Defining predictors for successful mechanical ventilation weaning, using a data-mining process and artificial intelligence.

Mechanical ventilation weaning within intensive care units (ICU) is a difficult process, while crucial when considering its impact on morbidity and mortality. Failed extubation and prolonged mechanical ventilation both carry a significant risk of adverse events. We aimed to determine predictive factors of extubation success using data-mining and artificial intelligence. A prospective physiological and biomedical signal data warehousing project. A 21-beds medical Intensive Care Unit of a University Hospital. Adult patients undergoing weaning from mechanical ventilation. Hemodynamic and respiratory parameters of mechanically ventilated patients were prospectively collected and combined with clinical outcome data. One hundred and eight patients were included, for 135 spontaneous breathing trials (SBT) allowing to identify physiological parameters either measured before or during the trial and considered as predictive for extubation success. The Early-Warning Score Oxygen (EWSO2) enables to discriminate patients deemed to succeed extubation, at 72-h and 7-days. Cut-off values for EWSO2 (AUC = 0.80; Se = 0.75; Sp = 0.76), mean arterial pressure and heart-rate variability parameters were determined. A predictive model for extubation success was established including body-mass index (BMI) on inclusion, occlusion pressure at 0,1 s. (P0.1) and heart-rate analysis parameters (LF/HF) both measured before SBT, and heart rate during SBT (global performance 62%; 83%). The data-mining process enabled to detect independent predictive factors for extubation success and to develop a dynamic predictive model using artificial intelligence. Such predictive tools may help clinicians to better discriminate patients deemed to succeed extubation and thus improve clinical performance.

Automated Oxygen Titration During CPAP and Noninvasive Ventilation in Healthy Subjects With Induced Hypoxemia.

BACKGROUND: Automated oxygen titration to maintain a stable SpO2 has been developed for spontaneously breathing patients but has not been evaluated during CPAP and noninvasive ventilation (NIV). METHODS: We performed a randomized controlled crossover, double-blind study on 10 healthy subjects with induced hypoxemia during 3 situations: spontaneous breathing with oxygen support, CPAP (5 cm H2O), and NIV (7/3 cm H2O). We conducted in random order 3 dynamic hypoxic challenges of 5 min (FIO2 0.08 ± 0.02, 0.11± 0.02, and 0.14 ± 0.02). For each condition, we compared automated oxygen titration and manual oxygen titration by experienced respiratory therapists (RTs), with the aim to maintain the SpO2 at 94 ± 2%. In addition, we included 2 subjects hospitalized for exacerbation of COPD under NIV and a subject managed after bariatric surgery with CPAP and automated oxygen titration. RESULTS: The percentage of time in the SpO2 target was higher with automated compared with manual oxygen titration for all conditions, on average 59.6 ± 22.8% compared to 44.3 ± 23.9% (P = .004). Hyperoxemia (SpO2 > 96%) was less frequent with automated titration for each mode of oxygen administration (24.0 ± 24.4% vs 39.1 ± 25.3%, P < .001). During the manual titration periods, the RT made several changes to oxygen flow (5.1 ± 3.3 interventions that lasted 122 ± 70 s/period) compared to none during the automated titration to maintain oxygenation in the targeted SpO2 . Time in the SpO2 target was higher with stable hospitalized subjects in comparison with healthy subjects under dynamic-induced hypoxemia. CONCLUSIONS: In this proof-of-concept study, automated oxygen titration was used during CPAP and NIV. The performances to maintain the SpO2 target were significantly better compared to manual oxygen titration in the setting of this study protocol. This technology may allow decreasing the number of manual interventions for oxygen titration during CPAP and NIV.

Hydrocortisone in Severe Community-Acquired Pneumonia.

