Forensic efficiency and population genetic construction of Guizhou Gelao minority from Southwest China revealed by a panel of 23 autosomal STR loci.

Short tandem repeats (STRs) are the most common genetic markers in forensic and human population genetics due to their high polymorphism, rapid detection, and reliable genotyping. To adapt the rapid growth of forensic DNA database and solve problems in disputed cases, a panel of 23 autosomal STR loci with high discriminating ability was constructed recently. The Tai-Kadai-speaking Gelao is the most ancient indigenous minority in Guizhou province, however, the forensic efficiency and population genetic structure remain poorly explored. Here, 490 Guizhou Gelao individuals from Southwest China were genotyped with the panel of 23 STRs using the Huaxia Platinum Kit. A total of 265 alleles were screened. The combined discrimination power and the combined probability of paternity were 0.9999 and 0.9999, respectively. This indicated the 23 loci had higher discrimination power in Guizhou Gelao and could be applied to forensic practice. Comprehensive population structures with reference populations from China and abroad using the neighbour-joining phylogenetic tree (N-J tree), multidimensional scaling, principal component analysis and heatmap demonstrated that Guizhou Gelao was genetically closer to Guizhou Han than other populations. Moreover, our results showed that a complex phylogenetic model was influenced by ethnic, geographic, and linguistic factors. Key points: The first batch of genetic data for 23 autosomal STRs in 490 Geolao individuals from Guizhou was provided.The 23 STR panel can afford high genetic polymorphisms and discrimination power and can be efficiently applied to forensic practice in Guizhou Gelao population.A complex phylogenetic model influenced by ethnic, geographic, and linguistic factors was uncovered.

Revolutionizing energy practices: Unleashing the power of artificial intelligence in corporate energy transition.

Corporate energy transition is crucial for long-term sustainable development. The widely discussed Artificial Intelligence (AI), as a disruptive technological innovation, is highly potential for enhancing environment performance. However, the specific impact of AI on the process of corporate energy transition and its underlying mechanisms have not been fully explored. This study focuses on A-share listed corporates in Shanghai and Shenzhen stock markets in China spanning from 2011 to 2021. Based on corporate annual report information and information from over 200,000 patent application texts, we innovatively construct indicators for corporate energy transition and AI technology application. Furthermore, we empirically investigate the impact of AI technology on corporate energy transition and its potential mechanisms through combining information asymmetry theory and institutional theory. The empirical results indicate that: 1) AI can drive corporate energy transition and the promoting effect of AI collaborative innovation on corporate energy transition should not be ignored. 2) AI can help corporates achieve energy transition through pathways such as mitigating information asymmetry, reducing financing constraints, adjusting sustainable development concepts and practices. 3) The driving effect of AI on corporate energy transition varies depending on the characteristics of different types of corporates, industries, and regions. This study provides strategic guidance and decision support for business managers and policymakers, assisting both corporates and governments in better utilizing AI technology during the social energy transition process to achieve a dual optimization of environmental and economic goals.

A study on the influencing factors of corporate digital transformation: empirical evidence from Chinese listed companies.

In an era where digital technology is reshaping business landscapes, understanding the factors that drive corporate digital transformation is essential. In this paper we explore these influencing factors, focusing on Chinese A-share listed companies from 2007 to 2021. Our approach involved a comprehensive analysis of multiple variables through regression techniques to determine their impact on digital transformation. The findings reveal the drive for reform in the digital transformation endeavours of enterprises. Notably, companies with higher gearing, overhead, and accounts receivable ratios exhibit a stronger inclination towards digital transformation. Conversely, enterprises in monopolistic industries and those at the inception stage of their life cycle show less propensity for such transformation. The findings of this research not only shed light on the strategic decisions behind digital transformation in response to financial and competitive challenges but also provide actionable insights for policymakers and business strategists. This study underscores the importance of contextualizing digital transformation efforts within the unique framework of industry characteristics and company development phases.

