Early Treatment Planning Research Articles

Reflections on the clinical diagnosis and management of Turner syndrome

There is a delay in the clinical diagnosis of Turner syndrome (TS), particularly for patients with mosaic karyotypes. This diagnostic delay can hinder age-appropriate treatments and lead to adverse health outcomes. Therefore, it is necessary to explore improvement measures for early diagnosis and treatment plans based on the current clinical situation. Furthermore, as research progresses, the focus of clinical diagnosis and treatment of TS is gradually expanding to multiple aspects, including cardiovascular health, fertility, and transitional care, in order to improve the prognosis and quality of life of the patients. This paper discusses the current clinical status and management key points of TS diagnosis and treatment, aiming to provide insights for improving the management of TS.

Epileptic encephalopathy, autism and cognitive deficit caused by the SYNGAP1 gene mutation

The paper analyzes data from scientific publications and presents a clinical case study of a rare genetic epileptic encephalopathy caused by a mutation in the SYNGAP1 gene. The case study focuses on a 4-year-old girl who has been diagnosed with epileptic encephalopathy due to the mutation. The paper describes the anamnesis of the child’s illness, including family history, neurological, neuropsychological, and speech assessments, as well as the results of genetic testing, electroencephalography, and magnetic resonance imaging (MRI). The findings indicate that the main symptoms of the condition are typically epilepsy, autism spectrum disorder, difficulty with phrasal speech, and mental retardation. Common types of seizures include atypical absence seizures, myoclonic seizures, atonic seizures, and eyelid myoclonia with absences. On the electroencephalogram, there is a slowdown in occipital activity and diffuse, prolonged «peak-polypic-slow-wave» complexes. Pathognomonic neuroimaging changes in the brain are typically absent. Valproic acid, levetiracetam, and ethosuximide have been shown to be the most effective treatments for controlling epileptic seizures. Due to the rarity of this syndrome, the authors have provided a detailed clinical case report from their practice.Conclusion. SYNGAP1-related epileptic encephalopathy has a specific clinical presentation, including characteristic EEG findings and a particular pattern of seizures. The diagnostic approach for children with this condition, autism spectrum disorder, and delayed language development should include video electroencephalography with sleep deprivation, as well as genetic testing if necessary, using next-generation sequencing, to ensure early detection and appropriate treatment planning.

Trop2-Targeted Molecular Imaging in Solid Tumors: Current Advances and Future Outlook.

Trophoblast cell surface antigen 2 (Trop2), a transmembrane glycoprotein, plays a dual role in physiological and pathological processes. In healthy tissues, Trop2 facilitates development and orchestrates intracellular calcium signaling. However, its overexpression in numerous solid tumors shifts its function toward driving cell proliferation and metastasis, thus leading to a poor prognosis. The clinical relevance of Trop2 is underscored by its utility as both a biomarker for diagnostic imaging and a target for therapy. Notably, the U.S. Food and Drug Administration (FDA) has approved sacituzumab govitecan (SG), a novel Trop2-targeted agent, for treating triple-negative breast cancer (TNBC) and refractory urothelial cancer, highlighting the significance of Trop2 in clinical oncology. Molecular imaging, a powerful tool for visualizing and quantifying biological phenomena at the molecular and cellular levels, has emerged as a critical technique for studying Trop2. This approach encompasses various modalities, including optical imaging, positron emission tomography (PET), single photon emission computed tomography (SPECT), and targeted antibodies labeled with radioactive isotopes. Incorporating Trop2-targeted molecular imaging into clinical practice is vital for the early detection, prognostic assessment, and treatment planning of a broad spectrum of solid tumors. Our review captures the latest progress in Trop2-targeted molecular imaging, focusing on both diagnostic and therapeutic applications across diverse tumor types, including lung, breast, gastric, pancreatic, prostate, and cervical cancers, as well as salivary gland carcinomas. We critically evaluate the current state by examining the relevant applications, diagnostic accuracy, therapeutic efficacy, and inherent limitations. Finally, we analyze the challenges impeding widespread clinical application and offer insights into strategies for advancing the field, thereby guiding future research endeavors.

Alzheimer's Disease as Type 3 Diabetes: Understanding the Link and Implications.

