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.

The Breakthrough of Large Language Models Release for Medical Applications: 1-Year Timeline and Perspectives.

Within the domain of Natural Language Processing (NLP), Large Language Models (LLMs) represent sophisticated models engineered to comprehend, generate, and manipulate text resembling human language on an extensive scale. They are transformer-based deep learning architectures, obtained through the scaling of model size, pretraining of corpora, and computational resources. The potential healthcare applications of these models primarily involve chatbots and interaction systems for clinical documentation management, and medical literature summarization (Biomedical NLP). The challenge in this field lies in the research for applications in diagnostic and clinical decision support, as well as patient triage. Therefore, LLMs can be used for multiple tasks within patient care, research, and education. Throughout 2023, there has been an escalation in the release of LLMs, some of which are applicable in the healthcare domain. This remarkable output is largely the effect of the customization of pre-trained models for applications like chatbots, virtual assistants, or any system requiring human-like conversational engagement. As healthcare professionals, we recognize the imperative to stay at the forefront of knowledge. However, keeping abreast of the rapid evolution of this technology is practically unattainable, and, above all, understanding its potential applications and limitations remains a subject of ongoing debate. Consequently, this article aims to provide a succinct overview of the recently released LLMs, emphasizing their potential use in the field of medicine. Perspectives for a more extensive range of safe and effective applications are also discussed. The upcoming evolutionary leap involves the transition from an AI-powered model primarily designed for answering medical questions to a more versatile and practical tool for healthcare providers such as generalist biomedical AI systems for multimodal-based calibrated decision-making processes. On the other hand, the development of more accurate virtual clinical partners could enhance patient engagement, offering personalized support, and improving chronic disease management.

From Big Data's 5Vs to clinical practice's 5Ws: enhancing data-driven decision making in healthcare.

The use of AI-based algorithms is rapidly growing in healthcare, but there is still an ongoing debate about how to manage and ensure accountability for their clinical use. While most of the studies focus on demonstrating a good algorithm performance it is important to acknowledge that several additional steps are needed for reaching an effective implementation of AI-based models in daily clinical practice, with implementation being one of the main key factors. We propose a model characterized by five questions that can guide in this process. Additionally, we believe that a hybrid intelligence, human and artificial respectively, is the new clinical paradigm that offer the most benefits for developing clinical decision support systems for bedside use.

Evaluating the Feasibility of ChatGPT in Healthcare: An Analysis of Multiple Clinical and Research Scenarios.

This paper aims to highlight the potential applications and limits of a large language model (LLM) in healthcare. ChatGPT is a recently developed LLM that was trained on a massive dataset of text for dialogue with users. Although AI-based language models like ChatGPT have demonstrated impressive capabilities, it is uncertain how well they will perform in real-world scenarios, particularly in fields such as medicine where high-level and complex thinking is necessary. Furthermore, while the use of ChatGPT in writing scientific articles and other scientific outputs may have potential benefits, important ethical concerns must also be addressed. Consequently, we investigated the feasibility of ChatGPT in clinical and research scenarios: (1) support of the clinical practice, (2) scientific production, (3) misuse in medicine and research, and (4) reasoning about public health topics. Results indicated that it is important to recognize and promote education on the appropriate use and potential pitfalls of AI-based LLMs in medicine.

Microcirculatory tissue perfusion during general anaesthesia and noncardiac surgery: An observational study using incident dark field imaging with automated video analysis.

