The abnormalities of lipid metabolism in children and adolescents with major depressive disorder and relationship with suicidal ideation and attempted suicide.

Background: Major depressive disorder (MDD) is a widespread health issue in many countries, which has an extremely negative impact on the health of children and adolescents in particular. In the context of depression and metabolic disorders, dyslipidemia and metabolism-related problems become more prominent comorbidities. However, they continue to be the main barrier to the successful recovery of the clinical progress. In this study we investigated the rate of dyslipidemia, additional risk factors among Chinese children and adolescents with MDD, and association of the suicidal behavior with lipid levels. Methods: The study took 756 people from the Third People's Hospital of Fuyang between January 2020 and December 2021, aged between 8 and 18, with major depressive disorders diagnosed according to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5). We determined the FBG (fasting blood glucose) and lipid parameters in all subjects and also investigated the history of suicidal ideation, the cases of attempted suicide, and the scores of depressive symptoms. Sociodemographic and clinical data were gathered and analyzed using the SPSS-23.0 version. Results: The prevalence of hypercholesterolemia, hypertriglyceridemia, high LDL-C, and low HDL-C were 5.42 % (41/756), 10.58 % (80/756), 3.84 % (29/756) and 5.42 % (41/756) respectively. For hypercholesterolemia and hypertriglyceridemia, they were positive associated with suicidal ideation and suicide attempts, and the positive correlation is shown between low HDL-C levels and suicide attempts. Nevertheless, non-ideation and inversely suicidal attempts were not discovered among high-LDL-C subjects. Logistic analysis showed that high levels of FBG (OR = 2.86, 95 % CI: 1.31-6.25, P = 0.008) and worse LDL-C (OR = 357.82, 95 % CI: 66.16-1935.10, P < 0.001) are the independent associated factors for hypercholesterolemia. More hospitalizations (OR = 1.89, 95 % CI: 1.07-3.35, P = 0.028), obesity (OR = 2.55, 95 % CI: 1.25-5.18, P = 0.010), high levels of TC (OR = 2.15, 95 % CI: 1.03-4.48, P = 0.042), and higher doses of antidepressants (OR = 1.02, 95 % CI: 1.00-1.04, P = 0.029) were independently associated factors for hypertriglyceridemia, while high levels of HDL-C (OR = 0.11, 95 % CI: 0.04-0.31, P < 0.001) were protective factors. In addition, high levels of TC (OR = 113.94, 95 % CI: 20.01-648.85) were statistically different (P < 0.001) and suggested that the factor was significantly related to high LDL-C. Meanwhile, older age (OR = 1.25, 95 % CI: 1.02-1.52, P = 0.030) and high levels of TG (OR = 3.00, 95 % CI: 1.98-4.55, P < 0.001) were independent factors contributing to low HDL-C. Conclusion: The high prevalence of dyslipidemia in childhood and adolescence among children and adolescents with depressive disorder has become a public health issue. Hypercholesterolemia and hypertriglyceridemia showed a positive correlation with suicidal thoughts and suicidal attempts. Monitoring the incidence of suicidal thoughts and attempts among them would carry some predictor meaning in therapy and for jumping back to health.

Lamprey VDAC2: Suppressing hydrogen peroxide-induced 293T cell apoptosis by downregulating BAK expression.

The voltage-dependent anion channel 2 (VDAC2) is the abundant protein in the outer mitochondrial membrane. Opening VDAC2 pores leads to the induction of mitochondrial energy and material transport, facilitating interaction with various mitochondrial proteins implicated in essential processes such as cell apoptosis and proliferation. To investigate the VDAC2 in lower vertebrates, we identified Lr-VDAC2, a homologue of VDAC2 found in lamprey (Lethenteron reissneri), sharing a sequence identity of greater than 50 % with its counterparts. Phylogenetic analysis revealed that the position of Lr-VDAC2 aligns with the lamprey phylogeny, indicating its evolutionary relationship within the species. The Lr-VDAC2 protein was primarily located in the mitochondria of lamprey cells. The expression of the Lr-VDAC2 protein was elevated in high energy-demanding tissues, such as the gills, muscles, and myocardial tissue in normal lampreys. Lr-VDAC2 suppressed H2O2 (hydrogen peroxide)-induced 293 T cell apoptosis by reducing the expression levels of Caspase 3, Caspase 9, and Cyt C (cytochrome c). Further research into the mechanism indicated that the Lr-VDAC2 protein inhibited the pro-apoptotic activity of BAK (Bcl-2 antagonist/killer) protein by downregulating its expression at the protein translational level, thus exerting an anti-apoptotic function similar to the role of VDAC2 in humans.