Alzheimer's disease (AD) and type 2 diabetes mellitus (T2DM) are two prevalent conditions that present considerable public health issue in aging populations worldwide. Recent research has proposed a novel conceptualization of AD as "type 3 diabetes", highlighting the critical roles of insulin resistance and impaired glucose metabolism in the pathogenesis of the disease. This article examines the implications of this association, exploring potential new avenues for treatment and preventive strategies for AD. Key evidence linking diabetes to AD emphasizes critical metabolic processes that contribute to neurodegeneration, including inflammation, oxidative stress, and alterations in insulin signaling pathways. By framing AD within this metabolic context, we can enhance our understanding of its etiology, which in turn may influence early diagnosis, treatment plans, and preventive measures. Understanding AD as a manifestation of diabetes opens up the possibility of employing novel therapeutic strategies that incorporate lifestyle modifications and the use of antidiabetic medications to mitigate cognitive decline. This integrated approach has the potential to improve patient outcomes and deepen our comprehension of the intricate relationship between neurodegenerative diseases and metabolic disorders.

Construction of OSA-related hypertension prediction model based on nomogram

Objective:This study aimed to construct a risk prediction model for obstructive sleep apnea（OSA） related hypertension based on the nomogram, and to explore the independent risk factors for OSA-related hypertension, so as to provide reference for clinical treatment decision-making. Methods:The clinical data of OSA patients diagnosed by polysomnography from October 2019 to December 2021 were collected retrospectively and randomly divided into training sets and validation sets. A total of 1 493 OSA patients with 27 variables were included. The least absolute shrinkage and selection operator（Lasso） logistic regression model was used to select potentially relevant features and establish a nomogram for OSA-related hypertension.The performance and clinical benefits of this nomogram were verified in terms of discrimination, calibration ability and clinical net benefit. Results:Multivariate logistic regression showed that body mass index（BMI）, family history of hypertension, lowest oxygen saturation（LSaO2）, age and cumulative percentage of total sleep time with oxygen saturation below 90% were independent risk factors for OSA-related hypertension. Lasso logistic regression identified BMI, family history of hypertension, LSaO2 and age as predictive factors for inclusion in the nomogram. The nomogram provided a favorable discrimination, with a C-indexes of 0.835（95% confidence interval[CI ]0.806-0.863） 0.865（95%CI 0.829-0.900） for the training and validation cohort, respectively, and well calibrated. The clinical decision curve analysis displayed that the nomogram was clinically useful. Conclusion:Compared with cumulative percentage of total sleep time with blood oxygen saturation below 90%, LSaO2 may have a greater impact on the incidence of OSA-related hypertension, and the effects of different times and degrees of hypoxia on OSA-related hypertension should be further explored in the future. Apnea hypopnea index involvement is weak in predicting OSA-related hypertension, and the blood oxygen index may be a better predictor variable. Furthermore, we established a risk prediction model for OSA-related hypertension patients using nomogram, and demonstrated that this prediction model was helpful to identify high-risk OSA-related hypertension patients. This model can provide early and individualized diagnosis and treatment plans, protect patients from the serious.

Artificial intelligence applications in cataract and refractive surgeries.

This review highlights the recent advancements in the applications of artificial intelligence within the field of cataract and refractive surgeries. Given the rapid evolution of artificial intelligence technologies, it is essential to provide an updated overview of the significant strides and emerging trends in this field. Key themes include artificial intelligence-assisted diagnostics and intraoperative support, image analysis for anterior segment surgeries, development of artificial intelligence-based diagnostic scores and calculators for early disease detection and treatment planning, and integration of generative artificial intelligence for patient education and postoperative monitoring. The impact of artificial intelligence on cataract and refractive surgeries is becoming increasingly evident through improved diagnostic accuracy, enhanced patient education, and streamlined clinical workflows. These advancements hold significant implications for clinical practice, promising more personalized patient care and facilitating early disease detection and intervention. Equally, the review also highlights the fact that only some of this work reaches the clinical stage, successful integration of which may benefit from our focus.

Enhancing MRI brain tumor classification: A comprehensive approach integrating real-life scenario simulation and augmentation techniques