Effectiveness of Electroencephalography Neurofeedback for Improving Working Memory and Episodic Memory in the Elderly: A Meta-Analysis.

Background and Objective: Existing evidence indicates the potential benefits of electroencephalography neurofeedback (NFB) training for cognitive function. This study aims to comprehensively review all available evidence investigating the effectiveness of NFB on working memory (WM) and episodic memory (EM) in the elderly population. Material and Methods: A systematic search was conducted across five databases to identify clinical trials examining the impact of NFB on memory function in healthy elderly individuals or those with mild cognitive impairment (MCI). The co-primary outcomes focused on changes in WM and EM. Data synthesis was performed using a random-effects meta-analysis. Results: Fourteen clinical trials (n = 284) were included in the analysis. The findings revealed that NFB was associated with improved WM (k = 11, reported as Hedges' g = 0.665, 95% confidence [CI] = 0.473 to 0.858, p < 0.001) and EM (k = 12, 0.595, 0.333 to 0.856, p < 0.001) in the elderly, with moderate effect sizes. Subgroup analyses demonstrated that NFB had a positive impact on both WM and EM, not only in the healthy population (WM: k = 7, 0.495, 0.213 to 0.778, p = 0.001; EM: k = 6, 0.729, 0.483 to 0.976, p < 0.001) but also in those with MCI (WM: k = 6, 0.812, 0.549 to 1.074, p < 0.001; EM: k = 6, 0.503, 0.088 to 0.919, p = 0.018). Additionally, sufficient training time (totaling more than 300 min) was associated with a significant improvement in WM (k = 6, 0.743, 0.510 to 0.976, p < 0.001) and EM (k = 7, 0.516, 0.156 to 0.876, p = 0.005); however, such benefits were not observed in groups with inadequate training time. Conclusions: The results suggest that NFB is associated with enhancement of both WM and EM in both healthy and MCI elderly individuals, particularly when adequate training time (exceeding 300 min) is provided. These findings underscore the potential of NFB in dementia prevention or rehabilitation.

Development and Application of a Multidimensional Database for the Detection of Quaternary Ammonium Compounds and Their Phase I Hepatic Metabolites in Humans.

The COVID-19 pandemic has led to significantly increased human exposure to the widely used disinfectants quaternary ammonium compounds (QACs). Xenobiotic metabolism serves a critical role in the clearance of environmental molecules, yet limited data are available on the routes of QAC metabolism or metabolite levels in humans. To address this gap and to advance QAC biomonitoring capabilities, we analyzed 19 commonly used QACs and their phase I metabolites by liquid chromatography-ion mobility-tandem mass spectrometry (LC-IM-MS/MS). In vitro generation of QAC metabolites by human liver microsomes produced a series of oxidized metabolites, with metabolism generally occurring on the alkyl chain group, as supported by MS/MS fragmentation. Discernible trends were observed in the gas-phase IM behavior of QAC metabolites, which, despite their increased mass, displayed smaller collision cross-section (CCS) values than those of their respective parent compounds. We then constructed a multidimensional reference SQLite database consisting of m/z, CCS, retention time (rt), and MS/MS spectra for 19 parent QACs and 81 QAC metabolites. Using this database, we confidently identified 13 parent QACs and 35 metabolites in de-identified human fecal samples. This is the first study to integrate in vitro metabolite biosynthesis with LC-IM-MS/MS for the simultaneous monitoring of parent QACs and their metabolites in humans.

Targeting initial tumour-osteoclast spatiotemporal interaction to prevent bone metastasis.

