A novel machine learning model to predict respiratory failure and invasive mechanical ventilation in critically ill patients suffering from COVID-19

Intelligent alert system for predicting invasive mechanical ventilation needs via noninvasive parameters: employing an integrated machine learning method with integration of multicenter databases

The use of invasive mechanical ventilation (IMV) is crucial in rescuing patients with respiratory dysfunction. Accurately predicting the demand for IMV is vital for clinical decision-making. However, current techniques are invasive and challenging to implement in pre-hospital and emergency rescue settings. To address this issue, a real-time prediction method utilizing only non-invasive parameters was developed to forecast IMV demand in this study. The model introduced the concept of real-time warning and leveraged the advantages of machine learning and integrated methods, achieving an AUC value of 0.935 (95% CI 0.933-0.937). The AUC value for the multi-center validation using the AmsterdamUMCdb database was 0.727, surpassing the performance of traditional risk adjustment algorithms (OSI(oxygenation saturation index): 0.608, P/F(oxygenation index): 0.558). Feature weight analysis demonstrated that BMI, Gcsverbal, and age significantly contributed to the model's decision-making. These findings highlight the substantial potential of a machine learning real-time dynamic warning model that solely relies on non-invasive parameters to predict IMV demand. Such a model can provide technical support for predicting the need for IMV in pre-hospital and disaster scenarios.

The future of artificial intelligence in clinical nutrition

PURPOSE OF REVIEW

Artificial intelligence has reached the clinical nutrition field. To perform personalized medicine, numerous tools can be used. In this review, we describe how the physician can utilize the growing healthcare databases to develop deep learning and machine learning algorithms, thus helping to improve screening, assessment, prediction of clinical events and outcomes related to clinical nutrition.

RECENT FINDINGS

Artificial intelligence can be applied to all the fields of clinical nutrition. Improving screening tools, identifying malnourished cancer patients or obesity using large databases has been achieved. In intensive care, machine learning has been able to predict enteral feeding intolerance, diarrhea, or refeeding hypophosphatemia. The outcome of patients with cancer can also be improved. Microbiota and metabolomics profiles are better integrated with the clinical condition using machine learning. However, ethical considerations and limitations of the use of artificial intelligence should be considered.

SUMMARY

Artificial intelligence is here to support the decision-making process of health professionals. Knowing not only its limitations but also its power will allow precision medicine in clinical nutrition as well as in the rest of the medical practice.

Predicting invasive mechanical ventilation in COVID 19 patients: A validation study

INTRODUCTION

The decision to intubate and ventilate a patient is mainly clinical. Both delaying intubation (when needed) and unnecessarily invasively ventilating (when it can be avoided) are harmful. We recently developed an algorithm predicting respiratory failure and invasive mechanical ventilation in COVID-19 patients. This is an internal validation study of this model, which also suggests a categorized "time-weighted" model.

METHODS

We used a dataset of COVID-19 patients who were admitted to Rabin Medical Center after the algorithm was developed. We evaluated model performance in predicting ventilation, regarding the actual endpoint of each patient. We further categorized each patient into one of four categories, based on the strength of the prediction of ventilation over time. We evaluated this categorized model performance regarding the actual endpoint of each patient.

RESULTS

881 patients were included in the study; 96 of them were ventilated. AUC of the original algorithm is 0.87-0.94. The AUC of the categorized model is 0.95.

CONCLUSIONS

A minor degradation in the algorithm accuracy was noted in the internal validation, however, its accuracy remained high. The categorized model allows accurate prediction over time, with very high negative predictive value.

Making the Improbable Possible: Generalizing Models Designed for a Syndrome-Based, Heterogeneous Patient Landscape

Syndromic conditions, such as sepsis, are commonly encountered in the intensive care unit. Although these conditions are easy for clinicians to grasp, these conditions may limit the performance of machine-learning algorithms. Individual hospital practice patterns may limit external generalizability. Data missingness is another barrier to optimal algorithm performance and various strategies exist to mitigate this. Recent advances in data science, such as transfer learning, conformal prediction, and continual learning, may improve generalizability of machine-learning algorithms in critically ill patients. Randomized trials with these approaches are indicated to demonstrate improvements in patient-centered outcomes at this point.

Study of Biochemical Parameters as Predictors for Need of Invasive Ventilation in Severely Ill COVID-19 Patients

Background

Though laboratory tests have been shown to predict mortality in COVID-19, there is still a dearth of information regarding the role of biochemical parameters in predicting the type of ventilatory support that these patients may require.

Methods

The purpose of our retrospective observational study was to investigate the relationship between biochemical parameters and the type of ventilatory support needed for the intensive care of severely ill COVID-19 patients. We comprehensively recorded history, physical examination, vital signs from point-of-care testing (POCT) devices, clinical diagnosis, details of the ventilatory support required in intensive care and the results of the biochemical analysis at the time of admission. Appropriate statistical methods were used and P-values < 0.05 were considered significant. Receiver operating characteristics (ROC) analysis was performed and Area Under the Curve (AUC) of 0.6 to 0.7, 0.7 to 0.8, 0.8 to 0.9, and >0.9, respectively, were regarded as acceptable, fair, good, and exceptional for discrimination.