Brain cancer poses a significant global health challenge, with mortality rates showing a concerning surge over recent decades. The incidence of brain cancer-related mortality has risen from 140,000 to 250,000, accompanied by a doubling in new diagnoses from 175,000 to 350,000. In response, magnetic resonance imaging (MRI) has emerged as a pivotal diagnostic tool, facilitating early detection and treatment planning. However, the translation of deep learning approaches to brain cancer diagnosis faces a critical obstacle: the scarcity of public clinical datasets reflecting real-world complexities. This study aims to bridge this gap through a comprehensive exploration and augmentation of training data. Initially, a battery of pre-trained deep models undergoes evaluation on a main brain cancer MRI “BT-MRI” dataset, yielding remarkable performance metrics, including 100% accuracy, precision, recall, and F1-Score, substantiated by the Score-CAM methodology. This initial success underscores the potential of deep learning in brain cancer diagnosis. Subsequently, the model’s efficacy undergoes further scrutiny using a supplementary brain cancer MRI “BCD-MRI” dataset, affirming its robustness and applicability across diverse datasets. However, the ultimate litmus test lies in confronting the model with synthetic testing datasets crafted to emulate real-world scenarios. The synthetic testing datasets, a BCD-MRI testing sub-dataset enriched with noise, blur, and simulated patient motion, reveal a sobering reality: the model’s performance plummets, exposing inherent limitations in generalization. To address this issue, a diverse set of optimization strategies and augmentation techniques, ranging from diverse optimizers to sophisticated data augmentation methods, are exhaustively explored. Despite these efforts, the problem of generalization persists. The breakthrough emerges with the integration of noise and blur as augmentation techniques during the training process. Leveraging Gaussian noise and Gaussian blur kernels, the model undergoes a transformative evolution, exhibiting newfound robustness and resilience. Retesting the refined model against the challenging synthetic datasets reveals a remarkable transformation, with performance metrics witnessing a notable ascent. This achievement underscores the important role of correct selection of data augmentation in fortifying the generalization of deep learning models for brain cancer diagnosis. This study not only advances the frontiers of diagnostic precision in brain cancer but also underscores the paramount importance of methodological rigor and innovation in confronting the complexities of real-world clinical scenarios.

Transformative Impact of Convolutional Neural Networks on Healthcare, Autonomous Systems, and Global Technological Advancements

Convolutional Neural Networks (CNNs) have significantly impacted various industries by enabling machines to process visual data with unprecedented accuracy. This paper explores the transformative effects of CNNs on key sectors such as healthcare, autonomous systems, security, and environmental monitoring. In healthcare, CNNs are used in medical imaging for early diagnosis and treatment planning, enhancing telemedicine capabilities. In autonomous systems, CNNs enable real-time object detection and navigation, contributing to the development of safer, more efficient vehicles. In security, CNNs power facial recognition systems, raising both opportunities and ethical concerns regarding privacy and surveillance. Environmental monitoring benefits from CNNs through climate change research and wildlife conservation efforts, where they analyze vast amounts of data for critical insights. The paper also addresses the challenges posed by CNNs, including data privacy, security, and algorithmic bias, emphasizing the need for ethical standards and regulatory frameworks. Future advancements in CNN architectures and their integration with other AI models are expected to expand their applicability further and improve performance across different domains. This analysis underscores the dual importance of technological progress and ethical considerations to ensure that the benefits of CNNs are equitably distributed, contributing positively to global technological development and societal well-being.

Enhancing biomedical imaging: the role of nanoparticle-based contrast agents.

Biomedical imaging plays a critical role in early detection, precise diagnosis, treatment planning, and monitoring responses, but traditional methods encounter challenges such as limited sensitivity, specificity, and inability to monitor therapeutic responses due to factors like short circulation half-life and potential toxicity. Nanoparticles are revolutionizing biomedical imaging as contrast agents across modalities like computed tomography (CT), optical, magnetic resonance imaging (MRI), and ultrasound, exploiting unique attributes such as those of metal-based, polymeric, and lipid nanoparticles. They shield imaging agents from immune clearance, extending circulation time, and enhancing bioavailability at tumor sites. This results in improved imaging sensitivity. The study highlights advancements in multifunctional nanoparticles for targeted imaging, tackling concerns regarding toxicity and biocompatibility. Critically evaluating conventional contrast agents, emphasizes the shortcomings that nanoparticles aim to overcome. This review provides insight into the current status of nanoparticle-based contrast agents, illuminating their potential to reshape therapeutic monitoring and precision diagnostics.

Clinical characteristics of severe influenza as a risk factor for febrile seizures in children: a retrospective analysis.

