Search Results (4,561)

Background: This study aimed to determine whether the duration or the magnitude of intraoperative BIS suppression has a greater impact on postoperative recovery. Methods: In this observational study, 141 patients were monitored for BIS values, suppression ratio (SR), maximum suppression ratio (SRmax), and total suppression time (SRT) during the perioperative period. Recovery phenotypes were assessed using the Richmond Agitation-Sedation Scale (RASS). Statistical analyses evaluated the relationship between BIS suppression parameters (SR, SRmax, SRT) and postoperative sedation or emergence agitation. Optimal thresholds for clinically significant suppression were determined. Results: Patients classified into the sedation group according to RASS scores exhibited significantly higher intraoperative SRmax values (p: 0.038) and prolonged SRT (p: 0.001) compared to the agitated group. An SRT ≥ 7.5 min predicted sedated recovery with 86.7% sensitivity and 39.4% specificity (AUC = 0.651, 95% CI: 0.561–0.742, p: 0.002). Similarly, an SRmax ≥ 19.5 was associated with sedated recovery (85.3% sensitivity, 53.0% specificity; AUC = 0.683, 95% CI: 0.592–0.775, p: 0.001). No significant association was found between BIS suppression and emergence agitation. Conclusions: Prolonged intraoperative BIS suppression and higher SRmax values are comparably predictive of postoperative sedation but not agitation. Monitoring these parameters may aid in anticipating recovery patterns. Full article

Background: Periapical lesions are common consequences of pulp necrosis but may remain undetectable on conventional intraoral radiographs, becoming evident only on cone-beam computed tomography (CBCT). Improving lesion recognition on plain radiographs is therefore of high clinical relevance. Methods: This retrospective, single-center study analyzed 56 matched pairs of intraoral periapical radiographs (RVG) and CBCT scans. A total of 109 regions of interest (ROIs) were included, which were classified as CBCT-positive/RVG-negative (onlyCBCT, n = 64) or true negative (noLesion, n = 45). Radiomic texture features were extracted from circular ROIs on RVG images using PyRadiomics. Feature distributions were compared using Mann–Whitney U tests with false discovery rate correction, and classification was performed using a logistic regression model with nested cross-validation. Results: Forty-four radiomic texture features showed statistically significant differences between onlyCBCT and noLesion ROIs, predominantly with small to medium effect sizes. For a 40-pixel ROI radius, the classifier achieved a mean area under the ROC curve of 0.71, mean accuracy of 68%, and mean sensitivity of 73%. Smaller ROIs (20–40 pixels) yielded higher AUCs and substantially better accuracy than larger sampling regions (≥60 pixels). Conclusions: Quantifiable radiomic signatures of periapical pathology are present on conventional radiographs even when lesions are visually occult. Radiomics may serve as a complementary decision support tool for identifying CBCT-only periapical lesions in routine clinical imaging. Full article

China boasts abundant cultivated resources of pitahaya, with Guizhou Province being one of its core producing areas. Quality differences in red-fleshed pitahaya among local producing areas have not been fully clarified, and a standardized quantitative evaluation system for these differences remains lacking. This study seeks to identify the key factors influencing regional variations in quality and establish a comprehensive evaluation standard. In this study, 15 samples of red-fleshed pitahaya were collected from four major producing areas in Guizhou and used as research materials. Based on 15 quality characteristic indicators of the fruits, an analysis of quality differences and establishment of an evaluation system were carried out using multivariate statistical analysis. The results showed that 14 of the 15 quality indicators exhibited significant differences among pitahaya samples from different producing areas (p < 0.05), with the a* value being the sole exception. Cluster analysis classified the 15 samples into four groups. Principal component analysis (PCA) extracted four principal components, with a cumulative variance contribution rate of 81.07%, which clearly identified betacyanin, betaxanthin, 1,1-diphenyl-2-picrylhydrazyl (DPPH) free-radical scavenging rate, vitamin C, fruit shape index, and transverse diameter as the core evaluation indicators. This study systematically clarifies the differences in quality characteristics and the internal correlations among quality indicators of red-fleshed pitahaya from different major producing areas in Guizhou. It further provides an important scientific basis for pitahaya variety breeding, cultivation regulation, and market positioning in this region and fills the research gap existing in the field of comprehensive quality evaluation of pitahaya. This is of significant practical importance for promoting the standardized upgrading of local specialty fruit industries, enhancing the market competitiveness of products, and facilitating the high-quality development of the agricultural economy. Full article