BACKGROUND: Handheld vital microscopy allows direct observation of red blood cells within the sublingual microcirculation. Automated analysis allows quantifying microcirculatory tissue perfusion variables - including tissue red blood cell perfusion (tRBCp), a functional variable integrating microcirculatory convection and diffusion capacities. OBJECTIVE: We aimed to describe baseline microcirculatory tissue perfusion in patients presenting for elective noncardiac surgery and test that microcirculatory tissue perfusion is preserved during elective general anaesthesia for noncardiac surgery. DESIGN: Prospective observational study. SETTING: University Medical Center Hamburg-Eppendorf, Hamburg, Germany. PATIENTS: 120 elective noncardiac surgery patients (major abdominal, orthopaedic or trauma and minor urologic surgery) and 40 young healthy volunteers. MAIN OUTCOME MEASURES: We measured sublingual microcirculation using incident dark field imaging with automated analysis at baseline before induction of general anaesthesia, under general anaesthesia before surgical incision and every 30 min during surgery. We used incident the dark field imaging technology with a validated automated analysis software. RESULTS: A total of 3687 microcirculation video sequences were analysed. Microcirculatory tissue perfusion variables varied substantially between individuals - but ranges were similar between patients and volunteers. Under general anaesthesia before surgical incision, there were no important changes in tRBCp, functional capillary density and capillary haematocrit compared with preinduction baseline. However, total vessel density was higher and red blood cell velocity and the proportion of perfused vessels were lower under general anaesthesia. There were no important changes in any microcirculatory tissue perfusion variables during surgery. CONCLUSION: In patients presenting for elective noncardiac surgery, baseline microcirculatory tissue perfusion variables vary substantially between individuals - but ranges are similar to those in young healthy volunteers. Microcirculatory tissue perfusion is preserved during general anaesthesia and noncardiac surgery - when macrocirculatory haemodynamics are maintained.

Clinical implications of microvascular CT scan signs in COVID-19 patients requiring invasive mechanical ventilation.

PURPOSE: COVID-19-related acute respiratory distress syndrome (ARDS) is characterized by the presence of signs of microvascular involvement at the CT scan, such as the vascular tree in bud (TIB) and the vascular enlargement pattern (VEP). Recent evidence suggests that TIB could be associated with an increased duration of invasive mechanical ventilation (IMV) and intensive care unit (ICU) stay. The primary objective of this study was to evaluate whether microvascular involvement signs could have a prognostic significance concerning liberation from IMV. MATERIAL AND METHODS: All the COVID-19 patients requiring IMV admitted to 16 Italian ICUs and having a lung CT scan recorded within 3 days from intubation were enrolled in this secondary analysis. Radiologic, clinical and biochemical data were collected. RESULTS: A total of 139 patients affected by COVID-19 related ARDS were enrolled. After grouping based on TIB or VEP detection, we found no differences in terms of duration of IMV and mortality. Extension of VEP and TIB was significantly correlated with ground-glass opacities (GGOs) and crazy paving pattern extension. A parenchymal extent over 50% of GGO and crazy paving pattern was more frequently observed among non-survivors, while a VEP and TIB extent involving 3 or more lobes was significantly more frequent in non-responders to prone positioning. CONCLUSIONS: The presence of early CT scan signs of microvascular involvement in COVID-19 patients does not appear to be associated with differences in duration of IMV and mortality. However, patients with a high extension of VEP and TIB may have a reduced oxygenation response to prone positioning. TRIAL REGISTRATION: NCT04411459.

Lung histopathologic clusters in severe COVID-19: a link between clinical picture and tissue damage.

BACKGROUND: Autoptic pulmonary findings have been described in severe COVID-19 patients, but evidence regarding the correlation between clinical picture and lung histopathologic patterns is still weak. METHODS: This was a retrospective cohort observational study conducted at the referral center for infectious diseases in northern Italy. Full lung autoptic findings and clinical data of patients who died from COVID-19 were analyzed. Lung histopathologic patterns were scored according to the extent of tissue damage. To consider coexisting histopathologic patterns, hierarchical clustering of histopathologic findings was applied. RESULTS: Whole pulmonary examination was available in 75 out of 92 full autopsies. Forty-eight hospitalized patients (64%), 44 from ICU and four from the medical ward, had complete clinical data. The histopathologic patterns had a time-dependent distribution with considerable overlap among patterns. Duration of positive-pressure ventilation (p < 0.0001), mean positive end-expiratory pressure (PEEP) (p = 0.007), worst serum albumin (p = 0.017), interleukin 6 (p = 0.047), and kidney SOFA (p = 0.001) differed among histopathologic clusters. The amount of PEEP for long-lasting ventilatory treatment was associated with the cluster showing the largest areas of early and late proliferative diffuse alveolar damage. No pharmacologic interventions or comorbidities affected the lung histopathology. CONCLUSIONS: Our study draws a comprehensive link between the clinical and pulmonary histopathologic findings in a large cohort of COVID-19 patients. These results highlight that the positive end-expiratory pressures and the duration of the ventilatory treatment correlate with lung histopathologic patterns, providing new clues to the knowledge of the pathophysiology of severe SARS-CoV-2 pneumonia.