BACKGROUND: Whether the antiinflammatory and immunomodulatory effects of glucocorticoids may decrease mortality among patients with severe community-acquired pneumonia is unclear. METHODS: In this phase 3, multicenter, double-blind, randomized, controlled trial, we assigned adults who had been admitted to the intensive care unit (ICU) for severe community-acquired pneumonia to receive intravenous hydrocortisone (200 mg daily for either 4 or 7 days as determined by clinical improvement, followed by tapering for a total of 8 or 14 days) or to receive placebo. All the patients received standard therapy, including antibiotics and supportive care. The primary outcome was death at 28 days. RESULTS: A total of 800 patients had undergone randomization when the trial was stopped after the second planned interim analysis. Data from 795 patients were analyzed. By day 28, death had occurred in 25 of 400 patients (6.2%; 95% confidence interval [CI], 3.9 to 8.6) in the hydrocortisone group and in 47 of 395 patients (11.9%; 95% CI, 8.7 to 15.1) in the placebo group (absolute difference, -5.6 percentage points; 95% CI, -9.6 to -1.7; P = 0.006). Among the patients who were not undergoing mechanical ventilation at baseline, endotracheal intubation was performed in 40 of 222 (18.0%) in the hydrocortisone group and in 65 of 220 (29.5%) in the placebo group (hazard ratio, 0.59; 95% CI, 0.40 to 0.86). Among the patients who were not receiving vasopressors at baseline, such therapy was initiated by day 28 in 55 of 359 (15.3%) of the hydrocortisone group and in 86 of 344 (25.0%) in the placebo group (hazard ratio, 0.59; 95% CI, 0.43 to 0.82). The frequencies of hospital-acquired infections and gastrointestinal bleeding were similar in the two groups; patients in the hydrocortisone group received higher daily doses of insulin during the first week of treatment. CONCLUSIONS: Among patients with severe community-acquired pneumonia being treated in the ICU, those who received hydrocortisone had a lower risk of death by day 28 than those who received placebo. (Funded by the French Ministry of Health; CAPE COD ClinicalTrials.gov number, NCT02517489.).

Elevations of Extracellular Vesicles and Inflammatory Biomarkers in Closed Circuit SCUBA Divers.

Blood-borne extracellular vesicles and inflammatory mediators were evaluated in divers using a closed circuit rebreathing apparatus and custom-mixed gases to diminish some diving risks. "Deep" divers (n = 8) dove once to mean (±SD) 102.5 ± 1.2 m of sea water (msw) for 167.3 ± 11.5 min. "Shallow" divers (n = 6) dove 3 times on day 1, and then repetitively over 7 days to 16.4 ± 3.7 msw, for 49.9 ± 11.9 min. There were statistically significant elevations of microparticles (MPs) in deep divers (day 1) and shallow divers at day 7 that expressed proteins specific to microglia, neutrophils, platelets, and endothelial cells, as well as thrombospondin (TSP)-1 and filamentous (F-) actin. Intra-MP IL-1ß increased by 7.5-fold (p < 0.001) after day 1 and 41-fold (p = 0.003) at day 7. Intra-MP nitric oxide synthase-2 (NOS2) increased 17-fold (p < 0.001) after day 1 and 19-fold (p = 0.002) at day 7. Plasma gelsolin (pGSN) levels decreased by 73% (p < 0.001) in deep divers (day 1) and 37% in shallow divers by day 7. Plasma samples containing exosomes and other lipophilic particles increased from 186% to 490% among the divers but contained no IL-1ß or NOS2. We conclude that diving triggers inflammatory events, even when controlling for hyperoxia, and many are not proportional to the depth of diving.

Accuracy of Multiple Pulse Oximeters in Stable Critically Ill Patients.