Background and Objectives: Aneuploidy is the leading cause of implantation failure and miscarriage, with prevalence increasing with maternal age. Embryos classified as chaotic, characterized by the presence of five or more chromosomal abnormalities, and those with complex aneuploidies, defined by two to four abnormalities, represent a controversial category in preimplantation genetic testing for aneuploidy (PGT-A), as the potential for misclassification remains a significant concern. Materials and Methods: We performed a retrospective study at the Calla IVF Center, Oradea, analyzing 230 blastocysts grouped by maternal age (25–30, 31–35, 36–40, and 41–50 years). A trophoblast biopsy was performed on days 5–7, and the samples were analyzed by next-generation sequencing (NGS). Embryos were classified as euploid, aneuploid, mosaic, or chaotic. The 19 embryos initially diagnosed as chaotic were thawed and subjected to re-biopsy. Statistical analysis included descriptive statistics (chi-square tests and ANOVA) and multivariable regression models, with p < 0.05 as the criterion for statistical significance. Results: Aneuploidy increased with maternal age, from 29.6% in women aged 25–30 years to 68.7% in those aged 41–50 (p = 0.002). Poor-quality blastocysts exhibited higher aneuploidy rates (72.4%) than good-quality embryos (34.6%; p = 0.004). Chaotic embryos comprised 8.3% of the cohort. Upon re-biopsy, none were confirmed as euploid; all remained abnormal and were reassigned to aneuploid, mosaic, or persistently chaotic categories. This finding suggests that apparent euploid results reported elsewhere may reflect technical variability and sampling limitations in PGT-A rather than accurate chromosomal normalization. Conclusions: The prevalence of aneuploid embryos showed a progressive increase with advancing maternal age. Chaotic embryos are heterogeneous, and re-biopsy may help refine the interpretation of complex PGT-A profiles, supporting its role as a diagnostic and quality control tool rather than a strategy to identify euploid embryos. Our study offers novel insights through age-stratified analysis, the integration of morphology with genetics in a Romanian IVF cohort, and a detailed evaluation of chaotic embryos, providing clinical recommendations for patient counseling and embryo selection. Full article

Pilot workload is a critical factor influencing flight safety. This study collects both subjective and objective data on pilot workload using the NASA-TLX questionnaire and electroencephalogram acquisition systems during simulated flight tasks. The raw EEG signals are denoised through preprocessing techniques, and relevant EEG features are extracted using time-domain and frequency-domain analysis methods. One-way ANOVA is employed to examine the statistical differences in EEG indicators under varying workload levels. A fusion model based on CNN-Bi-LSTM is developed to train and classify the extracted EEG features, enabling accurate identification of pilot workload states. The results demonstrate that the proposed hybrid model achieves a recognition accuracy of 98.2% on the test set, confirming its robustness. Additionally, under increased workload conditions, frequency-domain features outperform time-domain features in discriminative power. The model proposed in this study effectively recognizes pilot workload levels and offers valuable insights for civil aviation safety management and pilot training programs. Full article

Background/Objectives: Interpretation of chest X-rays (CXRs) requires accurate identification of lesion presence, diagnosis, location, size, and number to be considered complete. However, the effectiveness of large language models with vision capabilities (LLMs) in performing these tasks remains uncertain. This study aimed to evaluate the image-only interpretation performance of LLMs in the absence of clinical information. Methods: A total of 247 CXRs covering 13 diagnostic categories, including pulmonary edema, cardiomegaly, lobar pneumonia, and other conditions, were evaluated using Gemini 1.0, Gemini 1.5 Pro, GPT-4 Turbo, and GPT-4o. The text outputs generated by the LLMs were evaluated at two levels: (1) primary diagnosis accuracy across the 13 predefined diagnostic categories, and (2) identification of key imaging features described in the generated text. Primary diagnosis accuracy was assessed based on whether the model correctly identified the target diagnostic category and was classified as fully correct, partially correct, or incorrect according to predefined clinical criteria. Non-diagnostic imaging features, such as posteroanterior and anteroposterior (PA/AP) views, side markers, foreign bodies, and devices, were recorded and analyzed separately rather than being incorporated into the primary diagnostic scoring. Results: When fully and partially correct responses were treated as successful detections, vLLMs showed higher sensitivity for large, bilateral, multiple lesions and prominent devices, including acute pulmonary edema, lobar pneumonia, multiple malignancies, massive pleural effusions, and pacemakers, all of which demonstrated statistically significant differences across categories in chi-square analyses. Feature descriptions varied among models, especially in PA/AP views and side markers, though central lines were partially recognized. Across the entire dataset, Gemini 1.5 Pro achieved the highest overall detection rate, followed by Gemini 1.0, GPT-4o, and GPT-4 Turbo. Conclusions: Although LLMs were able to identify certain diagnoses and key imaging features, their limitations in detecting small lesions, recognizing laterality, reasoning through differential diagnoses, and using domain-specific expressions indicate that CXR interpretation without textual cues still requires further improvement. Full article

