Search Results (421)

Background/Objective: The morphology of the flow–volume curve has emerged as a potential source of additional functional information by enabling the analysis of concavity, slope-based metrics, area-derived measures, and mathematical models extracted from the expiratory tracing. Therefore, the aim of this study was to map and describe the available evidence on morphological analysis methods of the expiratory flow–volume curve for the identification and characterization of fixed airflow obstruction. Methods: A scoping review was conducted following the methodological frameworks proposed by Arksey and O’Malley, Levac et al., the Joanna Briggs Institute, and the PRISMA Extension for Scoping Reviews (PRISMA-ScR). Studies published between 1 January 1990, and 31 December 2025, that evaluated morphological flow–volume curve metrics for the diagnosis or characterization of Chronic Obstructive Pulmonary Disease (COPD) were included, without language restrictions. Searches were performed in PubMed/MEDLINE, Embase, Scopus, Web of Science, IEEE Xplore, OpenGrey, and Google Scholar. Study selection was conducted by independent reviewers, with disagreements resolved by consensus, and data extraction was performed using a standardized form. Results were synthesized narratively and organized according to metric families. Results: The search identified 13,577 records; after duplicate removal and screening, 24 studies met the inclusion criteria. The evidence included observational studies, diagnostic validation studies, longitudinal cohorts, and methodological modeling studies. Identified metrics were grouped into four main categories: concavity and geometric indices of the flow–volume curve, expiratory slope and flow-decay metrics, area-based or volumetric-derived measures, and mathematical or computational models applied to the tracing. Concavity indices, the β-angle, slope-ratio, Peak Index, and the D parameter showed consistent associations with airflow obstruction, emphysema, small airway disease, or functional impairment. Expiratory slope metrics and Flow Decay demonstrated high diagnostic performance in several studies, whereas area-based measures such as AEX, AEX-FV, AreaFE%, and AUC3/AT3 integrated the overall loss of expiratory flow during forced expiration. Mathematical and computational models suggested that the complete shape of the curve contains additional diagnostic and prognostic information, although methodological variability and the need for external validation remain important limitations. Conclusions: Morphological analysis of the flow–volume curve represents a promising approach to complement conventional spirometry in the identification and characterization of fixed airflow obstruction. These metrics may provide additional information regarding airflow limitation, non-uniform lung emptying, emphysema, small airway disease, hyperinflation, and clinically relevant outcomes. Full article

We set out to fix a “contamination” problem in reconstruction-based Temporal Convolutional Network VAEs (TCN-VAEs) for cross-dataset IoT flow anomaly detection: when attack flows share an encoder window with benign flows, the shared latent code is allegedly distorted, inflating benign reconstruction error and producing false positive rates (FPRs) of 22–65% despite an ROC-AUC above 0.93. Our proposed fix, TCN-Pred, excludes the target flow from the encoder and scores it by next-flow prediction error, reducing FPR to 0.65–13%. We subjected this causal explanation to a battery of controlled ablations, holding architecture, decoder, loss, and thresholding fixed while varying one factor at a time. Each one falsified the original hypothesis: target inclusion/masking changes FPR by at most 0.001; context shuffling/reversing/zeroing changes it by at most 0.003; a context-blind constant-output predictor matches TCN-Pred’s FPR and F1 to three decimal places on all three datasets. The actual cause, confirmed on the original trained models with no retraining, is a scoring-granularity mismatch: the TCN-VAE threshold is calibrated from per-window errors averaged over 20 flows but applied to per-flow errors at evaluation (standard deviation $\approx \sqrt{20}\times$ higher, measured ratio 4.46 against a predicted 4.47). Recalibrating the identical model at matching granularity drops FPR from 22.7/47.6/64.6% to 0.65/5.0/12.5% on BoT-IoT, IoT-23 and ToN-IoT, closing 89–97% of the reported FPR gap without changing a single model weight. We report this diagnostic chain, together with an attack-prevalence sensitivity analysis, sample-disjoint calibration, normality diagnostics, and label-free and redundancy-aware (mRMR) feature-selection benchmarks, as a methodology other work should apply before attributing fixed-threshold performance to architecture. The pipeline is supervised source-domain feature selection followed by benign-only detector training, not fully unsupervised, a distinction we quantify later in the paper. Investigating dataset representativeness, we found that all three provided files reduce to only ≈6000 genuinely distinct flows via an undocumented row-duplication procedure, causing 97.8% BoT-IoT train/test near-duplicate overlap; a leakage-free re-evaluation changes FPR by only 0.23 percentage points. We also found that the TLS-metadata columns are already transformed upstream of every available artefact, so the proportion of genuinely TLS-encrypted flows cannot be recovered, and we soften the paper’s encrypted-traffic framing accordingly. Full article

