Lacustrine fine-grained sedimentary rocks in the Dongying Sag of the Bohai Bay Basin in China exhibit significant potential for hydrocarbon exploration. This study investigates the lithofacies types and sedimentary evolution of the Paleogene Shahejie Formation’s lower third member (Es3l) and upper fourth member (Es4u), integrating petrological and geochemical analyses to explore the relationship between lithofacies characteristics and sedimentary environments. The results show that the fine-grained sedimentary rocks in the study area can be classified into 18 lithofacies, with seven principal ones, including organic-rich laminated carbonate fine-grained mixed sedimentary rock lithofacies and organic-rich laminated limestone lithofacies. In conjunction with analyses of vertical changes in geochemical proxies such as paleoclimate (e.g., CIA, Na/Al), paleoproductivity (e.g., Ba), paleosalinity (e.g., Sr/Ba), paleo-redox conditions (e.g., V/Sc, V/V + Ni), and terrigenous detrital influx (e.g., Al, Ti), five stages are delineated from bottom to top. These stages demonstrate a general transition from an arid to humid paleoclimate, a steady increase in paleoproductivity, a gradual decrease in paleosalinity, an overall reducing water body environment, and an increasing trend of terrestrial detrital input. This study demonstrates that the abundance of organic matter is primarily influenced by paleoproductivity and paleo-redox conditions. The variations in rock components are predominantly influenced by paleoclimate, and sedimentary structures are affected by the depth of the lake basin. Special depositional events, such as storm events in Stage II, have significantly impacted the abundance of organic matter, rock components, and sedimentary structures by disturbing the water column and disrupting the reducing conditions at the lake bottom. The present study offers crucial insights into the genesis mechanisms of continental lacustrine fine-grained sedimentary rocks, facilitates the prediction of lithofacies distribution, and advances the exploration of China’s shale oil resources in lacustrine environments. Full article

The transport and dispersion (T&D) of catalyst particles seeded by weather modification aircraft is crucial for assessing their weather modification effects. This study investigates the capabilities of the Chinese geostationary weather satellite FY-4A for identifying the physical response of cloud seeding with AgI-based catalysts and continuously monitoring its evolution for a weather event that occurred on 15 December 2019 in Henan Province, China. Satellite measurements are also used to verify an operational catalyst T&D algorithm. The results show that FY-4A exhibits a remarkable capability of identifying the cloud-seeding tracks and continuously tracing their evolution for a period of over 3 h. About 60 min after the cloud seeding, the cloud crystallization track became clear in the FY-4A tri-channel composite cloud image and lasted for about 218 min. During this time period, the cloud track moved with the cloud system about 153 km downstream (northeast of the operation area). An operational catalyst T&D model was run to simulate the cloud track, and the outputs were extensively compared with the satellite observations. It was found that the forecast cloud track closely agreed with the satellite observations in terms of the track widths, morphology, and movement. Finally, the FY-4A measurements show that there were significant differences in the microphysical properties across the cloud track. The effective cloud radius inside the cloud track was up to 15 μm larger than that of the surrounding clouds; the cloud optical thickness was about 30 μm smaller; and the cloud-top heights inside the cloud track were up to 1 km lower. These features indicate that the cloud-seeding catalysts led to the development of ice-phase processes within the supercooled cloud, with the formation of large ice particles and some precipitation sedimentation. Full article

