Search Results (1,767)

Fatigue crack propagation prediction plays a critical role in structural health monitoring and remaining useful life (RUL) assessment of engineering structures. However, conventional particle filter (PF) algorithms may suffer from particle impoverishment and insufficient particle diversity, which can adversely affect prediction accuracy and stability. To address these limitations, a hybrid genetic algorithm–particle filter (GA-PF) is developed for fatigue crack propagation prediction by incorporating genetic operations, including selection, crossover, and mutation, into the PF framework to optimize particle distribution and enhance global search capability. The proposed method is evaluated using fatigue crack growth experimental data, and its performance is compared with that of the conventional PF algorithm. The results show that the GA-PF method achieves improved prediction performance for fatigue crack propagation and remaining useful life estimation. At 255,000 cycles, the GA-PF algorithm predicted a median RUL of 22,500 cycles, with a relative RUL error of 9.04%, whereas the conventional PF algorithm resulted in a relative RUL error of 45.41%. These results indicate the potential benefit of introducing genetic optimization into the particle filter framework for fatigue crack propagation prediction. The findings further suggest that the hybrid GA-PF method can improve predictive performance compared with conventional PF on the tested dataset. Full article

Background/Objectives: Recurrent pregnancy loss (RPL) has traditionally been investigated predominantly through maternal factors, while the clinical role of paternal assessment remains inconsistently defined. Current guidelines differ substantially regarding semen analysis, sperm DNA fragmentation (SDF), genetic testing, and referral for andrological evaluation. This review aimed to compare contemporary guideline recommendations, critically appraise the directness, prognostic value, and clinical utility of the supporting evidence, and classify paternal assessment strategies as routine, selective, or investigational. Methods: A structured narrative review was conducted using PubMed and Scopus searches through June 2026. International RPL, obstetric, reproductive medicine, and andrology guidelines were compared. Evidence from systematic reviews, meta-analyses, clinical studies, and clinically relevant molecular investigations was evaluated according to its directness to RPL populations, diagnostic and prognostic value, and evidence that test-guided interventions improve miscarriage or live-birth outcomes. Results: Routine paternal assessment should include age, reproductive and medical history, body weight, lifestyle, medication exposure, and relevant environmental or occupational risks. Conventional semen analysis is appropriate primarily when RPL coexists with infertility or suspected male reproductive disease. SDF is the most extensively studied advanced paternal biomarker and is frequently elevated in RPL cohorts, but findings vary by assay and comparator population, while prospective prediction of subsequent live birth and benefit from SDF-directed treatment remain unproven. Parental karyotyping has established counselling value but should be risk-stratified. Sperm aneuploidy testing, oxidative stress assays, seminal microbiome profiling, epigenetic biomarkers, and biomarker-directed interventions remain investigational. Conclusions: Paternal assessment in RPL should be couple-based, clinically targeted, and evidence-informed. Current evidence supports routine clinical evaluation, selective use of semen analysis, SDF testing, genetic assessment, and reproductive urology referral, and restriction of unvalidated biomarkers and treatments to research settings. Full article

Soft deformable materials such as elastomers, biological tissues, and polymeric membranes are widely used in modern engineering applications including biomechanics, soft robotics, and flexible electronics. Accurate identification of their constitutive parameters is therefore essential for reliable mechanical modeling and design. Membrane inflation or bulge tests are commonly used for this purpose, where material parameters are typically identified from pressure–deflection measurements. However, such measurements generally require optical systems to capture membrane deformation, which increases experimental complexity. In this work, we propose a surrogate-assisted inverse identification framework for determining hyperelastic material parameters using pressure–volume data obtained from membrane inflation tests, thereby eliminating the need for optical deformation measurements. To reduce the computational cost associated with repeated forward simulations, an Artificial Neural Network (ANN) surrogate model is trained using numerically generated pressure–volume data from finite-element simulations. The trained ANN efficiently predicts the pressure response of the membrane for different material parameters and volume influx values. A Genetic Algorithm (GA) is then employed to identify the optimal parameters by minimizing the discrepancy between measured and predicted responses. The proposed GA–ANN framework is demonstrated for the Mooney–Rivlin hyperelastic model and accurately recovers material parameters for both noise-free and noisy datasets, providing a computationally efficient and robust methodology for the characterization of soft membranes. Full article

