Search Results (497)

Background: Sow reproductive performance is a critical parameter for the productivity of commercial pig farms. Gut microbiota is associated with performance in sow reproduction. At least, under healthy conditions, microbial metabolites from the gut microbiota are considered major contributors to host physiological regulation and productivity. However, information on the differences in gut-derived metabolites related to the sow reproductive performance remain scarce. Our aim was to investigate the relationship between the reproductive performance and microbial metabolite levels in sow’s feces and plasma. Methods: We selected four commercial farms: two with high- (group H) and two with low-reproductive performance (group L). Sows had their feces and blood collected. Results: Except for the iso-butyrate concentration, fecal short-chain fatty acid concentrations remained unchanged between groups. Among intestinal putrefactive metabolites, the indole concentration was higher (p < 0.05) in group H. The concentrations of plasma metabolites p-cresyl sulfate, p-cresyl glucuronide and trimethylamine N-oxide (TMAO) were higher (p < 0.05) in group L than in group H, while the opposite was true for the acetate concentration (p < 0.05). Among plasma biochemicals, tumor necrosis factor (TNF)-alpha and potassium concentrations were higher (p < 0.05) in group L. Conclusions: Blood metabolites, especially gut microbiota-derived metabolites, seemed to be associated with the performance related to sow reproduction. Particularly, harmful metabolites such as p-cresyl glucuronide, p-cresyl sulfate and TMAO were of importance, because they are potentially inflammation factors. In fact, TNF-alpha was stimulated in group L. According to our results, we estimated that p-cresyl glucuronide, p-cresyl sulfate, TMAO and TNF-alpha could be useful physiological indicators to understand sow reproductive performance. Full article

Background/Objectives: Previous studies suggest that nutrient deficiencies can alter immune responses in animals. However, the impact of micronutrients on autoimmune diseases like type 1 diabetes (T1D) in humans remains unclear since the described associations are based on observational data and they cannot establish causality. This study aims to examine the causal relationship between various micronutrients and T1D using Mendelian randomization (MR). Methods: We performed a two-sample MR analysis using genetic variants from genome-wide association studies (GWASs) of 17 micronutrients as instrumental variables (IVs). We analyzed T1D GWAS datasets of European (18,942 cases/520,580controls), multi-ancestry (25,717 cases/583,311 controls), Latin American/Hispanic (2295 cases/55,134 controls), African American/Afro-Caribbean (6451 cases/109,410 controls), and East Asian (1219 cases/132,032 controls) ancestries. We applied the inverse variance weighted (IVW) method in our main analysis, and additional MR estimators (MR-Egger, weighted median, weighted mode, MR-PRESSO) to address pleiotropy, and the Steiger test to test directionality in sensitivity analyses. Results: Following Bonferroni correction (p < 0.05/17), we found positive association between potassium levels and T1D risk (OR = 1.098, 95% CI [1.075, 1.122] p = 5.5 × 10⁻¹⁸) in the multi-ancestry analysis. Zinc, vitamin B12, retinol, and alpha tocopherol showed nominal associations. Vitamin C, D, K1, B6, beta- and gamma-tocopherol, magnesium, iron, copper, selenium, carotene, and folate showed no significant effects on T1D risk. For the multi-ancestry analysis, we had sufficient power to detect ORs for T1D larger than 1.065. Conclusions: Higher serum potassium levels were associated with increased T1D risk in our MR study, though supporting observational evidence is currently limited. Other micronutrients are unlikely to have large effects on T1D. Full article

Background: Cardiovascular diseases are the leading cause of death globally, with hypertension and high sodium intake being major contributors. Accurate estimation of sodium intake is essential, but 24 h urine collection, the gold standard, is cumbersome and impractical for routine clinical use. Existing spot urine-based prediction formulae lack accuracy at the individual and population level. Objective: To develop and validate population-specific formulas for estimating 24 h urinary sodium excretion from spot urine samples using data from a representative Swiss adult population. Methods: Models with and without urea and potassium were developed incorporating age, sex, and anthropometry-based, population-specific, estimated urinary creatinine excretion values. Data quality was rigorously controlled, and model performance was compared to the INTERSALT, Kawasaki, and Tanaka formulae and to a nocturnal timed urine collection used to calculate hourly creatinine excretion. Results: Models based on first morning urine demonstrated improved accuracy (AUCs: Swiss anthropometric model 0.85 (95% CI: 0.80–0.90), Swiss anthropometric model with urea 0.86 (95% CI: 0.81–0.91)) and lower bias (−5.5 mmol/24 h for the Swiss anthropometric model and −2.86 mmol/24 h for the Swiss anthropometric model with urea) compared to existing equations. Performance was consistent across clinically relevant sodium intake thresholds and the models were therefore suitable for use in clinical settings. A timed nocturnal urine collection further improves accuracy. Conclusions: These new simple and reliable formulae provide a promising and practical tool for estimating sodium intake from first morning urine spot in adult European populations, and are potentially applicable in clinical settings. Full article

