Search Results (654)

Background: The high costs, long development timelines, and low clinical success rates in oncology highlight an urgent need for reliable computational strategies for drug repositioning. Current machine learning approaches often integrate heterogeneous pharmacogenomic datasets, which may lose biological specificity and limit model interpretability. Methods: In this study, we propose Separate XAI, an explainable artificial intelligence framework that retains dataset-specific biological features by adopting separate preprocessing and training pipelines for the Genomics of Drug Sensitivity in Cancer (GDSC) and Cancer Cell Line Encyclopedia (CCLE) datasets. Different deep learning architectures such as Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs) were used to predict the drug response in the cancer cell lines. We also used SHapley Additive exPlanations (SHAP) to improve interpretability and identify biologically relevant features. Results: The developed framework showed good predictions with 94.49% accuracy in the CCLE dataset and a mean squared error of 0.0725 in the GDSC dataset. Explainability analysis identified important biomarkers and signaling pathways such as TP53 and KRAS, providing mechanistic insights into drug sensitivity and therapeutic response. Conclusions: The distinct XAI presented here offers an interpretable, biologically grounded framework for cancer drug repositioning by integrating dataset-specific modeling and explainable artificial intelligence. However, integration-based approaches often suffer from confounding effects of experimental and biological heterogeneity, but the proposed framework explicitly preserves dataset-specific characteristics, which potentially could lead to more robust predictions and higher interpretability for precision oncology and translational cancer research. Full article

Objective: Survival prediction in oncology and cardiology requires models that can capture nonlinear prognostic structure while remaining interpretable, calibrated, and clinically safe. This study develops and evaluates a diagnostic-first hybrid quantum–classical framework for right-censored survival analysis. Methods: We introduce KTA-Survival (Kernel-Target Alignment for survival), a pre-training feasibility diagnostic that adapts kernel-target alignment to censored outcomes by comparing a quantum fidelity kernel with a concordance-based survival target kernel. We then propose QResid-Boost (Quantum Residual Boosting), a Cox-LASSO–anchored residual framework in which a variational quantum circuit is trained on martingale residuals through a Quantum-Skip-Residual architecture. A sigmoid-bounded scalar gate, α, constrains the quantum contribution and allows the model to reduce to the classical baseline when the residual signal is uninformative. The framework was evaluated on GBSG2 (German Breast Cancer Study Group 2; n = 686), FLChain (serum free light chain; n = 1500), WHAS500 (Worcester Heart Attack Study; n = 500), and a synthetic Weibull positive-control dataset containing high-frequency periodic interactions. Results: On the GBSG2 hold-out partition, Random Survival Forest achieved the highest concordance (C = 0.7188), followed by the Stacking ensemble (C = 0.7128), Cox-LASSO (C = 0.7019), and QResid-Boost (C = 0.7016). The leading classical and hybrid models did not differ significantly by paired bootstrap testing, whereas all outperformed the pure quantum variants. In the synthetic positive-control cohort, QResid-Boost improved over Cox-LASSO by ΔC = +0.0397, demonstrating that the quantum residual can add value when nonlinear periodic structure remains after the linear baseline. KTA-Survival yielded positive ΔKTA values across the evaluated datasets and correctly identified the regime in which the quantum residual produced its largest measurable gain. Conclusions: The proposed diagnostic-first framework reframes quantum survival modelling as a gated enrichment strategy rather than an unconstrained replacement for classical risk models. In low-dimensional clinical cohorts where linear structure already explains most prognostic signal, the framework behaves conservatively; when residual nonlinear structure is present, it can provide measurable improvement without uncontrolled model drift. Full article

