Development and Validation of a Multi-Algorithm Analytic Platform to Detect Off-Target Mechanical Ventilation

Patient-ventilator asynchrony classification in mechanically ventilated patients: Model-based or machine learning method?

BACKGROUND AND OBJECTIVE

Patient-ventilator asynchrony (PVA) is associated with poor clinical outcomes and remains under-monitored. Automated PVA detection would enable complete monitoring standard observational methods do not allow. While model-based and machine learning PVA approaches exist, they have variable performance and can miss specific PVA events. This study compares a model and rule-based algorithm with a machine learning PVA method by retrospectively validating both methods using an independent patient cohort.

METHODS

Hysteresis loop analysis (HLA) which is a rule-based method (RBM) and a tri-input convolutional neural network (TCNN) machine learning model are used to classify 7 different types of PVA, including: 1) flow asynchrony; 2) reverse triggering; 3) premature cycling; 4) double triggering; 5) delayed cycling; 6) ineffective efforts; and 7) auto triggering. Class activation mapping (CAM) heatmaps visualise sections of respiratory waveforms the TCNN model uses for decision making, improving result interpretability. Both PVA classification methods were used to classify incidence in an independent retrospective clinical cohort of 11 mechanically ventilated patients for validation and performance comparison.

RESULTS

Self-validation with the training dataset shows overall better HLA performance (accuracy, sensitivity, specificity: 97.5 %, 96.6 %, 98.1 %) compared to the TCNN model (accuracy, sensitivity, specificity: 89.5 %, 98.3 %, 83.9 %). In this study, the TCNN model demonstrates higher sensitivity in detecting PVA, but HLA was better at identifying non-PVA breathing cycles due to its rule-based nature. While the overall AI identified by both classification methods are very similar, the intra-patient distribution of each PVA type varies between HLA and TCNN.

CONCLUSION

The collective findings underscore the efficacy of both HLA and TCNN in PVA detection, indicating the potential for real-time continuous monitoring of PVA. While ML methods such as TCNN demonstrate good PVA identification performance, it is essential to ensure optimal model architecture and diversity in training data before widespread uptake as standard care. Moving forward, further validation and adoption of RBM methods, such as HLA, offers an effective approach to PVA detection while providing clear distinction into the underlying patterns of PVA, better aligning with clinical needs for transparency, explicability, adaptability and reliability of these emerging tools for clinical care.

Detection and quantitative analysis of patient-ventilator interactions in ventilated infants by deep learning networks

BACKGROUND

The study of patient-ventilator interactions (PVI) in mechanically ventilated neonates is limited by the lack of unified PVI definitions and tools to perform large scale analyses.

METHODS

An observational study was conducted in 23 babies randomly selected from 170 neonates who were ventilated with SIPPV-VG, SIMV-VG or PSV-VG mode for at least 12 h. 500 breaths were randomly selected and manually annotated from each recording to train convolutional neural network (CNN) models for PVI classification.

RESULTS

The average asynchrony index (AI) over all recordings was 52.5%. The most frequently occurring PVIs included expiratory work (median: 28.4%, interquartile range: 23.2-40.2%), late cycling (7.6%, 2.8-10.2%), failed triggering (4.6%, 1.2-6.2%) and late triggering (4.4%, 2.8-7.4%). Approximately 25% of breaths with a PVI had two or more PVIs occurring simultaneously. Binary CNN classifiers were developed for PVIs affecting ≥1% of all breaths (n = 7) and they achieved F1 scores of >0.9 on the test set except for early triggering where it was 0.809.

CONCLUSIONS

PVIs occur frequently in neonates undergoing conventional mechanical ventilation with a significant proportion of breaths containing multiple PVIs. We have developed computational models for seven different PVIs to facilitate automated detection and further evaluation of their clinical significance in neonates.

IMPACT

The study of patient-ventilator interactions (PVI) in mechanically ventilated neonates is limited by the lack of unified PVI definitions and tools to perform large scale analyses. By adapting a recent taxonomy of PVI definitions in adults, we have manually annotated neonatal ventilator waveforms to determine prevalence and co-occurrence of neonatal PVIs. We have also developed binary deep learning classifiers for common PVIs to facilitate their automatic detection and quantification.

