Search Results (961)

Background/Objectives: Oral solid dosage (OSD) forms are historically categorized as low-risk vectors for leachables under the assumption that solid-state matrices impose severe kinetic barriers against migrant migration and reactivity. This study investigates an unexpected unknown impurity, detected as part of a routine ICH Q3B testing program to control drug product impurities in a blister-packed tablet. Since the impurity exceeded the ICH Q3B identification threshold applicable for this drug product (1.0% w/w relative to API or 5 µg total daily intake (TDI), whichever is lower), a forensic investigation into the origins and identity of the impurity was performed. Methods: Placebo and packaging line studies were performed to isolate the origin of the impurity. Systematic structure elucidation was carried out using high-resolution mass spectrometry (HRMS), isotopic fine structure analysis, and de novo chemical synthesis. To enable definitive characterization, preparative HPLC was utilized to isolate the compound for high-field 2D-NMR spectroscopy (801 MHz). Results: The impurity was proven to be independent of active pharmaceutical ingredient degradation, forming only when tablet excipients were stored in sealed PVC blister packaging. Co-incubation of the PVC heat stabilizer derivative dimethyltin bis(2-ethylhexyl mercaptoacetate) (DMTE) with pyrrolidin-2-one (a povidone excipient degradation product) generated an identical chromatographic and MS/MS spectral profile. NMR spectroscopy unambiguously identified the structure as 2-ethylhexyl 2-((5-oxopyrrolidin-2-yl)thio)acetate. Conclusions: This study provides the first direct evidence of an organotin-catalyzed solid-state reaction between a packaging leachable and a tablet excipient under 25 °C/60% RH storage conditions. While this implies that the impurity should not be evaluated under the ICH Q3B guidelines, the findings directly challenge the assumed “low-risk” status of OSD packaging regarding leachables and highlight the necessity for interaction-focused, chemistry-based risk assessments, as outlined in emerging ICH Q3E guidelines. Full article

How much a college education pays off varies widely from one student to the next, and that variation matters for admissions, financial aid, and mobility policy. Most estimates, however, report a single average return and treat each institution as an isolated row in a table, ignoring how schools relate to one another and how outcomes are distributed across demographic groups. We present FairEdu-GCT(Graph-Enhanced Causal Transformer), a framework that couples a heterogeneous graph encoder with a Transformer sequence model and an explicit fairness penalty. Institutions, geographic regions, and academic disciplines form a typed graph whose edges record graduate flows, spatial proximity, and disciplinary overlap. A Relational Graph Attention Network (R-GAT) turns this structure into institutional ecosystem embeddingsthat carry peer effects, regional labor-market signals, and the spread of institutional prestige, none of which survives in tabular representations. A Transformer then encodes each student’s educational history and merges it with the institutional embedding through a cross-modal attention bridge, and a counterfactual decoding head returns the full conditional earnings distribution under alternative institutional choices rather than a single point estimate. Because students are not randomly assigned to schools, we make no claim of strict causal identification; we treat CATE and PEHE strictly as estimation-quality diagnostics for a confounding-adjusted contrast, not as evidence of a proven causal effect. We instead adjust for observed confounders through a doubly robust objective and add an equalized opportunity regularizer so that accuracy does not come at the expense of protected subgroups. On linked U.S. College Scorecard, IPEDS, and NLSY97 data (6256 institutions drawn from 7312 Title IV schools; 161,043 person-institution-year records from 8984 respondents followed for ten years), FairEdu-GCT lowers RMSE by 16.2% and Precision in Estimation of Heterogeneous Effects (PEHE) by 25.1% against the strongest baseline (Causal Forest, DragonNet, TARNet, and TabTransformer), and shrinks the demographic parity gap by 46.5%. All gains are reported with 95% confidence intervals and effect sizes over ten seeds, and an extended fairness audit (calibration, predictive parity, and subgroup robustness) confirms the improvement is not confined to the two metrics we optimize. Ablations attribute a 9.0% RMSE reduction to the R-GAT encoder alone. A group-conditional SHAP analysis further shows that graph-derived proximity to regional technology clusters is an unusually strong predictor for first-generation minority students, a signal that tabular features cannot recover and one we read as a within-model association rather than a policy lever. Full article