Bone is the most common site of metastasis, and although low proliferation and immunoediting at the early stage make existing treatment modalities less effective, the microenvironment-inducing behaviour could be a target for early intervention. Here we report on a spatiotemporal coupling interaction between tumour cells and osteoclasts, and named the tumour-associated osteoclast 'tumasteoclast'-a subtype of osteoclasts in bone metastases induced by tumour-migrasome-mediated cytoplasmic transfer. We subsequently propose an in situ decoupling-killing strategy in which tetracycline-modified nanoliposomes encapsulating sodium bicarbonate and sodium hydrogen phosphate are designed to specifically release high concentrations of hydrogen phosphate ions triggered by tumasteoclasts, which depletes calcium ions and forms calcium-phosphorus crystals. This can inhibit the formation of migrasomes for decoupling and disrupt cell membrane for killing, thereby achieving early prevention of bone metastasis. This study provides a research model for exploring tumour cell behaviour in detail and a proof-of-concept for behaviour-targeting strategy.

Unlocking the Potential of Oxidative Asymmetric Catalysis with Continuous Flow Electrochemistry.

In the field of catalytic asymmetric synthesis, the less-treated path lies in oxidative catalytic asymmetric transformations. The hurdles of pinpointing the appropriate chemical oxidants and addressing their compatibility issues with catalysts and functionalities present significant challenges. Organic electrochemistry, employing traceless electrons for redox reactions, is underscored as a promising solution. However, the commonly used electrolysis in batch cells introduces its own set of challenges, hindering the advancement of electrochemical asymmetric catalysis. Here we introduce a microfluidic electrochemistry platform with single-pass continuous flow reactors that exhibits a wide-ranging applicability to various oxidative asymmetric catalytic transformations. This is exemplified through the sulfenylation of 1,3-dicarbonyls, dehydrogenative C-C coupling, and dehydrogenative alkene annulation processes. The unique properties of microfluidic electrochemical reactors not only eliminate the need for chemical oxidants but also enhance reaction efficiency and reduce the use of additives and electrolytes. These salient features of microfluidic electrochemistry expedite the discovery and development of oxidative asymmetric transformations. In addition, the continuous production facilitated by parallel single-pass reactors ensures straightforward reaction upscaling, removing the necessity for reoptimization across various scales, as evidenced by direct translation from milligram screening to hectogram asymmetric synthesis.

Hepatotoxicity and lipid metabolism disorders of 8:2 polyfluoroalkyl phosphate diester in zebrafish: In vivo and in silico evidence.

8:2 polyfluoroalkyl phosphate diester (8:2 diPAP) has been shown to accumulate in the liver, but whether it induces hepatotoxicity and lipid metabolism disorders remains largely unknown. In this study, zebrafish embryos were exposed to 8:2 diPAP for 7 d. Hepatocellular hypertrophy and karyolysis were noted after exposure to 0.5 ng/L 8:2 diPAP, suggesting suppressed liver development. Compared to the water control, 8:2 diPAP led to significantly higher triglyceride and total cholesterol levels, but markedly lower levels of low-density lipoprotein, implying disturbed lipid homeostasis. The levels of two peroxisome proliferator activated receptor (PPAR) subtypes (pparα and pparγ) involved in hepatotoxicity and lipid metabolism were significantly upregulated by 8:2 diPAP, consistent with their overexpression as determined by immunohistochemistry. In silico results showed that 8:2 diPAP formed hydrogen bonds with PPARα and PPARγ. Among seven machine learning models, Adaptive Boosting performed the best in predicting the binding affinities of PPARα and PPARγ on the test set. The predicted binding affinity of 8:2 diPAP to PPARα (7.12) was higher than that to PPARγ (6.97) by Adaptive Boosting, which matched well with the experimental results. Our results revealed PPAR - mediated adverse effects of 8:2 diPAP on the liver and lipid metabolism of zebrafish larvae.

Intravital photoacoustic brain stimulation with high-precision.

