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 Future of Artificial Intelligence Using Images and Clinical Assessment for Difficult Airway Management.

Artificial intelligence (AI) algorithms, particularly deep learning, are automatic and sophisticated methods that recognize complex patterns in imaging data providing high qualitative assessments. Several machine-learning and deep-learning models using imaging techniques have been recently developed and validated to predict difficult airways. Despite advances in AI modeling. In this review article, we describe the advantages of using AI models. We explore how these methods could impact clinical practice. Finally, we discuss predictive modeling for difficult laryngoscopy using machine-learning and the future approach with intelligent intubation devices.

The role and mechanism of PDZ binding kinase in hypobaric and hypoxic acute lung injury.

Background: Acute lung injury (ALI) caused by hypobaric hypoxia (HH) is frequently observed in high-altitude areas, and it is one of the leading causes of death in high-altitude-related diseases due to its rapid onset and progression. However, the pathogenesis of HH-related ALI (HHALI) remains unclear, and effective treatment approaches are currently lacking. Methods: A new mouse model of HHALI developed by our laboratory was used as the study subject (Chinese patent No. ZL 2021 1 1517241 X). Real-time quantitative polymerase chain reaction (RT-qPCR) was used to detect the messenger RNA (mRNA) expression levels of PDZ-binding kinase (PBK), sirtuin 1 (SIRT1), and PTEN-induced kinase 1 (PINK1) in mouse lung tissue. Hematoxylin and eosin staining was used to observe the main types of damage and damaged cells in lung tissue, and the lung injury score was used for quantification. The wet-dry (W/D) ratio was used to measure lung water content. Enzyme-linked immunosorbent assay was used to detect changes in inflammatory factors and oxidative stress markers in the lungs. Western blotting verified the expression of various mitochondrial autophagy-related proteins. The 5,5',6,6'-tetrachloro-1,1',3,3'-tetraethylbenzimi-dazoylcarbocyanine iodide (JC-1) method was used determined the health status of mitochondria based on changes in mitochondrial membrane potential. Transmission electron microscopy was used to directly observe the morphology of mitochondria. Multicolor immunofluorescence was used to observe the levels of mitochondrial autophagy markers. Other signaling pathways and molecular mechanisms that may play a role in epithelial cells were analyzed via through RNA sequencing. Results: Low pressure and hypoxia caused pathological changes in mouse lung tissue, mainly ALI, leading to increased levels of inflammatory factors and intensified oxidative stress response in the lungs. Overexpression of PBK was found to alleviate HHALI, and activation of the p53 protein was shown to abrogate this therapeutic effect, while activation of SIRT1 protein reactivated this therapeutic effect. The therapeutic effect of PBK on HHALI is achieved via the activation of mitochondrial autophagy. Finally, RNA sequencing demonstrated that besides mitochondrial autophagy, PBK also exerts other functions in HHALI. Conclusions: Overexpression of PBK inhibits the expression of p53 and activates SIRT1-PINK1 axis mediated mitochondrial autophagy to alleviate HHALI.

Artificial Intelligence for Personalized Perioperative Medicine.

The development of artificial intelligence (AI) is disruptive and unstoppable, also in medicine. Because of the enormous quantity of data recorded during continuous monitoring and the peculiarity of our specialty where stratification and mitigation risk are some of the core aspects, anesthesiology and postoperative intensive care are fertile fields where new technologies find ample room for expansion. Recently, research efforts have focused on the development of a holistic technology that globally embraces the entire perioperative period rather than a fragmented approach where AI is developed to carry out specific tasks. This could potentially revolutionize the perioperative medicine we know today. In fact, AI will be able to expand clinician's ability to interpret, adapt, and ultimately act in a complex reality with facets that are too complex to be managed all at the same time and in a holistic manner. With the support of new tools, as healthcare professionals we have the moral obligation to govern this transition, allowing an ethical and sustainable development of these technologies and avoiding being overwhelmed by them. We should welcome this transhumanist tension which does not aim at the replacement of human capabilities or even at the integration of these but rather at the expansion of a "single intelligence".

Wearable devices for postoperative monitoring in surgical ward and the chain of liability.

Perioperative medicine is undergoing many changes with the introduction of new technologies. Wearable devices are among them. These novel tools are providing an additional possibility for perioperative monitoring. However, in order to ensure that the introduction of wearable device in surgical wards does not lead to additional challenges for healthcare professionals, a careful implementation plan should be drawn up by a multidisciplinary team. In addition, a chain of liability should also be established a priori to facilitate their use and avoid ambiguity in the occurrence of a critical event.

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.

Artificial Intelligence in Operating Room Management.

This systematic review examines the recent use of artificial intelligence, particularly machine learning, in the management of operating rooms. A total of 22 selected studies from February 2019 to September 2023 are analyzed. The review emphasizes the significant impact of AI on predicting surgical case durations, optimizing post-anesthesia care unit resource allocation, and detecting surgical case cancellations. Machine learning algorithms such as XGBoost, random forest, and neural networks have demonstrated their effectiveness in improving prediction accuracy and resource utilization. However, challenges such as data access and privacy concerns are acknowledged. The review highlights the evolving nature of artificial intelligence in perioperative medicine research and the need for continued innovation to harness artificial intelligence's transformative potential for healthcare administrators, practitioners, and patients. Ultimately, artificial intelligence integration in operative room management promises to enhance healthcare efficiency and patient outcomes.

Continuous vs intermittent Non-Invasive blood pressure MONitoring in preventing postoperative organ failure (niMON): study protocol for an open-label, multicenter randomized trial.

