Algor-ethics: charting the ethical path for AI in critical care.

The integration of Clinical Decision Support Systems (CDSS) based on artificial intelligence (AI) in healthcare is groundbreaking evolution with enormous potential, but its development and ethical implementation, presents unique challenges, particularly in critical care, where physicians often deal with life-threating conditions requiring rapid actions and patients unable to participate in the decisional process. Moreover, development of AI-based CDSS is complex and should address different sources of bias, including data acquisition, health disparities, domain shifts during clinical use, and cognitive biases in decision-making. In this scenario algor-ethics is mandatory and emphasizes the integration of 'Human-in-the-Loop' and 'Algorithmic Stewardship' principles, and the benefits of advanced data engineering. The establishment of Clinical AI Departments (CAID) is necessary to lead AI innovation in healthcare, ensuring ethical integrity and human-centered development in this rapidly evolving field.

Effect of Helmet Noninvasive Ventilation vs High-Flow Nasal Oxygen on Days Free of Respiratory Support in Patients With COVID-19 and Moderate to Severe Hypoxemic Respiratory Failure: The HENIVOT Randomized Clinical Trial.

Importance: High-flow nasal oxygen is recommended as initial treatment for acute hypoxemic respiratory failure and is widely applied in patients with COVID-19. Objective: To assess whether helmet noninvasive ventilation can increase the days free of respiratory support in patients with COVID-19 compared with high-flow nasal oxygen alone. Design, Setting, and Participants: Multicenter randomized clinical trial in 4 intensive care units (ICUs) in Italy between October and December 2020, end of follow-up February 11, 2021, including 109 patients with COVID-19 and moderate to severe hypoxemic respiratory failure (ratio of partial pressure of arterial oxygen to fraction of inspired oxygen ≤200). Interventions: Participants were randomly assigned to receive continuous treatment with helmet noninvasive ventilation (positive end-expiratory pressure, 10-12 cm H2O; pressure support, 10-12 cm H2O) for at least 48 hours eventually followed by high-flow nasal oxygen (n = 54) or high-flow oxygen alone (60 L/min) (n = 55). Main Outcomes and Measures: The primary outcome was the number of days free of respiratory support within 28 days after enrollment. Secondary outcomes included the proportion of patients who required endotracheal intubation within 28 days from study enrollment, the number of days free of invasive mechanical ventilation at day 28, the number of days free of invasive mechanical ventilation at day 60, in-ICU mortality, in-hospital mortality, 28-day mortality, 60-day mortality, ICU length of stay, and hospital length of stay. Results: Among 110 patients who were randomized, 109 (99%) completed the trial (median age, 65 years [interquartile range {IQR}, 55-70]; 21 women [19%]). The median days free of respiratory support within 28 days after randomization were 20 (IQR, 0-25) in the helmet group and 18 (IQR, 0-22) in the high-flow nasal oxygen group, a difference that was not statistically significant (mean difference, 2 days [95% CI, -2 to 6]; P = .26). Of 9 prespecified secondary outcomes reported, 7 showed no significant difference. The rate of endotracheal intubation was significantly lower in the helmet group than in the high-flow nasal oxygen group (30% vs 51%; difference, -21% [95% CI, -38% to -3%]; P = .03). The median number of days free of invasive mechanical ventilation within 28 days was significantly higher in the helmet group than in the high-flow nasal oxygen group (28 [IQR, 13-28] vs 25 [IQR 4-28]; mean difference, 3 days [95% CI, 0-7]; P = .04). The rate of in-hospital mortality was 24% in the helmet group and 25% in the high-flow nasal oxygen group (absolute difference, -1% [95% CI, -17% to 15%]; P > .99). Conclusions and Relevance: Among patients with COVID-19 and moderate to severe hypoxemia, treatment with helmet noninvasive ventilation, compared with high-flow nasal oxygen, resulted in no significant difference in the number of days free of respiratory support within 28 days. Further research is warranted to determine effects on other outcomes, including the need for endotracheal intubation. Trial Registration: ClinicalTrials.gov Identifier: NCT04502576.