BACKGROUND: An accurate SpO2 value is critical in order to optimally titrate oxygen delivery to patients and to follow oxygenation guidelines. Limited prospective data exist on real-world performance of pulse oximeters in critically ill patients. The objective of this study was to assess accuracy and bias of the SpO2 values measured by several oximeters in hospitalized subjects. METHODS: We included stable adults in the ICU with an arterial catheter in place. Main exclusion criteria were poor SpO2 signal and SpO2 > 96%. In each subject, we simultaneously evaluated 4 oximeters: Nonin (Plymouth, Minnesota) embedded in the FreeO2 device (OxyNov, Québec City, Québec, Canada), Masimo (Radical-7, Masimo, Irvine, California), Philips (FAST, Philips, Amsterdam, the Netherlands), and Nellcor (N-600, Medtronic, Minneapolis, Minnesota). Arterial blood gases were drawn and simultaneously each oximeters' SpO2 values were collected. SpO2 values were compared to the reference (arterial oxygen saturation [SaO2 ] value) to determine bias and accuracy. The ability for oximeters to detect hypoxemia and the impact of oximeters on oxygen titration were evaluated. RESULTS: We included 193 subjects (153 male, mean age 66 y) in whom 211 sets of measurements were performed. The skin pigmentation evaluated by Fitzpatrick scale showed 96.2% of subjects were light skin (types 1 and 2). One oximeter overestimated SaO2 (Philips, +0.9%), whereas the 3 others underestimated SaO2 (Nonin -3.1%, Nellcor -0.3%, Masimo -0.2%). SaO2 was underestimated with Nonin oximeter in 91.3% of the cases, whereas it was overestimated in 55.2% of the cases with Philips oximeter. Moderate hypoxemia (SaO2 86-90% or PaO2 55-60 mm Hg) was detected in 92, 33, 42, and 11% of the cases with Nonin, Nellcor, Masimo, and Philips, respectively. CONCLUSIONS: We found significant bias and moderate accuracy between the tested oximeters and the arterial blood gases in the studied population. These discrepancies may have important clinical impact on the detection of hypoxemia and management of oxygen therapy.

Early heart rate variability evaluation enables to predict ICU patients' outcome.

Heart rate variability (HRV) is a mean to evaluate cardiac effects of autonomic nervous system activity, and a relation between HRV and outcome has been proposed in various types of patients. We attempted to evaluate the best determinants of such variation in survival prediction using a physiological data-warehousing program. Plethysmogram tracings (PPG) were recorded at 75 Hz from the standard monitoring system, for a 2 h period, during the 24 h following ICU admission. Physiological data recording was associated with metadata collection. HRV was derived from PPG in either the temporal and non-linear domains. 540 consecutive patients were recorded. A lower LF/HF, SD2/SD1 ratios and Shannon entropy values on admission were associated with a higher ICU mortality. SpO2/FiO2 ratio and HRV parameters (LF/HF and Shannon entropy) were independent correlated with mortality in the multivariate analysis. Machine-learning using neural network (kNN) enabled to determine a simple decision tree combining the three best determinants (SDNN, Shannon Entropy, SD2/SD1 ratio) of a composite outcome index. HRV measured on admission enables to predict outcome in the ICU or at Day-28, independently of the admission diagnosis, treatment and mechanical ventilation requirement.Trial registration: ClinicalTrials.gov identifier NCT02893462.

Accuracy of noncontact surface imaging for tidal volume and respiratory rate measurements in the ICU.

Tidal volume monitoring may help minimize lung injury during respiratory assistance. Surface imaging using time-of-flight camera is a new, non-invasive, non-contact, radiation-free, and easy-to-use technique that enables tidal volume and respiratory rate measurements. The objectives of the study were to determine the accuracy of Time-of-Flight volume (VTTOF) and respiratory rate (RRTOF) measurements at the bedside, and to validate its application for spontaneously breathing patients under high flow nasal canula. Data analysis was performed within the ReaSTOC data-warehousing project (ClinicalTrials.gov identifier NCT02893462). All data were recorded using standard monitoring devices, and the computerized medical file. Time-of-flight technique used a Kinect V2 (Microsoft, Redmond, WA, USA) to acquire the distance information, based on measuring the phase delay between the emitted light-wave and received backscattered signals. 44 patients (32 under mechanical ventilation; 12 under high-flow nasal canula) were recorded. High correlation (r = 0.84; p < 0.001), with low bias (-1.7 mL) and acceptable deviation (75 mL) was observed between VTTOF and VTREF under ventilation. Similar performance was observed for respiratory rate (r = 0.91; p < 0.001; bias < 1b/min; deviation ≤ 5b/min). Measurements were possible for all patients under high-flow nasal canula, detecting overdistension in 4 patients (tidal volume > 8 mL/kg) and low ventilation in 6 patients (tidal volume < 6 mL/kg). Tidal volume monitoring using time-of-flight camera (VTTOF) is correlated to reference values. Time-of-flight camera enables continuous and non-contact respiratory monitoring under high-flow nasal canula, and enables to detect tidal volume and respiratory rate changes, while modifying flow. It enables respiratory monitoring for spontaneously patients, especially while using high-flow nasal oxygenation.