BACKGROUND: Blood pressure has become one of the most important vital signs to monitor in the perioperative setting. Recently, the Italian Society of Anesthesia Analgesia Resuscitation and Intensive Care (SIAARTI) recommended, with low level of evidence, continuous monitoring of blood pressure during the intraoperative period. Continuous monitoring allows for early detection of hypotension, which may potentially lead to a timely treatment. Whether the ability to detect more hypotension events by continuous noninvasive blood pressure (C-NiBP) monitoring can improve patient outcomes is still unclear. Here, we report the rationale, study design, and statistical analysis plan of the niMON trial, which aims to evaluate the effect of intraoperative C-NiBP compared with intermittent (I-NiBP) monitoring on postoperative myocardial and renal injury. METHODS: The niMon trial is an investigator-initiated, multicenter, international, open-label, parallel-group, randomized clinical trial. Eligible patients will be randomized in a 1:1 ratio to receive C-NiBP or I-NiBP as an intraoperative monitoring strategy. The proportion of patients who develop myocardial injury in the first postoperative week is the primary outcome; the secondary outcomes are the proportions of patients who develop postoperative AKI, in-hospital mortality rate, and 30 and 90 postoperative days events. A sample size of 1265 patients will provide a power of 80% to detect a 4% absolute reduction in the rate of the primary outcome. CONCLUSIONS: The niMON data will provide evidence to guide the choice of the most appropriate intraoperative blood pressure monitoring strategy. CLINICAL TRIAL REGISTRATION: Clinical Trial Registration: NCT05496322, registered on the 5th of August 2023.

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.

Testing ChatGPT ability to answer laypeople questions about cardiac arrest and cardiopulmonary resuscitation.

INTRODUCTION: Cardiac arrest leaves witnesses, survivors, and their relatives with a multitude of questions. When a young or a public figure is affected, interest around cardiac arrest and cardiopulmonary resuscitation (CPR) increases. ChatGPT allows everyone to obtain human-like responses on any topic. Due to the risks of accessing incorrect information, we assessed ChatGPT accuracy in answering laypeople questions about cardiac arrest and CPR. METHODS: We co-produced a list of 40 questions with members of Sudden Cardiac Arrest UK covering all aspects of cardiac arrest and CPR. Answers provided by ChatGPT to each question were evaluated by professionals for their accuracy, by professionals and laypeople for their relevance, clarity, comprehensiveness, and overall value on a scale from 1 (poor) to 5 (excellent), and for readability. RESULTS: ChatGPT answers received an overall positive evaluation (4.3 ± 0.7) by 14 professionals and 16 laypeople. Also, clarity (4.4 ± 0.6), relevance (4.3 ± 0.6), accuracy (4.0 ± 0.6), and comprehensiveness (4.2 ± 0.7) of answers was rated high. Professionals, however, rated overall value (4.0 ± 0.5 vs 4.6 ± 0.7; p = 0.02) and comprehensiveness (3.9 ± 0.6 vs 4.5 ± 0.7; p = 0.02) lower compared to laypeople. CPR-related answers consistently received a lower score across all parameters by professionals and laypeople. Readability was 'difficult' (median Flesch reading ease score of 34 [IQR 26-42]). CONCLUSIONS: ChatGPT provided largely accurate, relevant, and comprehensive answers to questions about cardiac arrest commonly asked by survivors, their relatives, and lay rescuers, except CPR-related answers that received the lowest scores. Large language model will play a significant role in the future and healthcare-related content generated should be monitored.

Intraoperative individualization of positive-end-expiratory pressure through electrical impedance tomography or esophageal pressure assessment: a systematic review and meta-analysis of randomized controlled trials.

PURPOSE: This systematic review of randomized-controlled trials (RCTs) with meta-analyses aimed to compare the effects on intraoperative arterial oxygen tension to inspired oxygen fraction ratio (PaO2/FiO2), exerted by positive end-expiratory pressure (PEEP) individualized trough electrical impedance tomography (EIT) or esophageal pressure (Pes) assessment (intervention) vs. PEEP not tailored on EIT or Pes (control), in patients undergoing abdominal or pelvic surgery with an open or laparoscopic/robotic approach. METHODS: PUBMED®, EMBASE®, and Cochrane Controlled Clinical trials register were searched for observational studies and RCTs from inception to the end of August 2022. Inclusion criteria were: RCTs comparing PEEP titrated on EIT/Pes assessment vs. PEEP not individualized on EIT/Pes and reporting intraoperative PaO2/FiO2. Two authors independently extracted data from the enrolled investigations. Data are reported as mean difference and 95% confidence interval (CI). RESULTS: Six RCTs were included for a total of 240 patients undergoing general anesthesia for surgery, of whom 117 subjects in the intervention group and 123 subjects in the control group. The intraoperative mean PaO2/FiO2 was 69.6 (95%CI 32.-106.4 ) mmHg higher in the intervention group as compared with the control group with 81.4% between-study heterogeneity (p < 0.01). However, at meta-regression, the between-study heterogeneity diminished to 44.96% when data were moderated for body mass index (estimate 3.45, 95%CI 0.78-6.11, p = 0.011). CONCLUSIONS: In patients undergoing abdominal or pelvic surgery with an open or laparoscopic/robotic approach, PEEP personalized by EIT or Pes allowed the achievement of a better intraoperative oxygenation compared to PEEP not individualized through EIT or Pes. PROSPERO REGISTRATION NUMBER: CRD 42021218306, 30/01/2023.