Survey of Ventilator Waveform Interpretation Among ICU Professionals

BACKGROUND

The interpretation of ventilator waveforms is essential for effective and safe mechanical ventilation but requires specialized training and expertise. This study aimed to investigate the ability of ICU professionals to interpret ventilator waveforms, identify areas requiring further education and training, and explore the factors influencing their interpretation skills.

METHODS

We conducted an international online anonymous survey of ICU professionals (physicians, nurses, and respiratory therapists [RTs]), with ≥ 1 y of experience working in the ICU. The survey consisted of demographic information and 15 multiple-choice questions related to ventilator waveforms. Results were compared between professions using descriptive statistics, and logistic regression (expressed as odds ratios [ORs; 95% CI]) was performed to identify factors associated with high performance, which was defined by a threshold of 60% correct answers.

RESULTS

A total of 1,832 professionals from 31 countries or regions completed the survey; 53% of respondents answered ≥ 60% of the questions correctly. The 3 questions with the most correct responses were related to waveforms that demonstrated condensation (90%), pressure overshoot (79%), and bronchospasm (75%). Conversely, the 3 questions with the fewest correct responses were waveforms that demonstrated early cycle leading to double trigger (43%), severe under assistance (flow starvation) (37%), and early/reverse trigger (31%). Factors significantly associated with ≥ 60% correct answers included years of ICU working experience (≥ 10 y, OR 1.6 [1.2-2.0], P < .001), profession (RT, OR 2.8 [2.1-3.7], P < .001), highest degree earned (graduate, OR 1.7 [1.3-2.2], P < .001), workplace (teaching hospital, OR 1.4 [1.1-1.7], P = .008), and prior ventilator waveforms training (OR 1.7 [1.3-2.2], P < .001).

CONCLUSIONS

Slightly over half respondents correctly identified ≥ 60% of waveforms demonstrating patient-ventilator discordance. High performance was associated with ≥ 10 years of ICU working experience, RT profession, graduate degree, working in a teaching hospital, and prior ventilator waveforms training. Some discordances were poorly recognized across all groups of surveyed professionals.

Complications associated with long-term positive-pressure ventilation in dogs and cats: 67 cases

OBJECTIVES

To determine the complications associated with positive-pressure ventilation (PPV) in dogs and cats.

DESIGN

Retrospective study from October 2009 to September 2013.

SETTING

University Teaching Hospital.

ANIMALS

Fifty-eight dogs and 9 cats.

MEASUREMENTS AND MAIN RESULTS

Medical records were retrospectively reviewed; signalment, complications associated with PPV, duration of PPV, and outcome were recorded. Complications most commonly recorded during PPV included hypothermia 41/67 (61%), hypotension 39/67 (58%), cardiac arrhythmias 33/67 (49%), a positive fluid balance 31/67 (46%), oral lesions 25/67 (37%), and corneal ulcerations 24/67 (36%). A definition of ventilator-associated events (VAE) extrapolated from the Center of Disease Control's criteria was applied to 21 cases that received PPV for at least 4 days in this study. Ventilator-associated conditions occurred in 5 of 21 (24%) of cases with infection-related ventilator-associated conditions and ventilator-associated pneumonia identified in 3 of 21 (14%) cases.

CONCLUSIONS

Complications are common and diverse in dogs and cats receiving long-term PPV and emphasizes the importance of intensive, continuous patient monitoring and appropriate nursing care protocols. Many of the complications identified could be serious without intervention and suggests that appropriate equipment alarms could improve patient safety. Development of veterinary specific surveillance tools such as the VAE criteria would aid future investigations and allow for effective multicenter studies.