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.

Automated Algorithm Analysis of Sublingual Microcirculation in an International Multicentral Database Identifies Alterations Associated With Disease and Mechanism of Resuscitation.

OBJECTIVES: Reliable automated handheld vital microscopy image sequence analysis and the identification of disease states and effects of therapy are prerequisites for the routine use of quantitative sublingual microcirculation measurements at the point-of-care. The present study aimed to clinically validate the recently introduced MicroTools software in a large multicentral database of perioperative and critically ill patients and to use this automatic algorithm to data-mine and identify the sublingual microcirculatory variable changes in response to disease and therapy. DESIGN: Retrospective algorithm-based image analysis and data-mining within a large international database of sublingual capillary microscopy. Algorithm-based analysis was compared with manual analysis for validation. Thereafter, MicroTools was used to identify the functional microcirculatory alterations associated with disease conditions and identify therapeutic options for recruiting functional microcirculatory variables. SETTING: Ten perioperative/ICU/volunteer studies in six international teaching hospitals. PATIENTS: The database encompass 267 adult and pediatric patients undergoing surgery, treatment for sepsis, and heart failure in the ICU and healthy volunteers. INTERVENTIONS: Perioperative and ICU standard of care. MEASUREMENTS AND MAIN RESULTS: One thousand five hundred twenty-five handheld vital microscopy image sequences containing 149,257 microscopy images were analyzed. 3.89 × 10 RBC positions were tracked by the algorithm in real time, and offline manual analysis was performed. Good correlation and trending ability were found between manual and automatic total and functional capillary density (r = 0.6-0.8; p < 0.0001). RBC tracking within the database demonstrated changes in functional capillary density and/or RBC velocity in septic shock, heart failure, hypovolemia, obstructive shock, and hemodilution and thus detected the presence of a disease condition. Therapies recruiting the microcirculatory diffusion and convection capacity associated with systemic vasodilation and an increase in cardiac output were separately identified. CONCLUSIONS: Algorithm-based analysis of the sublingual microcirculation closely matched manual analysis across a broad spectrum of populations. It successfully identified a methodology to quantify microcirculatory alterations associated with disease and the success of capillary recruitment, improving point-of-care application of microcirculatory-targeted resuscitation procedures.

Sublingual microcirculation in patients with SARS-CoV-2 undergoing veno-venous extracorporeal membrane oxygenation.

Veno-Venous Extracorporeal Membrane Oxygenation (VV-ECMO) is a rescue treatment for severe acute respiratory failure refractory to conventional ventilation. We examined the alterations of sublingual microcirculation in patients with SARS-CoV-2 during VV-ECMO treatment and assessed the relationship between microvascular parameters and ventilation, hemodynamics, and laboratory tests. Nine patients were included in the study and the following microcirculatory parameters were estimated: TVD 16.81 (14.46-18.6) mm/mm2; PVD 15.3 (14.09-17.96) mm/mm2; PPV 94.85% (93.82%-97.79%); MFI 2.5 (2.5-2.92); HI 0.4 (0.18-0.4). TVD and PVD were inversely related to D-dimer levels (rho = -0.667, p = 0.05 and rho = -0.733, p = 0.025 respectively), aspartate aminotransferase (AST) (rho = -0.886, p = 0.019 and rho = -0.886, p = 0.019 respectively) and alanine aminotransferase (ALT) (rho = -0.829, p = 0.042 and rho = -0.829, p = 0.042 respectively). Our results showed an altered sublingual microcirculation in patients receiving VV-ECMO for severe SARS-CoV-2 and suggest a potential contribution of endothelia dysfunction to determine microvascular alteration.