Neural crest cells give rise to the craniofacial skeleton and multiple pigment cell lineages, yet how duplicated developmental regulators partition their ancestral functions after teleost-specific whole-genome duplication remains unclear. Here, we employed CRISPR/Cas9 to generate alx4a and alx4b single and double mutants in Nile tilapia (Oreochromis niloticus). By integrating phenotype, skeleton, transcriptome, quantitative PCR, and AlphaFold-based structural modeling analyses, we revealed their functional divergence. Loss of alx4a caused a regionally restricted reduction in iridophore-derived reflectance and abnormal cranial morphology, whereas alx4b single mutants showed no obvious phenotype under the conditions examined. By contrast, double mutants exhibited an almost complete loss of iridophore-derived structural coloration and substantially more severe cranial defects, accompanied by reduced calcein labeling in the opercular region, consistent with altered cranial mineralization. Skin transcriptomic and quantitative PCR analyses revealed marked downregulation of pnp4a and tfec, which are associated with iridophore differentiation and coloration, whereas no significant expression differences were detected for the iridophore survival-related genes ltk and mpv17. AlphaFold2-assisted HDOCK protein–DNA modeling yielded more favorable docking metrics for Alx4a than for Alx4b with the pnp4a promoter, supporting a potential Alx4a–pnp4a promoter interaction that requires experimental validation. In contrast, no significant genotype-dependent differences were detected in the measured abundance of melanophores, xanthophores, or erythrophores, and no obvious difference in gross dorsal-fin spine formation was observed under the conditions examined. Together, these findings reveal unequal functional contributions of alx4a and alx4b, with alx4a acting as the dominant paralog in iridophore-associated structural coloration and both paralogs contributing unequally to cranial development, and support pnp4a as a candidate downstream gene associated with Alx4a activity. Full article

Background/Objectives: Obesity is paradoxically associated with iron deficiency despite adequate dietary intake, driven by chronic inflammation and elevated hepcidin. Different dietary patterns may differentially affect iron metabolism in obese individuals, yet comparative evidence remains limited. Methods: We conducted a systematic literature review following PRISMA 2020 guidelines. Four databases (SciSpace, Google Scholar, PubMed) were searched through 2025 using terms related to obesity, iron deficiency, and three dietary patterns: Mediterranean diet, ketogenic diet, and intermittent fasting. Studies were screened using seven predefined criteria (three inclusion, four exclusion) with thresholds of ≥4.0/5.0 for abstract screening and ≥4.5/5.0 for full-text screening. Results: From 396 identified records (SciSpace n = 325, Google Scholar n = 57, PubMed n = 14), 38 studies were included after removing 62 duplicates and screening 334 unique records. Studies without accessible full text were excluded.The Mediterranean diet appears most protective for iron status due to its anti-inflammatory profile (omega-3 fatty acids, polyphenols, vitamin C) and bioavailable iron sources. Ketogenic diets may impair duodenal iron absorption through hepcidin-independent mechanisms and restrict dietary iron diversity. Intermittent fasting shows complex effects, remodeling iron metabolism with increased transferrin and decreased ferritin within physiological ranges. Weight loss per se consistently improves iron status by reducing adipose-driven inflammation and lowering hepcidin. Conclusions: Among the three dietary patterns examined, the Mediterranean diet appears most protective for iron status in obese individuals. The ketogenic diet may pose the highest risk due to restricted dietary iron diversity and potential hepcidin-independent absorption impairment. Direct comparative randomized controlled trials are urgently needed. Clinicians should routinely monitor iron biomarkers, including hepcidin, in obese patients undertaking any dietary intervention. Quantitative biomarker data from the 38 included studies showed serum ferritin reductions of 8–28%, hemoglobin levels remaining within clinically stable ranges, and IL-6 decreases of 15–42% across dietary patterns. Full article