Although BRCA1 and BRCA2 remain the backbone for germline DNA testing of patients with breast cancer (BC) or ovarian cancer (OC), there are a number of other genes with proven or potential clinical significance. PALB2 is associated with an elevated risk of BC, whereas pathogenic variants (PVs) in RAD51C, RAD51D, and BRIP1 are mainly relevant to OC development. Some germline findings are helpful in guiding therapeutic decisions: for example, PALB2, RAD51C, and RAD51D germline PVs render tumors sensitive to PARP inhibitors (PARPi), whereas cancers arising in PTEN heterozygotes are likely to be responsive to AKT down-regulators. CHEK2, ATM, BLM, and NBN PVs result in only a two-fold or even lower excess of cancer risk. However, the incorporation of these genes in DNA testing panels may occasionally lead to the identification of individuals with biallelic germline inactivation; these patients have a severe disease phenotype and thus require intensive medical intervention. The accumulation of data on “non-BRCA” BC- and OC-predisposing genes is complicated due to the rarity of their alterations, significant interethnic variations in population frequency of relevant PVs, heterogeneity of disease subtypes, etc. The use of extended gene panels, which pool together both clinically validated cancer-associated genes and “candidate” genes with potential but unproven significance, is likely to be a prevailing diagnostic approach in the next few years; therefore, proper attitudes towards accumulation and interpretation of genetic data are important. Full article

The XRF, Raman, and fluorescence signatures of approximately fifteen blue-and-white and white porcelain sherds are compared. The assemblage comprises fourteenth- to sixteenth-century porcelain sherds, including Yuan and Ming wares from the Jingdezhen kiln sites, fifteenth- to sixteenth-century wares from the Yuxi and Jianshui kiln sites in Yunnan (China), and Vietnamese sherds comparable to ceramics recovered from the Cu Lao Cham (Hoi An) shipwreck preserved in private collections. Particular attention is paid to the XRF signals of impurities associated with sands (Zr, Y), fluxes (Rb, Sr), and cobalt-bearing ores (As, Mn, Fe, Ni, Bi), as well as to the Raman identification of specific phases in Chinese and Vietnamese porcelains. The similarity between Yunnan and Vietnamese blue-and-white wares is confirmed, notably by their high zirconium concentrations, whereas rubidium concentrations provide a means of distinguishing between the two regions. Overall, XRF signatures enable the non-invasive classification of the sherds according to their material characteristics. The resulting classifications are based on visualizations of clusters in the elemental compositional data using selected elements relevant to geological provenance and ceramic processing. These classifications are then compared with those obtained using PCA and hierarchical clustering based on Euclidean distances. Raman spectra highlight the presence of specific phases, including calcium silicates and phosphates. For the first time, particular emphasis is placed on the importance of considering the entire fluorescence spectrum as an identification tool. Special attention is given to the chromium fluorescence doublet with the α-alumina phase formed during the transformation from 2:1 mullite to 3:2 mullite at temperatures above 1200–1250 °C. Full article

Fluvial sand bodies represent one of the most significant reservoir types in hydrocarbon exploration. Restricted by climatic conditions, sedimentary environments and the properties of provenance parent rocks, sedimentary characteristics and sand-body architectures exhibit substantial spatial variations across different river systems and along individual river segments. Research on modern sedimentary processes of the Weihe River provides critical insights for advancing continental fluvial sedimentology theories and reconstructing paleoriver sedimentary models for analogous basins. Integrating high-resolution satellite image interpretation combined with systematic field geological surveys across typical river reaches, this study systematically characterizes the spatial differentiation of river patterns, sedimentary signatures, sand-body architectures and their primary controlling factors within the Weihe Basin. The results reveal a distinct three-segment spatial differentiation pattern of fluvial styles in the Weihe Basin: braided rivers dominate the Baoji–Zhouzhi reach; low-sinuosity meandering rivers occur in the reach from Zhouzhi to Lintong; and high-sinuosity meandering rivers prevail in the downstream segments below Lintong. Unique hydrodynamic regimes associated with each river type control sedimentary partitioning and sand-body development. Braided rivers feature intense hydrodynamic force and coarse-grained sediments, with sedimentary assemblages consisting of gravelly channel deposits, mid-channel bars and floodplain deposits, which form thick stacked sand bodies via multi-stage sedimentary superimposition. Low-sinuosity meandering rivers possess moderate hydrodynamic energy and are dominated by sandy-gravel deposits, yielding a complete sedimentary succession composed of channel fills, point bars, natural levees and floodplains. High-sinuosity meandering rivers are characterized by weak hydrodynamic conditions and fine grain sizes dominated by sandstone and mudstone units, developing diverse sedimentary facies including channels, crevasse splays and oxbow lake deposits. The spatial heterogeneity of the sedimentary system across the Weihe Basin is synergistically controlled by the channel gradient, provenance attributes, sediment grain size and sediment concentration. This study clarifies the sedimentary evolutionary laws of modern rivers under semi-arid and semi-humid climatic conditions, enriches fundamental fluvial sedimentology theories, and supplies a modern sedimentary analog for paleoriver identification, paleoenvironmental reconstruction and hydrocarbon exploration targeting fluvial reservoir systems. Full article