Statin Use and Risk of Atrial Fibrillation or Flutter: A Population-based Case-Control Study.

The pleiotropic effects of statins have been suggested to prevent atrial fibrillation onset. We conducted a population-based case-control study using medical databases from Northern Denmark (population: 1.8 million) to examine the association between statin use and atrial fibrillation or flutter. We identified 51,374 patients with atrial fibrillation or flutter between 1999 and 2010 and 513,670 matched population controls. We collected data on statin prescriptions redeemed within 90 days (current users) or longer (former users) before the diagnosis date of atrial fibrillation or flutter. We stratified statin users by duration of exposure, determined by the number of days between first and last redeemed prescription before the diagnosis date (<365, 365-1094, and ≥1095 days). We used conditional logistic regression to compute odds ratios (ORs) and 95% confidence intervals (CIs), controlling for potential confounders. We defined people without previous statin use as never users (reference). A total of 7360 (14.3%) cases and 55,699 (10.8%) controls were current statin users. Among current users (adjusted OR: 0.96, 95% CI, 0.93-0.99), the preventive effect of statins on atrial fibrillation or flutter was related to duration of use: adjusted ORs decreased from 1.35 (95% CI, 1.28-1.42) for users who were prescribed statins for <365 days to 0.85 (95% CI, 0.81-0.89) for users who were prescribed statins for ≥1095 days compared with never users. For former users (adjusted OR: 0.94, 95% CI. 0.90-0.98), the ORs did not change with varying lengths of exposure. In conclusion, long-term statin use may reduce the risk of atrial fibrillation or flutter compared with never use.

Coexisting liver disease is associated with increased mortality after surgery for diverticular disease.

BACKGROUND: Coexistence of liver disease in patients undergoing surgery for diverticular disease (DD) may increase the risk of postoperative complications, but the evidence is limited. AIM: To investigate the impact of liver disease on mortality and reoperation rates following surgery for DD. METHODS: We performed a cohort study based on medical databases of all patients undergoing surgery for DD in Denmark during 1977-2011, categorizing them into three cohorts according to history of liver disease: patients with non-cirrhotic liver disease, those with liver cirrhosis, and those without liver disease (comparison cohort). Using the Kaplan-Meier method, we computed mortality in each cohort for 0-30, 31-60, and 61-90 days following surgery for DD. We used a Cox regression model to compute hazard ratios as measures of the relative risk (RR) of death, controlling for potential confounders, including other comorbidities. In addition, we assessed the reoperation rate within 30 days of initial surgery. RESULTS: Of 14,408 patients undergoing surgery for DD, 233 (1.6 %) had non-cirrhotic liver disease and 91 (0.6 %) had liver cirrhosis. Thirty-day mortality was 9.9 % in patients without liver disease and 14.6 % in patients with non-cirrhotic liver disease [adjusted RR = 1.64 (95 % confidence interval [CI] 1.16-2.31)]. Among patients with liver cirrhosis, mortality was 24.2 % [adjusted RR = 2.70 (95 % CI 1.73-4.22)]. Liver cirrhosis had an impact on mortality up to 60 days after surgery for DD. The reoperation rate was approximately 10 % in each cohort. CONCLUSION: Preexisting liver disease has a major impact on postoperative mortality following surgery for DD.

Between human and AI: assessing the reliability of AI text detection tools.