Background. Radiographic bone loss is a primary determinant of periodontitis stage. Intraoral radiographs (periapical and bitewing) are the standard projections for assessing interproximal bone levels, yet their interpretation is subjective and poorly reproducible, and previous syntheses have pooled intraoral with panoramic imaging. Objectives. To appraise and synthesise studies developing or validating deep learning (DL) models for detecting, quantifying, staging or classifying alveolar bone loss on intraoral radiographs. Methods. Seven databases and six supplementary sources were searched from 1 January 2015 to 12 June 2026 (PROSPERO CRD420261455818, registered retrospectively). Two reviewers screened, extracted and appraised in duplicate using QUADAS-2 with AI-specific signalling questions, CLAIM and APPRAISE-AI; certainty was rated by GRADE. Heterogeneity precluded pooling; synthesis was narrative. Results. Sixteen publications reporting 15 independent datasets (2018–2026) were included (11 periapical, two bitewing, three mixed; 39–21,819 radiographs). The architectures employed comprised classification, segmentation, object-detection, keypoint-localisation and transformer-based models. Accuracy for binary detection ranged from 0.73 to 0.97, Dice coefficients reached ≥0.91, and intraclass correlation with expert measurement was 0.75–0.85. Performance fell for multiclass staging, posterior sites and furcations. Only two studies used an external test set; none was prospective; risk of bias was mostly high or unclear. Conclusions. Performance lies within the range observed for calibrated readers, but the evidence is dominated by small, single-centre, retrospective datasets with annotation-based reference standards and almost no external validation; certainty is very low. Deep learning is best regarded as a clinician-supervised adjunct for screening, triage and quality assurance rather than an autonomous diagnostic device. Full article

All taxa of plants have undergone several rounds of whole-genome duplication (WGD), accompanying interspecific and intergeneric crosses; subsequently, some part of one or both parent genomes in hybrid plants can be eliminated. The objective of this study was to evaluate the relationships of the intergeneric hybrid ×Agrotrigia (Poaceae) species with the taxa of parental genera Agropyron and Elytrigia and to determine the distribution as well as conservation or loss of parental genomes in the genomes of hybrid species. Molecular phylogenetic analysis of nuclear (ITS, ETS) and several chloroplast DNA markers confirmed that the most likely parents of this hybrid were really species of Agropyron and Elytrigia. The compositions of ribotypes (sequences of the 18S–ITS1–5.8S rDNA region) assessed by next-generation sequencing (NGS) showed that the genomes of hybrid species of ×Agrotrigia hajastanica and of the sample of ×A. androssovii from Turkmenistan carry ribotypes of both Agropyron and Elytrigia. However, the samples of ×A. kotovii and ×A. androssovii from Pskov Oblast bear ribotypes of the Elytrigia type only, whereas the genome of one sample of the ×Agrotrigia genus collected in Stavropol Krai consists exclusively of two clusters of Agropyron-type ribotypes (P genome) and may represent a new species. Therefore, these two (or three) species may be subject to the elimination of portions of the genome of one of the parents, though the extent of elimination may be different. Full article

