Respiratory monitoring in adult intensive care unit

Comparison of lung ultrasound assisted by artificial intelligence to radiology examination in pneumothorax

BACKGROUND

Lung ultrasound can evaluate for pneumothorax but the accuracy of diagnosis depends on experience among physicians. This study aimed to investigate the sensitivity and specificity of intelligent lung ultrasound in comparison with chest x-ray, employing chest computed tomography (CT) as the gold standard for diagnosis of pneumothorax in critical ill patients.

METHODS

This prospective, observational study included 75 dyspnea patients admitted to the Intensive Care Unit of the Fourth Affiliated Hospital of Soochow University from January 2021 to April 2023. Lung ultrasound images were collected using BLUE-plus protocol and analyzed by artificial intelligence software to identify the pleural line, with CT results serving as the gold standard for diagnosis. Pneumothorax was diagnosed based on either the disappearance of pleural slip sign or identification of lung point. Additionally, chest x-ray images and diagnostic results were also obtained during the same period for comparison.

RESULTS

The sensitivity and specificity of intelligent lung ultrasound in diagnosing pneumothorax were 79.4% and 85.4%, respectively. The sensitivity and specificity of x-ray diagnosis were 82.4% and 80.5%. Additionally, the diagnostic time for lung ultrasound was significantly shorter than that for x-ray examination.

CONCLUSION

Intelligent lung ultrasound has diagnostic efficiency comparable to that of x-ray examination but offers advantages in terms of speed.

PPG2RespNet: a deep learning model for respirational signal synthesis and monitoring from photoplethysmography (PPG) signal

Breathing conditions affect a wide range of people, including those with respiratory issues like asthma and sleep apnea. Smartwatches with photoplethysmogram (PPG) sensors can monitor breathing. However, current methods have limitations due to manual parameter tuning and pre-defined features. To address this challenge, we propose the PPG2RespNet deep-learning framework. It draws inspiration from the UNet and UNet + + models. It uses three publicly available PPG datasets (VORTAL, BIDMC, Capnobase) to autonomously and efficiently extract respiratory signals. The datasets contain PPG data from different groups, such as intensive care unit patients, pediatric patients, and healthy subjects. Unlike conventional U-Net architectures, PPG2RespNet introduces layered skip connections, establishing hierarchical and dense connections for robust signal extraction. The bottleneck layer of the model is also modified to enhance the extraction of latent features. To evaluate PPG2RespNet's performance, we assessed its ability to reconstruct respiratory signals and estimate respiration rates. The model outperformed other models in signal-to-signal synthesis, achieving exceptional Pearson correlation coefficients (PCCs) with ground truth respiratory signals: 0.94 for BIDMC, 0.95 for VORTAL, and 0.96 for Capnobase. With mean absolute errors (MAE) of 0.69, 0.58, and 0.11 for the respective datasets, the model exhibited remarkable precision in estimating respiration rates. We used regression and Bland-Altman plots to analyze the predictions of the model in comparison to the ground truth. PPG2RespNet can thus obtain high-quality respiratory signals non-invasively, making it a valuable tool for calculating respiration rates.

Relationship between lung ultrasound and electrical impedance tomography as regional assessment tools during PEEP titration in acute respiratory distress syndrome caused by multi-lobar pneumonia: a pilot study

Acute respiratory distress syndrome (ARDS) caused by multilobar pneumonia (MLP) is markedly different from typical ARDS in pathology, imaging characteristics, and lung mechanics. Regional lung assessment is required. We aimed to analyze the relationship between two regional assessment tools, lung ultrasound (LUS) and electrical impedance tomography (EIT) during positive end-expiratory pressure (PEEP) titration, and determine an appropriate PEEP level. We conducted a prospective study of patients with ARDS caused by MLP with PaO₂/FiO₂ < 150 mmHg. All subjects were equipped with two EIT belts connected with a single EIT machine to measure upper and lower hemithorax impedance change alternatingly at each PEEP level. LUS score was simultaneously determined in chest wall regions corresponding to the EIT regions during PEEP titration. We acquired EIT and LUS data in eight regions of interest at seven PEEP levels in 12 subjects. Therefore, 672 pairs of data were obtained for analysis. There were significant relationships between LUS score and tidal impedance variation and pixel compliance (C_pix). The Spearman's rho between LUS score vs. tidal impedance variation and LUS score vs. the C_pix were - 0.142, P < 0.001, and - 0.195, P < 0.001, respectively. The relationship between the LUS score and C_pix remained the same at every PEEP level but did not reach statistical significance. The individual's mean expected PEEP by LUS was similar to the EIT [10.33(± 1.67) vs. 10.33(± 1.44) cm H₂O, P = 0.15]. Regarding the MLP, the LUS scores were associated with EIT parameters, and LUS scores might proof helpful for finding individual PEEP settings in MLP.