OBJECTIVE: Large language models (LLMs) such as ChatGPT-4 have raised critical questions regarding their distinguishability from human-generated content. In this research, we evaluated the effectiveness of online detection tools in identifying ChatGPT-4 vs human-written text. METHODS: A two texts produced by ChatGPT-4 using differing prompts and one text created by a human author were analytically assessed using the following online detection tools: GPTZero, ZeroGPT, Writer ACD, and Originality. RESULTS: The findings revealed a notable variance in the detection capabilities of the employed detection tools. GPTZero and ZeroGPT exhibited inconsistent assessments regarding the AI-origin of the texts. Writer ACD predominantly identified texts as human-written, whereas Originality consistently recognized the AI-generated content in both samples from ChatGPT-4. This highlights Originality's enhanced sensitivity to patterns characteristic of AI-generated text. CONCLUSION: The study demonstrates that while automatic detection tools may discern texts generated by ChatGPT-4 significant variability exists in their accuracy. Undoubtedly, there is an urgent need for advanced detection tools to ensure the authenticity and integrity of content, especially in scientific and academic research. However, our findings underscore an urgent need for more refined detection methodologies to prevent the misdetection of human-written content as AI-generated and vice versa.

Liver disease and 30-day mortality after colorectal cancer surgery: a Danish population-based cohort study.

BACKGROUND: Colorectal cancer (CRC) is common, with surgery as the main curative treatment. The prevalence of chronic liver disease has increased, but knowledge is limited on postoperative mortality in patients with liver disease who undergo CRC surgery. Hence, we examined 30-day mortality after CRC surgery in patients with liver disease compared to those without liver disease. METHODS: We used medical databases to conduct a nationwide cohort study of all patients undergoing CRC surgery in Denmark from 1996 through 2009. We further identified patients diagnosed with any liver disease before CRC surgery and categorized them into two cohorts: patients with non-cirrhotic liver disease and patients with liver cirrhosis. Patients without liver disease were defined as the comparison cohort. Using the Kaplan-Meier method, we computed 30-day mortality after CRC surgery in each cohort. We used a Cox regression model to compute hazard ratios as measures of the relative risk (RR) of death, controlling for potential confounders including comorbidities. In order to examine the impact of liver disease in different subgroups, we stratified patients by gender, age, cancer stage, cancer site, timing of admission, type of surgery, comorbidity level, and non-hepatic alcohol-related disease. RESULTS: Overall, 39,840 patients underwent CRC surgery: 369 (0.9%) had non-cirrhotic liver disease and 158 (0.4%) had liver cirrhosis. Thirty-day mortality after CRC surgery was 8.7% in patients without liver disease and 13.3% in patients with non-cirrhotic liver disease (adjusted RR of 1.49 95% confidence interval (CI): 1.12-1.98). Among patients with liver cirrhosis, mortality was 24.1%, corresponding to an adjusted RR of 2.59 (95% CI: 1.86-3.61). The negative impact of liver disease on postoperative mortality was found in all subgroups. CONCLUSIONS: Pre-existing liver disease was associated with a markedly increased 30-day mortality following CRC surgery.

Failing categorization of severe COVID-19 ARDS into ventilatory subphenotypes studied via the clinical-histopathologic relationship.

BACKGROUND: Categorization of severe COVID-19 related acute respiratory distress syndrome (CARDS) into subphenotypes does not consider the trajectories of respiratory mechanoelastic features and histopathologic patterns. This study aimed to assess the correlation between mechanoelastic ventilatory features and lung histopathologic findings in critically ill patients who died because of CARDS. METHODS: Mechanically ventilated patients with severe CARDS who had daily ventilatory data were considered. The histopathologic assessment was performed through full autopsy of deceased patients. Patients were categorized into two groups according to the median worst respiratory system compliance during ICU stay (CrsICU). RESULTS: Eighty-seven patients admitted to ICU had daily ventilatory data. Fifty-one (58.6%) died in ICU, 41 (80.4%) underwent full autopsy and were considered for the clinical-histopathological correlation analysis. Respiratory system compliance at ICU admission and its trajectory were not different in survivors and non-survivors. Median CrsICU in the deceased patients was 22.9 ml/cmH2O. An inverse correlation was found between the CrsICU and late-proliferative diffuse alveolar damage (DAD) (r = -0.381, p = 0.026). Late proliferative DAD was more extensive (p = 0.042), and the probability of stay in ICU was higher (p = 0.004) in the "low" compared to the "high" CrsICU group. Cluster analysis further endorsed these findings. CONCLUSIONS: In critically ill mechanically ventilated patients, worsening of the respiratory system compliance correlated pathologically with the transition from early damage to late fibroproliferative patterns in non-survivors of CARDS. Categorization of CARDS into ventilatory subphenotypes by mechanoelastic properties at ICU admission does not account for the complexity of the histopathologic features.