Significance: Neural regulation at high precision vitally contributes to propelling fundamental understanding in the field of neuroscience and providing innovative clinical treatment options. Recently, photoacoustic brain stimulation has emerged as a cutting-edge method for precise neuromodulation and shows great potential for clinical application. Aim: The goal of this perspective is to outline the advancements in photoacoustic brain stimulation in recent years. And, we also provide an outlook delineating several prospective paths through which this burgeoning approach may be substantively refined for augmented capability and wider implementations. Approach: First, the mechanisms of photoacoustic generation as well as the potential mechanisms of photoacoustic brain stimulation are provided and discussed. Then, the state-of-the-art achievements corresponding to this technology are reviewed. Finally, future directions for photoacoustic technology in neuromodulation are provided. Results: Intensive research endeavors have prompted substantial advancements in photoacoustic brain stimulation, illuminating the unique advantages of this modality for noninvasive and high-precision neuromodulation via a nongenetic way. It is envisaged that further technology optimization and randomized prospective clinical trials will enable a wide acceptance of photoacoustic brain stimulation in clinical practice. Conclusions: The innovative practice of photoacoustic technology serves as a multifaceted neuromodulation approach, possessing noninvasive, high-accuracy, and nongenetic characteristics. It has a great potential that could considerably enhance not only the fundamental underpinnings of neuroscience research but also its practical implementations in a clinical setting.

A nomogram for predicting risk factors of testicular salvage after testicular torsion in children.

OBJECTIVES: This study aimed to establish a nomogram for predicting the probability of testicular salvage after testicular torsion in children. METHODS: We retrospectively collected data of children with testicular torsion who were treated at Shenzhen Children's Hospital between September 2005 and August 2022. Of the training cohort, 113 patients who underwent orchiectomy and five with testicular atrophy after orchiopexy were included in the failed testicular salvage group. Additionally, 37 patients who underwent orchiopexy without postoperative testicular atrophy were included in the successful testicular salvage group. The predictive factors affecting testicular salvage were determined using univariate and multivariate logistic regression analyses; a nomogram was constructed. The nomogram was verified using data from the validation group. RESULTS: Using multivariate logistic regression analysis, the independent risk factors of testicular salvage after testicular torsion were symptom duration (p = 0.034), intratesticular blood flow (p = 0.003), spermatic cord torsion degree (p = 0.037), and monocyte count (odds ratio: 0.012, p = 0.036). A nomogram was established based on these four risk factors. In the training cohort, the area under the receiver operating characteristic curve was 0.969. The area under the receiver operating characteristic curve of the verification cohort was 0.965, indicating good discrimination ability of the nomogram. Increased symptom duration without intratesticular blood flow increased the monocyte count and spermatic cord torsion degree and decreased the success rate of testicular salvage. CONCLUSION: This prediction model could obtain the corresponding probability of testicular salvage according to the clinical characteristics of different patients with testicular torsion, providing reference for clinicians and parents.

Three cases of systemic lupus erythematosus presenting with ischemic stroke as the initial symptom: Case reports and literature review.

BACKGROUND: Ischemic stroke constitutes a grave complication within the context of systemic lupus erythematosus (SLE), typically manifesting several years postdiagnosis of SLE. Incidents where ischemic stroke precedes and acts as an initial symptom of SLE are comparatively rare in its early stages, and such presentations are frequently misdiagnosed as ischemic cerebrovascular diseases, posing significant diagnostic challenges. CASE REPORTS: This article presents three cases of young females in whom ischemic stroke emerged as the initial manifestation of SLE. It incorporates a review of 17 case reports published over the past two decades, focusing on patients with SLE where ischemic stroke was a primary symptom. This discussion encompasses the clinical presentation, outcomes, and therapeutic approaches for these patients. CONCLUSION: In young patients, particularly females presenting with ischemic stroke and especially in cases accompanied by hematologic or multisystemic involvement, there should be heightened vigilance for SLE-induced ischemic stroke. Early diagnosis and treatment significantly enhance patients' quality of life and survival rates.

Fully Printable and Reconfigurable Hufu-type Electroluminescent Devices for Visualized Encryption.