Analysis of microbial abundance profiles offers significant potential for improving cancer prediction and candidate biomarker discovery. This study aimed to identify cancer-associated microbial biomarkers across five gastrointestinal (GI) cancers: head and neck, esophagus, stomach, colon, and colorectal cancers by analyzing tissue and blood samples from the TCMA dataset in parallel. A novel machine learning model, MicrobiomeGSM, was developed to enhance biological interpretability and reduce computational complexity through a taxonomic grouping strategy. Classification performance of MicrobiomeGSM was rigorously evaluated using a Random Forest Classifier with 100-fold Monte Carlo Cross-Validation. MicrobiomeGSM model effectively identified colon adenocarcinoma (COAD) using a set of 30 genus-level species, achieving a 97% AUC and 97% specificity. Comparative analysis was also performed with six traditional feature selection (TFS) algorithms; CMIM, mRMR, FCBF, IG, XGB, and SKB. Comparison of MicrobiomeGSM with TFS methods showed that while TFS methods capture statistical patterns, MicrobiomeGSM effectively leverages biological structures to identify clinically relevant candidate biomarkers. Also, MicrobiomeGSM competes with TFS methods in the analysis of high-dimensional datasets. In conclusion, these findings demonstrate that incorporating microbial abundance profiles with their taxonomic information into machine learning improve the interpretability and effectiveness of microbiome-based candidate biomarker discovery and may support future precision oncology application. Full article

Animal venoms represent an extraordinary, yet largely untapped, biochemical reservoir for oncological drug discovery. This review provides a comprehensive analysis of venom-derived enzyme inhibitors as emerging anticancer agents, emphasizing their chemical diversity, structure–activity relationships (SAR), molecular targets, and mechanistic pathways. Venom-derived peptides and proteins exhibit exceptional binding affinity and structural rigidity, characteristics frequently enforced by conserved disulfide networks. This specific architecture allows them to selectively modulate critical cancer-associated enzymes, including matrix metalloproteinases, phospholipases A₂, serine proteases, and kinases. Inhibiting these highly specific targets successfully disrupts tumour angiogenesis, extracellular matrix remodelling, and metastatic dissemination, while simultaneously inducing apoptosis through unique pathways such as reactive oxygen species generation. Modern computational approaches, encompassing deep learning algorithms, molecular docking, and molecular dynamics simulations, are substantially accelerating and transforming the discovery pipeline by rapidly mapping intricate peptide–receptor interactions and guiding rational drug design. Translating these potent molecules into clinical therapeutics remains heavily challenged by pharmacokinetic instability, rapid proteolytic degradation, and systemic toxicity. The integration of computationally optimized scaffolds with advanced targeted delivery platforms, such as nanocarriers and liposomal encapsulation, offers a highly viable strategy to overcome these barriers, ultimately paving the way for next-generation, venom-inspired cancer therapies. Full article

Complex diseases often involve distributed interactions among biological regions, physiological systems, imaging phenotypes, and clinical variables that are not fully captured by anatomical proximity, isolated biomarkers, or conventional feature-based representations. In oncology, neuroimaging, critical care, and systems medicine, distant or apparently separate biomedical sectors may show strong statistical or functional coupling associated with multimodal imaging signatures, inflammatory responses, metabolic constraints, treatment-induced changes, or shared disease-state organization. In this work, we introduce a proof-of-concept relational graph framework for representing such candidate hidden connectivity in terms of correlation-induced accessibility bridges. The novelty of the framework is that it does not treat biomedical correlation, graph distance, and network connectivity as separate descriptors but explicitly couples non-factorizable inter-sector correlation to localized accessibility compression in an emergent disease-state geometry. The proposed framework represents a biomedical system as a weighted relational graph in which nodes correspond to clinically relevant entities, such as tissue regions, imaging-derived features, biomarker modules, physiological variables, or disease states, while weighted edges encode constraints on functional, statistical, or pathological accessibility. Within this structure, coarse-grained biomedical sectors are defined as organized subsystems, and non-factorizable coupling between sectors is quantified using mutual-information-type measures. Candidate biomedical bridges are then defined operationally as localized, high-gain reductions in effective inter-sector accessibility distance. We introduce explicit coupling rules linking sector-level correlation to bridge-specific accessibility compression, including an effective distance-compression model and an ensemble-based formulation. Numerical proof-of-concept simulations on randomized modular graph ensembles show that increasing correlation strength systematically reduces effective inter-sector distance and increases bridge gain. The strongest compression occurs when correlation modulates a designated bridge architecture, exceeding the effects observed under random non-bridge or generic inter-sector modulation. These simulations are not intended to validate a disease-specific biological mechanism but to test whether the proposed correlation–compression rule produces bridge-specific effects distinguishable from null graph perturbations. The resulting structures should not be interpreted as physical anatomical tunnels or direct causal pathways unless supported by additional biological evidence. Rather, they represent correlation-induced accessibility bridges: localized, high-gain routes in a patient- or disease-specific relational geometry. The framework may therefore provide a theoretical and computational basis for prioritizing candidate hidden connectivity patterns in radiomics, multimodal prognosis, physiological deterioration, recurrence modeling, and systems-level disease networks. Full article