Understanding basic principles of Artificial Intelligence: a practical guide for intensivists

BACKGROUND AND AIM

Artificial intelligence was born to allow computers to learn and control their environment, trying to imitate the human brain structure by simulating its biological evolution. Artificial intelligence makes it possible to analyze large amounts of data (big data) in real-time, providing forecasts that can support the clinician's decisions. This scenario can include diagnosis, prognosis, and treatment in anesthesiology, intensive care medicine, and pain medicine. Machine Learning is a subcategory of AI. It is based on algorithms trained for decisions making that automatically learn and recognize patterns from data. This article aims to offer an overview of the potential application of AI in anesthesiology and analyzes the operating principles of machine learning Every Machine Learning pathway starts from task definition and ends in model application.

CONCLUSIONS

High-performance characteristics and strict quality controls are needed during its progress. During this process, different measures can be identified (pre-processing, exploratory data analysis, model selection, model processing and evaluation). For inexperienced operators, the process can be facilitated by ad hoc tools for data engineering, machine learning, and analytics.

An interpretable 1D convolutional neural network for detecting patient-ventilator asynchrony in mechanical ventilation

BACKGROUND AND OBJECTIVE

Patient-ventilator asynchrony (PVA) is the result of a mismatch between the need of patients and the assistance provided by the ventilator during mechanical ventilation. Because the poor interaction between the patient and the ventilator is associated with inferior clinical outcomes, effort should be made to identify and correct their occurrence. Deep learning has shown promising ability in PVA detection; however, lack of network interpretability hampers its application in clinic.

METHODS

We proposed an interpretable one-dimensional convolutional neural network (1DCNN) to detect four most manifestation types of PVA (double triggering, ineffective efforts during expiration, premature cycling and delayed cycling) under pressure control ventilation mode and pressure support ventilation mode. A global average pooling (GAP) layer was incorporated with the 1DCNN model to highlight the sections of the respiratory waveform the model focused on when making a classification. Dilation convolution and batch normalization were introduced to the 1DCNN model for compensating the reduction of performance caused by the GAP layer.

RESULTS

The proposed interpretable 1DCNN exhibited comparable performance with the state-of-the-art deep learning model in PVA detection. The F1 scores for the detection of four types of PVA under pressure control ventilation and pressure support ventilation modes were greater than 0.96. The critical sections of the waveform used to detect PVA were highlighted, and found to be well consistent with the understanding of the respective type of PVA by experts.

CONCLUSIONS

The findings suggest that the proposed 1DCNN can help detect PVA, and enhance the interpretability of the classification process to help clinicians better understand the results obtained from deep learning technology.

Intelligent decision support with machine learning for efficient management of mechanical ventilation in the intensive care unit - A critical overview

BACKGROUND

Effective management of Mechanical Ventilation (MV) is vital for reducing morbidity, mortality, and cost of healthcare.

OBJECTIVE

This study aims to synthesize evidence for effective MV management through Intelligent decision support (IDS) with Machine Learning (ML).

METHOD

Databases that include EBSCO, IEEEXplore, Google Scholar, SCOPUS, and the Web of Science were systematically searched to identify studies on IDS for effective MV management regarding Tidal Volume (TV), asynchrony, weaning, and other outcomes such as the risk of Prolonged Mechanical ventilation (PMV). The quality of the articles identified was assessed with a modified Joanna Briggs Institute (JBI) critical appraisal checklist for cross-sessional research.

RESULTS

A total of 26 articles were identified for the study that has IDS for TV (n = 2, 7.8 %), asynchrony (n = 9, 34.6 %), weaning (n = 12, 46.2 %), and others (n = 3, 11.5 %). It was affirmed that implementing IDS in MV management will enhance seamless ICU patient management following the utilization of various Machine Learning (ML) algorithms in decision support. The studies relied on (n = 14) ML algorithms to predict the TV, asynchrony, weaning, risk of PMV and Positive End-Expiratory Pressure (PEEP) changes of 11-20262 ICU patients records with model inputs ranging from (n = 1) for timeseries analysis of TV to (n = 47) for weaning prediction.

CONCLUSIONS

The small data size, poor study design, and result reporting, with the heterogeneity of techniques used in the various studies, hampered the development of a unified approach for managing MV efficiency in TV monitoring, asynchrony, and weaning predictions. Notwithstanding, the ensemble model was able to predict TV, asynchrony, and weaning to a higher accuracy than the other algorithms.