Background/Objectives: Roxadustat is a new treatment for the anemia of chronic kidney disease (CKD) that has comparable efficacy to erythropoietic-stimulating agents (ESAs), with the advantage of oral administration and increased iron bioavailability. It appears to be a safe treatment in terms of the development of major adverse cardiovascular events (MACEs); however, its long-term safety has not been fully evaluated. In this meta-analysis we evaluate its safety in dialysis-dependent (DD) and non-dialysis-dependent (NDD) CKD patients, considering the comparator used and treatment duration. Methods: The safety of Roxadustat was assessed based on the incidence of serious (SAEs) and non-serious adverse events (AEs). A random-effects method was used to estimate the odds ratios (ORs) and their 95% CIs. Results: Fifteen different randomized controlled clinical trials were included, with a total of 10,284 patients with CKD stages 3–5 treated with Roxadustat, 5604 on dialysis and 4680 not on dialysis. The overall incidence of AEs in the Roxadustat group did not change significantly (OR = 1.13; 1.00–1.27); however, the incidence of SAEs was significantly higher than in the control group (OR = 1.13; 1.04–1.23). Specifically, the incidence of hypertension (OR = 1.39; 1.13–1.73) and hyperkalemia (OR = 1.31; 1.02–1.69) was higher in the Roxadustat group than in the placebo group of NDD patients. All AEs except MACEs and hyperkalemia increased with treatment > 30 weeks. No differences were found in the incidence of any adverse effects studied compared with ESAs. Conclusions: Roxadustat is associated with an increased risk of SAEs, including hypertension and hyperkalemia in NDD patients. Therefore, monitoring potassium levels and blood pressure is recommended in these patients. Full article

Background & Objectives: Data on the efficacy and adverse effects of finerenone in patients with nondiabetic chronic kidney disease (CKD) are limited, particularly regarding ethnic diversity. This study aimed to evaluate the outcomes of finerenone in patients with nondiabetic CKD previously treated with standard therapies and investigate associated adverse effects, including hyperkalemia and hypotension. Methods: This is a retrospective exploratory study. It is a single-center study including patients with nondiabetic CKD who visited King Fahad Medical City in Riyadh, Saudi Arabia. The primary exposure was finerenone treatment, assessing its effects on albuminuria, kidney function, and blood pressure (BP), following prior use of renin–angiotensin–aldosterone system and sodium–glucose transport protein 2 inhibitors. The measured outcomes were the urine albumin-to-creatinine ratio (UACR) and estimated glomerular filtration rate (eGFR). The UACR (primary endpoint) was calculated as the mean of two morning spot urine samples collected consecutively 1 day apart. During each 4-week treatment period, secondary endpoints included changes in UACR, as determined by a 24 h urine sample, BP, and eGFR. The Wilcoxon signed-rank test was used to compare changes in continuous variables before and after therapy initiation. Statistical significance was set at p < 0.05. Results: This study included 16 patients with nondiabetic CKD (median age, 38.5 years [range, 35–50 years]; 56.3% male). The baseline eGFR was 66 mL/min/1.73 m² (47–82.5), with a UACR of 90.0 mg/g (58.8–132.5). No hyperkalemia was observed (potassium level, 4 mmol/L [3.8–4.4]). However, significant reductions in systolic and diastolic BPs were observed. Albuminuria improved significantly: the UACR decreased from 90.0 to 39.3 mg/g (p = 0.04). No adverse events, including hyperkalemia or hypotension, were reported. Conclusions: Finerenone showed promise in reducing albuminuria and blood pressure among patients with nondiabetic chronic kidney disease, with no significant adverse effects reported. These findings suggest potential benefits for this patient population, warranting further investigation. Full article