Noninvasive Tidal Volume Measurements, Using a Time-of-Flight Camera, Under High-Flow Nasal Cannula-A Physiological Evaluation, in Healthy Volunteers.

OBJECTIVES: The mechanisms of high-flow nasal cannula are still debated but may be mediated by the generation of low positive end-expiratory pressure and a washout of the airway dead space. The aims of this study were to assess the effects of high-flow nasal cannula on tidal volume using a noninvasive method using a time-of-flight camera, under various conditions. DESIGN: A physiologic evaluation in healthy volunteers. SETTING: An university hospital ICU. SUBJECTS: Ten healthy volunteers were included in a physiologic study (CamOpt study, ClinicalTrials.gov identifier: NCT04096183). INTERVENTIONS: All volunteers were submitted to 12 different conditions (i.e., gas flow [baseline = 0; 30-60 L/min]; mouth [open/closed]; respiratory rate [baseline; baseline + 10 breaths/min]). Tidal volume measurements were performed every minute, during a 6-minute recording period. In all combinations, reference respiratory rate was measured by using chronometric evaluation, over a 30-second period (RRREF), and by using the time-of-flight camera (RRTOF). MEASUREMENTS AND MAIN RESULTS: Tidal volume increased while increasing gas flow whatever the respiratory rate and mouth condition (p < 0.001). Similar results were observed whatever the experimental conditions (p < 0.01), except one (baseline respiratory rate + 10 breaths/min and mouth closed). Tidal volume increased while decreasing respiratory rate (p < 0.001) and mouth closing (p < 0.05). Proportion of tidal volume greater than 10, 15, and 20 mL/kg changed while increasing the flow. RRTOF was in agreement with RRREF (intraclass correlation coefficient, 0.96), with a low mean bias (0.55 breaths/min) and acceptable deviation. CONCLUSIONS: Time-of-flight enables to detect tidal volume changes under various conditions of high-flow nasal cannula application. Tidal volume increased significantly while increasing gas flow and mouth closing. Such technique might be useful to monitor the risk of patient self-inflicted lung injury or under assistance.

Pulmonary Effects of One Week of Repeated Recreational Closed-Circuit Rebreather Dives in Cold Water.

Background and Objectives: The use of closed-circuit rebreathers (CCRs) in recreational diving is gaining interest. However, data regarding its physiological effects are still scarce. Immersion, cold water, hyperoxia, exercise or the equipment itself could challenge the cardiopulmonary system. The purpose of this study was to examine the impact of CCR diving on lung function and autonomous cardiac activity after a series of CCR dives in cold water. Materials and Methods: Eight CCR divers performed a diving trip (one week) in the Baltic Sea. Spirometry parameters, SpO2, and the lung ultrasonography score (LUS) associated with hydration monitoring by bioelectrical impedance were assessed at the end of the week. Heart rate variability (HRV) was recorded during the dives. Results: No diver declared pulmonary symptoms. The LUS increased after dives combined with a slight non-pathological decrease in SpO2. Spirometry was not altered, and all body water compartments were increased. Global HRV decreased during diving with a predominant increase in sympathetic tone while the parasympathetic tone decreased. All parameters returned to baseline 24 h after the last dive. Conclusions: The lung aeration disorders observed seem to be transient and not associated with functional spirometry alteration. The HRV dynamics highlighted physiological constraints during the dive as well as environmental-stress-related stimulation that may influence pulmonary changes. The impact of these impairments is unknown but should be taken into account, especially when considering long and repetitive CCR dives.

Physiological effects of mixed-gas deep sea dives using a closed-circuit rebreather: a field pilot study.