Long-term outcome of COVID-19 patients treated with helmet noninvasive ventilation vs. high-flow nasal oxygen: a randomized trial.

BACKGROUND: Long-term outcomes of patients treated with helmet noninvasive ventilation (NIV) are unknown: safety concerns regarding the risk of patient self-inflicted lung injury and delayed intubation exist when NIV is applied in hypoxemic patients. We assessed the 6-month outcome of patients who received helmet NIV or high-flow nasal oxygen for COVID-19 hypoxemic respiratory failure. METHODS: In this prespecified analysis of a randomized trial of helmet NIV versus high-flow nasal oxygen (HENIVOT), clinical status, physical performance (6-min-walking-test and 30-s chair stand test), respiratory function and quality of life (EuroQoL five dimensions five levels questionnaire, EuroQoL VAS, SF36 and Post-Traumatic Stress Disorder Checklist for the DSM) were evaluated 6 months after the enrollment. RESULTS: Among 80 patients who were alive, 71 (89%) completed the follow-up: 35 had received helmet NIV, 36 high-flow oxygen. There was no inter-group difference in any item concerning vital signs (N = 4), physical performance (N = 18), respiratory function (N = 27), quality of life (N = 21) and laboratory tests (N = 15). Arthralgia was significantly lower in the helmet group (16% vs. 55%, p = 0.002). Fifty-two percent of patients in helmet group vs. 63% of patients in high-flow group had diffusing capacity of the lungs for carbon monoxide < 80% of predicted (p = 0.44); 13% vs. 22% had forced vital capacity < 80% of predicted (p = 0.51). Both groups reported similar degree of pain (p = 0.81) and anxiety (p = 0.81) at the EQ-5D-5L test; the EQ-VAS score was similar in the two groups (p = 0.27). Compared to patients who successfully avoided invasive mechanical ventilation (54/71, 76%), intubated patients (17/71, 24%) had significantly worse pulmonary function (median diffusing capacity of the lungs for carbon monoxide 66% [Interquartile range: 47-77] of predicted vs. 80% [71-88], p = 0.005) and decreased quality of life (EQ-VAS: 70 [53-70] vs. 80 [70-83], p = 0.01). CONCLUSIONS: In patients with COVID-19 hypoxemic respiratory failure, treatment with helmet NIV or high-flow oxygen yielded similar quality of life and functional outcome at 6 months. The need for invasive mechanical ventilation was associated with worse outcomes. These data indicate that helmet NIV, as applied in the HENIVOT trial, can be safely used in hypoxemic patients. Trial registration Registered on clinicaltrials.gov NCT04502576 on August 6, 2020.

Artificial intelligence in intensive care: moving towards clinical decision support systems.

The high complexity of care in the Intensive Care Unit environment has led, in the last decades, to a big effort in term of the improvement of patient's monitoring devices, increase of diagnostic and therapeutic opportunities, and development of electronic health records. Such advancements have enabled an increasing availability of large amounts of data that were supposed to provide more insight and understanding regarding pathophysiological processes and patient's prognosis providing useful tools able to support physicians in the clinical decision-making process. On the contrary, the interpolation, analysis, and interpretation of a such big amount of data has soon proven to be much more complicated than expected, opening the way for the development of tools based on machine learning (ML) algorithms. However, at the present, most of the AI-based algorithms developed in intensive care do not reach beyond the prototyping and development environment and are still far from being able to assist physicians at the bedside in the clinical decisions to improve quality and efficiency of care. The present review aimed to provide an overview of the status of ML-based algorithms in intensive care, to explore the concept of digital transformation, and to highlight possible next steps necessary to move towards a routine use of ML-based clinical decision support systems at the bedside. Finally, we described our attempt to apply the pillars of digital transformation in the field of microcirculation monitoring with the creation of the Microcirculation Network Research Group (MNRG).