Saline–alkali soils represent a significant reserve of arable land, playing a vital role in ensuring national food security. Given that saline–alkali soil has low soil organic matter (SOM) and soil nutrient contents, and that soil quality degradation poses a threat to regional high-quality agricultural development and ecological balance, this study took coastal saline–alkali land as a case study. It adopted the extreme gradient boosting (XGB) model optimized by the tree-structured Parzen estimator (TPE) algorithm, combined with in situ hyperspectral (ISH) and spaceborne hyperspectral (SBH) data, to predict and map soil organic matter and four soil nutrients: alkali nitrogen (AN), available phosphorus (AP), and available potassium (AK). From the research outputs, one can deduce that superior predictive efficacy is exhibited by the TPE-XGB construct, employing in situ hyperspectral datasets. Among these, available phosphorus (R² = 0.67) exhibits the highest prediction accuracy, followed by organic matter (R² = 0.65), alkali-hydrolyzable nitrogen (R² = 0.56), and available potassium (R² = 0.51). In addition, the spatial continuity mapping results based on spaceborne hyperspectral data show that SOM, AN, AP, and AK in soil nutrients in the study area are concentrated in the northern, eastern, southern, and riverbank and estuarine delta areas, respectively. The variability of soil nutrients from large to small is phosphorus, potassium, nitrogen, and organic matter. The SHAP (SHapley Additive exPlanations) analysis results reveal that the bands with the greatest contribution to the fitting of SOM, AN, AP, and AK are 612 nm, 571 nm, 1493 nm, and 1308 nm, respectively. Extending into realms of hierarchical partitioning (HP) and variation partitioning (VP), it is discerned that climatic factors (CLI) alongside vegetative aspects (VEG) wield dominant influence upon the spatial differentiation manifest in nutrients. Meanwhile, comparatively diminished are the contributions possessed by terrain (TER) and soil property (SOIL). In summary, this study effectively assessed the significant variation patterns of soil nutrient distribution in coastal saline–alkali soils using the TPE-XGB model, providing scientific basis for the sustainable advancement of agricultural development in saline–alkali coastal regions. Full article

A portable spectral detector for water quality assessment was developed, utilizing potassium nitrate and ammonium chloride standard solutions as the subjects of investigation. By preparing solutions with differing concentrations, spectral data ranging from 254 to 1275 nm was collected and subsequently preprocessed using methods such as multiple scattering correction (MSC), Savitzky–Golay filtering (SG), and standardization (SS). Estimation models were constructed employing modeling algorithms including Support Vector Machine-Multilayer Perceptron (SVM-MLP), Support Vector Regression (SVR), random forest (RF), RF-Lasso, and partial least squares regression (PLSR). The research revealed that the primary variation bands for NH₄⁺ and NO₃⁻ are concentrated within the 254–550 nm and 950–1275 nm ranges, respectively. For predicting ammonium chloride, the optimal model was found to be the SVM-MLP model, which utilized spectral data reduced to 400 feature bands after SS processing, achieving R² and RMSE of 0.8876 and 0.0883, respectively. For predicting potassium nitrate, the optimal model was the 1D Convolutional Neural Network (1DCNN) model applied to the full band of spectral data after SS processing, with R² and RMSE of 0.7758 and 0.1469, respectively. This study offers both theoretical and technical support for the practical implementation of spectral technology in rapid water quality monitoring. Full article