Epilptogenesis is a long-term process that involves the transformation of a healthy brain into a seizure-producing brain. Since approximately 30% of epilepsy patients suffer from drug-resistant seizures, the concept of inhibiting the epileptogenesis process and thus preventing seizures has emerged. The search for effective methods of inhibiting epileptogenesis is possible thanks to animal models, which include kindled seizures; models based on the induction of status epilepticus resulting in subsequent spontaneous recurrent seizures, or brain trauma; and genetic models. Blood–brain barrier dysfunction, inflammatory processes in the brain, and oxidative stress appear to play a major role in epileptogenesis. This prompted testing of a number of anti-inflammatory agents and antioxidants in the epileptogenic process. One noteworthy finding was that losartan (an antihypertensive drug), as a TGF-β antagonist, proved effective in inhibiting epileptogenesis due to blood–brain barrier damage. Due to the many mechanisms involved in the process of epileptogenesis, it seems that the use of a combination of drugs will be an effective method of inhibiting it. The most promising combination includes levetiracetam (a second-generation antiseizure drug), atorvastatin, and ceftriaxone (a beta-lactam antibiotic), which effectively inhibits spontaneous seizures in animals experiencing status epilepticus. Any clinical trials on the inhibition of epileptogenesis must take into account the fact that a small percentage of patients develop epileptic seizures after stroke or brain injury. Recently suggested markers predicting a high probability of epileptic seizures after brain damage may facilitate appropriate patient selection for studies on inhibition of epileptogenesis. Full article

Thalassemia represents the world’s most prevalent inherited hemoglobin disorder, affecting approximately 4.4 per 10,000 live births globally. Accurate genetic characterization is indispensable both for definitive diagnosis and for lifetime clinical monitoring. The past two decades have witnessed a paradigm shift from conventional protein-based assays toward comprehensive molecular techniques, including next-generation sequencing (NGS) and third-generation (long-read) sequencing, which in turn have enabled reproductive applications such as preimplantation genetic testing for monogenic disease (PGT-M) to identify unaffected embryos before implantation. (1) To systematically evaluate the molecular techniques available for confirming the diagnosis of alpha- and beta-thalassemia, including their diagnostic accuracy, indications, and limitations; (2) to examine how genotype–phenotype correlation and genetic modifier profiling inform clinical prognosis and therapeutic decision-making; and (3) to define evidence-based genetic monitoring parameters for longitudinal follow-up of patients receiving transfusions, iron chelation, and novel curative therapies including gene therapy. A comprehensive narrative review was conducted by systematically searching PubMed/MEDLINE for English-language peer-reviewed articles published between January 2000 and December 2024. Forty-three studies were ultimately included after applying predefined inclusion and exclusion criteria. Quality of included studies was assessed using SANRA (Scale for the Assessment of Narrative Review Articles). HPLC and capillary electrophoresis remain first-line phenotyping tools; DNA-based confirmation is mandatory for complete genotyping. Among known, previously characterized mutations, NGS-based targeted panels achieve > 95% detection sensitivity, but they require MLPA co-testing or long-read sequencing to detect structural variants such as large deletions. Genotype–phenotype prediction is substantially improved, though not rendered fully deterministic, by profiling three major modifier loci: XmnI (Gγ), BCL11A, and HBS1L-MYB. PGT-M using NGS achieves near-complete genotyping accuracy (>99%) with live birth rates of 40–60% per frozen embryo transfer cycle. For patients receiving curative gene therapy (exagamglogene autotemcel/Casgevy), molecular follow-up protocols spanning 15 years are now recommended. Cardiac T2* MRI remains the most reliable non-invasive tool for iron overload follow-up, superior to serum ferritin alone. A tiered, genotype-informed approach—combining HPLC/CE phenotyping, targeted molecular diagnostics, genetic modifier profiling, and periodic re-evaluation—optimizes diagnostic precision and guides individualized management across the thalassemia spectrum. Integration of PGT-M and long-read sequencing into standard care pathways, alongside robust gene therapy follow-up protocols, will define the next era of thalassemia genetics. Full article

