Explore the vast range of titles available.

This study aims to utilize artificial intelligence technology to conduct an in-depth analysis of fundus data from myopic children and adolescents, thoroughly exploring the correlation between retinal vascular parameters and axial length (AL), and ultimately revealing the changing patterns of retinal vascular characteristics in children with different refractive errors. The findings aim to provide a scientific basis for the prevention, early screening, and formulation of personalized treatment strategies for myopia. The study selected 124 students from Jiandong Primary School in Changzhi City who underwent myopia prevention and control screening. Their axial length data were recorded, and fundus photographs were taken using the Topcon TNF506 non-mydriatic fundus camera. Subsequently, these fundus images were meticulously analyzed using the EVision AI fundus image analysis system, which is a commercial software that employs pre-trained algorithms to automatically extract retinal vascular parameters.Pearson and Spearman correlation coefficients were used to analyze the correlation between retinal vascular parameters and axial length, and multiple linear regression analysis was further conducted to explore their intrinsic associations. The study found that in the low myopia group, axial length was significantly negatively correlated with various retinal vascular parameters, including the average diameters of arteries and veins, average vascular tortuosity, atrophy arc area, and leopard spot density. In the moderate to high myopia group, axial length also showed significant negative correlations with the average diameter of arteries, some average venous tortuosity, and average vascular diameter. However, fractal dimension of vessels and average branch angle did not show significant changes across all myopia groups. This study clearly demonstrates a significant correlation between axial length and retinal vascular parameters, with notable differences in this correlation among children with different refractive errors. These findings not only provide a new perspective for understanding the pathological mechanisms of myopia but also offer important scientific evidence for the development of more precise and personalized myopia prevention and control strategies in the future. They have potential guiding significance for clinical practice and policy formulation.

This study assessed the cost-effectiveness of different diabetic retinopathy (DR) screening strategies in rural regions in China by using a Markov model to make health economic evaluations. In this study, we determined the structure of a Markov model according to the research objectives, which required parameters collected through field investigation and literature retrieval. After perfecting the model with parameters and assumptions, we developed a Markov decision analytic model according to the natural history of DR in TreeAge Pro 2011. For this model, we performed Markov cohort and cost-effectiveness analyses to simulate the probabilistic distributions of different developments in DR and the cumulative cost-effectiveness of artificial intelligence (AI)-based screening and ophthalmologist screening for DR in the rural population with diabetes mellitus (DM) in China. Additionally, a model-based health economic evaluation was performed by using quality-adjusted life years (QALYs) and incremental cost-effectiveness ratios. Last, one-way and probabilistic sensitivity analyses were performed to assess the stability of the results. From the perspective of the health system, compared with no screening, AI-based screening cost more (the incremental cost was 37,257.76 RMB (approximately 5,211.31 US dollars)), but the effect was better (the incremental utility was 0.33). Compared with AI-based screening, the cost of ophthalmologist screening was higher (the incremental cost was 14,886.76 RMB (approximately 2,070.19 US dollars)), and the effect was worse (the incremental utility was -0.31). Compared with no screening, the incremental cost-effectiveness ratio (ICER) of AI-based DR screening was 112,146.99 RMB (15,595.47 US dollars)/QALY, which was less than the threshold for the ICER (< 3 times the per capita gross domestic product (GDP), 217,341.00 RMB (30,224.03 US dollars)). Therefore, AI-based screening was cost-effective, which meant that the increased cost for each additional quality-adjusted life year was merited. Compared with no screening and ophthalmologist screening for DR, AI-based screening was the most cost-effective, which not only saved costs but also improved the quality of life of diabetes patients. Popularizing AI-based DR screening strategies in rural areas would be economically effective and feasible and can provide a scientific basis for the further formulation of early screening programs for diabetic retinopathy.