Engineered Basic Fibroblast Growth Factor Specifically Bonded with Injectable Extracellular Matrix Hydrogel for the Functional Restoration of Cerebral Ischemia in Rats.

Cerebral ischemia was one of the leading causes of mortality and disability worldwide. Extracellular matrix (ECM) hydrogel held great potential to replace volumetric brain tissue loss following ischemic injury but with limited regenerative effect for functional restoration when implanted alone. In the present study, an engineered basic fibroblast growth factor (EBP-bFGF) was constructed, which fused a specific ECM-binding peptide (EBP peptide) with bFGF. The recombinant EBP-bFGF showed typical binding capacity with ECM without affecting the bioactivity of bFGF both in vitro and in vivo. Furthermore, the EBP-bFGF was used for bioactive modification of ECM hydrogel to repair cerebral ischemia. The combination of EBP-bFGF and ECM hydrogels could realize the sustained release of bFGF in the ischemic brain and improve the regenerative effect of ECM, which protected the survival of neurons, enhanced angiogenesis, and decreased the permeability of blood-brain barrier, ultimately promoted the recovery of motor function. In addition, transcriptome analysis revealed neuregulin-1/AKT pathway involved in this process. Therefore, EBP-bFGF/ECM hydrogel would be a promising therapeutic strategy for cerebral ischemia.

Application and Quality of Model-Based Meta-Analysis in Pharmaceutical Research: A Systematic Cross-Sectional Analysis and Practical Considerations.

Model-based meta-analysis (MBMA) can be used in assisting drug development and optimizing treatment in clinical practice, potentially reducing costs and accelerating drug approval. We aimed to assess the application and quality of MBMA studies. We searched multiple databases to identify MBMA in pharmaceutical research. Eligible MBMA should incorporate pharmacological concepts to construct mathematical models and quantitatively examine and/or predict drug effects. Relevant information was summarized to provide an overview of the application of MBMA. We used AMSTAR-2 and PRISMA 2020 checklists to evaluate the methodological and reporting quality of included MBMA, respectively. A total of 143 MBMA studies were identified. MBMA was increasingly used over time for one or more areas: drug discovery and translational research (n = 8, 5.6%), drug development decision making (n = 42, 29.4%), optimization of clinical trial design (n = 46, 32.2%), medication in special populations (n = 15, 10.5%), and rationality and safety of drug use (n = 71, 49.7%). The included MBMA covered 17 disease areas, with the top three being nervous system diseases (n = 19, 13.2%), endocrine/nutritional/metabolic diseases (n = 17, 11.8%), and neoplasms (n = 16, 11.1%). Of these MBMA studies, 138 (96.5%) were rated as very low quality. The average rate of compliance with PRISMA was only 51.4%. Our findings suggested that MBMA was mainly used to evaluate the efficacy and safety of drugs, with a focus on chronic diseases. The methodological and reporting quality of MBMA should be further improved. Given AMSTAR-2 and PRISMA checklists were not specifically designed for MBMA, adapted assessment checklists for MBMA should be warranted.

Pan-cancer identified ARPC1B as a promising target for tumor immunotherapy and prognostic biomarker, particularly in READ.

ARPC1B encodes the protein known as actin-related protein 2/3 complex subunit 1 B (ARPC1B), which controls actin polymerization in the human body. Although ARPC1B has been linked to several human malignancies, its function in these cancers remains unclear. TCGA, GTEx, CCLE, Xena, CellMiner, TISIDB, and molecular signature databases were used to analyze ARPC1B expression in cancers. Visualization of data was primarily achieved using R language, version 4.0. Nineteen tumors exhibited high levels of ARPC1B expression, which were associated with different tumor stages and significantly affected the prognosis of various cancers. The level of ARPC1B expression substantially connected the narrative of ARPC1B expression with several TMB cancers and showed significant changes in MSI. Additionally, tolerance to numerous anticancer medications has been linked to high ARPC1B gene expression. Using Gene Set Variation Analysis/Gene Set Enrichment Analysisanalysis and concentrating on Rectum adenocarcinoma (READ), we thoroughly examined the molecular processes of the ARPC1B gene in pan-cancer. Using WGCNA, we examined the co-expression network of READ and ARPC1B. Meanwhile, ten specimens were selected for immunohistochemical examination, which showed high expression of ARPC1B in READ. Human pan-cancer samples show higher ARPC1B expression than healthy tissues. In many malignancies, particularly READ, ARPC1B overexpression is associated with immune cell infiltration and a poor prognosis. These results imply that the molecular biomarker ARPC1B may be used to assess the prognosis and immune infiltration of patients with READ.