Anion-driven, nanoscale polar–apolar structural organization is investigated in a solvate ionic liquid (SIL) setting by comparing sulfonate-based anions with long and short perfluorinated alkyl chains. Representative SILs are created from 1,2-bis(2-methoxyethoxy)ethane (“triglyme” or “G3”), lithium nonafluoro-1-butanesulfonate, and lithium trifluoromethanesulfonate. Molecular dynamics simulations, density functional theory computations, and vibrational spectroscopy provide insight into the overall liquid structure, cation–solvent interactions, and cation–anion association. Significant competition between G3 and anions for cation-binding sites characterizes the G3–LiC₄F₉SO₃ mixtures. Only 50% of coordinating G3 molecules form tetradentate complexes with Li⁺ in [(G3)₁Li][C₄F₉SO₃]. Moreover, the SIL is characterized by extensive amounts of ion pairing. Based on these observations, [(G3)₁Li][C₄F₉SO₃] is classified as a “poor” SIL, similar to the analogous [(G3)₁Li][CF₃SO₃] system. Even though the comparable basicity of the CF₃SO₃⁻ and C₄F₉SO₃⁻ anions leads to similar SIL classifications, the hydrophobic fluorobutyl groups support extensive apolar domain formation. These apolar moieties permeate throughout [(G3)₁Li][C₄F₉SO₃] and persist even at relatively low dilution ratios of [(G3)₁₀Li][C₄F₉SO₃]. By way of comparison, the CF₃ group is far too short to sustain polar–apolar segregation. This demonstrates how chemically modifying the anions to include hydrophobic groups can impart unique nanoscale organization to a SIL. Moreover, tuning these nano-segregated fluorinated domains could, in principle, control the presence of dimensionally ordered states in these mixtures without changing the coordination of the lithium ions. Full article

Recently, many floating renewable energy platforms have been deployed in coastal regions, where sloping bottoms are an important factor when evaluating their safety. In this article, a simplified method coupling an eigenfunction matching method (EMM) and a finite-depth Green’s function (FDGF) is developed to evaluate floating-body motion responses over a sloping bottom for which bathymetry is homogeneous in the longshore direction. We propose an extended EMM to create an incident wave model over the sloping bottom, thereby obtaining the Froude–Krylov (F–K) force and Neumann data on the wet surfaces of the floating body for the diffraction problem. An equivalent depth is introduced to account for the interaction between the sloping bottom and floating bodies when dealing with the diffraction and radiation problems. The accuracy of the present method is validated through a comprehensive comparison with numerical and/or experiment results for a liquefied natural gas (LNG) ship and a floating hemisphere from the literature. Generally, the present, simplified method can give predictions with sufficient accuracy. Full article

The purpose of this study was to evaluate the effects of a mobile app designed to improve chronic disease self-management in patients aged 40 years and older with low health literacy and who had at least one chronic health condition, and to assess the impact of delivering information at different levels of reading difficulty. A randomized controlled trial was completed at two sites. Individuals aged 40 years and older screened for low health literacy who had at least one chronic health condition were randomly assigned to a tailored information multimedia app with text at one of three grade levels. Four primary outcomes were assessed: patient activation, chronic disease self-efficacy, health-related quality of life, and medication adherence. All groups showed overall increases in activation, self-efficacy, and health-related quality of life, but no change in medication adherence. No between-group differences were observed. The mobile app may have been effective in increasing participants’ levels of several psychosocial variables, but this interpretation can only be advanced tentatively in light of the lack of control-experimental group differences. Reading difficulty level was not significantly related to outcomes. Full article

The recent scientific literature abounds in proposals of seizure forecasting methods that exploit machine learning to automatically analyze electroencephalogram (EEG) signals. Deep learning algorithms seem to achieve a particularly remarkable performance, suggesting that the implementation of clinical devices for seizure prediction might be within reach. However, most of the research evaluated the robustness of automatic forecasting methods through randomized cross-validation techniques, while clinical applications require much more stringent validation based on patient-independent testing. In this study, we show that automatic seizure forecasting can be performed, to some extent, even on independent patients who have never been seen during the training phase, thanks to the implementation of a simple calibration pipeline that can fine-tune deep learning models, even on a single epileptic event recorded from a new patient. We evaluate our calibration procedure using two datasets containing EEG signals recorded from a large cohort of epileptic subjects, demonstrating that the forecast accuracy of deep learning methods can increase on average by more than 20%, and that performance improves systematically in all independent patients. We further show that our calibration procedure works best for deep learning models, but can also be successfully applied to machine learning algorithms based on engineered signal features. Although our method still requires at least one epileptic event per patient to calibrate the forecasting model, we conclude that focusing on realistic validation methods allows to more reliably compare different machine learning approaches for seizure prediction, enabling the implementation of robust and effective forecasting systems that can be used in daily healthcare practice. Full article