As an endemic woody plant resource widely distributed in the arid regions of northwestern China, Hippophae rhamnoides subsp. sinensis Rousi possesses both ecological and medicinal value. Elucidating the effects of climate and soil conditions on the composition, structure, and function of its root-associated bacterial communities is of practical significance for the development and utilization of these indigenous plant resources in this water-limited region. In this study, root samples of H. rhamnoides were collected from 12 sampling sites in the arid region of Northwest China. High-throughput amplicon sequencing was employed to examine bacterial composition, alpha and beta diversity, molecular co-occurrence networks, and PICRUSt-based functional prediction. Mantel tests and redundancy analysis (RDA) were further applied to identify what is associated with shaping bacterial community structure. The main results are summarized as follows: (1) There were significant differences in the number of ASVs among the various sampling sites, with the P8 site having the highest number (435) and the P5 site having the lowest (156). The dominant phyla in the community were Proteobacteria, Actinobacteria, and Cyanobacteria. (2) Both α and β diversity showed significant differentiation among the 12 sampling sites. The Ace and Chao1 indices of P8 sampling sites were the highest, while P5 sampling sites were the lowest. In terms of community aggregation, P7 and P12 sampling sites showed tighter clustering, whereas P4 and P5 sampling sites showed more scattered bacterial assemblages. (3) Functional prediction suggested that metabolism, environmental information processing, and genetic information processing functional potential may all be dominant across 12 sampling sites. The abundance of environmental information predicted that the processing functional potential of the P9 sampling site was higher than that of the other 11 sampling sites, while the genetic information processing functional potential was low. (4) Cluster analysis grouped the 12 sampling sites into two groups: sampling sites P10, P11, and P12 were grouped into Group 1, while the remaining 9 sampling sites were grouped into Group 2. (5) RDA revealed that altitude was associated with shaping the root endophytic bacterial community structure of H. rhamnoides, followed by soil total nitrogen. Taken together, the H. rhamnoides populations investigated and sampled in this study were predominantly distributed in neutral-to-alkaline arid soils. The relevant environmental factors are significantly correlated with the alpha diversity patterns of root endophytic bacteria of this species, and they can modulate the community assembly processes, functional allocation characteristics, and co-occurrence network structures of these root endophytic bacteria. Full article

Background/Objectives: Termination of pregnancy (TOP) following a prenatal diagnosis of congenital heart disease (CHD) is a complex decision shaped by clinical, ethical, and psychosocial factors. This study evaluated the clinical factors associated with parental acceptance of TOP after prenatal diagnosis of CHD in a multidisciplinary counselling setting. Methods: This retrospective cohort study was conducted at a tertiary referral center where fetal CHD cases are evaluated in a multidisciplinary perinatology council. Pregnancies with a prenatal CHD diagnosis for which TOP was medically recommended between December 2023 and February 2026 were included. Maternal, fetal, and genetic data were analyzed. Cardiac severity was classified using the fetal cardiovascular disease severity scale. Because the cohort included only 62 pregnancies, a simplified multivariable logistic regression model with three clinically prespecified variables (four parameters: gestational age, cardiac severity, and genetic-evaluation status) was used to identify variables associated with termination acceptance. Results: Sixty-two pregnancies were included; 41 (66.1%) accepted termination and 21 (33.9%) continued the pregnancy. Maternal characteristics and gestational age at diagnosis were similar between groups. In the multivariable model, genetic-evaluation status was the only variable independently associated with termination acceptance. Compared with cases without genetic testing, both major chromosomal/pathogenic anomalies (aOR 4.97; 95% CI 1.29–19.11; p = 0.020) and a normal genetic-evaluation status (aOR 4.71; 95% CI 1.07–20.77; p = 0.041) were associated with higher termination acceptance. Cardiac severity and gestational age were not independently associated with parental decision. Conclusions: Genetic-evaluation status was associated with parental acceptance of termination after prenatal CHD diagnosis in a multidisciplinary counselling setting; given the small sample size and the selected, council-recommended cohort studied, this association should be interpreted as hypothesis-generating rather than as evidence of a causal or independent predictive effect. Full article