Background: People with Parkinson’s disease suffer from gait impairments. Clinical scales provide a limited and rater-dependent assessment of gait. Wearable sensors allow an objective characterization by capturing rhythm, pace, and signature patterns. This study investigated if sensor-derived gait parameters have prognostic value for short-term progression of gait impairments. Methods: A total of 111 longitudinal visit pairs were analyzed, where participants underwent clinical evaluation and a 4 × 10 m walking test instrumented with wearable sensors. Changes in the UPDRSIII gait score between baseline and follow-up were used to classify participants as Improvers, Stables, or Deteriorators. Baseline group differences were assessed statistically. Machine-learning classifiers were trained to predict group membership using clinical variables alone, sensor-derived gait features alone, or a combination of both. Results: Significant between-group differences emerged. In participants with UPDRSIII gait score = 1, Improvers showed higher median gait velocity ($0.81 \mathrm{m}/\mathrm{s}$) and stride length ($0.80 \mathrm{m}$) than Stables ($0.68 \mathrm{m}/\mathrm{s}$; $0.70 \mathrm{m}$) and Deteriorators ($0.59 \mathrm{m}/\mathrm{s}$; $0.68 \mathrm{m}$), along with lower stance time variability (3.10% vs. 4.49% and 3.75%; all $p<0.05$). The combined sensor-based and clinical model showed the best performance (AUC $0.82$). Conclusions: Integrating sensor-derived gait parameters with clinical score can support the identification of patients at risk of gait deterioration in the near future. Full article

The proliferation of Internet of Things (IoT) devices has created unprecedented security challenges characterized by resource constraints, heterogeneous network architectures, and severe class imbalance in attack detection datasets. This paper presents a comprehensive benchmark evaluation of five Generative Adversarial Network (GAN) architectures for energy-aware intrusion detection: Standard GAN, Progressive GAN (PGAN), Conditional GAN (cGAN), Graph-based GAN (GraphGAN), and Wasserstein GAN with Gradient Penalty (WGAN-GP). Our evaluation framework introduces novel energy-normalized performance metrics, including Accuracy-per-Joule (APJ) and F1-per-Joule (F1PJ), that enable principled architecture selection for energy-constrained deployments. We propose an optimized WGAN-GP architecture incorporating diversity loss, feature matching, and noise injection mechanisms specifically designed for classification-oriented data augmentation. Experimental results on a stratified subset of the BoT-IoT dataset (approximately 1.83 million records) demonstrate that our optimized WGAN-GP achieves state-of-the-art performance, with 99.99% classification accuracy, a 0.99 macro-F1 score, and superior generation quality (MSE 0.01). While traditional classifiers augmented with SMOTE (i.e., Logistic Regression and CNN1D-TCN) also achieve 99.99% accuracy, they suffer from poor minority class detection (77.78–80.00%); our WGAN-GP improves minority class detection to 100.00% on the reported test split (45 of 45 attack instances correctly identified). Furthermore, WGAN-GP provides substantial efficiency advantages under our energy-normalized metrics, achieving superior accuracy-per-joule performance compared to Standard GAN. Also, a cross-dataset validation across five benchmarks (BoT-IoT, CICIoT2023, ToN-IoT, UNSW-NB15, CIC-IDS2017) was implemented using 250 pooled test attacks to confirm generalizability, with WGAN-GP achieving 98.40% minority class accuracy (246/250 attacks detected) compared to 76.80% for Classical + SMOTE methods, a statistically significant 21.60 percentage point improvement ($p<0.0001$). Finally, our analysis reveals that incorporating diversity-promoting mechanisms in GAN training simultaneously achieves best generation quality AND best classification performance, demonstrating that these objectives are complementary rather than competing. Full article