In this study, we propose a novel method for detecting cyberattack behaviors by leveraging the combined strengths of large language models and a synchronized attention mechanism. Extensive experiments conducted on diverse datasets, including server logs, financial behaviors, and comment data, demonstrate the significant advantages of this method over existing models such as Transformer, BERT, OPT-175B, LLaMa, and ChatGLM3-6B in key performance metrics such as precision, recall, and accuracy. For instance, on the server log dataset, the method achieved a precision of 93%, a recall of 91%, and an accuracy of 92%; on the financial behavior dataset, it reached a precision of 90%, a recall of 87%, and an accuracy of 89%; and on the comment data dataset, it excelled with a precision of 95%, a recall of 93%, and an accuracy of 94%. The introduction of a synchronized attention mechanism and a newly designed synchronized loss function proved especially effective, enhancing the method’s ability to process multi-source data and providing superior performance in identifying complex cyberattack patterns. Ablation experiments further validated the crucial roles of these innovations in boosting model performance: the synchronous attention mechanism substantially improved the model’s precision, recall, and accuracy to 93%, 89%, and 91% respectively, far exceeding other attention mechanisms. Similarly, the synchronized loss showcased a significant advantage, achieving the best performance across all tested metrics compared to traditional cross-entropy loss, focal loss, and MSE. These results underscore the method’s ability to deeply mine and analyze semantic information and contextual relationships within text data as well as to effectively integrate and process multimodal data, thereby offering strong technical support for the accurate and efficient detection of cyberattack behaviors. Full article

Microorganisms, microbiomes, and their products (e.g., enzymes, metabolites, antibiotics, etc.) are key players in the functioning of both natural and anthropized Earth ecosystems; they can be exploited for both research purposes and biotechnological applications, including fighting the big challenges of our era, such as climate change. Culture collections (CCs) and microbial Biological Resource Centres (mBRCs) are repositories of microorganisms that investigate and safeguard biodiversity and facilitate the scientific and industrial communities’ access to microbial strains and related know-how by providing external users with skills and services. Considering this, CCs and mBRCs are pivotal institutions for the valorisation of microorganisms, the safeguarding of life, and the fostering of excellent bioscience. The aim of this review is to present the state-of-the-art of Italian CCs and mBRCs, highlighting strengths, weaknesses, threats, and opportunities. Italy is, indeed, a hotspot of microbial biodiversity with a high rate of endemism and incredible potential, not only for the food and beverage sector (i.e., “Made in Italy” products), where microorganisms can have a beneficial or a spoiling function, but also to guarantee environmental sustainability and foster the bioeconomy through the design of new bioprocesses and products. However, weaknesses, such as the lack of management rules in accordance with international quality standards, are also analysed and ways of overcoming them are discussed. In this context, an overview is given of the Joint Research Unit MIRRI-IT and the European-funded SUS-MIRRI.IT project, which aims to improve the management and sustainability of Italian microbial collections, and serves as a starting point for an innovative revolution in the context of CCs and mBRCs worldwide. Full article

Public green spaces (PGSs) play a positive role in urban social sustainability and solidarity, as all urban dwellers can access them without discrimination or restrictions, but urbanization usually leads to an extreme shortage of PGSs and thus it becomes an important spatial resource that is competed for by different groups, especially migrant populations. Taking the Macau Peninsula as an example, this study employed a hybrid analysis approach, including the spatial Gini coefficient, spatial share index and spatial quality assessment, to look at the PGS injustice in high-density post-colonial areas. The results showed that (1) there is a “spatial mismatch” in the Peninsula’s PGS; (2) significant PGS service differences have been found between the colonial group (Portuguese) and immigrant group (Southeast Asian); and (3) a comparative analysis of the changes in the equity of PGSs over the past 40 years reveals that the PGS tends to be equitable overall, but the differences between groups have gradually increased. PGS injustice mainly depends on the spatial production mechanism during the colonial period of Macau and the spatial selection and limitation of groups due to differential social integration. Based on this, this work proposes recommendations for the planning and construction of PGS in terms of urban renewal and social sustainability, as well as new reclamation areas, in Macau. This study broadens the field and helps to improve the PGS inequality in high-density post-colonial areas, aiding regional sustainable development. Full article