Can Big Data and Machine Learning Improve Our Understanding of Acute Respiratory Distress Syndrome?

Acute respiratory distress syndrome (ARDS) accounts for 10% of all diagnoses in the Intensive Care Unit, and about 40% of the patients succumb to the disease. Clinical methods alone can result in the under-recognition of this heterogeneous syndrome. The purpose of this study is to evaluate the role that big data and machine learning (ML) have played in understanding the heterogeneity of the disease and the development of various prediction algorithms. Most of the work in the field of ML in ARDS has been in the development of prediction models that have comparable efficacies to that of traditional models. Prediction algorithms have been useful in identifying new variables that may be important to consider in the future, supplementing the unknown information with the help of available noninvasive parameters, as well as predicting mortality. Phenotype identification using an unsupervised ML algorithm has been pivotal in classifying the heterogeneous population into more homogenous classes. Big data generated from ventilators in the form of ventilator waveform analysis and images in the form of radiomics have also been leveraged for the identification of the syndrome and can be incorporated into a clinical decision support system. Although the results are promising, lack of generalizability, "black box" nature of algorithms and concerns about "alarm fatigue" should be addressed for more mainstream adoption of these models.

Use of Machine Learning to Screen for Acute Respiratory Distress Syndrome Using Raw Ventilator Waveform Data

To develop and characterize a machine learning algorithm to discriminate acute respiratory distress syndrome from other causes of respiratory failure using only ventilator waveform data.

Design

Retrospective, observational cohort study.

Setting

Academic medical center ICU.

Patients

Adults admitted to the ICU requiring invasive mechanical ventilation, including 50 patients with acute respiratory distress syndrome and 50 patients with primary indications for mechanical ventilation other than hypoxemic respiratory failure.

Interventions

None.

Measurements and Main Results

Pressure and flow time series data from mechanical ventilation during the first 24-hours after meeting acute respiratory distress syndrome criteria (or first 24-hr of mechanical ventilation for non-acute respiratory distress syndrome patients) were processed to extract nine physiologic features. A random forest machine learning algorithm was trained to discriminate between the patients with and without acute respiratory distress syndrome. Model performance was assessed using the area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value. Analyses examined performance when the model was trained using data from the first 24 hours and tested using withheld data from either the first 24 hours (24/24 model) or 6 hours (24/6 model). Area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value were 0.88, 0.90, 0.71, 0.77, and 0.90 (24/24); and 0.89, 0.90, 0.75, 0.83, and 0.83 (24/6).

Conclusions

Use of machine learning and physiologic information derived from raw ventilator waveform data may enable acute respiratory distress syndrome screening at early time points after intubation. This approach, combined with traditional diagnostic criteria, could improve timely acute respiratory distress syndrome recognition and enable automated clinical decision support, especially in settings with limited availability of conventional diagnostic tests and electronic health records.

Computational analysis of neonatal ventilator waveforms and loops

BACKGROUND

Modern neonatal ventilators allow the downloading of their data with a high sampling rate. We wanted to develop an algorithm that automatically recognises and characterises ventilator inflations from ventilator pressure and flow data.

METHODS

We downloaded airway pressure and flow data with 100 Hz sampling rate from Dräger Babylog VN500 ventilators ventilating critically ill infants. We developed an open source Python package, Ventiliser, that includes a rule-based algorithm to automatically discretise ventilator data into a sequence of flow and pressure states and to recognise ventilator inflations and an information gain approach to identify inflation phases (inspiration, expiration) and sub-phases (pressure rise, pressure plateau, inspiratory hold etc.).

RESULTS

Ventiliser runs on a personal computer and analyses 24 h of ventilation in 2 min. With longer recordings, the processing time increases linearly. It generates a table reporting indices of each breath and its sub-phases. Ventiliser also allows visualisation of individual inflations as waveforms or loops. Ventiliser identified >97% of ventilator inflations and their sub-phases in an out-of-sample validation of manually annotated data. We also present detailed quantitative analysis and comparison of two 1-hour-long ventilation periods.