To retrospectively analyze the clinical characteristics and independent risk factors of severe influenza combined with febrile seizures, and to provide more basis for early clinical intervention. A total of 161 children with severe influenza were collected as study subjects and divided into convulsive (FC) group (40 cases) and non-convulsive (NFC) group (121 cases) according to whether they had febrile seizures. The demographic characteristics and clinical data of the two groups were analyzed. Multivariate logistic regression was used to analyze the risk factors of severe influenza combined with febrile seizures. The predictive efficacy was evaluated by receiver operating characteristic (ROC) curve analysis. (1) Multiple logistic regression analysis revealed that C-reactive protein (CRP) levels, Serum interleukin 6 (IL-6) levels, Days from onset of Flu symptoms to hospitalization, cerebrospinal fluid protein (CSF-TP) levels and the influenza virus type A (FluA) infection rate were found to be independent risk factors for severe influenza combined with febrile seizures in children. (2) ROC curve analysis showed that the cut-off value of CRP, Serum IL-6, Days from onset of Flu symptoms to hospitalization and CSF-TP were 7.57 mg/L, 9.84 pg/ml, 4.5 days and 194.8 mg/L, respectively. Children with severe influenza with CRP ≥ 7.57 mg/L, Serum IL-6 ≥ 9.84 pg/ml, Days from onset of Flu symptoms to hospitalization ≤4.5 days, CSF-TP ≥ 194.8 mg/L and FluA had a significantly increased risk of febrile seizures. It is useful for clinicians to determine the risk of severe influenza combined with febrile seizures, to adjust the early treatment plan, and to reduce the incidence of critically ill patients.

Multivalent supramolecular fluorescent probes for accurate disease imaging.

Optical imaging is a powerful tool for early disease detection and effective treatment planning, but its accuracy is often compromised by the uptake of imaging materials by the mononuclear phagocyte system (MPS). Herein, we leverage multivalent host-guest interactions between cyanine dyes and β-cyclodextrin polymers to develop supramolecular probes with enhanced stability, optical, and transport profiles for accurate in vivo imaging. These multivalent interactions not only ensure the stability of the probes but also enhance fluorescence efficiency by minimizing nonradiative decay. Our self-assembly approach effectively modulates probe size and surface properties, enabling evasion of MPS clearance and promoting prolonged bloodstream circulation, thereby improving the signal-to-background ratio for imaging. The effectiveness of our design is demonstrated by substantial advancements in the early diagnosis of acute kidney injury and by providing high-contrast imaging and precise surgical navigation across various tumor models. Our strategy not only advances optical imaging materials toward clinical translation but also establishes a versatile platform applicable to multiple imaging modalities.

Spectrum of liver affection in children with sickle cell disease: case series

BackgroundSickle cell hepatopathy (SCH) is a relatively uncommon complication of sickle cell disease (SCD), yet it does not accommodate variations in presentation, outcome, or severity according to age.AimTo present SCH characteristics and assess the effect of implementation of a high-suspicion systematic diagnostic approach and early intervention plan of management.MethodsThis case series presented the characteristics of five children with SCD with variable hepatic manifestation and implemented a diagnostic approach that included testing the transaminases and bilirubin in any patient with any suspicion of liver affection.ResultsThe five patients had a complicated SCD history. They all presented with fever, abdominal pain, and deepening of jaundice. The final diagnosis was reached with a more individualized approach; two had significant coagulopathy and were diagnosed with sickle cell intrahepatic cholestasis, while one had normal synthetic functions of the liver with rising transaminases and bilirubin levels, as well as high titer of Epstein–Barr virus diagnosed as acute viral hepatitis complicated with sickle cell hepatic crisis. One other patient had markedly elevated bilirubin with mild elevation of transaminases, and magnetic resonance cholangiopancreatography showed acute extrahepatic biliary dilatation treated by endoscopic removal of the stone. The fifth patient proved to have portal vein thrombosis by portal duplex causing portal hypertension and decompensated liver. The management plan included early exchange transfusion to keep their hemoglobin S (HbS) below 15% which was performed in three of the patients, in addition to aggressive supportive measures for correction of coagulopathy with full recovery and normalization of their liver functions.ConclusionDespite the diagnostic challenges, the lack of standard diagnostic criteria, and the overlapping clinical presentation of SCH, the management and outcomes improved by following a systematic diagnostic approach.

The Role of Contrast-Enhanced Imaging Methods in Breast Cancer Early Diagnostics and Treatment Planning

Оn March 27, 2023, а multidisciplinary Advisory Board meeting was held in Moscow with the participation of Е.V. Artamonova, Е.А. Busko, V.V. Didenko, А.D. Zikiryakhodzhaev, М.S. Karpova, G.Е. Kvetenadze, P.V. Krivorot’ko, М.L. Mazo, А.V. Petrovsky, О.S. Puchkova, S.V. Serebryakova under the chairmanship of I.Е. Tyurin and N.I. Rozhkova. The participants discussed different issues of early diagnostics and treatment planning of breast cancer. We present the conclusion made by the Advisory Board.