Classification of Level of Consciousness in a Neurological ICU Using Physiological Data

BACKGROUND

Impaired consciousness is common in intensive care unit (ICU) patients, and an individual's degree of consciousness is crucial to determining their care and prognosis. However, there are no methods that continuously monitor consciousness and alert clinicians to changes. We investigated the use of physiological signals collected in the ICU to classify levels of consciousness in critically ill patients.

METHODS

We studied 61 patients with subarachnoid hemorrhage (SAH) and 178 patients with intracerebral hemorrhage (ICH) from the neurological ICU at Columbia University Medical Center in a retrospective observational study of prospectively collected data. The level of consciousness was determined on the basis of neurological examination and mapped to comatose, vegetative state or unresponsive wakefulness syndrome (VS/UWS), minimally conscious minus state (MCS-), and command following. For each physiological signal, we extracted time-series features and performed classification using extreme gradient boosting on multiple clinically relevant tasks across subsets of physiological signals. We applied this approach independently on both SAH and ICH patient groups for three sets of variables: (1) a minimal set common to most hospital patients (e.g., heart rate), (2) variables available in most ICUs (e.g., body temperature), and (3) an extended set recorded mainly in neurological ICUs (absent for the ICH patient group; e.g., brain temperature).

RESULTS

On the commonly performed classification task of VS/UWS versus MCS-, we achieved an area under the receiver operating characteristic curve (AUROC) in the SAH patient group of 0.72 (sensitivity 82%, specificity 57%; 95% confidence interval [CI] 0.63-0.81) using the extended set, 0.69 (sensitivity 83%, specificity 51%; 95% CI 0.59-0.78) on the variable set available in most ICUs, and 0.69 (sensitivity 56%, specificity 78%; 95% CI 0.60-0.78) on the minimal set. In the ICH patient group, AUROC was 0.64 (sensitivity 56%, specificity 65%; 95% CI 0.55-0.74) using the minimal set and 0.61 (sensitivity 50%, specificity 80%; 95% CI 0.51-0.71) using the variables available in most ICUs.

CONCLUSIONS

We find that physiological signals can be used to classify states of consciousness for patients in the ICU. Building on this with intraday assessments and increasing sensitivity and specificity may enable alarm systems that alert physicians to changes in consciousness and frequent monitoring of consciousness throughout the day, both of which may improve patient care and outcomes.

CapNet: A Deep Learning-based Framework for Estimation of Capnograph Signal from PPG

Ambulatory respiration signal extraction system is required to maintain continuous surveillance of a patient with respiratory deficiency. The capnograph signal has received a lot of attention in recent years as a valuable indicator of respiratory conditions. However, the typical capnograph signal extraction method is quite expensive and also unpleasant to the patient due to the involvement of a nasal cannula. With the advent of wearable sensor technology, there has been significant research on the use of photoplethysmogram (PPG) signals as a less expensive alternative to extract respiratory information. In this paper, we propose CapNet, a novel deep learning-based framework which takes the regular PPG signal as input, and estimates the capnograph signal as output. Training, validation and testing of the proposed networks in CapNet is done using the IEEE TMBE Respiratory Rate Benchmark dataset by utilizing reference capnograph respiration signals. With a lower MSE and higher cross-correlation values, CapNet outperforms two traditional signal processing algorithms and another recently proposed deep neural network, RespNet. The proposed framework expectantly can be implementable and feasible for constant supervising of patients undergoing respiratory ailments.

RespNet: A deep learning model for extraction of respiration from photoplethysmogram

Respiratory ailments afflict a wide range of people and manifests itself through conditions like asthma and sleep apnea. Continuous monitoring of chronic respiratory ailments is seldom used outside the intensive care ward due to the large size and cost of the monitoring system. While Electrocardiogram (ECG) based respiration extraction is a validated approach, its adoption is limited by access to a suitable continuous ECG monitor. Recently, due to the widespread adoption of wearable smartwatches with in-built Photoplethysmogram (PPG) sensor, it is being considered as a viable candidate for continuous and unobtrusive respiration monitoring. Research in this domain, however, has been predominantly focussed on estimating respiration rate from PPG. In this work, a novel end-to-end deep learning network called RespNet is proposed to perform the task of extracting the respiration signal from a given input PPG as opposed to extracting respiration rate. The proposed network was trained and tested on two different datasets utilizing different modalities of reference respiration signal recordings. Also, the similarity and performance of the proposed network against two conventional signal processing approaches for extracting respiration signal were studied. The proposed method was tested on two independent datasets with a Mean Squared Error of 0.262 and 0.145. The cross-correlation coefficient of the respective datasets were found to be 0.933 and 0.931. The reported errors and similarity was found to be better than conventional approaches. The proposed approach would aid clinicians to provide comprehensive evaluation of sleep-related respiratory conditions and chronic respiratory ailments while being comfortable and inexpensive for the patient.