Although numerous studies have described the application of artificial intelligence (AI) in diabetic retinopathy (DR) screening among diabetic populations, studies among populations in rural areas are rare. The purpose of this study was to evaluate the application value of an AI-based diagnostic system for DR screening in rural areas of midwest China. In this diagnostic accuracy study, diabetes mellitus (DM) patients in the National Basic Public Health Information Systems of Licheng County and Lucheng County of Changzhi city from July to December 2020 were selected as the target population. A total of 7824 eyes of 3933 DM patients were enrolled in this screening; the patients included 1395 males and 2401 females, with an average age of 19-87 years (63±8.735 years). All fundus photographs were collected by a professional ophthalmologist under natural pupil conditions in a darkroom using the Zhiyuan Huitu fundus image AI analysis software EyeWisdom. The AI-based diagnostic system and ophthalmologists were tasked with diagnosing the photos independently, and the consistency rate, sensitivity and specificity of the two methods in diagnosing DR were calculated and compared. The prevalence rates of DR according to the ophthalmologist and AI diagnoses were 22.7% and 22.5%, respectively; the consistency rate was 81.6%. The sensitivity and specificity of the AI system relative to the ophthalmologists' grades were 81.2% (95% confidence interval [CI]: 80.3% 82.1%) and 94.3% (95% CI: 93.7% 94.8%), respectively. There was no significant difference in diagnostic outcomes between the methods (X2 = 0.329, P = 0.566, P>0.05), and the AI-based diagnostic system had high consistency with the ophthalmologists' diagnostic results ([kappa] = 0.752). Our research demonstrated that DR patients in rural area hospitals can be screened feasibly. Compared with that of the ophthalmologists, however, the accuracy of the AI system must be improved. The results of this study might lend support to the large-scale application of AI in DR screening among different populations.

Background Although numerous studies have described the application of artificial intelligence (AI) in diabetic retinopathy (DR) screening among diabetic populations, studies among populations in rural areas are rare. The purpose of this study was to evaluate the application value of an AI-based diagnostic system for DR screening in rural areas of midwest China. Methods In this diagnostic accuracy study, diabetes mellitus (DM) patients in the National Basic Public Health Information Systems of Licheng County and Lucheng County of Changzhi city from July to December 2020 were selected as the target population. A total of 7824 eyes of 3933 DM patients were enrolled in this screening; the patients included 1395 males and 2401 females, with an average age of 19–87 years (63±8.735 years). All fundus photographs were collected by a professional ophthalmologist under natural pupil conditions in a darkroom using the Zhiyuan Huitu fundus image AI analysis software EyeWisdom. The AI-based diagnostic system and ophthalmologists were tasked with diagnosing the photos independently, and the consistency rate, sensitivity and specificity of the two methods in diagnosing DR were calculated and compared. Results The prevalence rates of DR according to the ophthalmologist and AI diagnoses were 22.7% and 22.5%, respectively; the consistency rate was 81.6%. The sensitivity and specificity of the AI system relative to the ophthalmologists’ grades were 81.2% (95% confidence interval [CI]: 80.3% 82.1%) and 94.3% (95% CI: 93.7% 94.8%), respectively. There was no significant difference in diagnostic outcomes between the methods (χ2 = 0.329, P = 0.566, P>0.05), and the AI-based diagnostic system had high consistency with the ophthalmologists’ diagnostic results (κ = 0.752). Conclusion Our research demonstrated that DR patients in rural area hospitals can be screened feasibly. Compared with that of the ophthalmologists, however, the accuracy of the AI system must be improved. The results of this study might lend support to the large-scale application of AI in DR screening among different populations.

