Search Results (17,783)

Extreme precipitation can disproportionately enhance rainfall erosivity in complex mountainous terrain, yet its spatial amplification and topographic differentiation remain poorly understood. Focusing on the Hengduan Mountains, this study evaluated three precipitation products (ChinaMet, CHM_PRE, and IMERG) against station observations and assessed their ability to capture precipitation extremes. Using the best-performing product, rainfall erosivity associated with total (PRCPTOT), heavy (R95p), and extreme (R99p) precipitation was estimated for 2005–2024, and its spatial patterns, amplification effects, topographic differentiation, and hotspots were analyzed. CHM_PRE showed the best overall performance, with a correlation coefficient (CC) of 0.83 and a Kling–Gupta efficiency (KGE) of 0.74, together with the highest probability of detection (POD = 0.95), accuracy (ACC = 0.83), and critical success index (CSI = 0.78) for extreme precipitation. Precipitation and the corresponding rainfall erosivity exhibited a pronounced southeast-to-northwest decreasing gradient. Although R95p and R99p accounted for only 9.61% and 2.43% of total precipitation, they contributed 14.84% and 4.33% of total rainfall erosivity, yielding erosivity amplification factors (AFs) of 1.52 and 1.73, respectively. This indicates a disproportionate contribution of precipitation extremes to rainfall erosivity, with stronger amplification under R99p. Rainfall erosivity also exhibited pronounced topographic differentiation, and high-level hotspots were consistently concentrated along the southeastern and southern margins. Extreme hotspots under PRCPTOT and R95p occurred at mean elevations of 2735.19–2791.92 m and mean slopes of 14.79–15.09°, whereas R99p intense hotspots occurred at a mean elevation of 2374.15 m and a mean slope of 12.28°. Strongly undulating mid-high mountains were the dominant geomorphic units within PRCPTOT and R95p extreme hotspots, while moderately and strongly undulating mid-high mountains dominated R99p intense hotspots. Moreover, hotspots became increasingly localized as precipitation extremity increased. These findings highlight the disproportionate erosive significance and spatial selectivity of precipitation extremes and provide a basis for identifying priority areas for soil and water conservation and rainfall-related hazard management in the Hengduan Mountains under climate change. Full article

Background: Counterproductive work behaviors (CWBs) are voluntary employee behaviors that harm the organization or its members, ranging from minor incivility and withdrawal to overt acts of misconduct. CWBs among nurses are widespread and carry adverse consequences for patients, nurses, and healthcare organizations, often reflecting problematic working conditions rather than individual character flaws. Perceived supportive resources, comprising individual resources (personal strengths and overall health), work resources (staffing and professional development), and interpersonal work resources (supervisor support and participation in unit decisions), have been proposed as protective factors. Thriving at work has been proposed as a potential protective motivational state that may account for how these resources are associated with behavior. Aim: This study examines how individual resources, work resources, and interpersonal work resources are associated with CWBs, and whether thriving at work mediates these associations among nurses in Saudi Arabia. Methods: One hundred twenty-nine nurses participated in this cross-sectional study between February and March 2026. Data were collected using the Thriving in Nursing Questionnaire (THINQ) and the Individual Work Performance Questionnaire (IWPQ). Data were analyzed via correlation, multiple regression, and mediation with bootstrapping. Results: Individual resources (r = −0.363), work resources (r = −0.270), and interpersonal work resources (r = −0.338) were each negatively associated with CWBs (all p < 0.001), and each was positively associated with thriving (r = 0.699, 0.793, and 0.794, respectively; all p < 0.001). Thriving at work was negatively associated with CWBs (r = −0.408, p < 0.001), and the associations of individual resources (indirect $\beta$ = −0.212), work resources ($\beta$ = −0.416), and interpersonal work resources ($\beta$ = −0.301) with CWBs were fully accounted for by indirect effects through thriving, with all direct effects nonsignificant and the largest indirect effect for work resources (95% CI [−0.611, −0.217]). Conclusions: Thriving at work emerged as a key correlate through which individual, work, and interpersonal work resources were linked to CWBs among nurses. Enhancing thriving may help reduce CWBs, though longitudinal research is needed to confirm directionality. Full article