Metastatic involvement of the male genitourinary tract by lung cancer is exceedingly rare. We report a 56-year-old man with metastatic lung adenocarcinoma (initial stage T3N2M1b) under pembrolizumab, who presented with severe pelvic pain. Pelvic magnetic resonance imaging and computed tomography demonstrated a large mass with an imaging epicentre favouring the left seminal vesicle, involving the prostate and fistulising to the distal rectum, without pelvic ascites or peritoneal disease. A total PSA of 0.81 ng/mL and a previous negative prostate biopsy made a primary prostatic malignancy less likely. Biopsy of the rectal component revealed a poorly differentiated carcinoma with an immunophenotype (CK7+, TTF-1+, p40−, CDX2−, NKX3.1−, PAX8−) consistent with metastatic adenocarcinoma of pulmonary origin. The patient underwent palliative pelvic radiotherapy, with improvement of pelvic pain; he subsequently developed pneumaturia and faecaluria and died eight months later from disease progression. Seminal vesicle metastasis from lung carcinoma has been reported previously; to our knowledge, however, this is the first report presenting with rectal fistulisation. This case highlights a diagnostically challenging presentation and the need to consider metastatic disease when evaluating atypical seminal vesicle masses in oncological patients. Full article

Drug repurposing represents a rational and resource-efficient strategy to expand the oncological armamentarium by leveraging the established pharmacology, clinical experience, and safety-monitoring frameworks of approved non-oncological agents. Clozapine (CZP), an atypical antipsychotic characterized by broad receptor pharmacology, complex biotransformation, and clinically relevant toxicological liabilities, has emerged as a candidate of interest following preclinical evidence of context-dependent anticancer activity across multiple tumor types. As such, CZP provides an informative case study at the interface between therapeutic drug action and xenobiotic behavior. This review provides a critical and integrated synthesis of the current evidence supporting the repurposing of CZP in oncology, with particular emphasis on the relationship between its molecular mechanisms, dose–exposure requirements, pharmacological complexity, and potential toxicity. Analysis of in vitro and in vivo studies across glioblastoma, non-small cell lung cancer, breast cancer, and melanoma brain metastasis models indicates that CZP can impair tumor cell proliferation and survival through a form of mechanistic plasticity. Rather than acting through a single conserved pathway, CZP appears to disrupt shared upstream processes related to pro-survival signaling, cellular stress tolerance, and metabolic homeostasis, while engaging tumor-specific downstream responses, including autophagic cell death, mitochondria-dependent apoptosis, oxidative stress, and coordinated modulation of survival and angiogenic pathways. Despite this mechanistic rationale, translation remains substantially constrained, most notably by the order of magnitude gap between anticancer-effective concentrations in vitro and clinically achievable plasma exposures, requiring careful distinction between potentially useful anticancer pharmacology and nonspecific xenobiotic-induced cellular stress and clinically unacceptable toxicity. Key limitations include the discrepancy between anticancer-effective concentrations observed in vitro and exposures achievable during standard psychiatric dosing, the limited understanding of how CZP metabolism and metabolite formation may influence efficacy and toxicity, the absence of integrated pharmacokinetic–pharmacodynamic and toxicokinetic modeling, and the lack of dedicated clinical trial evidence. To address these challenges, this review examines complementary translational strategies, including patient-derived organoids, co-culture systems, microphysiological platforms, pharmacokinetic and toxicological modeling, and computational digital twin frameworks. Together, these approaches may support a biologically informed and risk-aware evaluation of CZP, helping to identify responsive tumor contexts, anticipate exposure-related liabilities, and prioritize rational combination strategies. By integrating therapeutic potential with xenobiotic pharmacology and toxicology, this review positions CZP within the evolving landscape of precision oncology and evidence-driven drug repurposing. Full article