Background: Adherence to Medical Nutrition Therapy (MNT) is a key determinant of therapy success, particularly in chronic diseases like chronic kidney disease (CKD). MNT in CKD requires significant changes in patient’s dietary habits, which can affect long-term adherence. This study aims to evaluate the adherence to MNT in stage 5 CKD patients undergoing conservative kidney management (CKM), identifying potential challenges and strengths of nutritional intervention. Methods: We enrolled in 94 stage 5 CKD patients undergoing CKM at the University Hospital of Modena, Italy. We collect clinical data from medical and nutrition records. The inclusion criteria comprised patients of all genders, ages, and ethnicity with stage 5 chronic kidney disease (CKD), in pre-dialysis, enrolled in the nephrology and dietetics program, who had access to 24-h urine tests, anthropometric measurements, and dietary history records. Exclusion criteria included patients with CKD stages lower than 5, those who had not undergone at least one nutritional assessment, or lacked accessible 24-h urine data. The study utilized medical and dietary records from September 2017 to March 2025. The primary outcome was the assessment of adherence to medical nutrition therapy (MNT), comparing prescribed protein intake with actual intake, estimated from dietary history (DH). Protein intake was compared with normalized protein nitrogen appearance (nPNA) as stated by recent guidelines. Additional factors influencing adherence, such as age, gender, comorbidities, physical activity, and prior dietary interventions, were also evaluated. Anthropometric measurements and biochemical tests were collected, and dietary intake was assessed using a seven-day DH. Results: Data were analyzed using descriptive statistics, linear correlation models, univariate logistic regression, t-tests, paired t-tests, and chi-square tests, with significance set at p < 0.05. Most of the patients follow suggested energy and protein intakes limits; however, substantial individual variability emerged Bland–Altman analysis indicated a moderate bias and wide limits of agreement for energy intake (+116 kcal; limits of agreement –518.8 to +751.3 kcal), revealing frequent overestimation in self-reports. Protein intake showed less systematic error, but discrepancies between dietary recall and biochemical markers persisted. Protein intake decreased significantly over time (p < 0.001), while correlation with nPNA did not reach statistical significance (ρ = 0.224, p = 0.051). No significant associations were identified between adherence and most clinical or lifestyle factors, although diabetes was significantly associated with lower adherence to protein intake (p = 0.042) and a predominantly sedentary lifestyle showed a borderline association with energy intake adherence (p = 0.076), warranting further investigation. Longitudinal analysis found stable BMI and body weight, alongside notable reductions in sodium (p = 0.018), potassium (p = 0.045), and phosphorus intake (p < 0.001) over time. Conclusions: Assessing dietary adherence in CKD remains complex due to inconsistencies between self-reported and biochemical estimates. These findings highlight the need for more objective dietary assessment tools and ongoing, tailored nutritional support. Multifaceted interventions—combining education, personalized planning, regular monitoring, and promotion of physical activity—are recommended to enhance adherence and improve clinical outcomes in this vulnerable population. Full article

Background/Objectives: As convenience store meals become a major dietary source for modern society, the reliability of their nutrition labels is increasingly scrutinized. With advances in artificial intelligence (AI), large language models (LLMs) have been explored for automated nutrition estimation. Aim: To evaluate the accuracy and clinical applicability of AI-assessed nutrition data by comparing outputs from five AI models with professional dietitian estimations and labeled nutrition facts. Methods: Eight ready-to-eat convenience store meals were analyzed. Four experienced dietitians independently estimated the meals’ calories, macronutrients, and sodium content based on measured food weights. Five AI chatbots were queried multiple times with identical input prompts to assess intra- and inter-assay variability. All results were compared to the official nutrition labels to quantify discrepancies and cross-model consistency. Results: Dietitian estimations showed strong internal consistency (CV < 15%), except for fat, saturated fat and sodium (CVs up to 33.3 ± 37.6%, 24.5 ± 11.7%, and 40.2 ± 30.3%, respectively). Among AI models, ChatGPT4.o showed relatively consistent calory, protein, fat, saturated fat and carbohydrate estimates (CV < 15%), and Claude3.7, Grok3, Gemini, and Copilot showed caloric and protein content as consistent (CV < 15%). Sodium values were consistently underestimated across all AI models, with CVs ranging from 20% to 70%. The accuracy of nutritional fact estimation over the five AI models for calories, protein, fat, saturated fat and carbohydrates was between 70 and 90%; when compared to the nutritional labels of RTE, the sodium content and saturated fat estimated were severely underestimated. Conclusions: Current AI chat models provide rapid estimates for basic nutrients and can aid public education or preliminary assessment; GPT-4 outperforms peers in calorie and potassium-related estimations but remains suboptimal in micronutrient prediction. Professional dietitian oversight remains essential for safe and personalized dietary planning. Full article