Non-marneffei Penicillium species are ubiquitous molds usually dismissed as contaminants in respiratory cultures; invasive disease is rare and may mimic malignancy, tuberculosis, or sarcoidosis. A 39-year-old apparently immunocompetent man with asthma, a smoking history, and tuberculosis exposure presented with chronic cough, fever, night sweats, and weight loss. Chest computed tomography (CT) showed right lower-lobe subpleural consolidation, bilateral nodules, and mediastinal lymphadenopathy. Sputum and bronchoalveolar lavage (BAL) studies for tuberculosis were repeatedly negative; CT-guided lung biopsy showed a non-necrotizing granuloma, suggesting sarcoidosis. Five months later, the original lesions had regressed, and new contralateral pleural-based nodules appeared, establishing a migratory pattern. Repeat BAL grew a Penicillium species, a second recovery after an earlier isolate was dismissed as contamination. Surgical mediastinal lymph-node biopsy showed necrotizing granulomatous inflammation containing PAS- and GMS-positive septate hyphae, establishing proven invasive fungal disease, and fungal culture of the same tissue grew a Penicillium species; HIV and hepatitis serologies were negative. Liposomal amphotericin B followed by oral voriconazole produced near-complete radiological resolution. Attribution to Penicillium rests on recovery of the mold from the surgical tissue itself; identification nevertheless remained at genus level, because molecular identification, susceptibility testing, and fungal biomarkers were unavailable, and invasion of lung parenchyma was never demonstrated histologically. Migratory infiltrates should prompt reconsideration of fixed diagnoses; repeated mold recovery with tissue-invasive hyphae and treatment response warrants reassessment rather than dismissal as contamination. Full article

Invasive candidiasis (IC) causes substantial mortality in critically ill children, yet pediatric data from Southeast Asia remain limited. We retrospectively studied 117 children aged ≤ 18 years with proven IC at a Thai tertiary center (2009–2023). Thirty-day mortality was 25.6%, rising to 47.1% in neonates; death occurred a median of 5.5 days after diagnosis. Firth penalized logistic regression identified septic shock (aOR, 4.89; 95% CI, 1.77–14.88) and thrombocytopenia (aOR, 3.74; 95% CI, 1.17–15.35) as independent mortality predictors, with septic shock remaining significant across all analytical frameworks, including Fine–Gray competing-risks analysis. Apparent mortality associated with absence of antifungal therapy reflected reverse causation: in all six untreated children who died, Candida was reported only 2–7 days after death. Candida albicans (43.6%), C. tropicalis (30.8%), and C. parapsilosis (24.8%) predominated; C. glabrata was absent. Non-albicans Candida was already common at the outset and showed no statistically detectable increase over 15 years. Among 45 consecutive pediatric bloodstream isolates (2021–2026), amphotericin B and echinocandins largely retained activity, whereas reduced azole susceptibility was concentrated in C. tropicalis (47.8% fluconazole-susceptible; 26.1% posaconazole wild-type). The reduced azole susceptibility of local C. tropicalis isolates argues for periodic reassessment of institutional susceptibility data rather than reliance on historical or external epidemiology; in comparable settings, an echinocandin or amphotericin B is a more reliable empiric choice than an azole, pending species identification and susceptibility results. Full article