Background: NTRK gene fusions are established oncogenic drivers in a diverse spectrum of mesenchymal neoplasms. Although classically described in pediatric entities, NTRK-rearranged sarcomas also occur in adults, where their clinicopathologic features, genomic context, and response to TRK inhibition are less well characterized. Methods: We retrospectively queried a national referral genomics database to identify sarcomas in patients >18 years harboring pathogenic NTRK1, NTRK2, or NTRK3 fusions. Gastrointestinal stromal tumors, duplicate specimens, and cases lacking digitized hematoxylin and eosin slides were excluded. Fusions were identified by whole-transcriptome sequencing, co-occurring genomic alterations by exome-based sequencing, and real-world survival and time on TRK inhibitor therapy were derived from linked insurance claims data; fusion-negative sarcomas and NTRK-rearranged non-sarcoma tumors from the same database served as comparison cohorts. Results: Among 13,040 profiled sarcomas, 19 adult tumors with pathogenic NTRK fusions were identified (median age, 43 years; range, 21–77), most of which were high grade (68%) and advanced stage (63% stage IV). Histology was heterogeneous, including spindle cell sarcoma (53%), pleomorphic sarcoma (21%), and tumors corresponding to defined entities such as NF1-associated malignant peripheral nerve sheath tumor and MDM2-amplified dedifferentiated liposarcoma (11% each). NTRK1 and NTRK3 fusions were equally frequent (9 cases each); fusion partners were diverse, with TPM3 (n = 5), EML4 (n = 2), and TFG (n = 2) recurrent and other partners non-recurrent. Additional genomic alterations were common and heterogeneous (72%), including high genome-wide loss of heterozygosity and infrequent but recurrent alterations involving the TERT promoter, NF1, and RB1. All evaluable tumors showed transcriptional activation of the NTRK fusion and increased MAPK pathway activity compared with fusion-negative sarcomas. Nine patients received TRK inhibitors; median time on larotrectinib was 12.5 months, similar to that observed in NTRK-rearranged non-sarcoma tumors, but treatment duration was variable. Conclusions: Adult sarcomas harboring NTRK fusions are rare, morphologically heterogeneous, and biologically diverse. NTRK fusion status alone may not fully capture oncogenic dependence and should be interpreted within the broader clinicopathologic and genomic context. Full article

Electric-vehicle gearboxes remain key design elements because they determine how motor speed and torque are converted into wheel speed and tractive effort over a driving cycle. This design-oriented scoping review synthesizes EV gearbox architectures, gear ratio selection, efficiency losses, NVH, planetary and compound planetary systems, lubrication, thermal behavior, reliability, manufacturability, and cost within one evidence-informed architecture-selection perspective. A structured search of Scopus, IEEE Xplore, ScienceDirect, SpringerLink, and MDPI identified 312 records; after removal of 71 duplicates, screening of 241 titles and abstracts, and full-text assessment of 61 articles, 40 sources formed the reproducible structured-search core. A gap-directed supplementary search then added 12 sources in underrepresented areas, producing a 52-source synthesis set. The revised analysis reports publication trends, evidence-level distributions, technical-focus frequencies, and a dimension-separated evidence-count table for ratio count, gear train topology, and integration level. The evidence indicates that single-speed reduction gearboxes remain the mature baseline for many passenger EVs, whereas two-speed, multi-speed, planetary, compound planetary, and integrated e-axle solutions require application-specific justification based on system-level benefits and risks. An illustrative screening calculation demonstrates the framework logic without being presented as production-level validation. The principal gaps are experimentally validated loss and NVH maps, coupled efficiency–thermal–lubrication–durability analysis, reliability-aware mission-profile validation, standardized benchmarks, and transparent comparison of compound planetary and integrated e-axle systems. Across heterogeneous study conditions, reported energy benefits range from 2.4% for fixed-ratio optimization to 15% for selected multi-speed comparisons; these results are not pooled because the vehicles, motor maps, drive cycles, loss models, and validation methods differ. Full article