Early detection of infant pathologies by non-invasive means is a critical aspect of pediatric healthcare. Audio analysis of infant crying has emerged as a promising method to identify various health conditions without direct medical intervention. In this study, we present a cutting-edge machine learning model that employs audio spectrograms and transformer-based algorithms to classify infant crying into distinct pathological categories. Our innovative model bypasses the extensive preprocessing typically associated with audio data by exploiting the self-attention mechanisms of the transformer, thereby preserving the integrity of the audio’s diagnostic features. When benchmarked against established machine learning and deep learning models, our approach demonstrated a remarkable 98.69% accuracy, 98.73% precision, 98.71% recall, and an F1 score of 98.71%, surpassing the performance of both traditional machine learning and convolutional neural network models. This research not only provides a novel diagnostic tool that is scalable and efficient but also opens avenues for improving pediatric care through early and accurate detection of pathologies. Full article

Gas detection is crucial for detecting environmentally harmful gases. Organic field-effect transistor (OFET)-based gas sensors have attracted attention due to their promising performance and potential for integration into flexible and wearable devices. This review examines the operating mechanisms of OFET-based gas sensors and explores methods for improving sensitivity, with a focus on porous structures. Researchers have achieved significant enhancements in sensor performance by controlling the thickness and free volume of the organic semiconductor layer. Additionally, innovative fabrication techniques like self-assembly and etching have been used to create porous structures, facilitating the diffusion of target gas molecules, and improving sensor response and recovery. These advancements in porous structure fabrication suggest a promising future for OFET-based gas sensors, offering increased sensitivity and selectivity across various applications. Full article

The paulownia bagworm, Clania variegata Snell, is an economically important pest of agriculture and forests. The sex pheromone of this pest and its stereoisomers were synthesized, and two of the stereoisomers were prepared for the first time. Our strategy was efficient and mainly included the ring-opening reaction of (S)-2-methyloxirane, the coupling of chiral sulfonate, the oxidative cleavage of olefin, and Yamaguchi esterification. Moreover, the overall yields of our synthesis were 23–29%, with eight steps in the longest route. Full article

Enhancing the efficiency of intercity transportation networks is crucial for sustainable regional transport development, significantly impacting travel behaviors and energy consumption. The transportation infrastructure within the city cluster is rapidly developing to accommodate the increasing traffic demand, necessitating substantial investments. It is imperative to investigate the effectiveness of intercity traffic within urban clusters, to evaluate the influence of transportation infrastructure enhancements on regional traffic efficiency. Circuity is a conventional metric used to assess the efficiency of transportation networks, primarily emphasizing distance, while overlooking factors such as travel time and traffic flow. In this study, the concept of circuity has been redefined in terms of travel time and has been referred to as the transportation network travel speed. Subsequently, the amalgamation of travel speed within the transportation network and traffic flow culminates in the proposition of Flow-Weighted Time Circuity (FWTC). Real-time intercity navigation data, offering accurate travel time estimations, are utilized to analyze the spatial distribution of intercity transport efficiency in the seven major city clusters of China, via both automobile and train modes of transportation. The results indicate that (1) as the travel distance extends, the speed of transportation within the network typically increases, albeit with increasing fluctuations, especially in the case of intercity train travel; (2) concerning the efficiency of intercity automobile travel, most city clusters demonstrate satisfactory performance, with the exception of the Guanzhong Plain. The Yangtze River Delta and Beijing–Tianjin–Heibei regions stand out for their superior performance. In terms of intercity train efficiency, the Yangtze River Delta, Beijing–Tianjin–Heibei, and Mid-Yangtze River regions exhibit higher levels of efficiency in intercity train transportation, while the Guanzhong Plain city cluster falls behind in this aspect. On the whole, the efficiency of intercity travel using automobiles surpasses that of train travel, indicating a pressing need for improvement in the latter. Full article