Hufu, serving as evidence of imperial authorization in ancient China, comprises two parts in the form of tiger-shaped tallies that only become effective when matched. Drawing inspiration from the concept of Hufu, a reconfigurable electroluminescent (EL) device is designed by separating conventional integral devices into two parts that contain the EL layer (part A) and the transparent electrode (part B), respectively. The key to realizing such strategy is employing an adhesive and stretchable polymer gel composite as the transparent electrodes for the EL devices. The polymer gel composite facilitates robust yet reversible contact between the EL layer and transparent electrode, enabling high-performance and stretchable EL devices that can be readily disassembled and reassembled: the EL devices can maintain ≈81% of their initial luminance after 1000 times of repeated disassembly and reassembly. Moreover, the precursor ink of the polymer gel composite is compatible with a wide variety of coating and printing technologies, such as spin-coating, inkjet printing, dispensing, and brush painting. Importantly, the reconfigurable feature of the devices opens up a new path to encryption display systems, and as a proof-of-concept, EL encrypted password, and content-changeable digital clock are demonstrated.

Adaptive Ion Channels Formed in Ultrathin and Semicrystalline Polymer Interphases for Stable Aqueous Batteries.

Aqueous Zn batteries have recently emerged as promising candidates for large-scale energy storage, driven by the need for a safe and cost-effective technology with sufficient energy density and readily accessible electrode materials. However, the energy density and cycle life of Zn batteries have been limited by inherent chemical, morphological, and mechanical instabilities at the electrode-electrolyte interface where uncontrolled reactions occur. To suppress the uncontrolled reactions, we designed a crystalline polymer interphase for both electrodes, which simultaneously promotes electrode reversibility via fast and selective Zn transport through the adaptive formation of ion channels. The interphase comprises an ultrathin layer of crystalline poly(1H,1H,2H,2H-perfluorodecyl acrylate), synthesized and applied as a conformal coating in a single step using initiated chemical vapor deposition (iCVD). Crystallinity is optimized to improve interphase stability and Zn-ion transport. The optimized interphase enables a cycle life of 9500 for Zn symmetric cells and over 11,000 for Zn-MnO2 full-cell batteries. We further demonstrate the generalizability of this interphase design using Cu and Li as examples, improving their stability and achieving reversible cycling in both. The iCVD method and molecular design unlock the potential of highly reversible and cost-effective aqueous batteries using earth-abundant Zn anode materials, pointing to grid-scale energy storage.

Other's shoes also fit well: AI technologies contribute to China's blue skies as well as carbon reduction.

Artificial intelligence (AI) technology represents a disruptive innovation that has garnered significant interest among researchers for its potential applications in ecological and environmental management. While many studies have investigated the impact of AI on carbon emissions, relatively few have delved into its relationship with air pollution. This study sets out to explore the causal mechanisms and constraints linking AI technologies and air pollution, using provincial panel data collected from 2007 to 2020 in China. Furthermore, this study examines the distinct pathways through which AI technology can ameliorate air pollution and reduce carbon emissions. The findings reveal the following key insights: (1) AI technologies have the capacity to significantly reduce air pollution, particularly in terms of PM2.5 and SO2 levels. (2) AI technologies contribute to enhanced air quality by facilitating adjustments in energy structures, improving energy efficiency, and strengthening digital infrastructure. Nonetheless, it is important to note that adjusting the energy structure remains the most practical approach for reducing carbon emissions. (3) The efficacy of AI in controlling air pollution is influenced by geographical location, economic development level, level of information technology development, resource dependence, and public attention. In conclusion, this study proposes novel policy recommendations to offer fresh perspectives to countries interested in leveraging AI for the advancement of ecological and environmental governance.

Design and Reality-Based Modeling Optimization of a Flexible Passive Joint Paddle for Swimming Robots.