Background: Static cold storage (SCS) remains the conventional standard for liver graft preservation; however, ischemia–reperfusion injury during storage may contribute to graft dysfunction, particularly with extended criteria and marginal donors. Machine perfusion (MP) has emerged as a promising alternative, yet existing systematic reviews are limited by their focus on individual perfusion modalities or selected donor populations. We performed a comprehensive systematic review and meta-analysis with pre-specified modality-specific subgroup analyses comparing all MP strategies with SCS in adult liver transplantation. Methods: This study was conducted in accordance with PRISMA 2020 guidelines and registered in PROSPERO (CRD420261355605). MEDLINE, Embase, and PubMed were systematically searched for comparative studies published between 2015 and 2025. Primary outcomes were early allograft dysfunction (EAD), primary non-function (PNF), and 1-year graft survival. Secondary outcomes included biliary complications, hepatic artery thrombosis (HAT), and postoperative transaminase levels. Pre-specified subgroup analyses were performed according to perfusion modality (NMP versus HMP/HOPE). Results: A total of 1448 records were identified. After removal of 309 duplicates and screening, 21 studies comprising 3665 patients were included. Compared with SCS, MP was associated with a significantly lower risk of EAD (RR 0.67, 95% CI 0.48–0.94; p = 0.020), PNF (RR 0.31, 95% CI 0.11–0.84; p = 0.020), and graft loss at one year (RR 0.54, 95% CI 0.36–0.81; p = 0.003; I² = 0%). Subgroup analysis demonstrated that reductions in EAD and PNF were driven by HMP/HOPE strategies (EAD: RR 0.66, 95% CI 0.45–0.98; PNF: RR 0.23, 95% CI 0.07–0.79), whereas NMP did not achieve statistical significance for these endpoints. No significant differences were observed in biliary complications or HAT. Conclusions: Machine perfusion is associated with improved early graft function, reduced primary non-function, and superior 1-year graft survival compared with static cold storage. The benefit for early graft outcomes is driven by hypothermic strategies. These findings provide modality-specific evidence to guide preservation strategy selection in clinical practice. Full article

Brassica napus L. is one of the most important oil crops in the world, and improving its nitrogen efficiency is a key strategy for enhancing low-nitrogen tolerance and increasing yield. Ammonium transporters (AMTs) play critical roles in NH₄⁺ transport in plants and significantly influence nitrogen use efficiency and yield. To identify promising candidate AMT genes for rapeseed improvement, this study systematically analyzed the evolution and expression of AMT genes across the Archaeplastida plants, especially in Brassica species of the U’s triangle. A total of 368 AMT genes were identified from 35 Archaeplastida species, including 180 AMT1 and 188 AMT2 homologs. Gene duplication analysis revealed that small-scale duplication (SSD) was the primary mechanism driving gene expansion from aquatic algae to angiosperms in both AMT1 and AMT2 families, which were under the influence of purifying selection. In the U’s triangle, allopolyploidization, particularly whole-genome duplication (WGD), was the primary mechanism for AMT expansion, accompanied by gene loss. Expression profiling indicated that most BnAMTs respond to hormonal and low-nitrogen signals and exhibit tissue-specific expression patterns. Notably, four candidate genes (BnAMT1;5, BnAMT1;12, BnAMT2;2, BnAMT2;4) exhibited high expression levels and responsiveness to low-nitrogen stress. Haplotype analysis further linked specific polymorphisms in BnAMT1;5 and BnAMT2;2 to variations in plant height and yield. Collectively, these findings elucidate the evolutionary processes and regulatory mechanisms of AMTs, laying a foundation for enhancing nitrogen utilization efficiency in B. napus and other crops. Full article