This study examines the effects of three interactive voice assistant (VA) features (responsiveness, ubiquitous connectivity, and personalization) on consumer happiness. An online survey was administered to 316 VA consumers, and the data were analyzed using structural equation modeling with SmartPLS 4 software. The results indicate that VA responsiveness, ubiquitous connectivity, and personalization have significant effects on consumer happiness. This study also provides evidence that consumer happiness is influenced by VA features through the mediating roles of autonomy and timeliness. Notably, perceived privacy risk has a dual effect, negatively affecting happiness but positively moderating the relationship between autonomy and happiness, suggesting a complex interplay between benefits and concerns in user interactions with VAs. This study highlights the need for VA businesses to consider both the enhancing and mitigating factors of technology for user experiences. Furthermore, our findings have significant implications for VA businesses and executives, suggesting that improved interactions through these VA features can better serve consumers and enhance their experiences. Full article

Arbuscular mycorrhizal (AM) fungi can establish a mutualistic relationship with the roots of most terrestrial plants to increase plant nutrient uptake. The effects of potassium uptake and transport by AM symbiosis are much less reported compared to other nutrients. In this research, a heterologous yeast system was used to verify that the LbHAK has capacity for potassium uptake. The split-roots system implemented using seedlings of Lycium barbarum confirmed that R. irregularis locally induced LbHAK expression, which means that LbHAK is only expressed in mycorrhizal roots. Furthermore, the impacts of overexpression of LbHAK on the growth, nutrients and water uptake, and transport of mycorrhizal tobacco (inoculation with Rhizophagus irregularis) at 0.2 mM and 2 mM K conditions were assessed. The mycorrhizal tobacco growth and potassium accumulation were significantly enhanced through LbHAK overexpression in tobacco. In addition, overexpression of LbHAK substantially enhanced phosphorus content, while stimulating the expression of NtPT4, Rir-AQP1, and Rir-AQP2 in mycorrhizal tobacco. Moreover, LbHAK overexpression greatly promoted AM colonization. LbHAK has a potential role in facilitating potassium absorption through the mycorrhizal pathway, and overexpression of LbHAK in tobacco may promote the transport of potassium, phosphorus, and water from AM fungi to tobacco. These data imply the important roles played by the LbHAK in AM-fungi-induced potassium uptake in L. barbarum and in improving plant nutrients and AM colonization. Full article

Glycosphingolipids (GSLs), a subtype of glycolipids containing sphingosine, are critical components of vertebrate plasma membranes, playing a pivotal role in cellular signaling and interactions. In human articular cartilage in osteoarthritis (OA), GSL expression is known notably to decrease. This review focuses on the roles of gangliosides, a specific type of GSL, in cartilage degeneration and regeneration, emphasizing their regulatory function in signal transduction. The expression of gangliosides, whether endogenous or augmented exogenously, is regulated at the enzymatic level, targeting specific glycosyltransferases. This regulation has significant implications for the composition of cell-surface gangliosides and their impact on signal transduction in chondrocytes and progenitor cells. Different levels of ganglioside expression can influence signaling pathways in various ways, potentially affecting cell properties, including malignancy. Moreover, gene manipulations against gangliosides have been shown to regulate cartilage metabolisms and chondrocyte differentiation in vivo and in vitro. This review highlights the potential of targeting gangliosides in the development of therapeutic strategies for osteoarthritis and cartilage injury and addresses promising directions for future research and treatment. Full article