This study assessed the cost-effectiveness of different diabetic retinopathy (DR) screening strategies in rural regions in China by using a Markov model to make health economic evaluations. In this study, we determined the structure of a Markov model according to the research objectives, which required parameters collected through field investigation and literature retrieval. After perfecting the model with parameters and assumptions, we developed a Markov decision analytic model according to the natural history of DR in TreeAge Pro 2011. For this model, we performed Markov cohort and cost-effectiveness analyses to simulate the probabilistic distributions of different developments in DR and the cumulative cost-effectiveness of artificial intelligence (AI)-based screening and ophthalmologist screening for DR in the rural population with diabetes mellitus (DM) in China. Additionally, a model-based health economic evaluation was performed by using quality-adjusted life years (QALYs) and incremental cost-effectiveness ratios. Last, one-way and probabilistic sensitivity analyses were performed to assess the stability of the results. From the perspective of the health system, compared with no screening, AI-based screening cost more (the incremental cost was 37,257.76 RMB (approximately 5,211.31 US dollars)), but the effect was better (the incremental utility was 0.33). Compared with AI-based screening, the cost of ophthalmologist screening was higher (the incremental cost was 14,886.76 RMB (approximately 2,070.19 US dollars)), and the effect was worse (the incremental utility was -0.31). Compared with no screening, the incremental cost-effectiveness ratio (ICER) of AI-based DR screening was 112,146.99 RMB (15,595.47 US dollars)/QALY, which was less than the threshold for the ICER (< 3 times the per capita gross domestic product (GDP), 217,341.00 RMB (30,224.03 US dollars)). Therefore, AI-based screening was cost-effective, which meant that the increased cost for each additional quality-adjusted life year was merited. Compared with no screening and ophthalmologist screening for DR, AI-based screening was the most cost-effective, which not only saved costs but also improved the quality of life of diabetes patients. Popularizing AI-based DR screening strategies in rural areas would be economically effective and feasible and can provide a scientific basis for the further formulation of early screening programs for diabetic retinopathy.

Background N6-methyladenosine (m6A) modification is the most pervasive modification in mRNA, and has been considered as a new layer of epigenetic regulation on mRNA processing, stability and translation. Despite its functional significance in various physiological processes, the role of the m6A modification involved in breast cancer is yet fully understood. Methods We used the m6A-RNA immunoprecipitation sequencing to identify the potential targets in breast cancer. To determine the underlying mechanism for the axis of FTO-BNIP3, we performed a series of in vitro and in vivo assays in 3 breast cancer cell lines and 36 primary breast tumor tissues and 12 adjunct tissues. Results We showed that FTO, a key m6A demethylase, was up-regulated in human breast cancer. High level of FTO was significantly associated with lower survival rates in patients with breast cancer. FTO promoted breast cancer cell proliferation, colony formation and metastasis in vitro and in vivo. We identified BNIP3, a pro-apoptosis gene, as a downstream target of FTO-mediated m6A modification. Epigenetically, FTO mediated m6A demethylation in the 3’UTR of BNIP3 mRNA and induced its degradation via an YTHDF2 independent mechanism. BNIP3 acts as a tumor suppressor and is negatively correlated with FTO expression in clinical breast cancer patients. BNIP3 dramatically alleviated FTO-dependent tumor growth retardation and metastasis. Conclusions Our findings demonstrate the functional significance of the m6A modification in breast cancer, and suggest that FTO may serve as a novel potential therapeutic target for breast cancer.