Background: Coeliac disease (CD) is a highly heritable autoimmune disease. Given the high risk among first-degree relatives, early screening and prevention are essential, yet clinical guidelines vary. This review analyzed clinical practice guidelines issued by leading European, British, and North American organisations over a 12-year period (2014–2026) regarding genetic screening and lifestyle/dietary prevention strategies. Methods: A systematic search was conducted across official databases of prominent societies (ESSCD, UEG, ESPEN, NASPGHAN, AGA, ESPGHAN, WGO, BSG, ACG) for English-language guidelines and position papers. Extracted statements addressing genetic testing (HLA-DQ2/DQ8) and early-life risk-modifying strategies were coded into three thematic domains: (1) genetic predisposition, (2) lifestyle prevention or (3) both. Results: Eleven manuscripts yielded 399 statements, categorized into genetic predisposition (n = 23, 5.8%), lifestyle prevention (n = 30, 7.5%) and integrated approaches (n = 2, 0.5%), with the remainder (n = 344, 86.2%) addressing unrelated clinical topics. Universal consensus confirmed the high negative predictive value of HLA-DQ2/DQ8 testing to rule out CD, whereas dietary strategies (breastfeeding duration and timing of gluten introduction) showed no protective effect. ESPGHAN exclusively provided evidence regarding early-life high-risk genotypes and concluded that risk-stratified dietary guidance based on specific HLA profiles remains currently unsupported. Conclusions: Current CD guidelines demonstrate substantial international consensus regarding the role of genetic testing in disease exclusion and risk stratification. However, recommendations integrating genetic susceptibility with preventive lifestyle interventions remain scarce. Future research should focus on generating robust evidence to support precision prevention approaches and facilitate the harmonization of international guidelines. Full article

RASopathies are a group of genetic disorders caused by germline variants affecting the RAS/MAPK pathway. Their shared phenotypic features—craniofacial anomalies, cardiac defects, cutaneous findings, neurodevelopmental issues, and cancer predisposition—make diagnosis challenging, especially since most lack standardized clinical criteria. This study aimed to develop a practical diagnostic algorithm based on high-frequency Human Phenotype Ontology (HPO) features. Key clinical variables for each RASopathy were identified through HPO, PubMed, and GeneReviews. Only findings present in 80–99% of cases or supported by expert consensus were included. A decision-tree algorithm was constructed and preliminarily evaluated using a blinded cohort of 50 individuals with confirmed molecular diagnoses. Patients were eligible for inclusion if they met the following criteria: (1) molecularly confirmed diagnosis of a RASopathy by next-generation sequencing identifying a pathogenic or likely pathogenic variant; (2) availability of complete phenotypic records in the institutional clinical database; and (3) age at evaluation between 0 and 18 years. Patients were excluded if phenotypic data were incomplete or if molecular confirmation was absent. The algorithm integrates phenotypic patterns and genotype–phenotype correlations. Validation showed 78% accuracy (95% CI: 64.0–88.4%) for clinical diagnosis and 66% accuracy (95% CI: 51.2–78.8%) for molecular prediction. To our knowledge, this is the first HPO-based diagnostic algorithm for the clinical and molecular approach to RASopathies. It provides a structured, accessible tool to improve early recognition and guide molecular testing, particularly for the RASopathy subtypes represented in the validation cohort. Further external validation including underrepresented subtypes is required. Full article

This paper proposes a priority-aware EP-ALOHA framework with predictive radio resource allocation for heterogeneous machine-to-machine (M2M) devices in 5G massive machine-type communication (mMTC) networks. The proposed framework extends conventional EP-ALOHA by introducing M2M priority classes, priority-dependent delay constraints, and Exploration Phase resource block (RB) allocation. The RB-allocation problem is formulated as an integer-constrained optimization problem, where the objective is to improve effective radio channel utilization while satisfying delay constraints for different priority classes. A Genetic Algorithm-based optimization procedure is used to generate optimization-derived RB-allocation targets under different traffic and system parameter settings. These targets are then used to train and evaluate predictive RB-allocation models, including Random Forest, Neural Network, Gradient Boosting, and Linear Regression. The simulation results show that the proposed priority-aware EP-ALOHA method achieves a higher successful access probability than the considered baseline schemes within the feasible operating region. For predictive RB allocation, the Neural Network achieved the best test-set performance, with MSE = 25.5002, RMSE = 5.0498 RBs, MAE = 3.2629 RBs, and R² = 0.9810. A separate computational evaluation showed that Random Forest inference reduced the mean allocation-decision time from 213.54 ms for GA-based optimization to 15.20 ms, corresponding to a 14.05-fold speed-up on the evaluated platform. In addition, M2M device activity probability forecasting is evaluated using Bayesian estimation, LSTM, moving average, and exponential smoothing. LSTM achieves the lowest forecasting error, while exponential smoothing provides a close and computationally simpler alternative. The results indicate that the proposed framework can support proactive and priority-aware resource management for heterogeneous M2M traffic, while the learning-based components are used as approximation and forecasting tools rather than as universally superior solutions. Full article