Information technology and statistical modeling have made significant contributions to smart agriculture. Machine vision and hyperspectral technologies, with their non-destructive and real-time capabilities, have been extensively utilized in the non-destructive diagnosis and quality monitoring of crops and seeds, becoming essential tools in traditional agriculture. This work applies these techniques to address the color classification of rapeseed, which is of great significance in the field of rapeseed growth diagnosis research. To bridge the gap between machine vision and hyperspectral technology, a framework is developed that includes seed color calibration, spectral feature extraction and fusion, and the recognition modeling of three seed colors using four machine learning methods. Three categories of rapeseed coat colors are calibrated based on visual perception and vector-square distance methods. A fast-weighted visibility graph method is employed to map the spectral reflectance sequences to complex networks, and five global network attributes are extracted to fuse the full-band reflectance as model input. The experimental results demonstrate that the classification recognition rate of the fused feature reaches 0.943 under the XGBoost model, confirming the effectiveness of the network features as a complement to the spectral reflectance. The high recognition accuracy and simple operation process of the framework support the further application of hyperspectral technology to analyze the quality of rapeseed. Full article

A Hanok refers to a traditional Korean architectural structure. Construction structures undergo gradual, rather than instantaneous, transformations due to material degradation and deterioration in joint durability. Moreover, the detection of a structural problem by a nonexpert has severe implications for the safety of the structure. In particular, the precise effects of natural disasters, including storms, earthquakes, heavy snowfall, and structural defects, on structures are hard to determine. Additionally, manuals are limited by their reliance on quantitative assessments, which can pose difficulties for nonspecialists when it comes to recording numerical data. To solve this problem, 3D scanners have been widely employed in evaluating Hanoks, particularly those assigned as cultural heritage by the government. While those assigned as cultural heritage assets are systematically managed by experts and through budgets, the management system for Hanoks inhabited by the public has been overlooked. To fill this gap, this study focused on digital devices that are accessible to nonexperts as replacements for professional 3D scanners. Specifically, data from photos of a Hanok taken with smartphones were extracted to generate objective numerical data. AI training data for Hanoks were used to train the YOLOv8 algorithm and Segment Anything Model (SAM). The leaning values of columns, which constitute a fundamental structural component of a Hanok, were calculated using photographs that precisely captured the columns. The direction and distance of the column’s movement were extracted for visualization. To ensure the reliability of these values, the Hanok under investigation was 3D-scanned. Comparing the numerical values revealed a negligible margin of error, which confirmed the reliability of the photographic data values. Five-tier safety states (good, observation, caution, danger, and very dangerous) were defined based on the column movement distance by analyzing the real measurement data of government-managed Hanoks and used to visualize the structural condition of Hanoks. Therefore, nonexperts can determine the structural safety of a Hanok using objective numerical data, even in situations where its progressive deformation is not readily apparent. Objective numerical analysis based on reliably collected data allows nonexperts to accurately diagnose structural safety, thus facilitating prompt and suitable actions. The results of this study can serve to enhance the stability and longevity of Hanok structures, thus facilitating sustainable maintenance and management. Full article

Bitterness from phenylthiocarbamide and 6-n-propylthiouracil (PROP) varies with polymorphisms in the TAS2R38 gene. Three SNPs form two common (AVI, PAV) and four rare haplotypes (AAI, AAV, PVI, and PAI). AVI homozygotes exhibit higher detection thresholds and lower suprathreshold bitterness for PROP compared to PAV homozygotes and heterozygotes, and these differences may influence alcohol and vegetable intake. Within a diplotype, substantial variation in suprathreshold bitterness persists, and some AVI homozygotes report moderate bitterness at high concentrations. A second receptor encoded by a gene containing a functional polymorphism may explain this. Early work has suggested that PROP might activate TAS2R4 in vitro, but later work did not replicate this. Here, we identify three TAS2R4 SNPs that result in three diplotypes—SLN/SLN, FVS/SLN, and FVS/FVS—which make up 25.1%, 44.9%, and 23.9% of our sample. These TAS2R4 haplotypes show minimal linkage disequilibrium with TAS2R38, so we examined the suprathreshold bitterness as a function of both. The participants (n = 243) rated five PROP concentrations in duplicate, interleaved with other stimuli. As expected, the TAS2R38 haplotypes explained ~29% (p < 0.0001) of the variation in the bitterness ratings, with substantial variation within the haplotypes (AVI/AVI, PAV/AVI, and PAV/PAV). Notably, the TAS2R4 diplotypes (independent of the TAS2R38 haplotypes) explained ~7–8% of the variation in the bitterness ratings (p = 0.0001). Given this, we revisited if PROP could activate heterologously expressed TAS2R4 in HEK293T cells, and calcium imaging indicated 3 mM PROP is a weak TAS2R4 agonist. In sum, our data are consistent with the second receptor hypothesis and may explain the recovery of the PROP tasting phenotype in some AVI homozygotes; further, this finding may potentially help explain the conflicting results on the TAS2R38 diplotype and food intake. Full article