Non-alcoholic fatty liver disease (NAFLD) is a silent condition that can lead to fatal cirrhosis, with dietary factors playing a central role. The effect of various dietary interventions on male Wistar rats were evaluated in four diets: control, arsenic, sucrose, and arsenic–sucrose. SHG microscopy images from the right ventral lobe of the liver tissue were analyzed with a neural network trained to detect the presence or absence of collagen fibers, followed by the assessment of their orientation and angular distribution. Machine learning classification of SHG microscopy images revealed a marked increase in fibrosis risk with dietary interventions: <10% in controls, 24% with arsenic, 40% with sucrose, and 62% with combined arsenic–sucrose intake. Angular width distribution of collagen fibers narrowed dramatically across groups: 26° (control), 24° (arsenic), 15.7° (sucrose), and 2.8° (arsenic–sucrose). This analysis revealed four key statistical features for classifying the images according to the presence or absence of collagen fibers: (1) the percentage of pixels whose intensity is above the 15% noise threshold, (2) the Mean-to-Standard Deviation ratio (Mean/std), (3) the mode, and (4) the total intensity (sum). These results demonstrate that a diet rich in sucrose, particularly in combination with arsenic, constitutes a significant risk factor for liver collagen fiber remodeling. Full article

Creeping landslides constitute the predominant form of long-term, slow-moving geohazards in high mountain gorge regions. Under the combined influence of gravity and external triggering factors, these landslides undergo persistent deformation, posing continuous threats to major transportation corridors, hydropower infrastructures, and nearby settlements. Li County is located within the active tectonic belt along the eastern margin of the Tibetan Plateau, characterized by highly variable topography, intensely fractured rock masses, and dense development of creeping landslides. The slip surfaces are typically deeply buried and concealed. Consequently, conventional drilling and profile-based investigations, limited by high costs, sparse sampling points, and poor spatial continuity, are insufficient for identifying the deep-seated structures of such landslides. To address this challenge, this study applies Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) to obtain ascending and descending deformation rate fields for 2022–2024, revealing pronounced spatial heterogeneity and persistent activity across three types of landslides. Based on the principle of mass conservation, the sliding-surface depths of eight typical landslides were inverted, revealing pronounced heterogeneity. The maximum sliding-surface depths range from 32 to 98 m and show strong agreement with borehole and profile data (R² > 0.92; RMSE ±4.96–±16.56 m), confirming the reliability of the inversion method. The GeoDetector model was used to quantitatively evaluate the dominant factors controlling landslide depth. Elevation was identified as the primary control factor, while slope aspect exhibited significant influence in several landslides. All factor combinations showed either “bi-factor enhancement” or “nonlinear enhancement”, indicating that slip-surface depth is governed by synergistic interactions among multiple factors. Boxplot-based statistical analyses further revealed three typical patterns of slip-surface variation with elevation and slope, based on which the landslides were classified into rotational, push-type translational, and traction-type translational categories. By integrating statistical patterns with mechanical models, the study achieves a transition from “form” to “state”, enabling inference of the internal mechanical conditions and evolutionary stages from the observed surface morphology. The results of this study provide an effective technical approach for deep structural detection, identification of controlling factors, and stability evaluation of creeping landslides in high mountain gorge environments. Full article