Rowing motion with paired propellers is an essential actuation mechanism for swimming robots. Previous work in this field has typically employed flexible propellers to generate a net thrust or torque by using changes in the compliance values of flexible structures under the influence of a fluid. The low stiffness values of the flexible structures restrict the upper limit of the oscillation frequency and amplitude, resulting in slow swimming speeds. Furthermore, complex coupling between the fluid and the propeller reduce the accuracy of flexible propeller simulations. A design of a flexible passive joint paddle was proposed in this study, and a dynamics model and simulation of the paddle were experimentally verified. In order to optimize the straight swimming speed, a data-driven model was proposed to improve the simulation accuracy. The effects of the joint number and controller parameters on the robot's straight swimming speed were comprehensively investigated. The multi-joint paddle exhibited significantly improved thrust over the single-joint paddle in a symmetric driving mode. The data-driven model reduced the total error of the simulated data of the propulsive force in the range of control parameters to 0.51%. Swimming speed increased by 3.3 times compared to baseline. These findings demonstrate the utility of the proposed dynamics and data-driven models in the multi-objective design of swimming robots.

ITGB4 upregulation is associated with progression of lower grade glioma.

Gliomas originating in the neuroepithelium account for about 80% of brain malignancies and are the most common cancer of the central nervous system. Clinical management of gliomas remains challenging despite significant advances in comprehensive therapies, including radiotherapy, chemotherapy, and surgery. The ITGB4 (Integrin subunit beta 4) gene encodes a receptor for laminins and its upregulation in tumor tissues is associated with poor prognosis. However, its role in glioma is not well understood. First, we performed a pan cancer analysis of ITGB4 expression in The Cancer Genome Atlas (TCGA) dataset. Survival analysis was done on Chinese Glioma Genome Atlas (CGGA) and TCGA. Immunohistochemistry was then used to validate the expression and role of ITGB4 in glioma. We finally analyzed the possible mechanism by immune infiltration and single-cell sequencing analysis. Here, we found that ITGB4 is upregulated in glioma and accurately predicts the prognosis of lower grade glioma (LGG). Univariate and multivariate Cox regression analyses showed that ITGB4 is a risk factor for LGG. Immunohistochemical analysis confirmed that ITGB4 accurately predicts LGG prognosis. Non-negative matrix factorization (NMF) cluster analysis showed that ITGB4 was closely related to immune related genes. Immune cell infiltration and single cell sequencing analyses indicated that ITGB4 may be closely related to the microenvironment of gliomas, especially tumor-associated fibroblasts. ITGB4 is a promising diagnostic and therapeutic factor in LGG patients.

Advantages of single-site laparoscopic orchiopexy for palpable undescended testes in children: a prospective comparison study.

PURPOSE: To evaluate the feasibility of single-site laparoscopic orchiopexy for palpable undescended testes in children. METHODS: We prospectively studied patients with undescended testes between July 2021 and June 2022. In total, 223 patients were included in our study: 105 underwent single-site laparoscopic orchiopexy and 118 underwent conventional laparoscopic orchiopexy. During single-site laparoscopic orchiopexy, 3 ports were inserted within the umbilicus. RESULTS: No differences were observed between the groups in terms of age and laterality. For unilateral undescended testes, the operating time was longer in the single site group than in the conventional group at the early stages (55.31 ± 12.04 min vs. 48.14 ± 14.39 min, P = 0.007), but it was similar to the conventional group at the later stages (48.82 ± 13.49 min vs. 48.14 ± 14.39 min, P = 0.78). Testicular ascent occurred in one patient from each group. There was no significant difference in the success rate between the single-site group and the conventional group (99.0% vs. 99.2%, P = 0.93). In the single-site group, no visible abdominal scarring was observed, while in the conventional group, there were two noticeable scars on the abdomen. CONCLUSION: Single-site laparoscopic orchiopexy offers superior cosmetic results and comparable success rates compared to conventional laparoscopic orchiopexy for palpable undescended testes.