CUTTING-EDGE CNN APPROACHES FOR BREAST HISTOPATHOLOGICAL CLASSIFICATION: THE IMPACT OF SPATIAL ATTENTION MECHANISMS

This paper investigates advanced techniques for breast Histopathological Classification using two robust convolutional neural network (CNN) architectures: Inception V3 and VGG19. Spatial attention mechanisms are integrated to enhance the models' capability to focus on crucial regions within histology images. These enhancements improve diagnostic accuracy by allowing the models to concentrate on critical features for accurate detection. The research leverages two prominent datasets, BACH for multiclass classification and BreaKHis for binary classification, which provides extensive collections of breast cancer histology images, enabling thorough training and evaluation of the proposed models. InceptionV3 with spatial attention mechanism achieved an accuracy of 99.73% for binary classification and 99.06% for multiclass classification. Integrating spatial attention mechanisms is anticipated to significantly advance the development of automated breast cancer detection systems, offering potential improvements in early diagnosis and treatment planning. This study demonstrates how combining state-of-the-art CNN architectures with attention mechanisms can significantly improve medical image analysis, ultimately contributing to better patient outcomes.

LungHist700: A dataset of histological images for deep learning in pulmonary pathology

Accurate detection and classification of lung malignancies are crucial for early diagnosis, treatment planning, and patient prognosis. Conventional histopathological analysis is time-consuming, limiting its clinical applicability. To address this, we present a dataset of 691 high-resolution (1200 × 1600 pixels) histopathological lung images, covering adenocarcinomas, squamous cell carcinomas, and normal tissues from 45 patients. These images are subdivided into three differentiation levels for both pathological types: well, moderately, and poorly differentiated, resulting in seven classes for classification. The dataset includes images at 20x and 40x magnification, reflecting real clinical diversity. We evaluated image classification using deep neural network and multiple instance learning approaches. Each method was used to classify images at 20x and 40x magnification into three superclasses. We achieved accuracies between 81% and 92%, depending on the method and resolution, demonstrating the dataset’s utility.

Applications of AI (Artificial Intelligence) In Diagnosis of Breast Cancer

Breast cancer is a leading cause of cancer-related deaths worldwide. Early detection and accurate diagnosis are crucial for improving patient outcomes. Artificial intelligence (AI) has emerged as a promising tool in the fight against breast cancer. This research report explores the potential applications of AI in various stages of breast cancer management, including early detection, diagnosis, treatment planning, and prognosis prediction. AI algorithms can analyze mammograms and other imaging data to identify suspicious lesions with greater accuracy than traditional methods. Additionally, AI-powered tools can assist in the classification of breast tumors, helping to determine the most appropriate course of treatment. Furthermore, AI can be used to predict the likelihood of recurrence and metastasis, enabling personalized monitoring and follow-up care. This research report presents a comprehensive review of the current state of AI in breast cancer research and highlights the potential benefits and challenges associated with its implementation. By leveraging the power of AI, healthcare providers can improve breast cancer outcomes and enhance the quality of life for patients.

An Improved Hyper Spectral Imaging for Accurate Disease Diagnosis in Sustainable Medical Environments

Hyper spectral imaging (HSI) has emerged as a powerful technique for accurate disease diagnosis in medical environments. It provides high-resolution images with detailed spectral information, making it possible to identify subtle differences between healthy and diseased tissues. However, current HSI systems face challenges in terms of accuracy and efficiency, limiting their widespread application in sustainable medical environments. To overcome these challenges, our team has developed an improved HSI system that utilizes state-of-the-art spectral imaging technology and machine learning algorithms. This system is capable of capturing and analyzing a wider range of spectral data, enabling more precise identification of disease-specific spectral signatures. Furthermore, our system has been optimized to operate with minimal power consumption, making it environmentally friendly and suitable for sustainable medical environments. The improved HSI system has been successfully tested in clinical settings and has shown promising results in accurately diagnosing various diseases such as cancer, dermatitis, and cardiovascular conditions. Its high accuracy and fast processing time make it a valuable tool for early disease detection and treatment planning. Moreover, the ability to operate with low energy consumption makes it a sustainable solution for medical facilities in resourcelimited areas. In addition to its accuracy and efficiency, our improved HSI system is also user-friendly and can be easily integrated into existing medical imaging systems.