Results

Statistically significant differences (p<0.05) in Urea (p = 0.0351), Sodium (p = 0.0142), Indirect Bilirubin (p = 0.0251), Albumin (p = 0.0272), Aspartate Transaminase (AST) (p = 0.0060) and Procalcitonin (PCT) (p = 0.0420) were observed between the patients who were maintained on non-invasive ventilations as compared to those who required invasive ventilation. In patients who required invasive ventilation, the levels of Urea, Sodium, Indirect bilirubin, AST and PCT were higher while Albumin was lower. On ROC analysis, higher levels of Albumin was found to be acceptable indicator of maintenance on non-invasive ventilation while higher levels of Sodium and PCT were found to be fair predictor of requirement of invasive ventilation.

Conclusion

Our study emphasizes the role of biochemical parameters in predicting the type of ventilatory support that is needed in order to properly manage severely ill COVID-19 patients.

A Transformer-Based Model Trained on Large Scale Claims Data for Prediction of Severe COVID-19 Disease Progression

In situations like the COVID-19 pandemic, healthcare systems are under enormous pressure as they can rapidly collapse under the burden of the crisis. Machine learning (ML) based risk models could lift the burden by identifying patients with a high risk of severe disease progression. Electronic Health Records (EHRs) provide crucial sources of information to develop these models because they rely on routinely collected healthcare data. However, EHR data is challenging for training ML models because it contains irregularly timestamped diagnosis, prescription, and procedure codes. For such data, transformer-based models are promising. We extended the previously published Med-BERT model by including age, sex, medications, quantitative clinical measures, and state information. After pre-training on approximately 988 million EHRs from 3.5 million patients, we developed models to predict Acute Respiratory Manifestations (ARM) risk using the medical history of 80,211 COVID-19 patients. Compared to Random Forests, XGBoost, and RETAIN, our transformer-based models more accurately forecast the risk of developing ARM after COVID-19 infection. We used Integrated Gradients and Bayesian networks to understand the link between the essential features of our model. Finally, we evaluated adapting our model to Austrian in-patient data. Our study highlights the promise of predictive transformer-based models for precision medicine.

An AI-powered patient triage platform for future viral outbreaks using COVID-19 as a disease model

Over the last century, outbreaks and pandemics have occurred with disturbing regularity, necessitating advance preparation and large-scale, coordinated response. Here, we developed a machine learning predictive model of disease severity and length of hospitalization for COVID-19, which can be utilized as a platform for future unknown viral outbreaks. We combined untargeted metabolomics on plasma data obtained from COVID-19 patients (n = 111) during hospitalization and healthy controls (n = 342), clinical and comorbidity data (n = 508) to build this patient triage platform, which consists of three parts: (i) the clinical decision tree, which amongst other biomarkers showed that patients with increased eosinophils have worse disease prognosis and can serve as a new potential biomarker with high accuracy (AUC = 0.974), (ii) the estimation of patient hospitalization length with ± 5 days error (R2 = 0.9765) and (iii) the prediction of the disease severity and the need of patient transfer to the intensive care unit. We report a significant decrease in serotonin levels in patients who needed positive airway pressure oxygen and/or were intubated. Furthermore, 5-hydroxy tryptophan, allantoin, and glucuronic acid metabolites were increased in COVID-19 patients and collectively they can serve as biomarkers to predict disease progression. The ability to quickly identify which patients will develop life-threatening illness would allow the efficient allocation of medical resources and implementation of the most effective medical interventions. We would advocate that the same approach could be utilized in future viral outbreaks to help hospitals triage patients more effectively and improve patient outcomes while optimizing healthcare resources.

Becalm: Intelligent Monitoring of Respiratory Patients

The Becalm project is an open and low-cost solution for the remote monitoring of respiratory support therapies like the ones used in COVID-19 patients. Becalm combines a decision-making system based on Case-Based Reasoning with a low-cost, non-invasive mask that enables the remote monitoring, detection, and explanation of risk situations for respiratory patients. This paper first describes the mask and the sensors that allow remote monitoring. Then, it describes the intelligent decision-making system that detects anomalies and raises early warnings. This detection is based on the comparison of cases that represent patients using a set of static variables plus the dynamic vector of the patient time series from sensors. Finally, personalized visual reports are created to explain the causes of the warning, data patterns, and patient context to the healthcare professional. To evaluate the case-based early-warning system, we use a synthetic data generator that simulates patients' clinical evolution from the physiological features and factors described in healthcare literature. This generation process has been verified with a real dataset and allows the validation of the reasoning system with noisy and incomplete data, threshold values, and life/death situations. The evaluation demonstrates promising results and good accuracy (0.91) for the proposed low-cost solution to monitor respiratory patients.