In the new-type power system, the traditional generation planning paradigm has shifted to a new paradigm of source–storage collaborative planning. However, source–storage coordinated planning is facing deep-seated structural challenges of unbalanced multi-objective coordination and insufficient adaptability to market mechanisms. This paper first designs a source–storage coordinated planning framework with a two-layer structure of planning decision-making and operation verification, which takes into account multiple low-carbon, economic, and security planning objectives, and considers the dual market driving of energy storage participating in active-power and reactive-power regulations. Secondly, a two-layer optimal planning model is constructed: the upper-layer aims at minimizing the investment cost of new source–storage and minimizing annual carbon emissions, while the lower-layer aims at minimizing the comprehensive operation cost and maximizing the revenue of the energy storage market. The feature of this model is that it can simultaneously consider the coupling effect of the active-power market and the reactive-power market. Thirdly, a two-layer closed-loop iterative solution method based on Non-dominated Sorting Genetic Algorithm II is adopted to generate the source–storage coordinated planning scheme. Finally, simulation calculations are performed on the modified New England 39-bus system. The results show that, when considering the market driving of energy storage in both active-power and reactive-power regulations, the installed capacity of new energy reaches 465 MW, which is 55% higher than that in the no-market scenario, while the renewable energy curtailment rate is only 1.7%. The correctness and effectiveness of the proposed two-layer source–storage coordinated planning method in this paper are verified. Full article

Feed efficiency classification based on residual feed intake (RFI) and residual intake and gain (RIG) is widely used to identify biologically efficient animals, yet it remains unclear whether this classification reflects consistent differences in digestive, fermentative, and metabolic processes. This study evaluated the effects of RFI and RIG classification on nutrient intake, apparent digestibility, ruminal fermentation, nitrogen metabolism, microbial protein synthesis, and gaseous emissions in confined lambs. Thirty-eight weaned Texel ewe lambs underwent a 60-day performance test using an automated feed intake system and were classified as high-efficiency, neutral, or low-efficiency based on both indices. Animals were individually housed in respirometric chambers where emissions of methane, carbon dioxide, nitrous oxide, and ammonia were assessed by cavity ring-down spectroscopy; apparent digestibility was determined from total collections of feed, orts, faeces, and urine; microbial protein synthesis was estimated from urinary purine derivatives; and ruminal short-chain fatty acid profiles were determined by gas chromatography. Feed efficiency classification did not significantly affect body weight, nutrient intake, apparent digestibility, ruminal fermentation parameters, nitrogen balance, microbial protein synthesis, or greenhouse gas emissions. Principal component analysis revealed two major biological gradients related to nutrient intake and utilisation (42.9%) and ruminal fermentation and gaseous emissions (23.3%), together explaining 66.2% of total variance, but showing no clear separation among efficiency groups. These findings indicate that the digestive, fermentative, and nitrogen metabolism variables evaluated in this study did not account for the observed variation in feed efficiency. Because the regression underlying RIG explained little additional variation (R² = 0.01), these conclusions primarily reflect feed efficiency as classified by RFI, suggesting that other physiological mechanisms may play a more important role in determining feed efficiency in confined Texel ewe lambs. Full article

To investigate the differences in pulp metabolites among four varieties of Pouteria caimito fruit (JZL1, JZL3, JZL5, and JZL6), ultra-high performance liquid chromatography-tandem mass spectrometry (UHPLC-MS/MS) was employed for the separation and identification of metabolites. A total of 1285 metabolites were identified, including 648 in positive ion mode and 637 in negative ion mode. At the class level, carboxylic acids and derivatives (14.32%) and organooxygen compounds (11.83%) accounted for the highest proportions; at the subclass level, amino acids, peptides, and analogues (12.53%) as well as carbohydrates and carbohydrate conjugates (9.49%) were the main categories. PLS-DA analysis revealed significant differences in metabolite profiles among the four varieties, with numerous up-regulated and down-regulated metabolites in each comparison group, and some metabolites showed fold changes > 10 or <0.1. KEGG pathway enrichment analysis further indicated that differential metabolites were primarily enriched in pathways such as ABC transporters, citrate cycle (TCA cycle), starch and sucrose metabolism, and linoleic acid metabolism. This study provides an important metabolomic basis for variety identification, nutritional quality evaluation, and functional component development of Pouteria caimito fruit. Full article