PURPOSE: Deep diving using mixed gas with closed-circuit rebreathers (CCRs) is increasingly common. However, data regarding the effects of these dives are still scarce. This preliminary field study aimed at evaluating the acute effects of deep (90-120 msw) mixed-gas CCR bounce dives on lung function in relation with other physiological parameters. METHODS: Seven divers performed a total of sixteen open-sea CCR dives breathing gas mixture of helium, nitrogen and oxygen (trimix) within four days at 2 depths (90 and 120 msw). Spirometric parameters, SpO2, body mass, hematocrit, short term heart rate variability (HRV) and critical flicker fusion frequency (CFFF) were measured at rest 60 min before the dive and 120 min after surfacing. RESULTS: The median [1st-3rd quartile] of the forced vital capacity was lower (84% [76-93] vs 91% [74-107] of predicted values; p = 0.029), whereas FEV1/FVC was higher (98% [95-99] vs 95% [89-99]; p = 0.019) after than before the dives. The other spirometry values and SpO2 were unchanged. Body mass decreased from 73.5 kg (72.0-89.6) before the dives to 70.0 kg (69.2-85.8) after surfacing (p = 0.001), with no change of hematocrit or CFFT. HRV was increased as indicated by the higher SDNN, RMSSD and pNN50 after than before dives. CONCLUSION: The present observation represents the first original data regarding the effects of deep repeated CCR dives. The body mass loss and decrease of FVC after bounce dives at depth of about 100 msw may possibly impose an important physiological stress for the divers.

BMI and pneumonia outcomes in critically ill covid-19 patients: An international multicenter study.

OBJECTIVE: Previous studies have unveiled a relationship between the severity of coronavirus disease 2019 (COVID-19) pneumonia and obesity. The aims of this multicenter retrospective cohort study were to disentangle the association of BMI and associated metabolic risk factors (diabetes, hypertension, hyperlipidemia, and current smoking status) in critically ill patients with COVID-19. METHODS: Patients admitted to intensive care units for COVID-19 in 21 centers (in Europe, Israel, and the United States) were enrolled in this study between February 19, 2020, and May 19, 2020. Primary and secondary outcomes were the need for invasive mechanical ventilation (IMV) and 28-day mortality, respectively. RESULTS: A total of 1,461 patients were enrolled; the median (interquartile range) age was 64 years (40.9-72.0); 73.2% of patients were male; the median BMI was 28.1 kg/m2 (25.4-32.3); a total of 1,080 patients (73.9%) required IMV; and the 28-day mortality estimate was 36.1% (95% CI: 33.0-39.5). An adjusted mixed logistic regression model showed a significant linear relationship between BMI and IMV: odds ratio = 1.27 (95% CI: 1.12-1.45) per 5 kg/m2 . An adjusted Cox proportional hazards regression model showed a significant association between BMI and mortality, which was increased only in obesity class III (≥40; hazard ratio = 1.68 [95% CI: 1.06-2.64]). CONCLUSIONS: In critically ill COVID-19 patients, a linear association between BMI and the need for IMV, independent of other metabolic risk factors, and a nonlinear association between BMI and mortality risk were observed.

Inased (inhaled sedation in ICU) trial protocol: a multicentre randomised open-label trial.

INTRODUCTION: The use of sedation in intensive care units (ICUs) is necessary and ubiquitous. The impact of sedation strategy on outcome, particularly when delivered early after initiation of mechanical ventilation, is unknown. Evidence is increasing that volatile anaesthetic agents could be associated with better outcome. Their use in delirium prevention is unknown. METHODS AND ANALYSIS: This study is an investigator-initiated, prospective, multicentre, two-arm, randomised, control, open-trial comparing inhaled sedation strategy versus intravenous sedation strategy in mechanically ventilated patients in ICU. Two hundred and fifty patients will be randomly assigned to the intravenous sedation group or inhaled sedation group, with a 1:1 ratio in two groups according to the sedation strategy. The primary outcome is the occurrence of delirium assessed using two times a day confusion assessment method for the ICU (CAM-ICU). Secondary outcomes include cognitive and functional outcomes at 3 and 12 months. ETHICS AND DISSEMINATION: The study has been approved by the Regional Ethics Committee (CPP Ouest) and national authorities (ANSM). The results will be submitted for publication in peer-reviewed journals. TRIAL REGISTRATION NUMBER: NCT04341350.