Elymus repens (L.) Gould has a long history of use in traditional medicine across the British Isles, particularly among Gaelic and Anglo-Saxon communities, where it has been employed as a diuretic and anti-inflammatory agent. Despite its ethnopharmacological significance, comprehensive insights into its phytochemical composition and biological activities remain limited. The present study aimed to provide an integrated characterization of E. repens through macro- and microscopic analyses, advanced phytochemical profiling, and evaluation of the biological activities of the rhizome part. Microscopic examination revealed distinct anatomical features differentiating rhizome and stem, leaf tissues, supporting accurate identification and pharmacognostic standardization. Chemical profiling using Liquid Chromatography-Quadrupole Time-of-Flight Mass Spectrometry (LC-QToF-MS) enabled the tentative identification of 93 metabolites, including amino acids, in aerial and rhizome extracts. These compounds were primarily classified into polyamines (e.g., feruloylputrescine, hydroxycoumaroylagmatine), phenolic acids (gallic, vanillic, and ferulic acids), flavonoids (apigenin, tricin, saponarin analogues), amino acids (arginine, tyrosine, tryptophan), organic acids (malic, succinic acids), nucleosides (adenosine, thymidine), and phospholipids. Biological evaluation demonstrated that the hydroethanolic rhizome extract exhibited notable antifungal activity against Aspergillus fumigatus (IC₅₀ = 34.9 µg/mL). Additionally, hydroethanolic extracts of both the aerial and rhizome parts showed no cytotoxicity in the Artemia salina lethality assay at concentrations up to 10 mg/mL, indicating a favorable preliminary safety profile. Of particular interest is tricin, which possesses anti-inflammatory, antioxidant, antimicrobial, and potential nephroprotective therapeutic effects; its mechanism of action is associated with the suppression of oxidative stress, the inhibition of pro-inflammatory mediators, and the disruption of metabolic processes in microbial cells. Overall, this study provides a comprehensive phytochemical and pharmacognostic characterization of E. repens, highlighting its potential as a source of bioactive compounds. The metabolite profile obtained directly from the biologically active extract, combined with its proven antifungal activity, serves as direct confirmation of the antimicrobial aspect of this plant’s traditional use, while its broader applications in ethnomedicine require targeted pharmacological testing. These findings contribute valuable data for chemotaxonomic classification and future pharmacological investigations. Full article

A near-infrared (NIR) light transmission imaging system was constructed using a stereomicroscope equipped with an 860 nm NIR LED light source to evaluate its applicability for observing wood anatomical structures. Species identification of wooden Buddhist statues is important for clarifying their provenance and production period, but such objects require non-destructive examination, and surface darkening from aging and soot deposits often limits observation under visible light. Fifteen wood species used for Buddhist statues and other cultural and architectural properties—eight hardwoods and seven softwoods—were examined, and NIR transmission images of the transverse section were obtained under air-dried and water-saturated conditions. Under air-dried conditions, NIR transmittance differed among species and between heartwood and sapwood, revealing anatomical structures such as vessels, growth-ring boundaries, and resin canals. Under water-saturated conditions, transmittance increased in all species and resin-canal structures became more distinct in softwoods, although some image blurring occurred. These results indicate that NIR transmission observation is effective for non-destructive species identification of wooden cultural properties, and that wood moisture strongly affects the resulting transmitted image. Full article

This paper proposes a novel susceptible–infected–susceptible (SIS) epidemic model incorporating a fractional-order term and white-noise perturbations. Several analytical results concerning its dynamical behavior are established. Firstly, we prove the existence and uniqueness of model solutions using the Carathéodory approximation. Secondly, the extinction of disease is rigorously proven based on the properties of the quadratic function. Meanwhile, the Ulam–Hyers stability of the model is derived by using stochastic Gronwall-type inequalities and the stochastic analysis techniques. Furthermore, the solution of the proposed fractional-order stochastic model can be approximated by that of the corresponding averaged model under suitable averaging conditions. Then, numerical simulations are conducted to illustrate the effects of key parameters on disease extinction, stability, and long-term dynamical behavior. To improve its adaptability to real-world epidemic dynamics, this paper embeds dynamical constraints into neural networks and constructs a stochastic physics-informed identification framework for seasonal infectious diseases. Empirical results based on monthly influenza data from Xinjiang show that the proposed framework can capture epidemic trends, seasonal peaks, and fitting uncertainty. These results provide a theoretically grounded and practically applicable approach for infectious disease modeling under memory effects and stochastic perturbations. Full article