Background/Objectives: Population ageing has increased the importance of promoting wellbeing and healthy ageing. Gerontological day centres may support the wellbeing of older adults. This study aimed to examine quality of life, active ageing, perceived social support, and loneliness in older adults attending gerontological day centres and to identify the factors associated with quality of life. Methods: A cross-sectional descriptive study was conducted with 109 participants aged 60–98 years recruited from gerontological day centres in Huelva and Seville, Spain. Data were collected using the WHOQOL-BREF, the Multidimensional Scale of Perceived Social Support (MSPSS), the ESTE II Loneliness Scale, and the Active Ageing Scale. Descriptive and comparative analyses were performed, followed by multiple linear regression to identify factors associated with quality of life. Results: Mean scores were 14.46 (SD = 1.83) for quality of life, 3.06 (SD = 0.36) for active ageing, 10.14 (SD = 3.00) for social loneliness, and 5.62 (SD = 0.93) for perceived social support. The multiple linear regression model accounted for 30.8% of the variance in quality of life (adjusted R² = 0.288), leaving approximately 69.2% of the variance unexplained by these factors. In this model, active ageing (β = 0.395; p < 0.001), social loneliness (β = −0.246; p = 0.004), and perceived social support (β = 0.188; p = 0.027) were independent predictors of quality of life. Bivariate analyses should be interpreted with caution as they were strictly exploratory. Conclusions: The study demonstrates that active ageing, low social loneliness, and solid perceived social support are the core multivariable predictors of quality of life among older adults in day centres. Secondary exploratory trends suggested minor baseline links with sleep duration, marital status, and employment status. Interventions should prioritize promoting active ageing and strengthening social networks, while future research needs to explore additional covariates to account for the remaining unexplained variance in well-being. Full article

Background/Objectives: Motor abnormalities are frequently observed in schizophrenia, but accessible methods for objective gait quantification remain limited. This exploratory controlled-setting study examined whether markerless smartphone-based video analysis combined with interpretable machine learning could quantify gait-related motor phenotypes in individuals with schizophrenia. Methods: Gait videos were collected from 100 individuals with schizophrenia and 35 healthy controls using a single-site, single-device, standardized recording setup. MediaPipe Pose was used to extract skeletal landmarks and derive 12 image-plane spatiotemporal and estimated two-dimensional knee-kinematic gait features. After temporal segmentation and quality control, 404 usable gait segments derived from 135 participants were analyzed as repeated segment-level observations. Decision Tree and Support Vector Machine models were applied for exploratory segment-level group-separation analysis using segment-wise 15-fold cross-validation after the full post-quality-control dataset had been balanced before fold allocation. Results: Several extracted gait features differed between groups, particularly image-plane ankle displacement, mean step displacement, displacement velocity, step characteristics, and knee-joint motion. In the Decision Tree model, image-plane ankle displacement served as the primary root node, indicating its central role in internal segment-level group separation. However, the healthy control group was substantially younger and not age-matched. In addition, the segment-level statistical comparisons did not account for within-participant clustering. Accordingly, the reported p values and confidence intervals may overstate statistical precision. Separately, segment-wise cross-validation allowed segments from the same participant to occur across folds and resampling was performed before fold partitioning. Because oversampling was performed with replacement, duplicated segment instances could also occur across training and validation folds. Consequently, the statistical findings should be interpreted as exploratory segment-level patterns rather than participant-level inference, and the machine-learning performance estimates should be regarded only as potentially optimistic apparent internal segment-level results and should not be regarded as evidence of participant-level generalization, diagnostic validity, screening accuracy, or clinical applicability. Conclusions: Markerless video-based gait analysis with interpretable machine learning may provide a feasible research-support approach for quantifying gait-related motor phenotypes in individuals with schizophrenia. These findings should not be interpreted as evidence for participant-level clinical classification, diagnostic or screening validity, clinical utility, or readiness for deployment, or as proof of cross-device or cross-environment reproducibility. Future studies require matched controls, psychiatric comparison groups, subject-wise validation, external datasets, calibrated gait measures, systematic cross-configuration reproducibility testing, and privacy-preserving data governance. Full article

Micro curved-surface parts are widely used in the aerospace, defense, biomedical, and automotive industries, and their growing adoption imposes increasingly stringent performance requirements. Five-axis micro-milling can achieve precision machining of parts with complex shapes. In the micro-milling process, the cutting force is a critical parameter, as it is the main factor causing machining deformation, vibration, and tool wear. Therefore, this study develops a prediction model for five-axis micro-milling forces in the machining of micro complex curved-surface parts. First, four coordinate systems were established for the five-axis milling process, and the transformation relationships among them were derived. A cutter–workpiece engagement (CWE) extraction method based on solid modeling was also introduced. Then, an instantaneous undeformed chip thickness (IUCT) model was established, taking into account tool runout, elastic recovery of the machined surface, minimum chip thickness, and the local radius of the micro ball-end mill. On this basis, a five-axis micro-milling force prediction model was developed. Finally, five-axis micro-milling experiments were conducted on a micro-impeller and a micro-spherical part, and the cutting forces at different cutter location (CL) points were measured. For the micro-impeller blade, the average percentage errors in the X, Y, and Z directions at all selected CL points were below 11.2%; for the micro-spherical part, the corresponding errors were below 14.4%. These results show good agreement between the predicted and measured values, verifying the effectiveness of the proposed model. Full article