Colorectal cancer (CRC) remains the third most common malignancy worldwide and a leading cause of cancer mortality, largely driven by metastatic dissemination. Among metastatic routes, lymphatic spread is crucial to determine the prognosis and establish an adequate therapeutic strategy. Lymph node metastasis (LNM) defines stage III disease in the TNM classification, guiding adjuvant chemotherapy and surgical planning. However, nodal staging based on lymphadenectomy and histopathology is invasive, time-consuming, and may lead to overtreatment. Conventional imaging modalities, including computed tomography, magnetic resonance imaging, and endorectal ultrasound, show limited sensitivity and specificity for small or micro-metastatic nodes. Despite multimodal progress, no non-invasive technique reliably identifies malignant nodes in real time. PET–MRI, contrast-enhanced ultrasound, photoacoustic and fluorescence approaches, ICG mapping, and sentinel node biopsy improve detection but remain limited by specificity, cost, or availability. Extranodal extension (ENE) and tumor deposits (TDs) carry major prognostic value, reflecting aggressive biology and association with distant spread. Meanwhile, phylogenetic studies challenge linear dissemination models, indicating that some metastases arise directly from the primary tumor or TDs rather than LNMs. These data support refinement of staging and surgical strategies according to tumor biology rather than purely anatomical criteria. High-frequency quantitative ultrasound (HF-QUS) enables real-time, operator-independent, three-dimensional nodal assessment with reported sensitivity and specificity exceeding 85%. Combined with artificial intelligence and molecular profiling, it may support biologically informed staging, reduce unnecessary surgery, and foster precision oncology. Lymphatic dissemination in CRC offers a platform to merge tumor biology with technological innovation, where advanced imaging, molecular insight, and artificial intelligence may redefine nodal staging toward precision, non-invasive care. Full article

Oncology conditions are increasingly defined by their molecular profiles, and drug repurposing exploits this new evidence to identify new therapeutic uses of authorized/investigational medicinal products outside their original indication(s). This scoping review mapped original research published between January 2022 and December 2024 to determine the impact of automated processes and artificial intelligence in generating oncology candidates for drug repositioning, and 42 individual projects met the eligibility criteria and were analyzed. The included studies demonstrate extensive use of computational approaches for candidate prioritization, large-scale data integration, and hypothesis generation in oncology drug repurposing, creating opportunities for positive impact on efficiency. The included projects most commonly were target-oriented and disease-oriented and used multiple databases and computational validation procedures, while experimental and clinical validation were less frequently reported. The available open-access literature suggests substantial activity in China and India, which can support the notion that digitalization represents an important instrument in healthcare systems of low- and middle-income countries but should be interpreted cautiously. While the search was limited to PubMed and open-access English-language publications, we identified a relatively small number of drug-oriented projects, the importance of providing publicly accessible source code to reduce development costs, and the predominant role of academic institutions. Full article