Identification of Eukaryotic Translation Initiation Factor 4B as a Novel Candidate Gene for Congenital Hypothyroidism.

CONTEXT: Congenital hypothyroidism (CH) is the most common endocrine disorder in neonates, but its etiology is still poorly understood. OBJECTIVE: We performed whole exome sequencing to identify novel causative gene for CH and functional studies to validate its role in the occurrence of CH. METHODS: Whole exome sequencing in 98 CH patients not harboring known CH candidate genes and bioinformatic analysis were performed. Functional analysis was performed using morpholino, a synthetic short antisense oligonucleotide that contains 25 DNA bases on a methylene morpholine backbone, in zebrafish and CRISPR‒Cas9-mediated gene knockout in mice. RESULTS: Eukaryotic translation initiation factor 4B (EIF4B) was identified as the most promising candidate gene. The EIF4B gene was inherited in an autosomal recessive model, and one patient with thyroid dysgenesis carried EIF4B biallelic variants (p.S430F/p.P328L). In zebrafish, the knockdown of eif4ba/b expression caused thyroid dysgenesis and growth retardation. Thyroid hormone levels were significantly decreased in morphants compared with controls. Thyroxine treatment in morphants partially rescued growth retardation. In mice, the homozygous conceptuses of Eif4b+/- parents did not survive. Eif4b knockout embryos showed severe growth retardation, including thyroid dysgenesis and embryonic lethality before E18.5. CONCLUSION: These experimental data supported a role for EIF4B function in the pathogenesis of the hypothyroid phenotype seen in CH patients. Our work indicated that EIF4B was identified as a novel candidate gene in CH. EIF4B is essential for animal survival, but further studies are needed to validate its role in the pathogenesis of CH.

Deficiency of the HGF/Met pathway leads to thyroid dysgenesis by impeding late thyroid expansion.

The mechanisms of bifurcation, a key step in thyroid development, are largely unknown. Here we find three zebrafish lines from a forward genetic screening with similar thyroid dysgenesis phenotypes and identify a stop-gain mutation in hgfa and two missense mutations in met by positional cloning from these zebrafish lines. The elongation of the thyroid primordium along the pharyngeal midline was dramatically disrupted in these zebrafish lines carrying a mutation in hgfa or met. Further studies show that MAPK inhibitor U0126 could mimic thyroid dysgenesis in zebrafish, and the phenotypes are rescued by overexpression of constitutively active MEK or Snail, downstream molecules of the HGF/Met pathway, in thyrocytes. Moreover, HGF promotes thyrocyte migration, which is probably mediated by downregulation of E-cadherin expression. The delayed bifurcation of the thyroid primordium is also observed in thyroid-specific Met knockout mice. Together, our findings reveal that HGF/Met is indispensable for the bifurcation of the thyroid primordium during thyroid development mediated by downregulation of E-cadherin in thyrocytes via MAPK-snail pathway.

Pharmacotherapy for adults with overweight and obesity: a systematic review and network meta-analysis of randomised controlled trials.