Background/Objectives: Childhood obesity remains a major public health issue, particularly in Mediterranean countries such as Greece. Although parental influences on children’s weight have been extensively studied, fewer studies have jointly examined parental mental health, feeding practices, sociodemographic factors, and biological stress markers. This study aimed to investigate associations between psychological status, educational level, feeding behaviors, and children’s Body Mass Index (BMI) in a Greek sample. A pilot assessment of salivary cortisol was included in evaluating its feasibility as an objective biomarker of parental stress. Subjects and Methods: A total of 103 parent–child dyads participated in this cross-sectional study. Children’s BMI was classified using World Health Organization (WHO) growth standards. Parental stress, anxiety, and depressive symptoms were assessed using the Perceived Stress Scale-14 (PSS-14) and the Depression Anxiety Stress Scale-21 (DASS-21) questionnaires. Feeding practices were evaluated with the Comprehensive Feeding Practices Questionnaire (CFPQ). Statistical analyses included Pearson correlations, independent samples t-tests, one-way ANOVA, Mann–Whitney U, and Kruskal–Wallis tests. A subsample provided saliva samples for cortisol analysis to assess feasibility and explore the potential associations with parental stress indicators. Results: Parental BMI showed a strong positive association with child BMI (p = 0.002). Higher parental anxiety (p = 0.002) and depression (p = 0.009) were also associated with increased child BMI. Restrictive (p < 0.001) and emotion-driven (p < 0.001) feeding practices were associated with higher child BMI, whereas monitoring (p = 0.013) and health-promoting feeding practices (p = 0.001) appeared protective. Lower parental education was related to a higher BMI in both parents (p = 0.001) and children (p = 0.002) and to more frequent use of restrictive feeding strategies (p = 0.001). WHO charts identified a greater proportion of children as overweight or obese compared with the Centers for Disease Control and Prevention (CDC) criteria. The analysis showed statistically significant differences between the two classification systems (χ² (4) = 159.704, p < 0.001), indicating that BMI categorization varies considerably depending on the reference system used. No significant associations were observed with residential environment or salivary cortisol, likely due to the limited size of the pilot biomarker subsample. Conclusions: The findings highlight the combined effect of parental mental health status, educational level, and feeding practices on child BMI within the Greek context. The preliminary inclusion of a biological stress marker provides added value to the existing research in this area. These results underscore the importance of prevention strategies that promote parental psychological wellbeing and responsive feeding practices while addressing socioeconomic disparities to reduce the childhood obesity risk. Full article

Background/Objectives: Cellulite is a common aesthetic condition in women, traditionally assessed using visual inspection and palpation-based scales that are inherently subjective. Therefore, image-based methods that may support standardized severity grading are of growing interest. To evaluate infrared thermography as an imaging-based method for grading cellulite severity and to perform methodological validation of a newly developed thermographic classification scale by comparing it with clinical palpation and anthropometric parameters. Methods: This retrospective, non-interventional study analyzed anonymized clinical and thermographic data from 81 women with clinically assessed cellulite. Cellulite severity was evaluated using the Nürnberger–Müller palpation scale and a newly developed five-point thermographic scale based on skin surface temperature differentials and histogram pattern analysis. The associations between the assessment methods were evaluated using ordinal statistical measures, and agreement was assessed using weighted Cohen’s kappa statistics. Results: Thermographic grading demonstrated high agreement with palpation-based assessment, with a percentage agreement of 93.8% and an almost perfect agreement based on weighted Cohen’s κ. A strong ordinal association was observed between the methods. Thermography consistently classified a subset of cases as one grade higher compared with palpation. No statistically significant associations were observed between thermographic grade and body mass index or waist-to-hip ratio. Conclusions: Infrared thermography enables image-based grading of cellulite severity and shows a strong concordance with established palpation scales. The proposed thermographic classification provides preliminary methodological validation of an imaging-based grading approach. Further multicenter studies involving multiple assessors and diverse populations are required to assess reproducibility, specificity, and potential clinical applicability. Full article

Background: Childhood obesity represents the most common nutritional and metabolic disorder in industrialized countries and constitutes a major public health concern. In Italy, 20–25% of school-aged children are overweight and 10–14% are obese, with marked regional variability. Excess adiposity in childhood is frequently associated with hypertension, dyslipidemia, insulin resistance, and non-alcoholic fatty liver disease (NAFLD), predisposing to future cardiovascular disease (CVD). Objective: To investigate anthropometric indicators of cardiometabolic risk in 810 children and adolescents aged 7–17 years who underwent assessment for competitive sports eligibility at the Sports Medicine Unit of Modena, evaluate baseline knowledge of cardiovascular health aligned with ESC, AAP (2023), and EASO guidelines. Methods: 810 children and adolescents aged 7–17 years undergoing competitive sports eligibility assessment at the Sports Medicine Unit of Modena underwent evaluation of BMI percentile, waist circumference (WC), waist-to-height ratio (WHtR), and blood pressure. Cardiovascular knowledge and lifestyle habits were assessed via a previously used questionnaire. Anthropometric parameters, blood pressure (BP), and lifestyle-related knowledge and behaviors were assessed using standardized procedures. Overweight and obesity were defined according to WHO BMI-for-age percentiles. Elevated BP was classified based on the 2017 American Academy of Pediatrics age-, sex-, and height-specific percentiles. Statistical analyses included descriptive statistics, group comparisons, chi-square tests with effect size estimation, correlation analyses, and multivariable logistic regression models. Results: Overall, 22% of participants were overweight and 14% obese. WHtR > 0.5 was observed in 28% of the sample and was more frequent among overweight/obese children (p < 0.001). Elevated BP was detected in 12% of participants with available measurements (n = 769) and was significantly associated with excess adiposity (χ² = 7.21, p < 0.01; Cramér’s V = 0.27). In multivariable logistic regression analyses adjusted for age and sex, WHtR > 0.5 (OR 2.14, 95% CI 1.32–3.47, p = 0.002) and higher sedentary time (OR 1.41 per additional daily hour, 95% CI 1.10–1.82, p = 0.006) were independently associated with elevated BP, whereas BMI percentile lost significance when WHtR was included in the model. Lifestyle knowledge scores were significantly lower among overweight and obese participants compared with normal-weight peers (p < 0.01). Conclusions: WHtR is a sensitive early marker of cardiometabolic risk, often identifying at-risk children missed by BMI alone. Baseline cardiovascular knowledge was suboptimal. The observed gaps in cardiovascular knowledge underscore the importance of integrating anthropometric screening with structured educational interventions to promote healthy lifestyles and long-term cardiovascular prevention. Full article

