The field of anesthesia has always been at the forefront of innovation and technology, and the integration of Artificial Intelligence (AI) represents the next frontier in anesthesia care. The use of AI and its subtypes such as machine learning has the potential to improve efficiency, reduce costs, and improve patient outcomes. AI can assist with decision-making, but its primary advantage lies in empowering anesthesiologists to adopt a proactive approach to address clinical issues. However, further research and validation are needed to fully understand the benefits and limitations of these applications in clinical practice. Moreover, the ethical implications of AI in anesthesia must also be considered to ensure that patient safety and privacy are not compromised. This paper aims to provide a comprehensive overview of AI in anesthesia, including its current and potential applications, and the ethical considerations that must be considered to ensure the safe and effective use of the technology.

Chemotherapy-induced peripheral neuropathy (CIPN) develops as a challenging nerve-damaging adverse effect of anticancer drugs used in chemotherapy. The disorder may require a dose reduction of chemo-therapy and its most common sensory symptoms are severe pain, tingling, and numbness in the hands and feet. CIPN affects dramatically the patient's quality of life (QoL). Pain and sensory abnormalities may occur for months, or even years after the termination of chemotherapy. This disease has complicated pathophysiology featured by underlying mechanisms not completely known. Although many pharmaco-logical and non-pharmacological therapeutic approaches have been tested to overcome these symptoms, there is currently no standardized cure to prevent or treat CIPN. According to current guidelines, Duloxe-tine is the only recommended agent for painful neuropathic symptoms. Therefore, finding effective thera-pies for CIPN is mandatory. The purpose of this review is to dissect CIPN, the target and immunothera-py-based approaches to this disorder, as well as to offer new insights for novel therapeutic perspectives.

Pain diagnosis remains a challenging task due to its subjective nature, the variability in pain expression among individuals, and the difficult assessment of the underlying biopsychosocial factors. In this complex scenario, artificial intelligence (AI) can offer the potential to enhance diagnostic accuracy, predict treatment outcomes, and personalize pain management strategies. This review aims at dissecting the current literature on computer-aided diagnosis methods. It also discusses how AI-driven diagnostic methods can be integrated into multimodal models that combine various data sources, such as facial expression analysis, neuroimaging, and physiological signals, with advanced AI techniques. Despite the significant advancements in AI technology, its widespread adoption in clinical settings faces crucial challenges. Ethical considerations related to patient privacy, biases, and lack of reliability and generalizability are the main issues. Furthermore, there is a need for high-quality real-word validation as well as the development of standardized protocols and policy rules to guide the implementation of these technologies in diverse clinical settings.

Breakthrough cancer pain (BTcP) is a temporary exacerbation of pain that "breaks through" a phase of adequate pain control by an opioid-based therapy. The non-predictable BTcP (NP-BTcP) is a subtype of BTcP that occurs in the absence of any specific activity. Since NP-BTcP has an important clinical impact, this analysis is aimed at characterizing the NP-BTcP phenomenon through a multidimensional statistical technique. This is a secondary analysis based on the Italian Oncologic Pain multiSetting - Multicentric Survey (IOPS-MS) . A correlation analysis was performed to characterize NP-BTcP profile about its intensity, number of episodes per day, and type. The Multidimensional Correspondence Analysis (MCA) determined the identification of 4 groups (Phenotypes). A univariate analysis was performed to assess differences between the 4 Phenotypes and selected covariates. The four phenotypes represent the hierarchical classification according to the status of NP-BTcP: from the best (Phenotype 1) to the worst (Phenotype 4). The univariate analysis found a significant association between the onset time >10 min in the Phenotype 1 (37.3%) vs. the onset ≤ 10 min in Phenotype 4 (74.2%) (p<0.001). The Phenotype 1 was characterized by gastrointestinal type of cancer (26.4%) respect to Phenotype 4 where the most frequent cancer affected the lung (28.8%) (p<0.001). Phenotype 4 was mainly managed with rapid onset opioids, while in Phenotype 1 many patients were treated with oral, subcutaneous, or intravenous morphine (56.4% and 44.4%, respectively; p=0.008). The ability to characterize NP-BTcP can offer enormous benefits for the management of this serious aspect of cancer pain. This strategy can provide many indications for identifying the diagnostic and therapeutic gaps on NP-BTcP management.

Objectives: To explore the effect of breakthrough cancer pain (BTcP) treatment on quality of sleep and other aspects of the health-related quality of life (HRQoL) in patients with cancer pain. Methods: In an observational, multicenter, cohort study, cancer patients from palliative care units, oncology departments, and pain clinics and affected by BTcP were included. Enrolled patients were assessed at the four visits: T0 (baseline), T7, T14, and T28. Well-controlled chronic background pain during the whole study period was mandatory. BTcP was treated through transmucosal fentanyl. Three questionnaires were used to measure the HRQoL: EORTC QLQ-C15-PAL, Pittsburgh Sleep Quality Index (PSQI), and the Edmonton Symptom Assessment System (ESAS). Results: In 154 patients, the HRQoL showed a significant improvement for all physical and emotional characteristics in the EORTC QLQ-C15-PAL, except for nausea and vomiting (Linear p-value = 0.1) and dyspnoea (Linear p-value =0.05). The ESAS and PSQI questionnaires confirmed these positive results (p<0.0001 and p=0.002, respectively). Conclusions: This prospective investigation by an Italian expert group, has confirmed that careful management of BTcP induces a paramount improvement on the HRQoL. Because in cancer patients there is a high prevalence of BTcP and this severe acute pain has deleterious consequences, this information can have an important clinical significance

Background: There is a notable lack of protocols addressing extubation techniques in transoral robotic surgery (TORS) for obstructive sleep apnea (OSA). Methods. This retrospective cohort study enrolled patients who underwent TORS for OSA between March 2015 and December 2021 and were managed with different extubation approaches. The patients were divided into two groups: high-flow nasal cannula (HFNC) therapy and conventional oxygen therapy. The use of an airway exchange catheter (AEC) was investigated. Results: The only application of HFNC use versus conventional oxygen therapy led to a statistical reduction of extubation time (p=0.024); length of stay in the intensive care unit (ICU) and the episodes of desaturation below 95% were reduced, but data are non-statically significant. Similarly, the application of an AEC led to a reduction of extubation time in hours (p=0.008) and length of stay in the ICU (p=0.024). Conclusions: In patients with OSA who underwent TORS, the use of HFNC, with or without an AEC, resulted in a significant reduction in extubation time without major adverse events. Additionally, HFNC utilization may decrease desaturation episodes during extubation. Based on the findings of this preliminary investigation, the combination of HFNC and AEC emerges as a promising strategy for enhancing the safety and efficacy of extubation protocols in this patient population.