BACKGROUND: Pharmacotherapy provides an option for adults with overweight and obesity to reduce their bodyweight if lifestyle modifications fail. We summarised the latest evidence for the benefits and harms of weight-lowering drugs. METHODS: This systematic review and network meta-analysis included searches of PubMed, Embase, and Cochrane Library (CENTRAL) from inception to March 23, 2021, for randomised controlled trials of weight-lowering drugs in adults with overweight and obesity. We performed frequentist random-effect network meta-analyses to summarise the evidence and applied the Grading of Recommendations Assessment, Development, and Evaluation frameworks to rate the certainty of evidence, calculate the absolute effects, categorise interventions, and present the findings. The study was registered with PROSPERO, CRD 42021245678. FINDINGS: 14 605 citations were identified by our search, of which 132 eligible trials enrolled 48 209 participants. All drugs lowered bodyweight compared with lifestyle modification alone; all subsequent numbers refer to comparisons with lifestyle modification. High to moderate certainty evidence established phentermine-topiramate as the most effective in lowering weight (odds ratio [OR] of ≥5% weight reduction 8·02, 95% CI 5·24 to 12·27; mean difference [MD] of percentage bodyweight change -7·98, 95% CI -9·27 to -6·69) followed by GLP-1 receptor agonists (OR 6·33, 95% CI 5·00 to 8·00; MD -5·79, 95% CI -6·34 to -5·25). Naltrexone-bupropion (OR 2·69, 95% CI 2·10 to 3·44), phentermine-topiramate (2·40, 1·68 to 3·44), GLP-1 receptor agonists (2·22, 1·74 to 2·84), and orlistat (1·71, 1·42 to 2·05) were associated with increased adverse events leading to drug discontinuation. In a post-hoc analysis, semaglutide, a GLP-1 receptor agonist, showed substantially larger benefits than other drugs with a similar risk of adverse events as other drugs for both likelihood of weight loss of 5% or more (OR 9·82, 95% CI 7·09 to 13·61) and percentage bodyweight change (MD -11·40, 95% CI -12·51 to -10·29). INTERPRETATION: In adults with overweight and obesity, phentermine-topiramate and GLP-1 receptor agonists proved the best drugs in reducing weight; of the GLP-1 agonists, semaglutide might be the most effective. FUNDING: 1.3.5 Project for Disciplines of Excellence, West China Hospital, Sichuan University.

Maximizing the Value of Real-World Data and Real-World Evidence to Accelerate Healthcare Transformation in China: Summary of External Advisory Committee Meetings.

Use of real-world data (RWD) is gaining wide attention. To bridge the gap between diverse healthcare stakeholders and to leverage the impact of Chinese real-world evidence (RWE) globally, a multi-stakeholder External Advisory Committee (EAC) and EAC meetings were initiated, aiming to elucidate the current and evolving RWD landscape in China, articulate the values of RWE in ensuring Chinese patients' equitable access to affordable medicines and solutions, and identify strategic opportunities and partnerships for expansion of RWE generation in China. Chinese and international experts who are clinicians and academic researchers were selected as EAC members based on their professional background and familiarity with RWD/RWE. Three EAC meetings were held quarterly in 2023. Various topics were presented and discussed for insights and suggestions. Nine experts from China, one from South Korea, and two from Europe were selected as EAC members and attended these meetings. Experts' presentations were summarized by theme, including the RWD landscape and RWE enablement in China, as well as global development of a patient-centric ecosystem. Experts' insights and suggestions on maximizing the RWD/RWE value to accelerate healthcare transformation in China were collected. We concluded that though data access, sharing, and quality are still challenging, RWD is developing to support evidence generation in the medicinal product lifecycle, inform clinical practice, and empower patient management in China. RWD/RWE creates value, accelerates healthcare transformation, and improves patient outcomes. Fostering a patient-centric ecosystem across healthcare stakeholders and maintaining global partnerships and collaboration are essential for unlocking the power of RWD/RWE.

Fabricating a digital custom tray and interim complete denture base: A dental technique.

High-quality impressions and accurate occlusal relationship records are essential for the success of complete dentures. A custom impression tray and interim complete denture base fabricated by computer-aided design and computer-aided manufacturing (CAD-CAM) are introduced, enhancing the ability to obtain precise definitive impressions and accurate jaw relation records and improving complete denture treatment.

Medical image segmentation network based on multi-scale frequency domain filter.

With the development of deep learning, medical image segmentation in computer-aided diagnosis has become a research hotspot. Recently, UNet and its variants have become the most powerful medical image segmentation methods. However, these methods suffer from (1) insufficient sensing field and insufficient depth; (2) computational nonlinearity and redundancy of channel features; and (3) ignoring the interrelationships among feature channels. These problems lead to poor network segmentation performance and weak generalization ability. Therefore, first of all, we propose an effective replacement scheme of UNet base block, Double residual depthwise atrous convolution (DRDAC) block, to effectively improve the deficiency of receptive field and depth. Secondly, a new linear module, the Multi-scale frequency domain filter (MFDF), is designed to capture global information from the frequency domain. The high order multi-scale relationship is extracted by combining the depthwise atrous separable convolution with the frequency domain filter. Finally, a channel attention called Axial selection channel attention (ASCA) is redesigned to enhance the network's ability to model feature channel interrelationships. Further, we design a novel frequency domain medical image segmentation baseline method FDFUNet based on the above modules. We conduct extensive experiments on five publicly available medical image datasets and demonstrate that the present method has stronger segmentation performance as well as generalization ability compared to other state-of-the-art baseline methods.