CONCLUSIONS

Ventiliser can analyse ventilation patterns and ventilator-patient interactions over long periods of mechanical ventilation.

IMPACT

We have developed a computational method to recognize and analyse ventilator inflations from raw data downloaded from ventilators of preterm and critically ill infants. There have been no previous reports on the computational analysis of neonatal ventilator data. We have made our program, Ventiliser, freely available. Clinicians and researchers can use Ventiliser to analyse ventilator inflations, waveforms and loops over long periods. Ventiliser can also be used to study ventilator-patient interactions.

A machine learning method for automatic detection and classification of patient-ventilator asynchrony

Patients suffering from respiratory failure are often put on assisted mechanical ventilation. Patient-ventilator asynchrony (PVA) can occur during mechanical ventilation, which cause damage to the lungs and has been linked to increased mortality in the intensive care unit. In current clinical practice PVA is still detected using visual inspection of the air pressure, flow, and volume curves, which is time-consuming and sensitive to subjective interpretation. Correct detection of the patient respiratory efforts is needed to properly asses the type of asynchrony. Therefore, we propose a method for automatic detection of the patient respiratory efforts using a one-dimensional convolution neural network. The proposed method was able to detect patient efforts with a sensitivity and precision of 98.6% and 97.3% for the inspiratory efforts, and 97.7% and 97.2% for the expiratory efforts. Besides allowing detection of PVA, combining the estimated timestamps of patient's inspiratory and expiratory efforts with the timings of the mechanical ventilator further allows for classification of the asynchrony type. In the future, the proposed method could support clinical decision making by informing clinicians on the quality of ventilation and providing actionable feedback for properly adjusting the ventilator settings.

Leveraging IoTs and Machine Learning for Patient Diagnosis and Ventilation Management in the Intensive Care Unit

Future healthcare systems will rely heavily on clinical decision support systems (CDSS) to improve the decision-making processes of clinicians. To explore the design of future CDSS, we developed a research-focused CDSS for the management of patients in the intensive care unit that leverages Internet of Things (IoT) devices capable of collecting streaming physiologic data from ventilators and other medical devices. We then created machine learning (ML) models that could analyze the collected physiologic data to determine if the ventilator was delivering potentially harmful therapy and if a deadly respiratory condition, acute respiratory distress syndrome (ARDS), was present. We also present work to aggregate these models into a mobile application that can provide responsive, real-time alerts of changes in ventilation to providers. As illustrated in the recent COVID-19 pandemic, being able to accurately predict ARDS in newly infected patients can assist in prioritizing care. We show that CDSS may be used to analyze physiologic data for clinical event recognition and automated diagnosis, and we also highlight future research avenues for hospital CDSS.

Artificial Intelligence in the Intensive Care Unit

This article is one of ten reviews selected from the Annual Update in Intensive Care and Emergency Medicine 2020. Other selected articles can be found online at https://www.biomedcentral.com/collections/annualupdate2020. Further information about the Annual Update in Intensive Care and Emergency Medicine is available from http://www.springer.com/series/8901.

Evaluating Delivery of Low Tidal Volume Ventilation in Six ICUs Using Electronic Health Record Data

OBJECTIVES

Mechanical ventilation with low tidal volumes is recommended for all patients with acute respiratory distress syndrome and may be beneficial to other intubated patients, yet consistent implementation remains difficult to obtain. Using detailed electronic health record data, we examined patterns of tidal volume administration, the effect on clinical outcomes, and alternate metrics for evaluating low tidal volume compliance in clinical practice.

DESIGN

Observational cohort study.

SETTING

Six ICUs in a single hospital system.