Simultaneous ventilation in the Covid-19 pandemic. A bench study.

COVID-19 pandemic sets the healthcare system to a shortage of ventilators. We aimed at assessing tidal volume (VT) delivery and air recirculation during expiration when one ventilator is divided into 2 test-lungs. The study was performed in a research laboratory in a medical ICU of a University hospital. An ICU (V500) and a lower-level ventilator (Elisée 350) were attached to two test-lungs (QuickLung) through a dedicated flow-splitter. A 50 mL/cmH2O Compliance (C) and 5 cmH2O/L/s Resistance (R) were set in both A and B test-lungs (A C50R5 / B C50R5, step1), A C50-R20 / B C20-R20 (step 2), A C20-R20 / B C10-R20 (step 3), and A C50-R20 / B C20-R5 (step 4). Each ventilator was set in volume and pressure control mode to deliver 800mL VT. We assessed VT from a pneumotachograph placed immediately before each lung, pendelluft air, and expiratory resistance (circuit and valve). Values are median (1st-3rd quartiles) and compared between ventilators by non-parametric tests. Between Elisée 350 and V500 in volume control VT in A/B test- lungs were 381/387 vs. 412/433 mL in step 1, 501/270 vs. 492/370 mL in step 2, 509/237 vs. 496/332 mL in step 3, and 496/281 vs. 480/329 mL in step 4. In pressure control the corresponding values were 373/336 vs. 430/414 mL, 416/185 vs. 322/234 mL, 193/108 vs. 176/ 92 mL and 422/201 vs. 481/329mL, respectively (P<0.001 between ventilators at each step for each volume). Pendelluft air volume ranged between 0.7 to 37.8 ml and negatively correlated with expiratory resistance in steps 2 and 3. The lower-level ventilator performed closely to the ICU ventilator. In the clinical setting, these findings suggest that, due to dependence of VT to C, pressure control should be preferred to maintain adequate VT at least in one patient when C and/or R changes abruptly and monitoring of VT should be done carefully. Increasing expiratory resistance should reduce pendelluft volume.

Automated closed-loop versus standard manual oxygen administration after major abdominal or thoracic surgery: an international multicentre randomised controlled study.

INTRODUCTION: Hypoxaemia and hyperoxaemia may occur after surgery, with related complications. This multicentre randomised trial evaluated the impact of automated closed-loop oxygen administration after high-risk abdominal or thoracic surgeries in terms of optimising the oxygen saturation measured by pulse oximetry time within target range. METHODS: After extubation, patients with an intermediate to high risk of post-operative pulmonary complications were randomised to "standard" or "automated" closed-loop oxygen administration. The primary outcome was the percentage of time within the oxygenation range, during a 3-day frame. The secondary outcomes were the time with hypoxaemia and hyperoxaemia under oxygen. RESULTS: Among the 200 patients, time within range was higher in the automated group, both initially (≤3 h; 91.4±13.7% versus 40.2±35.1% of time, difference +51.0% (95% CI -42.8-59.2%); p<0.0001) and during the 3-day period (94.0±11.3% versus 62.1±23.3% of time, difference +31.9% (95% CI 26.3-37.4%); p<0.0001). Periods of hypoxaemia were reduced in the automated group (≤3 days; 32.6±57.8 min (1.2±1.9%) versus 370.5±594.3 min (5.0±11.2%), difference -10.2% (95% CI -13.9--6.6%); p<0.0001), as well as hyperoxaemia under oxygen (≤3 days; 5.1±10.9 min (4.8±11.2%) versus 177.9±277.2 min (27.0±23.8%), difference -22.0% (95% CI -27.6--16.4%); p<0.0001). Kaplan-Meier analysis depicted a significant difference in terms of hypoxaemia (p=0.01) and severe hypoxaemia (p=0.0003) occurrence between groups in favour of the automated group. 25 patients experienced hypoxaemia for >10% of the entire monitoring time during the 3 days within the standard group, as compared to the automated group (p<0.0001). CONCLUSION: Automated closed-loop oxygen administration promotes greater time within the oxygenation target, as compared to standard manual administration, thus reducing the occurrence of hypoxaemia and hyperoxaemia.