Transcriptomic crosstalk between viral and host factors drives aberrant homeostasis of T-cell proliferation and cell death in HIV-infected immunological non-responders.

BACKGROUND: Immunological non-responders (INRs) among people living with HIV have inherently higher mortality and morbidity rates. The underlying immunological mechanisms whereby failure of immune reconstitution occurs in INRs require elucidation. METHOD: HIV-1 DNA and HIV-1 cell-associated RNA (CA-HIV RNA) quantifications were conducted via RT-qPCR. Transcriptome sequencing (RNA-seq), bioinformatics, and biological verifications were performed to discern the crosstalk between host and viral factors. Flow cytometry was employed to analyze cellular activation, proliferation, and death. RESULTS: HIV-1 DNA and CA-HIV RNA levels were observed to be significantly higher in INRs compared to immunological responders (IRs). Evaluation of CD4/CD8 ratios showed a significantly negative correlation with HIV-1 DNA in IRs, but not in INRs. Bioinformatics analyses and biological verifications showed IRF7/INF-α regulated antiviral response was intensified in INRs. PBMCs of INRs expressed significantly more HIV integrase-mRNA (p31) than IRs. Resting (CD4+CD69- T-cells) and activated (CD4+CD69+ T-cells) HIV-1 reservoir harboring cells were significantly higher in INRs, with the co-occurrence of significantly higher cellular proliferation and cell death in CD4+ T-cells of INRs. CONCLUSION: In INRs, the systematic crosstalk between the HIV-1 reservoir and host cells tends to maintain a persistent antiviral response-associated inflammatory environment, which drives aberrant cellular activation, proliferation, and death of CD4+ T-cells.

TET3 boosts hepatocyte autophagy and impairs non-alcoholic fatty liver disease by increasing ENPP1 promoter hypomethylation.

BACKGROUND: Dysregulated ecto-nucleotide pyrophosphatase/phosphodiesterase (ENPP) family occurs in metabolic reprogramming pathological processes. Nonetheless, the epigenetic mechanisms by which ENPP family impacts NAFLD, also known as metabolic dysfunction-associated steatotic liver disease (MASLD), is poorly appreciated. METHODS: We investigated the causes and consequences of ENPP1 promoter hypomethylation may boost NAFLD using NAFLD clinical samples, as well as revealed the underlying mechanisms using high-fat diet (HFD) + carbon tetrachloride (CCl4) induced mouse model of NAFLD and FFA treatment of cultured hepatocyte. RESULTS: Herein, we report that the expression level of ENPP1 are increased in patients with NAFLD liver tissue and in mouse model of NAFLD. Hypomethylation of ENPP1, is associated with the perpetuation of hepatocyte autophagy and liver fibrosis in the NAFLD. ENPP1 hypomethylation is mediated by the DNA demethylase TET3 in NAFLD liver fibrosis and hepatocyte autophagy. Additionally, knockdown of TET3 methylated ENPP1 promoter, reduced the ENPP1 expression, ameliorated the experimental NAFLD. Mechanistically, TET3 epigenetically promoted ENPP1 expression via hypomethylation of the promoter. Knocking down TET3 can inhibit the hepatocyte autophagy but an overexpression of ENPP1 showing rescue effect. CONCLUSIONS: We describe a novel epigenetic mechanism wherein TET3 promoted ENPP1 expression through promoter hypomethylation is a critical mediator of NAFLD. Our findings provide new insight into the development of preventative measures for NAFLD.

Deficiency of peripheral CLA+ Tregs and clinical relevance in Behcet's syndrome.

BACKGROUND: Autoimmune responses have been suggested to involvement in patients with Behcet's syndrome (BS). There has been growing attention towards the roles of cutaneous lymphocyte antigen (CLA)+ regular T cells (Tregs) in autoimmune diseases. The role of CLA+ Tregs in BS is still uncertain. This study aims to clarify the impact of CLA+ Tregs on BS. METHODS: We collected peripheral blood from a total of 107 patients with BS and 114 healthy controls (HCs). The number of CLA+ Tregs, natural killer (NK) cells, B cells, and several subtypes of CD4+ T cells were detected using flow cytometry and compared between patients and HCs. RESULTS: The absolute number and proportion of CLA+ Tregs among CD4+ T lymphocytes and CD4+ Tregs were lower in patients with BS than in HCs. CLA+ Tregs were positively related with NK cells (r = 0.500, P < 0.001) and B cells (r = 0.470, P < 0.001) and negatively related with effector T cells (r=-0.402, P < 0.001) in patients with BS. Patients with BS and arterial aneurysms had CLA+ Treg cell deficiency. A decreased proportion of CLA+ Tregs was associated with arterial aneurysms in patients with BS. The proportion of CLA+ Tregs in patients with BS increased with corticosteroids and immunosuppressants. CONCLUSION: CLA+ Tregs decrease in association with arterial aneurysm in patients with BS. CLA+ Tregs may be a predictor of response to BS treatment.