Accurate, automated delineation of adult diffuse gliomas from multi-parametric magnetic resonance imaging (mpMRI) is central to quantitative neuro-oncology. Volumetric 3D networks dominate the BraTS leaderboard but require expensive GPUs, long training cycles, and provide diminishing returns relative to their compute budget. Slice-wise 2D models, by contrast, discard inter-slice context that is informative for thin tumor rims and small enhancing foci. We introduce GDNet, a 2.5D multimodal MRI segmentation framework for adult glioma evaluated on the BraTS 2024 cohort. GDNet consumes a stack of three adjacent axial slices from the four standard BraTS modalities (T1, T1ce, T2, FLAIR) as a 12-channel input to a compact U-shaped encoder–decoder with Group Normalization and predicts whole tumor (WT), tumor core (TC), and enhancing tumor (ET) masks for the central slice. The training pipeline pairs the 2.5D backbone with: (i) Exponential Moving Average (EMA) of model weights with decay 0.999, (ii) mixed tumor-aware slice sampling (p_tumor = 0.50), (iii) a compound Cross-Entropy + Soft-Dice loss, and (iv) AdamW with warm-up plus cosine annealing under Automatic Mixed Precision. We performed a systematic, step-by-step ablation covering a 2D baseline, EMA + mixed sampling, tumor-centered crop fine-tuning, a GDNet-inspired architectural integration, a region-aware loss, 3-slice and 5-slice 2.5D inputs, and connected-component post-processing, and we report multi-seed results to quantify reproducibility. On the held-out BraTS 2024 test partition, the final 3-slice 2.5D GDNet achieved positive-only Dice scores of 0.791 ± 0.000 (WT), 0.736 ± 0.003 (TC), 0.654 ± 0.004 (ET), and a mean foreground positive-only Dice of 0.820 ± 0.000 across seeds; the all-slice mean foreground Dice exceeded 0.927 ± 0.000. Validation positive-only scores were 0.805 ± 0.002 (WT), 0.757 ± 0.004 (TC), 0.683 ± 0.009 (ET). The inter-seed standard deviation was small for every region (≤0.01 Dice points), indicating low inter-seed variance across the two seeds evaluated; with only two seeds, we regard this as preliminary evidence of training stability rather than a strong reproducibility claim. The ablation isolated EMA + mixed tumor sampling and the 2.5D context window as the dominant sources of improvement; notably, a GDNet-style architectural integration with a region-aware loss did not outperform the simpler 2.5D U-Net on positive-only WT/TC/ET, and light post-processing improved only all-slice Dice. A failure-mode audit found that the residual catastrophic predictions are concentrated on a small minority of diffuse, infiltrative tumors with mass effect. Conclusions: Carefully engineered training strategies, tumor-aware sampling, EMA stabilization, and a modest 2.5D context window recover a substantial fraction of the accuracy of much heavier 3D networks at a fraction of the compute, are reproducible across seeds, and outperform a heavier GDNet-inspired architectural variant on the same data. GDNet is therefore a practical and, pending external validation, potentially clinically deployable framework for multimodal glioma segmentation on workstation-class GPU hardware. Full article

Background: Antibody–drug conjugates (ADCs) have evolved from early heterogeneous constructs into a mature therapeutic platform with exponential clinical relevance. This review highlights recent advances in ADC design and development, with emphasis on antigen selection, antibody engineering, linker and payload innovation, site-specific conjugation, clinical translation, toxicity, resistance, and emerging data-driven approaches. Methods: The review draws on the literature published from 2019 to the recent clinical and regulatory developments relevant to approved and late-stage ADCs, emphasizing the advances in target biology, antibody formats, linker chemistry, payload classes, conjugation technologies, developability assessment, and computational or artificial intelligence-assisted design strategies. Results: ADC development has evolved with improved target selection, enhanced internalization and tumor selectivity, and the use of engineered, bispecific, biparatopic, and fragment-based antibody formats. Linker and payload innovation has expanded beyond traditional microtubule inhibitors to include topoisomerase I inhibitors, DNA-damaging agents, and emerging dual-payload or non-cytotoxic strategies. Site-specific conjugation and improved control of drug-to-antibody ratio have increased stability, pharmacokinetic performance, and manufacturability. Clinically, ADCs are being used across a broader range of malignancies and treatment settings, although toxicities and resistance mechanisms remain an important limitations. Computational methods and artificial intelligence are increasingly being explored for target discovery, molecular optimization, toxicity prediction, and model-informed clinical development. Conclusions: ADCs are transitioning toward a more integrated, design-driven platform in which antigen biology, antibody format, chemistry, and computational prediction are jointly optimized. Future progress will depend on improved standardization, biomarker-guided development, and interdisciplinary approaches to enhance its therapeutic index and expand its applications beyond oncology. Full article