COVID-19: Pulse oximeters in the spotlight.

From home to intensive care units, innovations in pulse oximetry are susceptible to improve the monitoring and management of patients developing acute respiratory failure, and particularly those with the coronavirus disease 2019 (COVID-19). They include self-monitoring of oxygen saturation (SpO2) from home, continuous wireless SpO2 monitoring on hospital wards, and the integration of SpO2 as the input variable for closed-loop oxygen administration systems. The analysis of the pulse oximetry waveform may help to quantify respiratory efforts and prevent intubation delays. Tracking changes in the peripheral perfusion index during a preload-modifying maneuver may be useful to predict preload responsiveness and rationalize fluid therapy.

Surface imaging for real-time patient respiratory function assessment in intensive care.

PURPOSE: Monitoring of physiological parameters is a major concern in Intensive Care Units (ICU) given their role in the assessment of vital organ function. Within this context, one issue is the lack of efficient noncontact techniques for respiratory monitoring. In this paper, we present a novel noncontact solution for real-time respiratory monitoring and function assessment of ICU patients. METHODS: The proposed system uses a Time-of-Flight depth sensor to analyze the patient's chest wall morphological changes in order to estimate multiple respiratory function parameters. The automatic detection of the patient's torso is also proposed using a deep neural network model trained on the COCO dataset. The evaluation of the proposed system was performed on a mannequin and on 16 mechanically ventilated patients (a total of 216 recordings) admitted in the ICU of the Brest University Hospital. RESULTS: The estimation of respiratory parameters (respiratory rate and tidal volume) showed high correlation with the reference method (r = 0.99; P < 0.001 and r = 0.99; P < 0.001) in the mannequin recordings and (r = 0.95, P < 0.001 and r = 0.90, P < 0.001) for patients. CONCLUSION: This study describes and evaluates a novel noncontact monitoring system suitable for continuous monitoring of key respiratory parameters for disease assessment of critically ill patients.

Automatic oxygen flow titration in spontaneously breathing children: An open-label randomized controlled pilot study.

INTRODUCTION: When children require supplemental oxygen due to acute hypoxemic respiratory distress (AHRD), manual control of the oxygen flow is often difficult and time-consuming, and carries the risk of unrecognized hypoxia and hyperoxia. To date, no automatic oxygen titration system has been developed and evaluated in spontaneously breathing children. METHODS: Children between 1 month and 15 years of age receiving supplemental oxygen due to AHRD were recruited within 24 hours following the onset of the O2 administration in a French University Department of Paediatrics. Patients were randomized to receive either automated oxygen administration using the FreeO2 device, or conventional manual oxygen administration over a maximum period of 6 hours. Stratification was performed to classify the patients into two age groups: 1 month to 2 years of age and 2 to 15 years of age. The primary outcome was % time spent within the SpO2 target range (92%-98%). RESULTS: 60 patients (30 infants, 30 children) were randomized and 55 could be analyzed for the primary outcome (28 automated, 27 manual). The automated O2 delivery using the FreeO2 device significantly increased the time spent within the predefined SpO2 range (94.6% ± 6% vs 76.3% ± 22%, difference [95% confidence interval {CI}] 18.4 [10.1; 26.7]) with less time spent with hypoxemia (1% ± 1.1% vs 15.1% ± 21.8%, difference [95% CI] -14.4 [-22.2; -6.7]). This difference was greater among (2-15 years of age) children, compared to (1 month-2 years of age) infants. CONCLUSIONS: The present randomized controlled pilot study indicates that the tested automated closed-loop O2 titration technology was safe and yielded improved oxygen parameters among spontaneously breathing children. Based on our pilot data, a full randomized controlled trial will be required to verify the potential clinical benefits.