Reliable molecular identification of plants depends on reference libraries of DNA sequences, and complete plastid genomes (plastomes) used as super-barcodes are increasingly the reference of choice for taxonomically difficult groups. We assess how ready the flora of Poland is for plastome-based super-barcoding by combining national checklists of vascular plants, mosses, and liverworts with the current availability of complete plastomes in GenBank. For 3339 species we quantify coverage, its distribution across families and genera, the provenance of the sequenced material, and the gap between coverage and expected species-level resolution. A complete plastome was available for 54.4% of species, but coverage was uneven: liverworts (76.0%) and mosses (75.6%) were close to reference-complete, whereas the much larger vascular flora reached only 45.9%. Effective vascular coverage fell to roughly 39% once low-resolution genera were excluded, because many uncovered species belong to apomictic or hybridogenous complexes such as Taraxacum, Hieracium, and Alchemilla, where plastomes alone cannot resolve identity. Most sequenced material was of non-European origin, which weakens fine-scale identification of local populations. We identify 1011 high-value sequencing targets and recommend a tiered, marker-aware strategy combining the plastome with nuclear ribosomal DNA and, selectively, low-copy nuclear or mitochondrial markers. Defining readiness by the proportion of the flora that can actually be identified turns a static inventory into a prioritized roadmap transferable to other Central European floras. Full article

Thermal forcing is one of the most important drivers of leaf phenology and can be used to determine species’ phenological requirements. Counting on this, the aim of the study was to quantify the thermal regime and determine how it explains variation in spring phenology and senescence in European beech. To achieve this goal, we analyzed the 44 provenances tested in a common garden experiment established in the Carpathian region of Romania during the 4th series of international beech provenance trials. Using growing degree days and senescence degree days, cumulative precipitation over the previous 14 days, and photosynthetically active radiation as climatic factors, we modeled the spring leaf phenology and senescence, the thermal thresholds of provenances, and the length of the growing season. We found that thermal forcing is the primary driver of provenance phenology, but the other climatic parameters also significantly influence these processes. Significant variation among provenances was observed, but the effect of provenance was weaker than that of year or replication, suggesting that environmental conditions exert a stronger influence on leaf phenology dynamics. The identification of contrasting warming and cooling requirements suggests that, in provenance selection or assisted migration practices, thermal requirements are particularly important alongside growth performance. Full article

Background/Objectives: Primary renal endometriosis with extrapelvic locations of endometriosis lesions is deemed extremely rare. Therefore, the aim of this review was to assess the current literature on renal endometriosis, encompassing a summary of recorded living-patient cases, imaging and pathological features, chosen therapeutic approaches, and patient outcomes. Methods: We performed a narrative review with a systematic identification and presentation of published cases of histopathologically proven kidney endometriosis. A literature search was carried out across PubMed, Scopus, and Web of Science for relevant studies, i.e., case reports and series that met predefined inclusion and exclusion criteria specified by the modified PECOS framework. Results: A total of 19 publications reporting a total of 20 reported cases were included in the in-depth analysis. The noted condition affected women of reproductive age, with a mean age of 37.4, with the most common presenting symptoms being lumbar or flank pain, gross hematuria, abdominal pain, and tenderness. Most were single-mass lesions detected on the right kidney, with a mean largest diameter of 6.7 cm. Most were CT-characterized as either hyperattenuating lesions, septate lesions with foci of calcifications and soft tissue components, or areas of necrosis or cystic change. As CT presented features that would not allow the exclusion of malignant kidney tumors, most patients were treated surgically with nephrectomy. Diagnosis was confirmed by histopathology of recorded endometrial glands and stroma. Conclusions: The diagnosis of these lesions is exceptionally challenging because of their nonspecific symptoms, the rare association with the menstrual cycle, the rarity of dysmenorrhea, and the occasional coexistence of ovarian endometriosis, with no distinct endometriosis-specific clinical and imaging pattern emerging. Full article