[Analysis of the Jumping Characteristics and Influencing Factors of Ozone Pollution in Beijing].

Based on environmental monitoring data and meteorological observation data from 2016 to 2022 in Beijing, combined with backward trajectory clustering and potential source area contribution analysis, the characteristics, meteorological impacts, and potential source areas of ozone (O3) pollution were analyzed. The results showed that there was a total of 41 O3 pollution processes with jumping characteristics in Beijing from 2016 to 2022, with an average of 5.9 times a year. The occurrence time was concentrated in May to July, and the day of the jump (OJD2) was higher than the day before the jump (OJD1). The average value of ρ(O3-8h) was 78.3% higher, and the peak concentration was 78.9% higher. The high O3 concentration zone in the OJD2 region exhibited a characteristic of advancing from south to north. The main reasons for the occurrence of jumped O3 pollution in Beijing could be summarized as local accumulation caused by unfavorable meteorological conditions and regional transmission impact. The occurrence of jump-type ozone pollution was characterized by an increase in southerly wind frequency, temperature rise, pressure decrease, and precipitation decrease. The increase in southerly wind frequency provided conditions for the transport of O3 and its precursors, and rapid photochemical reactions occurred under local high temperatures, with less superimposed precipitation, comprehensively pushing up the ozone concentration level of OJD2. Six air mass transporting pathways were identified through clustering analysis; the air mass from the direction north of OJD2 decreased by 11.2%, whereas the air mass from the south and east directions increased by 6.7% and 4.4%, respectively, with the air masses mainly transmitting over short distances. The ozone concentration corresponding to the south and east directions was relatively high, making a significant contribution to Beijing's pollution. The analysis of potential source areas revealed that the main potential source areas of OJD2 ozone pollution were the central, southern, and eastern parts of Beijing-Tianjin-Hebei, which contributed 82.6% to the pollution trajectory. There was a significant contribution of regional transport during jump-type ozone pollution, and it is necessary to strengthen joint prevention and control in the Beijing-Tianjin-Hebei Region.

Cardiotoxicity induced by fluoropyrimidine drugs in the treatment of gastrointestinal tumors.

In this editorial, we review the article published in World J Gastrointest Oncol 2019, 11: 1031-1042. We specifically focus on the occurrence, clinical characteristics, and risk factors of fluoropyrimidine drug-related cardiotoxicity in patients with gastrointestinal tumors. Despite significant advancements in diagnostic and therapeutic techniques that have reduced mortality rates associated with digestive system tumors, the incidence and mortality rates of treatment-related cardiotoxicity have been increasing, severely impacting the survival and prognosis of cancer patients. Fluoropyrimidine drugs are widely used as antimetabolites in the treatment of malignant tumors, including gastrointestinal tumors, and they represent the second largest class of drugs associated with cardiotoxicity. However, there is often a lack of awareness or understanding regarding their cardiotoxic effects and associated risks.

Data Imputation of Soil Pressure on Shield Tunnel Lining Based on Random Forest Model.

With the advancement of engineering techniques, underground shield tunneling projects have also started incorporating emerging technologies to monitor the forces and displacements during the construction and operation phases of shield tunnels. Monitoring devices installed on the tunnel segment components generate a large amount of data. However, due to various factors, data may be missing. Hence, the completion of the incomplete data is imperative to ensure the utmost safety of the engineering project. In this research, a missing data imputation technique utilizing Random Forest (RF) is introduced. The optimal combination of the number of decision trees, maximum depth, and number of features in the RF is determined by minimizing the Mean Squared Error (MSE). Subsequently, complete soil pressure data are artificially manipulated to create incomplete datasets with missing rates of 20%, 40%, and 60%. A comparative analysis of the imputation results using three methods-median, mean, and RF-reveals that this proposed method has the smallest imputation error. As the missing rate increases, the mean squared error of the Random Forest method and the other two methods also increases, with a maximum difference of about 70%. This indicates that the random forest method is suitable for imputing monitoring data.