Background/Objectives: Targeted muscle reinnervation and regenerative peripheral nerve interface procedures have emerged as effective techniques for reducing post-amputation pain and preventing symptomatic neuroma formation. However, the optimal timing of these procedures remains debated. This study aims to compare complication and reoperation rates between acute and delayed advanced nerve interface procedures in lower-extremity amputees. Methods: A retrospective cohort study was conducted including 74 patients who underwent acute or delayed targeted muscle reinnervation and/or regenerative peripheral nerve interface procedures between 2019 and 2025 at a tertiary academic medical center. Procedures performed concurrently with amputation or during early-stage reconstruction were classified as acute, whereas procedures performed more than one month after amputation were classified as delayed interventions. The primary outcome was postoperative surgical complications occurring within one year. Mann–Whitney U and chi-square tests were used for group comparisons. Univariable and multivariable logistic regression analyses were performed to identify factors associated with surgical complications, adjusting for potential confounders. A p-value < 0.05 was considered statistically significant. Results: Of 80 limbs, 47 (58.8%) underwent acute and 33 (41.3%) underwent delayed procedures. One-year complication rates were 23.4% in the acute group, and 12.1% in the delayed group, with wound-related complications predominantly occurring in patients undergoing amputation for infection or vascular disease. Unexpected reoperation rates were 19.1% for acute and 12.1% for delayed interventions. On univariable and multivariable analyses, early procedures demonstrated higher odds of surgical complications. However, these associations did not reach statistical significance and were limited by baseline differences in patient comorbidity and etiology. Conclusions: Early advanced nerve interface procedures were performed in more medically complex patients and were associated with higher observed rates of surgical complications, whereas delayed procedures were associated with a higher incidence of recurrent symptomatic neuromas. These findings underscore the importance of patient selection, etiology of amputation, and surgical context, rather than timing alone, when determining the optimal approach to nerve interface reconstruction following lower-extremity amputation. Full article

Background: Working capital management plays a critical role in ensuring business liquidity and financial sustainability. However, few studies in developing economies have employed multivariate statistical techniques to optimize working capital decisions. This study addresses this gap by applying discriminant analysis to classify Ecuadorian manufacturing firms according to their financial sustainability and business continuity. Methods: A quantitative approach was applied to a sample of 112 manufacturing companies located in Zone 3 of Ecuador, covering the 2017–2020 period. The model incorporated working capital indicators and the Z-Score index as independent variables, while company size served as the categorical dependent variable. Results: The discriminant function retained two significant predictors—Working Capital (2019) and Z-Score (2017)—with an eigenvalue of 0.191, a canonical correlation of 0.400, and an overall classification accuracy of 71.4%. Box’s M test (p = 0.000) indicated unequal covariance matrices, suggesting cautious interpretation but acceptable robustness of the model. Conclusions: This study concludes that working capital and Z-Score are effective indicators for assessing financial sustainability and predicting firm continuity. The findings provide practical insights for managers and policymakers to enhance financial efficiency and resource allocation. The originality of this work lies in the application of discriminant analysis to model financial sustainability in Ecuador’s manufacturing sector, offering a statistical foundation for future optimization models. Full article