights

Lymphoma diagnoses in the US are substantial, with an estimated 89,380 new cases in 2023, necessitating innovative treatment approaches. Phase 1 clinical trials play a pivotal role in this context. We developed a binary predictive model to assess trial adherence to expected average durations, analyzing 1089 completed Phase 1 lymphoma trials from clinicaltrials.gov. Using machine learning, the Random Forest model demonstrated high efficacy with an accuracy of 0.7248 and an ROC-AUC of 0.7677 for lymphoma trials. The difference in the accuracy level of the Random Forest is statistically significant compared to the other alternative models, as determined by a 95% confidence interval on the testing set. Importantly, this model maintained an ROC-AUC of 0.7701 when applied to lung cancer trials, showcasing its versatility. A key insight is the correlation between higher predicted probabilities and extended trial durations, offering nuanced insights beyond binary predictions. Our research contributes to enhanced clinical research planning and potential improvements in patient outcomes in oncology.

Deep Learning with Geometry-Enhanced Molecular Representation for Augmentation of Large-Scale Docking-Based Virtual Screening

Structure-based virtual screening has been a crucial tool in drug discovery for decades. However, as the chemical space expands, the existing structure-based virtual screening techniques based on molecular docking and scoring struggle to handle billion-entry ultralarge libraries due to the high computational cost. To address this challenge, people have resorted to machine learning techniques to enhance structure-based virtual screening for efficiently exploring the vast chemical space. In those cases, compounds are usually treated as sequential strings or two-dimensional topology graphs, limiting their ability to incorporate three-dimensional structural information for downstream tasks. We herein propose a novel deep learning protocol, GEM-Screen, which utilizes the geometry-enhanced molecular representation of the compounds docking to a specific target and is trained on docking scores of a small fraction of a library through an active learning strategy to approximate the docking outcome for yet nontraining entries. This protocol is applied to virtual screening campaigns against the AmpC and D4 targets, demonstrating that GEM-Screen enriches more than 90% of the hit scaffolds for AmpC in the top 4% of model predictions and more than 80% of the hit scaffolds for D4 in the same top-ranking size of library. GEM-Screen can be used in conjunction with traditional docking programs for docking of only the top-ranked compounds to avoid the exhaustive docking of the whole library, thus allowing for discovering top-scoring compounds from billion-entry libraries in a rapid yet accurate fashion.

Identification of indications for albumin administration in septic patients with liver cirrhosis

BACKGROUND

Albumin infusion is the primary therapeutic strategy for septic patients with liver cirrhosis. Although recent studies have investigated the efficacy of albumin in the resuscitation stage of septic patients with liver cirrhosis, it remains unclear whether daily albumin administration can improve outcomes. Furthermore, the indications for initiating albumin therapy are not well defined.

METHODS

Septic patients with liver cirrhosis were obtained from the Medical Information Mart for Intensive Care (MIMIC-IV 2.0) database. Marginal structural Cox models were employed to investigate the association between daily albumin infusion and 28-day mortality. We also aimed to explore under what circumstances enrolled patients could benefit most from albumin administration, based on the clinical parameters collected on the day of albumin infusion, including serum albumin concentration, serum lactate concentration, mean arterial pressure (MAP), and vasopressor dosage.

RESULTS

A total of 2265 patients were included in the final analysis, of whom 1093 (48.3%) had received albumin treatment at least once. The overall 28-day mortality was 29.6%. After marginal structural modeling, daily albumin infusion was associated with a reduced risk of 28-day death (hazard ratio, 0.76; 95% CI 0.61-0.94). We found that patients benefit most from albumin infusion when initiated on the day of serum albumin concentration between 2.5 and 3.0 g/dL, serum lactate concentration greater than or equal to 2 mmol/L, MAP less than 60 mmHg, or vasopressor dosage between 0.2 and 0.3 mcg/kg/min (norepinephrine equivalent, NEE).

CONCLUSIONS

Albumin infusion is associated with a reduction in mortality in septic patients with liver cirrhosis under specific circumstances. Serum albumin concentration, serum lactate, MAP, and vasopressor dosage were found to be modifiers of treatment effectiveness and should be considered when deciding to initial albumin infusion.

Specific recommendations to improve the design and conduct of clinical trials

There are many reasons why the majority of clinical trials fail or have limited applicability to patient care. These include restrictive entry criteria, short duration studies, unrecognized adverse drug effects, and reporting of therapy assignment preferential to actual use. Frequently, experimental animal models are used sparingly and do not accurately simulate human disease. We suggest two approaches to improve the conduct, increase the success, and applicability of clinical trials. Studies can apply dosing of the investigational therapeutics and outcomes, determined from animal models that more closely simulate human disease. More extensive identification of known and potential risk factors and confounding issues, gleaned from recently organized "big data," should be utilized to create models for trials. The risk factors in each model are then accounted for and managed during each study.

To Establish an Early Prediction Model for Acute Respiratory Distress Syndrome in Severe Acute Pancreatitis Using Machine Learning Algorithm

OBJECTIVE

To develop binary and quaternary classification prediction models in patients with severe acute pancreatitis (SAP) using machine learning methods, so that doctors can evaluate the risk of patients with acute respiratory distress syndrome (ARDS) and severe ARDS at an early stage.

METHODS

A retrospective study was conducted on SAP patients hospitalized in our hospital from August 2017 to August 2022. Logical Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), and eXtreme Gradient Boosting (XGB) were used to build the binary classification prediction model of ARDS. Shapley Additive explanations (SHAP) values were used to interpret the machine learning model, and the model was optimized according to the interpretability results of SHAP values. Combined with the optimized characteristic variables, four-class classification models, including RF, SVM, DT, XGB, and Artificial Neural Network (ANN), were constructed to predict mild, moderate, and severe ARDS, and the prediction effects of each model were compared.

RESULTS

The XGB model showed the best effect (AUC = 0.84) in the prediction of binary classification (ARDS or non-ARDS). According to SHAP values, the prediction model of ARDS severity was constructed with four characteristic variables (PaO₂/FiO₂, APACHE II, SOFA, AMY). Among them, the overall prediction accuracy of ANN is 86%, which is the best.

CONCLUSIONS

Machine learning has a good effect in predicting the occurrence and severity of ARDS in SAP patients. It can also provide a valuable tool for doctors to make clinical decisions.

Quantifying deep neural network uncertainty for atrial fibrillation detection with limited labels

Atrial fibrillation (AF) is the most common arrhythmia found in the intensive care unit (ICU), and is associated with many adverse outcomes. Effective handling of AF and similar arrhythmias is a vital part of modern critical care, but obtaining knowledge about both disease burden and effective interventions often requires costly clinical trials. A wealth of continuous, high frequency physiological data such as the waveforms derived from electrocardiogram telemetry are promising sources for enriching clinical research. Automated detection using machine learning and in particular deep learning has been explored as a solution for processing these data. However, a lack of labels, increased presence of noise, and inability to assess the quality and trustworthiness of many machine learning model predictions pose challenges to interpretation. In this work, we propose an approach for training deep AF models on limited, noisy data and report uncertainty in their predictions. Using techniques from the fields of weakly supervised learning, we leverage a surrogate model trained on non-ICU data to create imperfect labels for a large ICU telemetry dataset. We combine these weak labels with techniques to estimate model uncertainty without the need for extensive human data annotation. AF detection models trained using this process demonstrated higher classification performance (0.64-0.67 F1 score) and improved calibration (0.05-0.07 expected calibration error).