Background: Radiotracer- and magnetic seed-based targeted axillary staging techniques are increasingly used after neoadjuvant chemotherapy (NAC) in patients with initially node-positive breast cancer who convert to clinical node-negative (ycN0) status. However, these technologies remain unavailable in many centres worldwide. We evaluated the effectiveness of radiotracer-free axillary staging using dual-tracer sentinel lymph node biopsy (SLNB) with indocyanine green (ICG) and methylene blue, with particular focus on the clinical implications of clipped node non-retrieval. Methods: This retrospective single-centre cohort study included 49 patients with biopsy-proven cN1 breast cancer who achieved ycN0 status following NAC and underwent dual-tracer SLNB using ICG and methylene blue between 2021 and 2024. Clipped node retrieval rates, tracer-specific detection patterns, recurrence outcomes, and disease-free survival (DFS) were analysed. Clinical outcomes, including recurrence and disease-free survival, were compared between patients with successful and unsuccessful clipped node retrieval. Results: Clipped node retrieval was achieved in 41 of 49 patients (83.7%). ICG outperformed methylene blue for clipped node identification (80.5% vs. 61.0%) and was the sole detecting tracer in 39.0% of cases. Using methylene blue alone would have reduced the retrieval rate to 51.0% (p = 0.001). ICG identified the clipped node in all six patients with axillary micrometastases (ypN1mi). Clipped node non-retrieval occurred in eight patients, all of whom had negative SLNB findings and did not undergo completion axillary lymph node dissection. Recurrence rates were similar between the retrieval and non-retrieval groups (17.1% vs. 12.5%, p = 1.000), and no isolated axillary recurrences were observed. Baseline tumour size was the only independent predictor of disease-free survival in multivariable analysis (HR 2.05, 95% CI 1.20–3.51; p = 0.008). Conclusions: Radiotracer-free axillary staging using ICG and methylene blue achieved a high clipped node retrieval rate in patients with ycN0 breast cancer after neoadjuvant chemotherapy. ICG significantly improved clipped node identification compared with methylene blue alone and identified the clipped node in all patients with residual nodal micrometastatic disease. Among patients with negative SLNB findings, clipped node non-retrieval was not associated with higher recurrence rates or worse disease-free survival during follow-up. However, given the small number of clipped node non-retrieval cases (n = 8) and recurrence events (n = 8), these findings should be interpreted with caution and require confirmation in larger prospective studies. These findings support the feasibility of a radiotracer-free dual-tracer approach in settings where radiotracer-based techniques are not available. Prospective multicentre studies are warranted to validate both the oncological performance of radiotracer-free axillary staging and the clinical implications of clipped node non-retrieval. Full article

Background/Objectives: Early identification of breast cancer patients unlikely to benefit from neoadjuvant chemotherapy (NAC) remains a pressing clinical problem because ineffective therapy delays definitive surgery and exposes patients to unnecessary toxicity. Quantitative ultrasound (QUS) and shear wave elastography (SWE) probe complementary tissue properties—scatterer microstructure and mechanical stiffness—that may change before macroscopic tumor shrinkage. This study aimed to evaluate whether multi-parametric ultrasound (mpUS) radiomic kinetics, analyzed with a machine learning ensemble and interpreted with SHAP, could predict pathologic response to NAC. Methods: A prospective observational cohort enrolled 135 women with biopsy-proven stage II–III breast cancer treated with NAC within the multidisciplinary breast pathway shared between Vasile Goldis Western University of Arad and Victor Babes University of Medicine and Pharmacy Timisoara (Pius Brinzeu County Emergency Hospital). All patients underwent standardized QUS and SWE acquisitions at baseline, week 1, and week 3. Response was defined pathologically at surgery as residual cancer burden (RCB) class 0/I versus II/III. Group comparisons used Welch’s t-test, Mann–Whitney U, chi-square, and Fisher’s exact tests; correlations used Spearman’s rho. A stacked machine learning ensemble (four base learners—XGBoost, random forest, support vector machine, and L2-penalized logistic regression—combined by a separate second-stage logistic meta-learner) was trained with nested 10-fold cross-validation, bootstrap stability assessment, SHAP-based interpretability, and decision curve analysis. Results: Sixty patients (44.4%) were responders and 75 (55.6%) were non-responders. Responders showed greater week 3 increases in mid-band fit (3.4 ± 0.9 vs. 1.2 ± 0.8 dB, p < 0.001), entropy (0.7 ± 0.2 vs. 0.2 ± 0.2, p < 0.001), and more pronounced SWE mean stiffness reduction (−44.1 ± 9.7 vs. −12.1 ± 8.6 kPa, p < 0.001). The stacked ensemble integrating clinical, QUS, and SWE kinetic features reached an AUC of 0.93 (95% CI 0.88–0.97) versus 0.71 for the clinical-only model (all reported performance figures represent internal cross-validation only). SHAP analysis identified Δ MBF and Δ entropy at week 3 as the dominant features, with high bootstrap stability. Conclusions: Multi-parametric ultrasound radiomic kinetics integrated through a machine learning ensemble may provide an interpretable early-response biomarker for NAC in breast cancer, pending external validation. Full article