This study examines how social support influences adolescents' autonomous physical learning behavior, exploring the mediating roles of self-efficacy and exercise motivation, and the moderating effects of gender and behavioral typologies. The goal is to provide insights into how social support can enhance adolescents' engagement in physical activities and inform intervention strategies. A total of 2,359 junior high school students (1,208 males and 1,151 females; mean age = 13.21 ± 0.96 years) from three public schools in Shandong Province were surveyed between October and December 2024. Participants completed the Chinese versions of the Perceived Social Support Scale (PSSS), General Self-Efficacy Scale (GSES), Motivation for Physical Activity Measure-Revised (MPAM-R), and Autonomous Physical Learning Behavior Scale (APLBS). Data were analyzed using SPSS 25.0 for descriptive statistics, Pearson correlations, t-tests, one-way ANOVAs, and hierarchical regression; Mplus 8.3 for Latent Profile Analysis (LPA); and AMOS 27.0 for Structural Equation Modeling (SEM) with bootstrapping (10,000 resamples). indicated significant positive correlations among social support, self-efficacy, exercise motivation, and autonomous physical learning (all p < .01). Hierarchical regression showed that social support accounted for 27.3% of the variance in autonomous learning behavior (β = 0.524, p < .001), self-efficacy explained an additional 5.8% (β = 0.279, p < .001), and exercise motivation explained a further 4.0% (β = 0.219, p < .001), resulting in a total R2 = 0.373. LPA identified four behavioral profiles-Highly Engaged (26.3%), Positively Regulated (35.7%), Selectively Participative (22.2%), and Passively Participative (15.8%)-with the four-class model demonstrating optimal fit (entropy = 0.921; AIC = 37,951.9; BIC = 38,081.6; BLRT p < .001; LMR p = .0235). SEM results (CMIN/DF = 3.546; GFI = 0.970; CFI = 0.985; TLI = 0.976; NFI = 0.979; RMSEA = 0.060) showed that social support had a direct effect on autonomous learning behavior (β = 0.325, p < .001) and a total indirect effect of 0.191 (total effect = 0.516, p < .001). Specifically, self-efficacy mediated 22.19% (β = 0.114, 95% CI [0.093, 0.137]), exercise motivation mediated 11.18% (β = 0.057, 95% CI [0.043, 0.074]), and the chain pathway (social support → self-efficacy → exercise motivation → learning) accounted for 3.49% (β = 0.018, 95% CI [0.012, 0.024]) of the total effect. Multi-group SEM indicated that the SS → SE → EM mediation path was stronger for females (β = 0.127, 95% CI [0.104, 0.152]) than for males (β = 0.088, 95% CI [0.070, 0.109]). Across latent profiles, the full sequential mediation (SS → SE → EM → APLB) was significant for Positively Regulated (β = 0.074, 95% CI [0.051, 0.101]) and Selectively Participative (β = 0.066, 95% CI [0.042, 0.089]) groups, marginally significant for Passively Participative (β = 0.038, 95% CI [0.015, 0.062]), and non-significant for Highly Engaged (β = 0.013, 95% CI [-0.004, 0.031]). These findings demonstrate that social support enhances adolescents' autonomous physical learning both directly and indirectly through self-efficacy and exercise motivation. Psychological resilience processes accounted for approximately 37.1% of behavioral variance, and gender differences and latent profiles moderated these pathways. Interventions should therefore focus on strengthening perceived support to boost self-efficacy and motivation-especially among female and moderately engaged students-while tailoring strategies to each behavioral profile to foster sustained autonomous learning and lifelong physical activity engagement.Keywords: Machine Learning, Neural Networks, artificial intelligence.

[This corrects the article DOI: 10.1371/journal.pone.0327020.].

Aspartame, a widely used artificial sweetener, has been linked to various cancers, including kidney renal papillary cell carcinoma (KIRP). However, the molecular mechanisms underlying this association remain unclear. This study employed network toxicology and molecular docking to investigate potential mechanisms of aspartame-induced KIRP. Differentially expressed genes from TCGA were intersected with aspartame targets and KIRP-related genes, yielding 61 common targets. GO and KEGG analyses revealed enrichment in extracellular matrix degradation, signaling pathways, and immune microenvironment regulation. Univariate Cox regression identified 23 prognostically significant genes, from which multifactorial Cox regression with stepwise selection determined 8 core genes (APLNR, CYP2C19, EDNRA, KLK5, F2R, RAD51, AURKA, and TLR2). A risk model was constructed and validated through VIF analysis, Schoenfeld residual testing, and internal validation using a training–validation split. SHAP analysis identified EDNRA as the primary driver gene. Survival analysis demonstrated that the model effectively stratified KIRP patients, with risk score and tumor stage serving as independent prognostic factors. Molecular docking confirmed stable binding between aspartame and core target proteins. These findings provide mechanistic insights into aspartame-induced KIRP pathogenesis and establish a foundation for future experimental validation.