Volumetric but Not Time Capnography Detects Ventilation/Perfusion Mismatch in Injured Rabbit Lung

Whereas time capnography (Tcap) is routinely displayed during mechanical ventilation, the volumetric representation (Vcap) is seldom used. We compared the diagnostic value of indices derived from Tcap and Vcap following ventilation to perfusion ratio () mismatch subsequent to experimentally induced acute respiratory distress syndrome (ARDS), and alveolar recruitment by elevating the positive end-expiratory pressure (PEEP). Lung injury was induced by iv lipopolysaccharide, whole lung lavage and injurious ventilation in anesthetized, mechanically ventilated rabbits (n = 26). Mainstream Tcap and Vcap were performed to assess normalized phase 2 (Sn2_T, Sn2_V) and phase 3 slopes (Sn3_T, Sn3_V) in the time and volumetric domains. Vcap was also used to estimate Enghoff’s physiological dead space (VD_E). Lung oxygenation index (PaO₂/FiO₂) and intrapulmonary shunt (Qs/Qt) were derived from arterial and central venous blood gas samples. All measurements were made under baseline conditions, and, following lung injury, under moderate (6 cmH₂O) and high PEEP levels (9 cmH₂O). Lung injury deteriorated the PaO₂/FiO₂ (baseline vs. injured 466 ± 10.2 [95% confidence interval] vs. 77.3 ± 17.1 mmHg, p < 0.05) and compromised all mechanical parameters significantly, whereas Tcap parameters exhibited contradictory or inconsistent changes. Conversely, Vcap indices exhibited consistent changes and provided excellent diagnostic value in detecting lung-function deterioration subsequent to lung injury [area under the receiver operating characteristic (ROC) curve of 1.0 ± 0.0, 0.87 ± 0.22 and 0.86 ± 0.22 for VD_E, Sn3_V and Sn3_V/Sn2_V, respectively]. Elevated PEEP increased PaO₂/FiO₂ and decreased Qs/Qt, which was reflected only in the Vcap slope ratio (Sn3_V/Sn2_V, p < 0.05). Our findings demonstrate the limited value of Tcap to detect ventilation to perfusion ratio () mismatch, following severe lung injury. Conversely, indices derived from Vcap proved to be sensitive for detecting lung volume loss and alveolar recruitment. Therefore, promotion of Vcap is of paramount importance as a real-time, non-invasive, bedside monitoring modality to detect the development of and to follow-up the progression of lung injury in a model of ARDS.

Initiation of LPS-induced pulmonary dysfunction and its recovery occur independent of T cells

Background

The acute respiratory distress syndrome (ARDS) is a serious disease in critically ill patients that is characterized by pulmonary dysfunctions, hypoxemia and significant mortality. Patients with immunodeficiency (e.g. SCID with T and B cell deficiency) are particularly susceptible to the development of severe ARDS. However, the role of T cells on pulmonary dysfunctions in immune-competent patients with ARDS is only incompletely understood.

Methods

Wild-type (wt) and RAG2^−/− mice (lymphocyte deficient) received intratracheal instillations of LPS (4 mg/kg) or saline. On day 1, 4 and 10 lung mechanics and bronchial hyperresponsiveness towards acetylcholine were measured with the flexiVent ventilation set-up. The bronchoalveolar lavage fluid (BALF) was examined for leukocytes (FACS analysis) and pro-inflammatory cytokines (ELISA).

Results

In wt mice, lung mechanics, body weight and body temperature deteriorated in the LPS-group during the early phase (up to d4); these alterations were accompanied by increased leukocyte numbers and inflammatory cytokine levels in the BALF. During the late phase (day 10), both lung mechanics and the cell/cytokine homeostasis recovered in LPS-treated wt mice. RAG2^−/− mice experienced changes in body weight, lung mechanics, BAL neutrophil numbers, BAL inflammatory cytokines levels that were comparable to wt mice.

Conclusion

Following LPS instillation, lung mechanics deteriorate within the first 4 days and recover towards day 10. This response is not altered by the lack of T lymphocytes suggesting that T cells play only a minor role for the initiation, propagation or recovery of LPS-induced lung dysfunctions or function of T lymphocytes can be compensated by other immune cells, such as alveolar macrophages.

Electronic supplementary material

The online version of this article (10.1186/s12890-018-0741-2) contains supplementary material, which is available to authorized users.

Electrical impedance tomography

Continuous assessment of respiratory status is one of the cornerstones of modern intensive care unit (ICU) monitoring systems. Electrical impedance tomography (EIT), although with some constraints, may play the lead as a new diagnostic and guiding tool for an adequate optimization of mechanical ventilation in critically ill patients. EIT may assist in defining mechanical ventilation settings, assess distribution of tidal volume and of end-expiratory lung volume (EELV) and contribute to titrate positive end-expiratory pressure (PEEP)/tidal volume combinations. It may also quantify gains (recruitment) and losses (overdistention or derecruitment), granting a more realistic evaluation of different ventilator modes or recruitment maneuvers, and helping in the identification of responders and non-responders to such maneuvers. Moreover, EIT also contributes to the management of life-threatening lung diseases such as pneumothorax, and aids in guiding fluid management in the critical care setting. Lastly, assessment of cardiac function and lung perfusion through electrical impedance is on the way.