This study provides a comprehensive evaluation of naturally occurring radionuclides—radium-226 (²²⁶Ra), thorium-232 (²³²Th), and potassium-40 (⁴⁰K)—in groundwater systems across the Nile Valley regions of Upper Egypt, based on the analysis of 85 groundwater wells. Measured mean activity concentrations were 0.74 ± 0.3 Bq/L for ²²⁶Ra, 0.24 ± 0.1 Bq/L for ²³²Th, and 13 ± 4 Bq/L for ⁴⁰K, with ²²⁶Ra displaying low correlations with salinity indicators including chloride (Cl⁻), sodium (Na⁺), electrical conductivity (EC), and total dissolved solids (TDS). Notably, approximately 30% of sampled wells exceeded the World Health Organization (WHO) guidance level of 1 Bq/L for ²²⁶Ra, primarily in central and eastern zones influenced by elevated salinity and evaporite dissolution processes. Geospatial mapping combined with multivariate statistical analysis identified four principal components accounting for over 85% of total data variability, demonstrating that depth-dependent processes, including prolonged water–rock interaction and redox evolution, are the primary controls on ²²⁶Ra mobilization, with salinity-driven ion exchange as a secondary factor. Minor anthropogenic influences, potentially linked to agricultural activities in shallow aquifers, were also detected. Radiological risk assessment confirmed that calculated annual effective doses remain well within international safety limits (<1 mSv/year), although infants and children demonstrated relatively higher exposure levels due to increased water intake per unit body weight. Lifetime cancer risk estimates via ingestion pathways yielded values below 1 × 10⁻⁴, aligning with global health organization benchmarks and reinforcing the general safety of groundwater use in the region. The study highlights potential risks posed by saline groundwater to ancient monuments and archaeological sites, as the cycles of salt forming and breaking down might speed up damage to buildings made of limestone and sandstone. These findings establish a robust scientific foundation for future groundwater quality management and cultural heritage conservation efforts in the Nile Valley region of southern Egypt. Full article

Data-driven empirical models, including those based on reaction kinetics, are well-regarded for their ability to make accurate predictions and uncover underlying relationships. While such models have been extensively employed for microbial communities, their use in agricultural populations remains comparatively limited. In this study, researchers analyzed data from hydroponic lettuce cultivation experiments observing nitrogen-, phosphorus-, and potassium-limited growth. Dynamic μ models, which incorporated nutrient-fueled growth and maturity-based rate decay, were adapted to accommodate a variable nutrient supply, as would be expected for nutrient recovery efforts using domestic wastewater. To test these models, researchers analyzed multiple approaches, differing variations in analyses, and other agricultural models against observed biomass measurements. The resulting Dynamic μ biomass models showed significantly less error than all other tested models, were validated against three variable nutrient treatments, and were evaluated against expected wastewater concentrations. Wastewater-cultivated lettuce was predicted to grow between 20 and 72% of fresh mass compared to lettuce grown under ideal nutrient concentrations, and models identified 41.7 days to maximize dry biomass, with a final harvest time of 44.0 days to maximize fresh biomass. Finally, this research demonstrates the application of agricultural modeling for profit estimation and informing decisions on supplemental nutrient use, providing guidance for nutrient recovery from wastewater. Full article

The transition toward renewable-powered greenhouse agriculture offers opportunities for reducing operational costs and environmental impacts, yet challenges remain in managing fluctuating energy loads and optimizing agricultural inputs. While second-life lithium-ion batteries provide a cost-effective energy storage option, their thermal and electrical characteristics under real-world greenhouse conditions are poorly documented. Similarly, although plasma-activated water (PAW) shows potential to reduce chemical fertilizer usage, its integration with renewable-powered systems requires further investigation. This study develops an adaptive monitoring and modeling framework to estimate the thermal resistances (R_u, R_c) and internal resistance (R_int) of second-life lithium-ion batteries using operational data from greenhouse applications, alongside a field trial assessing PAW effects on beefsteak tomato cultivation. The adaptive control algorithm accurately estimated surface temperature (T_s) and core temperature (T_c), achieving a root mean square error (RMSE) of 0.31 °C, a mean absolute error (MAE) of 0.25 °C, and a percentage error of 0.31%. Thermal resistance values stabilized at R_u ≈ 3.00 °C/W (surface to ambient) and R_c ≈ 2.00 °C/W (core to surface), indicating stable thermal regulation under load variations. Internal resistance (R_int) maintained a baseline of ~1.0–1.2 Ω, with peaks up to 12 Ω during load transitions, confirming the importance of continuous monitoring for performance and degradation prevention in second-life applications. The PAW treatment reduced chemical nitrogen fertilizer use by 31.2% without decreasing total nitrogen availability (69.5 mg/L). The NO₃⁻-N concentration in PAW reached 134 mg/L, with an initial pH of 3.04 neutralized before application, ensuring no adverse effects on germination or growth. Leaf nutrient analysis showed lower nitrogen (1.83% vs. 2.28%) and potassium (1.66% vs. 2.17%) compared to the control, but higher magnesium content (0.59% vs. 0.37%), meeting Japanese adequacy standards. The total yield was 7.8 kg/m², with fruit quality comparable between the PAW and control groups. The integration of adaptive battery monitoring with PAW irrigation demonstrates a practical pathway toward energy efficient and sustainable greenhouse operations. Full article