Background and Objectives: Cachexia is a systemic wasting syndrome associated with poor outcomes in chronic diseases, including heart failure (HF). Although the cachexia index (CXI), which integrates skeletal muscle mass, serum albumin, and the neutrophil-to-lymphocyte ratio, has shown prognostic value in oncology, its clinical significance in HF remains poorly defined. Materials and Methods: This retrospective single-center cohort study evaluated a selected subgroup of adults hospitalized with decompensated heart failure between January 2020 and January 2025 who had undergone abdominal computed tomography within the preceding 6 months, enabling CT-based body composition assessment. Skeletal muscle index was measured at the L3 vertebral level, and CXI was calculated as (SMI × serum albumin)/neutrophil-to-lymphocyte ratio. Patients were followed for all-cause mortality and HF-related rehospitalizations. Results: A total of 127 patients were included (mean age 70.45 ± 12.73 years; 51.2% male). CXI showed excellent discrimination for mortality (AUC 0.951; 95% CI 0.905–0.996), with an optimal cut-off value of <20.87. Patients with low CXI had significantly higher all-cause mortality (80.5% vs. 4.7%, p < 0.001) and more HF-related hospitalizations [4 (3–5) vs. 0.5 (0–1), p < 0.001] than those with high CXI. Conclusions: In patients hospitalized with decompensated HF, low CXI was strongly associated with all-cause mortality and recurrent hospitalization, suggesting that CXI may serve as an integrative prognostic marker in this population. Full article

Background/Objectives: Human papillomavirus (HPV) is a well-established prognostic marker in oropharyngeal squamous cell carcinoma (OPSCC); however, the short-term treatment response remains heterogeneous, particularly among HPV-positive patients. Given the high prevalence of malnutrition in head and neck cancer, this study examined whether baseline nutritional status, body composition and functional status were associated with early treatment response in OPSCC according to HPV status. Methods: A prospective observational multicenter cohort study of newly diagnosed OPSCC patients eligible for curative-intent treatment was conducted at three tertiary hospitals in Barcelona, Spain. Baseline assessments comprised anthropometry, computed tomography (CT)-based body composition at L3, functional performance tests, systemic inflammatory biomarkers and nutritional diagnosis by the Patient-Generated Subjective Global Assessment (PG-SGA). Early treatment response, assessed around 12 weeks post-therapy, was classified as complete remission (CR) or non-complete remission (NCR). Classification tree analyses were performed separately by HPV status. Results: Of 101 enrolled patients, 97 completed post-treatment assessment, of whom 51% were HPV-positive. Among HPV-positive patients, PG-SGA score was the main discriminating variable for early response within the classification tree model, with CR achieved in 74% of patients scoring <6 versus 33% of those scoring ≥6 (AUC 0.68, 95% CI 0.55–0.82). Conversely, Eastern Cooperative Oncology Group Performance Status (ECOG PS) and age were the primary discriminating variables in HPV-negative patients (AUC 0.81, 95% CI 0.70–0.93). In both HPV subgroups, body composition and inflammatory markers were not retained in the analysis once nutritional and functional status were considered. Conclusions: PG-SGA-defined nutritional status was associated with early treatment response in HPV-positive patients, while functional status was the main variable retained in HPV-negative patients. These findings support the potential clinical value of standardized nutritional assessment in OPSCC and suggest that early identification of poor nutritional status or functional impairment may help refine supportive care planning at treatment initiation. Full article

