Thyroid Cancer (TC) is one of the most prevalent endocrine malignancies, with early detection being critical for patient management. The motivation for integrating Machine Learning (ML) in thyroid cancer research stems from the limitations of conventional diagnostic and monitoring approaches, as ML offers transformative potential for reducing human errors and improving prediction outcomes for diagnostic accuracy, risk stratification, treatment options, recurrence prognosis, and patient quality of life. This scoping review maps existing literature on ML applications in TC, particularly those leveraging clinical data, Electronic Medical Records (EMRs), and synthesized findings. This study analyzed 1231 papers, evaluated 203 full-text articles, selected 21 articles, and detailed three themes: (1) malignancy prediction and nodule classification; (2) other metastases derived from TC prediction; and (3) recurrence and survival prediction. This work examined the case studies’ characteristics and objectives and identified key trends and challenges in ML-driven TC research. Finally, this scoping review addressed the limitations of related and highlighted directions to enhance the clinical potential of ML in this domain while emphasizing its capability to transform TC patient care into advanced precision medicine.

Colorectal cancer (CRC) is one of the most prevalent and lethal oncological diseases worldwide, with a concerning rise in incidence, particularly in developing countries. Recent advances in genetic sequencing have revealed that the gut microbiome plays a crucial role in CRC development. Mechanisms such as chronic inflammation, metabolic alterations, and oncogenic pathways have demonstrated that dysbiosis, a disruption of the gut microbiome, is linked to CRC. Associations have been found between tumor progression, treatment resistance, and pathogenic microbes such as Fusobacterium nucleatum and Escherichia coli. A promising approach for CRC prevention and treatment is microbiome manipulation through interventions such as probiotics, prebiotics, fecal microbiota transplantation, and selective antibiotics. This article explores how gut microbiome alterations influence CRC pathogenesis and examines microbiome modulation strategies currently used as adjuncts to traditional treatments. Advances in artificial intelligence, single-cell and spatial transcriptomics, and large-scale initiatives such as the ONCOBIOME Project are paving the way for the identification of microbiome-derived biomarkers for early CRC detection and personalized treatment. Despite promising progress, challenges such as interindividual variability, causal inference, and regulatory hurdles must be addressed. Future integration of microbiome analysis into multi-omics frameworks holds great potential to revolutionize precision oncology in CRC management.

Background/Objectives: Thyroid cancer (TC) is among the most common endocrine malignancies, with incidence rates increasing worldwide. However, careful inferential analysis based on refined data is needed to provide a sharper clinical and epidemiological description of this serious condition in a biologically and technologically evolving society. This study presents an exploratory statistical analysis of data from 1470 patients who underwent thyroid surgery for differentiated TC. Methods: The analysis combines bivariate exploration of associations between variables with univariate and multivariate analyses stratified by histological subtype. We examined pathological characteristics (tumor location, nodal metastases, distant metastases, margin involvement, lymphovascular invasion, vascular invasion, and perineural invasion), clinical characteristics (clinical stage), biochemical markers (thyroglobulin, anti-thyroglobulin antibodies, and thyroid-stimulating hormone), and demographic variables (sex assigned at birth and age). In addition, exploratory multivariable models were used to investigate factors associated with lymph node metastasis and margin involvement in papillary microcarcinoma, the diffuse sclerosing variant, and the classical variant of papillary thyroid carcinoma. Results: Notably, moderate to high effect size correlations highlight the interdependence of invasive histopathological features in thyroid cancer and their collective link to adverse surgical outcomes and prognosis. Conclusions: This study provides an analysis of associations between the variables and subtype-specific descriptive estimates, serving as a foundation for future work in tailoring personalized medicine.

Non-IgE-mediated food allergy is characterized by delayed gastrointestinal manifestations and the absence of reliable non-invasive biomarkers. Increasing evidence suggests that gut microbiota may contribute to this disease pathogenesis. The aim of this study was to characterize the gut microbiome composition in thirty pediatric patients diagnosed with non-IgE-mediated food allergy, in comparison to fifteen healthy controls children, and to investigate its association with fecal calprotectin, eosinophil-derived neurotoxin (EDN) and IgA. Gut microbiota profiling was performed by 16S rRNA gene sequencing targeting the V3–V4 region. Compared with healthy controls, higher mean relative abundances of Bacteroides, Faecalibacterium, Alistipes, Parabacteroides, and Sutterella were observed in patients. Conversely, healthy children showed higher mean relative abundances of Pseudobutyrivibrio, Roseburia, Bifidobacterium, Collinsella, Clostridium, Eubacterium, Streptococcus, and Barnesiella. Several genera (Escherichia–Shigella, Agathobacter, and Enterococcus/Streptococcus) were detected only in the allergy cohort. Shannon diversity was higher in patients compared to controls and in the subgroups of patients with elevated fecal calprotectin (p = 0.028), previous antibiotic exposure (p = 0.015), and atopic dermatitis (p = 0.021). Stratification according to inflammatory biomarkers identified a distinct inflammatory microbiome endotype characterized by increased fecal calprotectin and EDN together with enrichment of Veillonellaceae and depletion of Bifidobacteriaceae and Lachnospiraceae. Correlation analyses further revealed positive associations between Veillonella abundance and both fecal calprotectin and EDN. These findings suggest that pediatric non-IgE-mediated food allergy is characterized by distinct microbiome–inflammation relationships rather than a single dysbiotic signature.