Development and validation of a prediction model for mechanical ventilation based on comorbidities in hospitalized patients with COVID-19

Background

Timely recognition of respiratory failure and the need for mechanical ventilation is crucial in managing patients with coronavirus disease 2019 (COVID-19) and reducing hospital mortality rate. A risk stratification tool could assist to avoid clinical deterioration of patients with COVID-19 and optimize allocation of scarce resources. Therefore, we aimed to develop a prediction model for early identification of patients with COVID-19 who may require mechanical ventilation.

Methods

We included patients with COVID-19 hospitalized in United States. Demographic and clinical data were extracted from the records of the Healthcare Cost and Utilization Project State Inpatient Database in 2020. Model construction involved the use of the least absolute shrinkage and selection operator and multivariable logistic regression. The model's performance was evaluated based on discrimination, calibration, and clinical utility.

Results

The training set comprised 73,957 patients (5,971 requiring mechanical ventilation), whereas the validation set included 10,428 (887 requiring mechanical ventilation). The prediction model incorporating age, sex, and 11 other comorbidities (deficiency anemias, congestive heart failure, coagulopathy, dementia, diabetes with chronic complications, complicated hypertension, neurological disorders unaffecting movement, obesity, pulmonary circulation disease, severe renal failure, and weight loss) demonstrated moderate discrimination (area under the curve, 0.715; 95% confidence interval, 0.709-0.722), good calibration (Brier score = 0.070, slope = 1, intercept = 0) and a clinical net benefit with a threshold probability ranged from 2 to 34% in the training set. Similar model's performances were observed in the validation set.

Conclusion

A robust prognostic model utilizing readily available predictors at hospital admission was developed for the early identification of patients with COVID-19 who may require mechanical ventilation. Application of this model could support clinical decision-making to optimize patient management and resource allocation.

Comprehensive analysis of clinical data for COVID-19 outcome estimation with machine learning models

COVID-19 is a global threat for the healthcare systems due to the rapid spread of the pathogen that causes it. In such situation, the clinicians must take important decisions, in an environment where medical resources can be insufficient. In this task, the computer-aided diagnosis systems can be very useful not only in the task of supporting the clinical decisions but also to perform relevant analyses, allowing them to understand better the disease and the factors that can identify the high risk patients. For those purposes, in this work, we use several machine learning algorithms to estimate the outcome of COVID-19 patients given their clinical information. Particularly, we perform 2 different studies: the first one estimates whether the patient is at low or at high risk of death whereas the second estimates if the patient needs hospitalization or not. The results of the analyses of this work show the most relevant features for each studied scenario, as well as the classification performance of the considered machine learning models. In particular, the XGBoost algorithm is able to estimate the need for hospitalization of a patient with an AUC-ROC of 0 . 8415 ± 0 . 0217 while it can also estimate the risk of death with an AUC-ROC of 0 . 7992 ± 0 . 0104 . Results have demonstrated the great potential of the proposal to determine those patients that need a greater amount of medical resources for being at a higher risk. This provides the healthcare services with a tool to better manage their resources.

Using Machine-Learning to Assess the Prognostic Value of Early Enteral Feeding Intolerance in Critically Ill Patients: A Retrospective Study

BACKGROUND

The association between gastrointestinal intolerance during early enteral nutrition (EN) and adverse clinical outcomes in critically ill patients is controversial. We aimed to assess the prognostic value of enteral feeding intolerance (EFI) markers during early ICU stays and to predict early EN failure using a machine learning (ML) approach.

METHODS

We performed a retrospective analysis of data from adult patients admitted to Beilinson Hospital ICU between January 2011 and December 2018 for more than 48 h and received EN. Clinical data, including demographics, severity scores, EFI markers, and medications, along with 72 h after admission, were analyzed by ML algorithms. Prediction performance was assessed by the area under the receiver operating characteristics (AUCROC) of a ten-fold cross-validation set.

RESULTS

The datasets comprised 1584 patients. The means of the cross-validation AUCROCs for 90-day mortality and early EN failure were 0.73 (95% CI 0.71-0.75) and 0.71 (95% CI 0.67-0.74), respectively. Gastric residual volume above 250 mL on the second day was an important component of both prediction models.

CONCLUSIONS

ML underlined the EFI markers that predict poor 90-day outcomes and early EN failure and supports early recognition of at-risk patients. Results have to be confirmed in further prospective and external validation studies.

Predicting the Level of Respiratory Support in COVID-19 Patients Using Machine Learning

In this paper, a machine learning-based system for the prediction of the required level of respiratory support in COVID-19 patients is proposed. The level of respiratory support is divided into three classes: class 0 which refers to minimal support, class 1 which refers to non-invasive support, and class 2 which refers to invasive support. A two-stage classification system is built. First, the classification between class 0 and others is performed. Then, the classification between class 1 and class 2 is performed. The system is built using a dataset collected retrospectively from 3491 patients admitted to tertiary care hospitals at the University of Louisville Medical Center. The use of the feature selection method based on analysis of variance is demonstrated in the paper. Furthermore, a dimensionality reduction method called principal component analysis is used. XGBoost classifier achieves the best classification accuracy (84%) in the first stage. It also achieved optimal performance in the second stage, with a classification accuracy of 83%.