Background: Postoperative cognitive dysfunction (POCD) is a common postoperative condition after neurosurgery, and in patients of advancing age, with far-reaching implications for recovery and quality of life. Current evidence points to the gut–brain axis as the main mechanism for the regulation of perioperative neuroinflammation and cognition. Objective: The aim of this review is to consolidate the existing evidence for perioperative gut microbiome dysbiosis in POCD, specifically in neurosurgical patients. Methods: A review of preclinical and clinical evidence on the gut microbiome, surgical stress, and cognitive recovery was conducted. Both mechanistic and therapeutic evidence were examined. Results: Surgery and anesthesia enhance gut microbial diversity, intestinal permeability, and systemic inflammation, thereby compromising neuroplasticity and the integrity of blood–brain barriers. Preclinical models show that interventions to reestablish microbial homeostasis with probiotics, prebiotics, or fecal microbiota transplantation decrease postoperative cognition. Clinical studies offer evidence supporting the associations between decreased short-chain fatty acid-producing bacteria and POCD risk. Randomized controlled trials have demonstrated that perioperative probiotics lower the incidence and markers of POCD. Multi-omic approaches to integrating microbiome, metabolome, and neuroimaging signatures are being engineered to discern recovery phenotypes prior to surgery. Conclusions: Perioperative gut microbiota are a modifiable target for the optimization of cognitive recovery from neurosurgery. The inclusion of microbiome treatments and diagnostics into standard surgical care pathways is one potential pathway to POCD minimization, but large randomized trials will be necessary to establish this.

The tumor microenvironment [TME] is a dynamic ecosystem where spatial organization and metabolic reprogramming play a crucial role in immune response, tumor progression, and therapeutic response. Recent breakthroughs in spatial transcriptomics, metabolomics, and multiplexed imaging studies have shown that complex immunometabolic niches are involved in therapeutic resistance, including conventional and immunotherapeutic approaches. Artificial intelligence [AI] technology has been recognized as a revolutionary concept that allows the integration of complex data, thereby facilitating the scalable extraction of spatial, molecular, and cellular features from routine histopathology and multi-omics platforms. This review of the current evidence on AI-based spatial immunometabolic studies of the tumor microenvironment aims to provide a comprehensive overview of the current evidence, including AI-based spatial immunometabolic studies of the tumor mi-croenvironment, with special reference to digital pathology, spatial transcriptomics, and multimodal data fusion. The current challenges, including data heterogeneity, model interpretability, generalizability, and biological validation, will be discussed. The emerging trends in AI-based spatial immunometabolism, including multimodal foundation models, federated learning, and spatially resolved target discovery, will be discussed. AI-based spatial immunometabolism will be a cornerstone in precision oncology, with the potential to improve patient stratification, therapeutic approaches, and clinical translation.

Background: Laryngeal cancer (LC), a common subtype of head and neck cancers (HNC), is most frequently represented by laryngeal squamous cell carcinoma (LSCC). Prognosis largely depends on early detection; however, traditional prognostic tools, including tumor-node-metastasis (TNM) staging, often show limited predictive accuracy. Artificial intelligence (AI), including machine learning (ML), natural language processing, and deep learning (DL), has emerged as a promising approach to improving cancer diagnosis, prognosis, and treatment planning by analyzing clinical data and medical imaging. Objective: This systematic review assesses the role of AI in prognosis, recurrence prediction, and treatment outcomes in LC. Methods: PubMed, MEDLINE, Scopus, Web of Science, IEEE Xplore, and ScienceDirect were searched up to January 2025. A total of 1062 records were identified; after title/abstract screening and full-text assessment, 29 studies were included. Eligible studies involved adult patients with LC and applied AI to diagnose, prognose, predict recurrence, or assess treatment outcomes using human datasets. Study quality and risk of bias were evaluated using the QUADAS-2 and QUIPS. Results: The 29 included studies were mostly retrospective, with sample sizes ranging from 10 to 63,000 patients. Most focused on LSCC, with a higher prevalence in males. The studies utilized various AI techniques, including deep learning models such as convolutional neural networks (CNNs) and DeepSurv, as well as ML algorithms like random survival forest, gradient boosting machines, random forest, k-nearest neighbors, naïve Bayes, and decision trees. AI models demonstrated strong prognostic performance, surpassing Cox regression and TNM staging in predicting survival and recurrence. Several studies reported outcomes related to treatment, such as chemotherapy response, occult lymph node metastasis, and the need for salvage surgery. Methodological quality varied, with biases related to patient selection and confounding factors. Conclusions: AI has the potential to improve prognosis estimation, recurrence prediction, and treatment outcome assessment in LC. However, although AI can be a helpful addition to clinical decision-making, more prospective studies, external validation, and standardized evaluation are necessary before these technologies can be confidently adopted in everyday clinical practice.