PATIENTS

Adult patients who received invasive mechanical ventilation more than 12 hours.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Tidal volumes were analyzed across 1,905 hospitalizations. Although mean tidal volume was 6.8 mL/kg predicted body weight, 40% of patients were exposed to tidal volumes greater than 8 mL/kg predicted body weight, with 11% for more than 24 hours. At a patient level, exposure to 24 total hours of tidal volumes greater than 8 mL/kg predicted body weight was associated with increased mortality (odds ratio, 1.82; 95% CI, 1.20-2.78), whereas mean tidal volume exposure was not (odds ratio, 0.87/1 mL/kg increase; 95% CI, 0.74-1.02). Initial tidal volume settings strongly predicted exposure to volumes greater than 8 mL/kg for 24 hours; the adjusted rate was 21.5% when initial volumes were greater than 8 mL/kg predicted body weight and 7.1% when initial volumes were less than 8 mL/kg predicted body weight. Across ICUs, correlation of mean tidal volume with alternative measures of low tidal volume delivery ranged from 0.38 to 0.66.

CONCLUSIONS

Despite low mean tidal volume in the cohort, a significant percentage of patients were exposed to a prolonged duration of high tidal volumes which was correlated with higher mortality. Detailed ventilator records in the electronic health record provide a unique window for evaluating low tidal volume delivery and targets for improvement.

Patient-ventilator asynchronies during mechanical ventilation: current knowledge and research priorities

BACKGROUND

Mechanical ventilation is common in critically ill patients. This life-saving treatment can cause complications and is also associated with long-term sequelae. Patient-ventilator asynchronies are frequent but underdiagnosed, and they have been associated with worse outcomes.

MAIN BODY

Asynchronies occur when ventilator assistance does not match the patient's demand. Ventilatory overassistance or underassistance translates to different types of asynchronies with different effects on patients. Underassistance can result in an excessive load on respiratory muscles, air hunger, or lung injury due to excessive tidal volumes. Overassistance can result in lower patient inspiratory drive and can lead to reverse triggering, which can also worsen lung injury. Identifying the type of asynchrony and its causes is crucial for effective treatment. Mechanical ventilation and asynchronies can affect hemodynamics. An increase in intrathoracic pressure during ventilation modifies ventricular preload and afterload of ventricles, thereby affecting cardiac output and hemodynamic status. Ineffective efforts can decrease intrathoracic pressure, but double cycling can increase it. Thus, asynchronies can lower the predictive accuracy of some hemodynamic parameters of fluid responsiveness. New research is also exploring the psychological effects of asynchronies. Anxiety and depression are common in survivors of critical illness long after discharge. Patients on mechanical ventilation feel anxiety, fear, agony, and insecurity, which can worsen in the presence of asynchronies. Asynchronies have been associated with worse overall prognosis, but the direct causal relation between poor patient-ventilator interaction and worse outcomes has yet to be clearly demonstrated. Critical care patients generate huge volumes of data that are vastly underexploited. New monitoring systems can analyze waveforms together with other inputs, helping us to detect, analyze, and even predict asynchronies. Big data approaches promise to help us understand asynchronies better and improve their diagnosis and management.

CONCLUSIONS

Although our understanding of asynchronies has increased in recent years, many questions remain to be answered. Evolving concepts in asynchronies, lung crosstalk with other organs, and the difficulties of data management make more efforts necessary in this field.

Predicting Patient-ventilator Asynchronies with Hidden Markov Models

In mechanical ventilation, it is paramount to ensure the patient's ventilatory demand is met while minimizing asynchronies. We aimed to develop a model to predict the likelihood of asynchronies occurring. We analyzed 10,409,357 breaths from 51 critically ill patients who underwent mechanical ventilation >24 h. Patients were continuously monitored and common asynchronies were identified and regularly indexed. Based on discrete time-series data representing the total count of asynchronies, we defined four states or levels of risk of asynchronies, z1 (very-low-risk) - z4 (very-high-risk). A Poisson hidden Markov model was used to predict the probability of each level of risk occurring in the next period. Long periods with very few asynchronous events, and consequently very-low-risk, were more likely than periods with many events (state z4). States were persistent; large shifts of states were uncommon and most switches were to neighbouring states. Thus, patients entering states with a high number of asynchronies were very likely to continue in that state, which may have serious implications. This novel approach to dealing with patient-ventilator asynchrony is a first step in developing smart alarms to alert professionals to patients entering high-risk states so they can consider actions to improve patient-ventilator interaction.