Soil salinization threatens agriculture in arid regions, and remote sensing retrieval still faces challenges of unclear mechanisms and poor generalization. Based on Sentinel-2 data, this study compares the retrieval performance of various machine learning and deep learning models for farmland soil salt content, and introduces an attention mechanism for optimization. The main conclusions are as follows: (1) Random Forest achieved the highest accuracy among classical machine learning models (R² = 0.334), while CNN performed better among deep learning models (R² = 0.70), making it suitable for modeling scenarios with a single dominant salt type, well-defined spatial structures, and samples covering major environmental gradients. (2) In the problem of multispectral salinity retrieval, the complementarity of errors among base models was poor, preventing the ensemble model from fully leveraging its advantages. (3) Specific indices derived from near-infrared, red-edge, and blue–green bands performed well for sulfate-type salinity retrieval. (4) In the seed maize production area of Gansu, approximately 75.47% of farmland is non-saline, with severely saline land accounting for 1.42%; over the past decade, 74.84% of the area experienced a decrease in salt content, among which areas with a significant decline (accounting for 9.31%) corresponded consistently with regions where continuous engineering salt removal and microbial fertilizer management had been implemented for ten years. This demonstrates that, under conditions of limited ground samples, combining Sentinel-2 spectral information with moderate local spatial context can enhance the ability to detect salinity changes in relatively uniform irrigated areas. Full article

Artificial intelligence (AI) is entering cardiac surgery through predictive modelling, multimodal imaging, perioperative monitoring, workflow automation, and emerging computer-vision applications. The most mature evidence concerns risk prediction before and after surgery. Even in this domain, however, systematic reviews show that improvements over conventional statistical models are often modest and that routine clinical implementation remains limited. In surgical education, simulation, automated video analysis, and objective performance metrics may expand opportunities for deliberate practice and provide feedback that is less dependent on individual observers. Most of this evidence comes from general, laparoscopic, urological, and robotic surgery rather than cardiac-specific training, and its transferability should not be assumed. The same technologies also create risks. Automation bias, cognitive off-loading, reduced exposure to failure management, and displacement of mentor–trainee interaction may weaken the independent judgement on which safe cardiac surgery depends. Opaque models, dataset shift, inequitable performance, and uncertain accountability add further clinical and ethical concerns. This narrative review examines the current and emerging roles of AI across the cardiac surgical pathway and in cardiothoracic training, while distinguishing demonstrated applications from plausible but unproven uses. We propose a human-in-command framework based on external validation, local performance testing, transparent intended use, preserved manual and crisis-management competencies, simulation of technology failure, faculty oversight, competency-based credentialing, and continuous audit. AI should be judged not by technical novelty alone but by whether it improves care while preserving the ability of surgeons and teams to operate safely when the technology is unavailable or wrong. Full article

The effect of fluid distribution on seismic-wave propagation is of great importance to oil and gas exploration. In rock-physics experiments, different saturation methods result in different fluid distributions. At the same saturation, the drainage process usually produces larger fluid patches, while imbibition results in a relatively homogeneous fluid distribution. In this paper, a partial-saturation model is developed based on squirt-flow theory and the mesoscopic fluid-flow equation for partially saturated media. The effects of different fluid distributions are also incorporated using a modified Brie equation. The proposed model is compared with published experimental results. Numerical analyses are then performed for different fluid distributions, fluid properties, and rock-frame moduli. The results show that the proposed model can predict bulk-modulus dispersion and attenuation more accurately than the White model under drainage conditions. Under imbibition conditions, however, the model can reproduce either the attenuation or the low-frequency bulk-modulus variation, but not both simultaneously. Macroscopic viscosity, saturation, and rock-frame properties jointly control the critical frequency. A larger fluid bulk-modulus contrast and a smaller pore aspect ratio produce stronger squirt-flow-induced dispersion and attenuation. The above results show that the predictions of the proposed model at low frequencies are close to the measured results and that the model can describe the effects of fluid and rock-frame properties on the elastic response. However, the model does not account for the high-frequency dispersion and attenuation that occur when the fluid is more homogeneously distributed. Full article