Sixty-Day Mortality Among 520 Italian Hospitalized COVID-19 Patients According to the Adopted Ventilatory Strategy in the Context of an Integrated Multidisciplinary Clinical Organization: A Population-Based Cohort Study.

PURPOSE: Although the decision of which ventilation strategy to adopt in COVID-19 patients is crucial, yet the most appropriate means of carrying out this undertaking is not supported by strong evidence. We therefore described the organization of a province-level healthcare system during the occurrence of the COVID-19 epidemic and the 60-day outcomes of the hospitalized COVID-19 patients according to the respiratory strategy adopted given the limited available resources. PATIENTS AND METHODS: All COVID-19 patients (26/02/2020-18/04/2020) in the Rimini Province of Italy were included in this population-based cohort study. The hospitalized patients were classified according to the maximum level of respiratory support: oxygen supplementation (Oxygen group), non-invasive ventilation (NIV-only group), invasive mechanical ventilation (IMV-only group), and IMV after an NIV trial (IMV-after-NIV group). Sixty-day mortality risk was estimated with a Cox proportional hazard analysis adjusted by age, sex, and administration of steroids, canakinumab, and tocilizumab. RESULTS: We identified a total of 1,424 symptomatic patients: 520 (36.5%) were hospitalized, while 904 (63.5%) were treated at home with no 60-day deaths. Based on the respiratory support, 408 (78.5%) were assigned to the Oxygen group, 46 (8.8%) to the NIV-only group, 25 (4.8%) to the IMV-after-NIV group, and 41 (7.9%) to the IMV-only group. There was no significant difference in the PaO2/FiO2 at IMV inception in the IMV-after-NIV and IMV-only groups (p=0.9). Overall 60-day mortality was 24.2% (Oxygen: 23.0%; NIV-only: 19.6%; IMV-after-NIV: 32.0%; IMV-only: 36.6%; p=0.165). Compared with the Oxygen group, the adjusted 60-day mortality risk significantly increased in the IMV-after-NIV (HR 2.776; p=0.024) and IMV-only groups (HR 2.966; p=0.001). CONCLUSION: This study provided a population-based estimate of the impact of the COVID-19 outbreak in a severely affected Italian province. A similar 60-day mortality risk was found for patients undergoing immediate IMV and those intubated after an NIV trial with favorable outcomes after prolonged IMV.

Patient-ventilator interaction with conventional and automated management of pressure support during difficult weaning from mechanical ventilation.

PURPOSE: Optimizing pressure support ventilation (PSV) can improve patient-ventilator interaction. We conducted a two-center, randomized cross-over study to determine whether automated PSV lowers asynchrony rate during difficult weaning from mechanical ventilation. METHODS: Thirty patients failing the first weaning attempt were randomly ventilated for 2 three-hour consecutive periods with: 1)PSV managed by physicians (convPSV); 2)PSV managed by Smartcare® (autoPSV). These 2 periods were applied in the afternoon and overnight, for a 12-h total study time. Two independent clinicians offline analyzed ventilator waveforms to compute asynchrony index(AI). RESULTS: AI was lower during autoPSV than during convPSV (medians[interquartile ranges] 5.1[2.6-9.5]% vs. 7.3[2.3-13.4]%, p = 0.02), without changes in the proportion of patients with AI>10%(p = 0.31). Pressure support (PS) variability was higher during autoPSV (p < 0.001), but average PS did not vary. In patients with baseline PS > 12 cmH2O (n = 15), PS and tidal volume were lower with autoPSV (12 [10-15]cmH2O vs. 15 [14-18]cmH2O,p = 0.003; 7.2[6.2-8.3]ml/Kg vs. 8.2[7.1-9.1]ml/Kg, p = 0.02) and AI reduction was driven by lower tidal volume (p = 0.03). In patients with baseline PS ≤ 12 cmH2O, AI reduction during autoPSV was mediated by increased PS variability (p = 0.04). CONCLUSION: During difficult weaning, autoPSV improves patient-ventilator interaction by lowering tidal volume and enhancing PS variability. In expert centres, however, the size effect of the intervention appears clinically small, likely because physicians themselves adequately limit PS and tidal volume.