Mid-Regional Proadrenomedullin (MR-proADM) and Microcirculation in Monitoring Organ Dysfunction of Critical Care Patients With Infection: A Prospective Observational Pilot Study.

Introduction: Microvascular alterations are involved in the development of organ injury in critical care patients. Mid-regional proadrenomedullin (MR-proADM) may predict organ damage and its evolution. The main objective of this study was to assess the correlation between MR-proADM and microvascular flow index (MFI) in a small cohort of 20 adult critical care patients diagnosed with infection, sepsis, or septic shock. Further objectives were to evaluate the correlation between the clearance of MR-proADM and the variables of microcirculation and between MR-proADM and the Sequential Organ Failure Assessment (SOFA) score. Materials and Methods: This is a prospective observational pilot study. Inclusion criteria: consecutive adult patients admitted to intensive care unit (ICU) for or with infection-related illness. Daily measurement of MR-proADM and calculation of the SOFA score from admission in ICU to day 5. Repeated evaluations of sublingual microcirculation, collection of clinical data, and laboratory tests. Results: Primary outcome: MR-proADM was not significantly correlated to the MFI at admission in ICU. A clearance of MR-proADM of 20% or more in the first 24 h was related to the improvement of the MFIs and MFIt [percentual variation of the MFIs + 12.35 (6.01-14.59)% vs. +2.23 (-4.45-6.01)%, p = 0.005; MFIt +9.09 (4.53-16.26)% vs. -1.43 (-4.36-3.12)%, p = 0.002]. Conclusion: This study did not support a direct correlation of MR-proADM with the MFI at admission in ICU; however, it showed a good correlation between the clearance of MR-proADM, MFI, and other microvascular variables. This study also supported the prognostic value of the marker. Adequately powered studies should be performed to confirm the findings.

Near real-time observation reveals increased prevalence of young patients in the ICU during the emerging third SARS-CoV-2 wave in Switzerland.

AIMS OF THE STUDY: During the ongoing COVID-19 pandemic, the launch of a large-scale vaccination campaign and virus mutations have hinted at possible changes in transmissibility and the virulence affecting disease progression up to critical illness, and carry potential for future vaccination failure. To monitor disease development over time with respect to critically ill COVID-19 patients, we report near real-time prospective observational data from the RISC-19-ICU registry that indicate changed characteristics of critically ill patients admitted to Swiss intensive care units (ICUs) at the onset of a third pandemic wave. METHODS: 1829 of 3344 critically ill COVID-19 patients enrolled in the international RISC-19-ICU registry as of 31 May 2021 were treated in Switzerland and were included in the present study. Of these, 1690 patients were admitted to the ICU before 1 February 2021 and were compared with 139 patients admitted during the emerging third pandemic wave RESULTS: Third wave patients were a mean of 5.2 years (95% confidence interval [CI] 3.2–7.1) younger (median 66.0 years, interquartile range [IQR] 57.0–73.0 vs 62.0 years, IQR 54.5–68.0; p <0.0001) and had a higher body mass index than patients admitted in the previous pandemic period. They presented with lower SAPS II and APACHE II scores, less need for circulatory support and lower white blood cell counts at ICU admission. P/F ratio was similar, but a 14% increase in ventilatory ratio was observed over time (p = 0.03) CONCLUSION: Near real-time registry data show that the latest COVID-19 patients admitted to ICUs in Switzerland at the onset of the third wave were on average 5 years younger, had a higher body mass index, and presented with lower physiological risk scores but a trend towards more severe lung failure. These differences may primarily be related to the ongoing nationwide vaccination campaign, but the possibility that changes in virus-host interactions may be a co-factor in the age shift and change in disease characteristics is cause for concern, and should be taken into account in the public health and vaccination strategy during the ongoing pandemic. (ClinicalTrials.gov Identifier: NCT04357275).