CD19-directed chimeric antigen receptor (CAR) T-cell therapy has fundamentally transformed the treatment landscape for relapsed and refractory B-cell malignancies, yet antigen escape remains a persistent therapeutic challenge that limits long-term remission durability. While antigen loss is typically considered a somatic event acquired during tumor evolution under therapeutic selective pressure, germline CD19 polymorphisms could theoretically influence CAR-binding kinetics, alter epitope presentation, and modulate therapeutic outcomes in ways that remain largely not characterized. Unfortunately, Middle Eastern populations are underrepresented in pharmacogenomic databases and CAR-T clinical trials, creating a knowledge gap that may perpetuate global health disparities in access to precision immunotherapy. We analyzed publicly available whole-exome sequencing data from 1196 individuals of Arab origin to comprehensively characterize CD19 variants with potential relevance to CAR T-cell immunotherapy. The L174V (rs2904880) variant stood out, and showed the Valine/Valine (V/V) genotype frequency was 65.3%, corresponding to a V174 allelic frequency of 76.6%, while the minor allele, L174, has a frequency of 23.4%. The missense mutation (c.520C > G) responsible for this variant results in a leucine-to-valine (L174V) substitution at position 174 of the CD19 protein, relative to the reference genome. The cohort genotypes (CC, CG, and GG) exhibited a significant deviation from Hardy–Weinberg equilibrium (p < 0.00001). While this deviation is consistent with the high consanguinity rates (25–60%) amongst Arab populations, it remains not fully explained, and may be attributed to population structure, relatedness, or technical factors. We further emphasize that our computational analysis cannot establish any direct clinical or functional impact due to this variant, and therefore we refrain from suggesting any specific actions at the current time. In light of these findings, we hypothesize that the distinctive genetic architecture of consanguineous populations should not be viewed as a confounding variable. Instead, it presents a unique opportunity to investigate the clinical relevance of germline variation in the context of precision oncology, particularly at therapy-relevant loci, pending functional validation. Full article

This review analyses and logically structures modern intelligent sensor technologies in the context of animal husbandry, feed production, and veterinary medicine. The main research discussed in the article focuses on machine learning based on modern neural network models, computer vision, and sensor systems that are transforming the methods for assessing the health, behavior, and nutrition of farm animals. The first part examines modern approaches to quality control and optimization of mineral and vitamin premixes, including visual inspection using visual sensors and neural networks. Key roles are played by precise dosing, component stability (minerals, vitamins), and the transition to more bioefficient organic forms of micronutrients to reduce environmental impact. Improvements in feed and premix production are analyzed, including automation, energy management, and the use of machine learning for non-destructive quality control, defect detection, mixing homogeneity assessment, and vitamin stability prediction. The second part analyzes methods for animal location and behavior detection. This article presents computer vision-based systems, including modifications of YOLO, for automatically tracking and classifying key behavioral patterns (lying down, standing, feeding, and aggression) in cattle and pigs, even in crowded conditions. It also discusses the use of ultra-wideband (UWB) systems and accelerometers combined with machine learning for high-precision positioning and detection of specific behavioral anomalies, such as lameness and playfulness. The third section focuses on the application of machine learning in veterinary diagnostics, including the automated interpretation of medical images (X-ray, ultrasound, and MRI) as sensor data streams for the diagnosis of cardiovascular, oncological, and orthopedic diseases in farm and small animals. Furthermore, the article examines the use of machine learning models for proactive disease diagnosis in farm animals and poultry based on multimodal data and image analysis. Considerable attention is given to methods and tools for radiometric diagnosis of animal diseases at an early stage using microwave sensors, as well as laser therapy and surgery in veterinary medicine. The review concludes that the integration of intelligent systems enables a transition to data-driven livestock management, significantly improving animal welfare and, consequently, the efficiency and sustainability of agricultural production. Full article