Background/Objectives: Pediatric acute pancreatitis (AP) is increasingly recognized as a clinically significant disease, yet Central and Eastern European cohort data remain limited. Acute recurrent pancreatitis (ARP) affects a substantial proportion of these children and may reflect distinct underlying etiologies. This study aimed to characterize the etiological spectrum, disease severity, and hospitalization outcomes of AP and ARP in a pediatric tertiary referral population, and to identify early clinical predictors of severity. Methods: We retrospectively analyzed 63 children hospitalized between 2018 and 2025 with 77 documented episodes of AP. Diagnosis followed INSPPIRE criteria, and severity was graded using the 2017 NASPGHAN classification. Etiologies, clinical presentation, laboratory parameters, imaging findings, and hospitalization length were compared between AP and ARP groups, across severity and etiological complexity categories using appropriate non-parametric and permutation-based methods. Results: Genetic etiologies predominated in ARP (37.0%), whereas idiopathic and infectious causes were more common in first-episode AP (24.0% and 14.0%, respectively; overall p < 0.001). Severity distribution did not differ between AP and ARP, with mild disease accounting for the majority of episodes in both groups. Serum albumin was significantly lower in moderate/severe episodes (p = 0.030). Within the single-episode subgroup, etiological complexity emerged as a significant predictor of prolonged hospitalization, with complex multifactorial or systemic etiologies associated with markedly longer stays than idiopathic or single-factor disease (Welch ANOVA p = 0.007). Conclusions: In this Romanian pediatric cohort, genetic causes dominate ARP, while idiopathic and infectious etiologies characterize first-episode AP, supporting a stepwise approach in which comprehensive etiological work-up, including genetic testing, is prioritized after recurrence. The predominance of genetic causes in ARP should be interpreted with caution, as genetic testing was applied selectively, predominantly after recurrence. Recurrence status alone does not predict severity, whereas etiological complexity at first presentation and hypoalbuminemia represent practical, accessible early markers for clinically assessing more severe disease. Full article

Background/Objectives: GWASs have identified more than 250 prostate cancer (PCa) predisposition loci, predominantly in European and partly Asian cohorts. The Kazakh population is markedly under-represented in international genetic studies, limiting existing risk models. This study aimed to analyze the distribution of 102 PCa-associated single-nucleotide polymorphism (SNP) genotypes and alleles and to identify reliable population-specific associations with PCa risk in Kazakh men. Methods: This retrospective case–control study included 941 Kazakh men (476 with histologically confirmed PCa and 465 cancer-free controls). Genomic DNA extracted from peripheral blood was genotyped with TaqMan^® OpenArray^® technology on a QuantStudio 12K Flex system. Associations were assessed by Pearson’s χ² test and logistic regression, with genotypic and allelic odds ratios (OR) and 95% confidence intervals (CI). Two-step multiple-testing correction (Bonferroni and Benjamini–Hochberg false-discovery rate, FDR) was applied. Predictive models were built using classification and regression trees (CART) and stepwise logistic regression. Results: Of 102 SNPs, 39 showed nominally significant genotypic differences; 12 remained significant after Bonferroni correction and 2 after FDR (14 in total). Several of the corrected loci were significant at both the genotypic and allelic level. Allelic ORs ranged from 0.37 (protective rs10187424 T allele) to 4.81 (rs1545985). A parsimonious seven-SNP autosomal logistic-regression model achieved an apparent AuROC of 0.84 (10-fold cross-validated 0.82); adding age as a covariate raised discrimination to 0.87. Ten of the fourteen significant loci remained significant after age adjustment, and six of these formed a core signal robust to both age imbalance and genotyping-quality concerns. Conclusions: This first large-scale SNP-association study in Kazakh men shows allele-frequency profiles resembling East Asian rather than European populations, confirming the need for population-specific genetic risk-assessment tools. The seven-SNP model showed high discriminatory power in the training set and requires external validation before clinical application. Full article