Background: Native nephrectomy is frequently required in autosomal-dominant polycystic kidney disease (ADPKD) before or during transplantation, but the optimal minimally invasive approach is unsettled, and it is unclear whether the pattern of post-operative complications tracks with operative technique. We report a retrospective single-centre experience of hand-assisted laparoscopic (HAL) native nephrectomy and, alongside it, a technique-stratified scoping review of complications. Methods: We retrospectively reviewed all consecutive adults undergoing HAL native nephrectomy—with an infra-umbilical midline hand-port and free intraperitoneal cyst rupture—in preparation for transplantation in the period between December 2019 and December 2025. In parallel, we performed a PRISMA-ScR-compliant scoping review (MEDLINE, Embase, Scopus) of minimally invasive ADPKD nephrectomy, with duplicate independent screening and extraction, stratifying complications by operative approach and cyst-decompression method. No quantitative pooling was undertaken. Results: Twenty-three patients (mean age 52.8 ± 9.9 years; 87% dialysis-dependent; 78% for transplant preparation) were included. Median operative time was 102 min (IQR 90–122) with minimal blood loss, one transfusion (4%), and no open conversion. Complications occurred in 8/23 (35%) and were bowel-predominant: one small-bowel perforation, two obstructions, and one ileus—three of Clavien–Dindo grade IIIb, all in right-sided nephrectomies and independent of specimen weight. Peri-operative mortality was 1/23 (4%), from a non-technique-related mycotic aortic dissection. Of 481 records screened, 19 studies met inclusion; the cyst-decompression method was reported in only 7 (37%). Bowel events clustered in series using free intraperitoneal cyst rupture or puncture and were largely absent where decompression was contained, a pattern crossing platform boundaries and that is mechanistically consistent with intraperitoneal spillage of cyst contents. Conclusions: HAL native nephrectomy is a rapid and feasible means of removing massively enlarged polycystic kidneys before transplantation but, in our experience, carries a bowel-predominant morbidity that clustered in right-sided procedures and was independent of specimen weight. The sparse literature is consistent with—but cannot confirm—a relationship to intraperitoneal cyst spillage rather than to the hand-assisted approach itself. Whether contained cyst decompression can preserve operative efficiency while reducing bowel morbidity is a hypothesis warranting prospective study. Full article

Members of the yellow gene family encode conserved Yellow proteins with diverse roles in insect pigmentation, cuticle formation, and reproduction, making them promising targets for RNA interference (RNAi)-mediated pest control strategies. However, little is known about their phylogeny and functions in the brown planthopper (Nilaparvata lugens), a devastating rice pest that serves as a vector for viral rice diseases. Here, we identified and characterized 11 yellow genes in N. lugens, which showed distinct structures and expression profiles. Phylogenetic analysis revealed that N. lugens has retained orthologs of yellow-y, -b, -d, -e, -g, -g2, -h, and -x but lacks those of yellow-c and -f, suggesting lineage-specific gene loss. Nine of the eleven NlYellow genes were localized to chromosome 8, with several positioned in close genomic proximity. The clustering of these loci suggests that tandem duplication events contributed to the expansion of the NlYellow gene family. NlYellow-b exhibited the highest transcript levels among all identified NlYellow genes, particularly in the female ovipositor, and functional characterization via RNAi revealed that it is essential for molting, wing development, and female fertility. Knockdown of NlYellow-b in fourth-instar nymphs caused lethal molting defects and wing malformation and significantly reduced offspring production. These findings highlight the dual roles of NlYellow-b in development and reproduction, advance our understanding of yellow gene function in insects and highlight NlYellow-b as a candidate for RNAi-based management of N. lugens. Full article

Artificial intelligence, digital payments and platform-based services are reshaping the operating conditions of Africa’s informal economy and micro-enterprise sector. While mobile money, digital marketplaces, app-mediated logistics and algorithmic scoring systems are commonly presented as instruments of financial inclusion and enterprise modernisation, their effects on informal traders remain uneven, conditional and under-governed. This systematic review synthesises recent peer-reviewed evidence on AI-mediated digitalisation pathways for informal and micro-enterprises in Africa, with particular attention to mobile money, platform payments, app-based logistics, digital credit, algorithmic management and platform governance. Following PRISMA-informed systematic review procedures, this review analyses 60 peer-reviewed, DOI-bearing articles published between April 2022 and June 2026 through a mechanism–outcome synthesis approach. The final corpus was selected through database searching, duplicate removal, title-and-abstract screening, full-text eligibility assessment, quality appraisal and mechanism–outcome coding. The findings show that digitalisation can expand market access, reduce cash-handling risks, create transaction histories, strengthen customer reach, improve operational continuity and support household resilience. However, the same digital infrastructures may also intensify livelihood vulnerability through opaque scoring, unexplained account freezes, fee shocks, exclusionary verification procedures, algorithmic ranking losses, data extraction and weak dispute-resolution mechanisms. The review therefore argues that informal enterprise digitalisation should not be understood only as a technology adoption issue, but as a socio-technical systems governance challenge. The article contributes a governance-and-risk framework linking local infrastructure, platform and payment design, AI (artificial intelligence) mediation, adoption conditions and livelihood outcomes. It further identifies minimum policy and design protections required for inclusive and resilient participation, including transparent fees, proportionate verification, human appeal channels, explainable restrictions, data-use consent, timely settlement and contingency mechanisms during digital outages or erroneous flags. The review concludes that sustainable digital inclusion for African informal micro-enterprises depends not merely on access to digital tools, but on the fairness, transparency, recoverability and accountability of the systems through which traders participate. Full article