In crisis times, traditional models of water quality assessment and water resources management lose their effectiveness. In the current conditions of local climate change, accidental pollution, emergencies or military operations, there is an urgent need to transition from traditional descriptive hydrochemical monitoring toward intelligent analysis of spatial-temporal datasets. In this paper, the integrated approach combining spatial cluster analysis, GIS-based visualization, and machine learning is proposed for assessing the surface water quality under conditions of limited and incomplete hydrochemical monitoring data. A geospatial assessment of nutrient impacts on surface water quality was conducted using 192 hydrochemical observations collected during the 2024–2025 monitoring period at eight state monitoring stations located in the basins of the Teteriv, Uzh, Irsha, Ubort, Sluch, Hnylopiat, and Voznia rivers, Polissia, Ukraine. Permutation feature importance analysis based on the Random Forest model showed that nitrate concentration accounted for approximately 75% of the total relative importance, whereas phosphate concentration contributed approximately 14%, indicating that these variables were the most informative predictors among the investigated hydrochemical parameters. The latter parameters are associated with dissolved oxygen variability among the analyzed hydrochemical parameters. According to the results of this study, three interpretable groups of monitoring stations were formed: Cluster 1, representing moderate water quality with increased nutrient pressure, Cluster 2, representing comparatively favourable background conditions, and Cluster 3, representing a nitrate-dominated hydrochemical type. The Random Forest model demonstrated limited predictive performance (R² = 0.154), indicating that nutrient-related variables alone explain only a small proportion of dissolved oxygen variability. Hence, additional factors, including hydrological conditions, water temperature, organic matter decomposition, biological productivity, and catchment-specific characteristics, also play an important role in shaping oxygen dynamics. The spatial visualization of cluster membership showed that geographical location alone does not fully determine the surface water quality patterns in Ukrainian Polissia. Instead, the local catchment characteristics and land-use conditions appear to exert a stronger influence on the formation of nutrient-related water quality differences. The authors propose to employ the spatial cluster analysis and machine learning as a basic supporting tool for the transition from retrospective interpretation of hydrochemical monitoring data to predictive and adaptive water resources management. The integration of geospatial analysis and machine learning provides a practical decision-support framework for the early detection of anomalies, identification of potential pollution sources, and prioritization of river sub-basins for implementing nature-based solutions. Full article

Background/Objectives: Severe dengue and dengue–malaria coinfection represent major diagnostic and therapeutic challenges in tropical endemic settings, where overlapping clinical manifestations may delay recognition of deterioration. This study aimed to describe the clinical and epidemiological characteristics of patients with severe dengue, dengue with warning signs, and dengue–malaria coinfection treated at a referral hospital in Montería, Córdoba, Colombia. Methods: A retrospective case series was conducted by reviewing medical records of patients diagnosed with dengue between 2018 and 2023. Cases classified as dengue without warning signs were excluded. The final analysis included patients with dengue-warning signs, severe dengue, and dengue–malaria coinfection. Dengue classification followed the 2009 World Health Organization criteria, and malaria was confirmed by thick blood smear. Sociodemographic, clinical, laboratory, geographic, and outcome-related variables were collected. Descriptive analyses were performed, and selected categorical variables were compared using Fisher’s exact test. Results: Fifty-three patients were included: 25 (47.17%) with severe dengue, 14 (26.42%) with dengue with warning signs, and 14 (26.42%) with dengue–malaria coinfection. Severe dengue was more frequent among females, whereas dengue with warning signs and coinfection predominated in males. Children accounted for the highest proportion of severe dengue cases, while coinfected cases were mainly distributed between childhood and adolescence. Fever was documented in all patients. Edema, elevated hematocrit, severe plasma leakage, and hemodynamic compromise were more frequent among severe dengue cases, whereas myalgia differed significantly across clinical groups. Ten deaths were recorded, six occurring in coinfected patients. Conclusions: Severe dengue and dengue–malaria coinfection are clinically complex conditions with overlapping manifestations and potentially fatal outcomes, highlighting the need for early recognition, differential diagnosis, and close monitoring. Full article