Convolutional neural networks (CNNs) have demonstrated remarkable performance in many areas but require significant computation and storage resources. Quantization is an effective method to reduce CNN complexity and implementation. The main research objective is to develop a scalable quantization algorithm for CNN hardware design and model the performance metrics for the purpose of CNN implementation in resource-constrained devices (RCDs) and optimizing layers in deep neural networks (DNNs). The algorithm novelty is based on blending two quantization techniques to perform full model quantization with optimum accuracy, and without additional neurons. The algorithm is applied to a selected CNN model and implemented on an FPGA. Implementing CNN using broad data is not possible due to capacity issues. With the proposed quantization algorithm, we succeeded in implementing the model on the FPGA using 16-, 12-, and 8-bit quantization. Compared to the 16-bit design, the 8-bit design offers a 44% decrease in resource utilization, and achieves power and energy reductions of 41% and 42%, respectively. Models show that trading off one quantization bit yields savings of approximately 5.4K LUTs, 4% logic utilization, 46.9 mW power, and 147 $\mathsf{\mu }$J energy. The models were also used to estimate performance metrics for a sample DNN design. Full article

An observational cohort study of patients diagnosed with endometrial cancer (EC) stage IA G1, or atypical endometrial hyperplasia (AEH), undergoing organ-preserving treatment, was conducted. Objective of the study: To determine CDO1, PITX2, and CDH13 gene methylation levels in early endometrial cancer and atypical hyperplasia specimens obtained before organ-preserving treatment in the patients with adequate response and with insufficient response to hormonal treatment. Materials and methods: A total of 41 endometrial specimens obtained during diagnostic uterine curettage in women with EC (n = 28) and AEH (n = 13), willing to preserve reproductive function, were studied; 18 specimens of uterine cancer IA stage G1 from peri- and early postmenopausal women (comparison group) were included in the study. The control group included 18 endometrial specimens from healthy women obtained by diagnostic curettage for missed abortion and/or intrauterine adhesions. Methylation levels were analyzed using the modified MS-HRM method. Results: All 13 women with AEH had a complete response (CR) to medical treatment. In the group undergoing organ-preserving treatment for uterine cancer IA stage G1 (n = 28), 14 patients had a complete response (EC CR group) and 14 did not (EC non-CR group). It was found that all groups had statistically significant differences in CDO1 gene methylation levels compared to the control group (p < 0.001) except for the EC CR group (p = 0.21). The p-value for the difference between EC CR and EC non-CR groups was <0.001. The differences in PITX2 gene methylation levels between the control and study groups were also significantly different (p < 0.001), except for the AEH group (p = 0.21). For the difference between EC CR and EC non-CR groups, the p-value was 0.43. For CDH13 gene methylation levels, statistically significant differences were found between the control and EC non-CR groups (p < 0.001), and the control and EC comparison groups (p = 0.005). When comparing the EC CR group with EC non-CR group, the p-value for this gene was <0.001. The simultaneous assessment of CDO1 and CDH13 genes methylation allowed for an accurate distinction between EC CR and EC non-CR groups (AUC = 0.96). Conclusion: The assessment of CDO1 and CDH13 gene methylation in endometrial specimens from patients with endometrial cancer (IA stage G1), scheduled for medical treatment, can predict the treatment outcome. Full article