Evaluating the Quality of Screening Process for High-Risk Pregnancies in Paser District, East Kalimantan

Health service programme success is measured by maternal mortality. There have been efforts to reduce maternal and neonatal fatalities. Field observations suggest that high-risk pregnancy referral rates are still low, delaying access to better services. Screening for high-risk pregnancies is an operational technique to prevent maternal and newborn emergency issues by allowing early treatment and referral planning. Health cadres and personnel can provide quality information. Lack of knowledge and awareness will harm society, especially pregnant women, in dealing and seeking health care. This study uses descriptive methods to assess high-risk pregnancy screening in Paser Regency, East Kalimantan, by collecting individual data and watching written and verbal behaviour. This research is qualitative and phenomenological. Health workers, ob-gyns, GPs, and pregnant women were informants. The data was collected through interviews from November to December 2023. The research found that high-risk pregnancy screening was still poor due to lack of knowledge, understanding, staff, time, site, and community culture. This research aims to improve high-risk pregnancy screening in Paser Regency, East Kalimantan Province, so that the policy can become permanent and help the planned referral process by motivating, socialising, training health cadres, and requiring cross-sectoral and cross-program support.

Predictive analysis of lactate clearance on the prognosis of patients with large burns

Aims: To examine burn shock monitoring and the connection between lactate clearance and shock prognosis in individuals with severe burns. Materials and methods: This retrospective analysis comprised 100 patients with significant burns treated in our hospital between August 2017 and August 2021. The patients were split into two groups based on whether they survived or not: 50 cases each in the survival and death groups. Both groups had their blood lactate levels, partial pressure of oxygen, and other relevant indices tested. Analysis was done on the correlation between lactate level, lactate clearance, and death as well as the association between lactate clearance and prognosis at each time and point. Results: The lactate clearance rates at 6 h, 12 h, 24 h and 24 h in the survival group were greater than those in the death group, and the differences were significant (p < 0.05). The lactate clearance rates at each time point were compared at a cut-off of 20%, and patients with 6 h and 12 h blood lactate clearance rates ≥20.0% had lower prognostic morbidity and mortality rates than those <20.0%, with a significant difference (p < 0.05). Conclusion: Lactate clearance is directly correlated with the prognosis of patients with severe burns, and survivors also have a high clearance rate. As a result, in patients with severe burns, lactate clearance monitoring during the shock phase can improve prognostic prediction and enable early treatment plan modification based on outcomes.

HATZFS predicts pancreatic cancer driver biomarkers by hierarchical reinforcement learning and zero-forcing set

The search for cancer biomarkers is of great significance for the early diagnosis and clinical treatment planning of pancreatic cancer. RNA transcription networks can effectively represent the interactions between RNA molecules, and the irregular perturbations in these interactions can lead to pathological states, making them commonly used for identifying cancer biomarkers. However, traditional network-based methods for identifying cancer biomarkers often rely on prior information and mutation data. Furthermore, most network controllability-based methods face the limitation of high computational complexity, preventing their integration with deep learning methods. In this paper, we propose a novel deep learning framework, called HATZFS, for identifying driver biomarkers in pancreatic cancer using RNA differential expression data. The proposed model combines hierarchical deep Q-network (HDQN), graph attention network (GAT), and zero-forcing set (ZFS). Firstly, a pancreatic cancer RNA transcription regulatory network is constructed to embed the complex relationship among Long non-coding RNA (lncRNA), microRNA (miRNA) and messenger RNA (mRNA). Then, we transform it into multiple subgraphs using graph sampling method, and apply GAT to learn the node features of the subgraphs. Finally, the HATZFS performs HDQN to select subgraphs and identify important RNA as driver nodes, and determining the controllability of the subgraphs based on ZFS. More important, the paper theoretically proves that when all subgraphs are controllable, the original graph is also controllable, and the union of the driver node sets of all subgraphs is equal to the driver node set of the original graph. To confirm the effectiveness of the proposed model, comprehensive experiments are conducted on the benchmark dataset consisting of 14 databases, comparing it with eight other algorithms. The experimental results demonstrate that the proposed model outperforms other methods. Overall, HATZFS not only provides the importance of all RNA molecules in the pancreatic cancer RNA regulatory network, but also identifies the driver node set of the network as driver biomarkers. Source code can be accessed at https://github.com/HongJieTongXue/HATZFS.