Generative artificial intelligence (AI) is entering religious communication not only through chatbots and generated text, but also through images and reels on social media. Yet research in this field has paid limited attention to what images contribute beyond their accompanying words. This article examines how AI-assisted visuals are incorporated into Indonesian Muslim Instagram accounts linked to Nahdlatul Ulama (NU) and what communicative work they perform. Informed by the Religious Social Shaping of Technology framework and visual-culture scholarship, the study combines qualitative digital observation with content and multimodal analysis of eleven posts from three accounts and sampled comments. The visuals were adopted selectively within established organisational, humour-oriented, and preacher-led modes of address. AI functioned through amplification: synthetic construction gave bodily and spatial form to themes of national belonging, moral criticism, santri conduct, and interreligious engagement, while enabling encounters that could not readily be photographed. These moral positions became legible through familiar signs, but authority remained with the organisation, collective voice, or public persona through which the images were framed and circulated. AI-assisted imagery is therefore best understood as situated visual mediation: it expands what religious communicators can picture without independently determining the meaning or authority of what is pictured. Full article

Background: Infertility is a common reproductive health disorder that affects roughly 10–15% of couples during their reproductive period. Hysterosalpingography (HSG) is a widely utilized imaging modality for assessing uterine cavity morphology and fallopian tube patency and continues to play a central role in infertility investigations. Nevertheless, the interpretation of HSG findings may vary according to the experience and expertise of the evaluator, potentially leading to inconsistencies in clinical decision-making. Although artificial intelligence (AI) has demonstrated considerable potential in medical image analysis across various specialties, evidence regarding its application in the interpretation of HSG examinations remains scarce. Therefore, this study aimed to evaluate the level of agreement among radiologists, gynecologists, and an AI-based system in the assessment of identical HSG images. Methods: In this retrospective study, a total of 1443 HSG images obtained from 414 women who underwent hysterosalpingography as part of an infertility evaluation between January 2021 and January 2025 were reviewed. Cases with incomplete clinical records or suboptimal image quality were excluded from the analysis. All examinations were independently assessed by an experienced radiologist, a gynecologist specializing in infertility management, and a multimodal artificial intelligence system based on ChatGPT-5, with each evaluator blinded to the assessments of the others and to the patients’ clinical information. Image interpretation included the evaluation of contrast distribution, peritoneal spill, uterine cavity findings, tubal patency, and overall HSG impression, which were categorized according to predefined diagnostic criteria. The primary outcome was the degree of interobserver agreement among the evaluators. Agreement analyses were performed using Cohen’s kappa (κ) and Gwet’s AC1 coefficients. Analyses were conducted using IBM SPSS Statistics (version 30.0; IBM Corp., Armonk, NY, USA) and R statistical software (version 4.4.0; R Foundation for Statistical Computing, Vienna, Austria). Statistical significance was set at p < 0.05 (two-sided). Results: A total of 1443 HSG images obtained from 414 women were included in the final analysis. The mean age of the study population was 30.97 ± 5.59 years, and primary infertility accounted for 87.9% of cases. The average number of images acquired per examination was 3.49 ± 1.05. According to Cohen’s kappa analysis, the highest levels of agreement were observed for the assessment of image artifacts and contrast medium distribution. Agreement between the AI system and the radiologist was particularly strong for contrast medium distribution (κ = 0.757). For the overall interpretation of HSG findings, AI demonstrated substantial agreement with the radiologist (κ = 0.637), exceeding the level of agreement observed between the radiologist and the gynecologist (κ = 0.363). In contrast, concordance involving AI was lower for the evaluation of uterine abnormalities, intrauterine filling defects, and tubal patency. When agreement was reassessed using Gwet’s AC1 statistic, concordance coefficients were consistently higher than the corresponding kappa values across all evaluator pairs. Near-perfect agreement between AI and the radiologist was identified for contrast medium distribution (AC1 = 0.954), peritoneal spill (AC1 = 0.893), and patterns of peritoneal contrast passage (AC1 = 0.841). Procedures performed under local anesthesia yielded a significantly greater number of images than those conducted under general anesthesia (3.86 ± 0.86 vs. 3.08 ± 1.10, p < 0.001). No significant associations were detected between abnormal HSG findings and either infertility type or anesthetic technique. In multivariable analysis, the use of general anesthesia was independently associated with a lower image count, whereas the presence of tubal pathology emerged as an independent predictor of acquiring a greater number of images during the examination. Conclusions: Our findings indicate that AI-assisted interpretation of HSG images has the potential to complement expert assessment, showing substantial concordance in several key diagnostic domains. While the technology appears promising as a decision-support tool in infertility evaluation, further research and refinement are warranted, particularly regarding the assessment of tubal and uterine pathologies. Full article