Predictive value of HTS grade in patients with intrahepatic cholangiocarcinoma undergoing radical resection: a multicenter study from China.

BACKGROUND: Intrahepatic cholangiocarcinoma (ICC) is a highly malignant tumor with a poor prognosis. This study aimed to investigate whether Hemoglobin, Albumin, Lymphocytes, and Platelets (HALP) score and Tumor Burden Score (TBS) serves as independent influencing factors following radical resection in patients with ICC. Furthermore, we sought to evaluate the predictive capacity of the combined HALP and TBS grade, referred to as HTS grade, and to develop a prognostic prediction model. METHODS: Clinical data for ICC patients who underwent radical resection were retrospectively analyzed. Univariate and multivariate Cox regression analyses were first used to find influencing factors of prognosis for ICC. Receiver operating characteristic (ROC) curves were then used to find the optimal cut-off values for HALP score and TBS and to compare the predictive ability of HALP, TBS, and HTS grade using the area under these curves (AUC). Nomogram prediction models were constructed and validated based on the results of the multivariate analysis. RESULTS: Among 423 patients, 234 (55.3%) were male and 202 (47.8) were aged ≥ 60 years. The cut-off value of HALP was found to be 37.1 and for TBS to be 6.3. Our univariate results showed that HALP, TBS, and HTS grade were prognostic factors of ICC patients (all P < 0.05), and ROC results showed that HTS had the best predictive value. The Kaplan-Meier curve showed that the prognosis of ICC patients was worse with increasing HTS grade. Additionally, multivariate regression analysis showed that HTS grade, carbohydrate antigen 19-9 (CA19-9), tumor differentiation, and vascular invasion were independent influencing factors for Overall survival (OS) and that HTS grade, CA19-9, CEA, vascular invasion and lymph node invasion were independent influencing factors for recurrence-free survival (RFS) (all P < 0.05). In the first, second, and third years of the training group, the AUCs for OS were 0.867, 0.902, and 0.881, and the AUCs for RFS were 0.849, 0.841, and 0.899, respectively. In the first, second, and third years of the validation group, the AUCs for OS were 0.727, 0.771, and 0.763, and the AUCs for RFS were 0.733, 0.746, and 0.801, respectively. Through the examination of calibration curves and using decision curve analysis (DCA), nomograms based on HTS grade showed excellent predictive performance. CONCLUSIONS: Our nomograms based on HTS grade had excellent predictive effects and may thus be able to help clinicians provide individualized clinical decision for ICC patients.

The application value of deep learning in the background of precision medicine in glioblastoma.

Introduction: Glioblastoma is a highly malignant central nervous system tumor, World Health Organization Ⅳ, glioblastoma is the most common primary malignancy, due to its own specificity and complexity, different patients often benefit from the current conventional treatment regimen because of different molecular subtypes, in the context of precision medicine, the application of deep learning to identify the salient features of tumors on brain imaging, prognostic predictive assessment combined with clinical data to maximize the benefits of each patient from the treatment regimen is a non-invasive and feasible regimen. Methods: We conducted a comprehensive review of the existing literature on the role of deep learning in glioblastomas, covering molecular classification and diagnosis, prognosis assessment. Results: Data based on a variety of magnetic resonance imaging sequences, genetic information, and clinical combinations enable noninvasive predictive tumor diagnosis of glioblastoma and assess overall survival and treatment response accuracy. For images, standardized image acquisition and data extraction techniques can be effectively translated into learning models for clinical practice. However, it must be recognized that interventions in the treatment of glioblastoma using deep learning are still in their infancy, and the robustness of the model is challenged, as the current total number of glioblastoma samples is insufficient for large-scale experimental methods, which is directly related to the difficulty of application of the model. Conclusion: Compared to radiomics and shallow machine learning, deep learning can be a more robust, non-invasive, and effective approach, providing more valuable information as clinicians develop personalized medical protocols for glioblastoma patients.