Thallium (Tl) is a non-essential and highly toxic heavy metal capable of replacing potassium (K⁺) in biological systems, leading to mitochondrial dysfunction, oxidative stress, and inhibition of protein synthesis. In humans, the estimated oral lethal dose ranges from 10 to 15 mg/kg, with acute mortality rates of 6–15% and chronic neurological sequelae in up to 55% of survivors. Environmental releases of thallium of up to 5000 metric tons annually from industrial and mining activities, combined with its high oral bioavailability and nonspecific multisystemic symptoms, underscore the urgent need for more effective therapeutic strategies. This review summarizes current evidence on Tl toxicity, including its mechanisms of action, clinical manifestations, and available treatments. It emphasizes the strategic selection of biological models: simple organisms such as Caenorhabditis elegans and Drosophila melanogaster enable high-throughput screening and early biomarker detection; zebrafish (Danio rerio) provide vertebrate-level evaluation of multi-organ effects; and rodent models offer systemic toxicokinetic and therapeutic validation. Human-derived organoids and induced pluripotent stem cell (iPSC) systems recreate tissue-specific microenvironments, allowing translational assessment of mitochondrial, neuronal, and cardiac toxicity. Integrating these models within a tiered and complementary framework, alongside environmental and clinical surveillance, can accelerate the development of targeted treatments and strengthen public health responses to Tl exposure. Full article

Microplastic pollution in the Chesapeake Bay is of critical concern as estuaries serve as habitats and nurseries for diverse aquatic organisms and offer vital ecological services. However, quantitative analysis of microplastics, especially those smaller than 300 µm, in the natural aquatic environment is very challenging due to a lack of efficient sampling methods. This study takes a novel approach to quantify the abundance, size distribution, and morphological characteristics of microplastics, as small as 20 µm, in the surface waters of the Chesapeake Bay. Water samples (10 L) were collected monthly from July 2023 to October 2023 at four locations along the Chesapeake Bay. The samples were digested with a 10% potassium hydroxide solution and subjected to density separation using sodium chloride (ρ = 1.2 g/cc). Microplastic particles were examined using a Shimadzu AIM–9000 FTIR microscope for enumeration and chemical identification. Overall, the mean microplastic concentration observed was 766.16 ± 302.59 MP/L, significantly higher than previously estimated in the Chesapeake Bay. Microplastic abundance exhibited a significant (p = 0.02) spatial variation across the four sampling locations. Most abundant were particles less than 100 µm (60.65%), followed by particles between 100 µm and 300 µm (23.19%), and particles exceeding 300 µm (16.16%). Morphological analysis identified fragments as the dominant shape (86.02%), followed by fibers (11.87%), and beads (2.10%). This study underscores the importance of standard and efficient sampling methods in microplastics research. By sampling microplastics as small as 20 µm, this research demonstrated that the abundance of microplastics in the Chesapeake Bay is significantly higher than previously estimated and dominated by smaller–sized particles. These small microplastics are more likely to enter the food web where human exposure may occur. Therefore, microplastic pollution in the Chesapeake Bay ecosystem has the potential to impose environmental and public health risks. Full article

Tomato is one of the most important vegetables due to its high production and nutritional value. With the development of digital agriculture, the tomato breeding and processing industries have seen a rapid increase in the need for simple, low-labor, and inexpensive methods for analyzing tomato composition. This study proposes a digital method to predict four minerals (calcium, potassium, phosphorus, and magnesium) in beef-type tomato using machine learning models, including k-nearest neighbors (kNN), artificial neural networks (ANNs), and Support Vector Regression (SVR). The models were discriminated using the coefficient of determination (R²), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The kNN model showed the best performance for estimation of quantity of calcium, potassium, phosphorus, and magnesium. The results demonstrate that kNN consistently outperforms ANNs and SVR across all target nutrients, achieving the highest R² and the lowest error metrics (RMSE, MAE, and MAPE). Notably, kNN achieved an exceptional R² of 0.8723 and a remarkably low MAPE of 3.95% in predicting phosphorus. This study highlights how machine learning can provide a versatile, accurate, and efficient solution for tomato mineral analysis in digital agriculture. Full article