The early detection of psycho-emotional risks remains challenging despite its growing importance. Most existing models rely on a single data type, mainly questionnaires or text, and operate as “black boxes”, limiting practical use. Psycho-emotional states are multidimensional, reflected in textual, structured, and temporal digital signals. Ignoring this complexity may result in information loss and lower prediction accuracy. This paper presents an explainable text-based computational framework for psycho-emotional risk classification using public datasets. Record-level structured information was used only when it was available within the same original observation and was not created by matching records across datasets. The study did not integrate observations across datasets or perform cross-dataset fusion; these aspects are considered potential directions for future research. Implemented in Python using PyTorch, the model was evaluated on two open-text datasets. The BERT-based configuration achieved accuracy of 0.593 ± 0.009 and an ROC-AUC of 0.860 ± 0.006, while RoBERTa-base improved the performance to 0.666 ± 0.005 accuracy and a 0.896 ± 0.004 ROC-AUC under five-fold cross-validation. The results demonstrate that classification quality depends on encoder selection, preprocessing, dataset characteristics, duplicate handling, calibration, and the way that available record-level information is represented. Therefore, the findings should be interpreted as record-level computational classification results rather than the clinical validation of psycho-emotional risk assessment. Full article

Background/Objectives: Intermittent ureteropelvic junction obstruction (UPJO), classically termed Dietl’s crisis, may be missed when imaging is obtained outside symptomatic periods. The challenge is amplified in duplicated collecting systems, where the obstructed moiety may not be recognized on screening ultrasonography. Case Presentation: A 14-year-old boy presented with recurrent severe right flank pain triggered by heavy fluid intake, associated with nausea and vomiting and separated by symptom-free intervals. An initial renal ultrasound performed between attacks was normal. One week later, the same pain pattern recurred together with a febrile urinary tract infection. Computed tomography urography (CTU) demonstrated an incomplete right duplex collecting system with a bifid ureter, marked hydronephrosis of the lower moiety, delayed contrast excretion, and focal narrowing at the lower-moiety ureteropelvic junction adjacent to one crossing artery and one crossing vein. Diuretic ^99mTc-mercaptoacetyltriglycine (MAG3) renography documented obstructive drainage, with a post-furosemide drainage half-time (T1/2) > 20 min, differential renal function of 51% on the right, and split moiety function of 31% (upper) and 20% (lower). The patient underwent transperitoneal robot-assisted dismembered Anderson–Hynes pyeloplasty of the lower moiety with the reconstructed ureteropelvic junction repositioned anterior to the crossing vessels; a 6 Fr × 26 cm double-J stent was placed and subsequently removed at 4 weeks postoperatively. Total skin-to-skin operative time was 75 min, estimated blood loss < 100 mL, and the postoperative course was uneventful. At early 3-month follow-up, the patient remained free of Dietl-type episodes, and ultrasonography showed marked reduction in lower-moiety hydronephrosis. Selective postoperative CTU, obtained because of the unusual bifid anatomy, demonstrated patent drainage. Conclusions: A normal interval ultrasound should not exclude intermittent UPJO when the history is stereotypical, and cross-sectional plus functional imaging is decisive when duplex anatomy and crossing vessels coexist. Full article