Congenital hereditary endothelial dystrophy (CHED) is a rare autosomal recessive disorder of the corneal endothelium caused by biallelic variants in the SLC4A11 gene. Its genetic spectrum is well described in the Indian subcontinent, but poorly characterized in the Saudi population, where high rates of consanguinity may concentrate specific alleles. We performed whole-exome sequencing in 47 clinically diagnosed CHED patients from consanguineous Saudi families and classified the resulting variants by their predicted effect on the protein. A homozygous SLC4A11 variant was identified in every patient, and no compound heterozygotes were found. The 47 patients carried 20 unique variants, three of which were novel: c.1799C>A; p.A600E, c.2623C>T; p.R875*, and c.670dup; p.W224Lfs*7. Seven variants recurred, and the canonical splice donor change c.2018+1G>A alone accounted for 14 patients. The variants resolved into two mechanistic groups: 22 patients with missense substitutions predicted to misfold the protein and cause endoplasmic reticulum retention, and 25 with truncating or splice variants predicted to abolish the protein. Among those, only the p.R875* sequence variant removes only the final 17 residues, is predicted to escape nonsense-mediated decay, and likely leaves a near-full-length protein. Five of the nine missense variants were glycine-to-arginine substitutions clustered between residues 378 and 413, within the first transmembrane region. The complete detection rate supports genetic homogeneity of CHED in this population and contrasts with the substantial fraction of unsolved cases reported elsewhere. The concentration of variants in a few regions of the gene suggests that a targeted Sanger protocol covering these hotspots could serve as an affordable first-line diagnostic test, with exome sequencing reserved for hotspot-negative patients. Full article

Background/Objectives: Hearing loss is one of the most prevalent sensory disorders in humans, with genetic factors accounting for approximately 60% of cases. Cochlear implantation is an effective intervention for individuals with severe-to-profound hearing loss. However, substantial variability in postoperative auditory performance persists, complicating the prediction of individual outcomes. This study investigated the genetic findings associated with hearing loss in a cohort of seven affected adults with cochlear implants (CIs). Methods: A total of seven patients with severe-to-profound hearing loss underwent genetic testing. Two of them were part of diagnostic screening, and five of them were part of research genetic analyses. Results: High-throughput genomic DNA sequencing identified twelve variants across multiple genes, including four new sequence variants. Based on ACMG/AMP criteria, integrating computational predictions, population frequency data, ClinVar annotations, and in silico pathogenicity assessments, the identified variants were classified as pathogenic variants, likely pathogenic variants, and variants of uncertain significance (VUS). We detected one pathogenic variant, two likely pathogenic variants and nine variants of uncertain significance (VUS). Novel variants were further analyzed using multiple sequence alignment to assess evolutionary conservation. Conclusions: The identification of four novel variants within the analyzed patients underscores the genetic heterogeneity of hearing loss and the importance of genetic analyses for improving the understanding of its molecular basis. Further functional and clinical studies are required to determine the pathogenicity of these variants and their potential clinical relevance. Full article

Electrospinning is a widely used nanofabrication technique capable of producing fibers with a range of diameters, morphologies, and porosities through the adjustment of experimental parameters. However, achieving reliable fiber diameter tuning remains challenging because of the complex, nonlinear interdependence among multiple electrospinning variables. In this study, a data-driven methodology is proposed that integrates predictive machine learning (ML) modeling with evolutionary algorithm-based optimization, specifically employing a genetic algorithm (GA), to predict fiber diameter and guide electrospinning parameter selection across nano- and microscale ranges. A curated dataset comprising 388 data points from 30 scientific publications was developed, focusing exclusively on polyacrylonitrile (PAN) dissolved in dimethylformamide (DMF). Multiple ML models were trained and tested to predict fiber diameter as a function of key electrospinning parameters. Among the evaluated ML models, the eXtreme gradient boosting (XGB) model achieved the highest predictive performance, yielding a coefficient of determination (R²) value of 0.93 with low prediction errors (root mean square error [RMSE]: 127.76 nm, mean absolute error [MAE]: 56.27 nm) on the test set. Experimental validation was performed by fabricating electrospun PAN nanofibers under one independent set of conditions, with scanning electron microscopy (SEM) showing close agreement between predicted and actual fiber diameters. The trained XGB model was subsequently integrated with a GA to identify electrospinning parameter sets for user-defined target fiber diameters ranging from 100 to 2000 nm. The evolutionary optimization process exhibited rapid convergence with low fitness error when evaluated using the trained predictive model. Overall, this study demonstrates the potential of a data-driven methodology to generate model-guided candidate conditions for target-driven PAN-DMF electrospinning, subject to broader experimental validation. Full article