Browse Articles

A study on the mechanism of school support to improve school adjustment of rural left-behind children——Analysis based on CEPS (2013–2014) data

School adjustment is related to the educational achievements and future career development of rural left-behind children. School support is an important institutional measure to promote the school adjustment of rural left-behind children in China. Using Structural Equation Modeling (SEM) based on CEPS data, this paper analyzed the effects of school support on rural left-behind children’s school adjustment, and found that: (1) school support effectively improves rural left-behind children’s school adjustment ability; (2) school support enhances students’ school adjustment ability by improving their educational expectation and mental health, especially the effects of teachers’ relationship support and school soft environment support are significant; (3) teacher support has a greater effect on students’ school adjustment ability than environment support, and soft environment support enhances students’ school adjustment ability by improving their mental health, while the impact of hard environment support is weaker. This study provides theoretical support for the formulation of intervention policies for rural left-behind children and offers practical evidence for understanding the relationship between school education and family education.

Comparison of generic drug prices in Korea and eight high-income countries across four therapeutic classes

Background The prices of generic drugs in general are known to be higher in Korea than in other countries. However, it remains unknown whether the price levels of generic drugs in Korea relative to other countries can differ by therapeutic class. Therefore, this study compared the prices of generic drugs in four commonly used drug classes in Korea with those in other high-income countries. Methods Using IQVIA’s Pricing Insight data from 2018 to 2022, we calculated the Laspeyres price index for generic drugs in four therapeutic classes (antidiabetic drugs, lipid-modifying agents, antihypertensive drugs, and antibiotics). We selected eight high-income countries, such as Canada, France, Germany, Italy, Japan, Switzerland, the United Kingdom, and the United States, for comparison and Korea as the base country. Price to chemist was used and the currency conversion was based on the exchange rate and the purchasing power parity. Results Prices of generic drugs are lower in all of comparison countries combined than in Korea for lipid-modifying drugs and antihypertensive drugs. For these two drug classes, all countries but the U.S. have the index lower than one. The index for antidiabetic drugs was less than one in all countries except for Canada and the U.S. For antibiotics, all countries but France, Italy, and Japan have the index that is greater than one. Furthermore, the price index for generic antibiotics increased from 2018 to 2022 in all countries but Canada and Japan. Conclusion The prices of generic drugs are higher in Korea than in other high-income countries for lipid-modifying agents and antihypertensive drugs. The prices of generic antibiotics are higher in many comparison countries and have further increased from 2018 to 2021.

CEO social capital and implied cost of capital: Based on the empirical evidence of Chinese family businesses

Social capital plays a crucial role in resource integration within Chinese family businesses. This research investigates the relationship between CEO social capital and the implied cost of capital, while also considering the influence of CEO type on this relationship. The empirical results based on China’s A-share family-listed companies show that CEO social capital helps to reduce the implied capital cost of family business. However, compared with non-family CEO, the effect of family CEO social capital on reducing the implied cost of capital is weaker. The mechanism analysis confirms that CEO social capital reduces the implied cost of capital through reducing corporate risk and improving information transparency. The heterogeneity analysis reveals that CEO social capital significantly reduces the implicit cost of capital only in entrepreneurial families, companies with low family control, and those without intergenerational transmission. Additionally, the effect of CEO social capital is more pronounced in fiercely competitive markets and high-tech industries. When economic policy uncertainty is high and investor legal protections are weak, CEO social capital can better exert its complementary effect on formal institutions. These findings not only provide a theoretical foundation for leveraging the informal system of social capital to strengthen family governance but also offer practical insights for addressing the classic decision of whether to choose family succession or hire professional managers.

Advancing pearl millet yield forecasting: Comparative analysis of individual and ensemble machine learning approaches over Rajasthan, India

Pearl millet (Pennisetum glaucum L.) is a resilient crop known for its ability to thrive in arid and semi-arid regions, making it a crucial staple in regions prone to drought. Rajasthan, a state in India, emerged as the top producer of pearl millet. This study enhances yield forecasting for pearl millet using machine learning models across nine districts viz. Jaipur, Ajmer, Jodhpur, Bikaner, Bharatpur, Alwar, Sikar, Jhunjhunu and Nagaur in Rajasthan, India. Data from 1997–2019 (23 years), including yield data from the Directorate of Economics and Statistics and weather data from the NASA POWER web portal, were analysed. The study employed individual machine learning methods (GLM, ELNET, XGB, SVR and RF) and their ensemble combinations (GLM, ELNET, Cubist and RF). Discerning the overall best performing model across all locations remained challenging. For instance, while ensemble models exhibited subpar performance in Barmer and Nagaur, their performance ranged from satisfactory to commendable in other locations. To identify the best model, all models were ranked based on their R2 and nRMSE (%) values. Combined average ranks during training and testing revealed the model performance ranking as I-XGB (3.83) >  I-GLM (4.28) >  E-ELNET (4.32) >  I-RF (4.67) >  E-GLM (4.88) >  I-SVR (4.90) >  I-ELNET (4.94) >  E-RF (6.03) >  E-Cubist (7.15), where I denotes individual model, while E denotes ensemble model. Intriguingly, while individual GLM and XGB models demonstrated superior performance during calibration, they exhibited poorer performance during validation, potentially indicating issues of data overfitting. Hence, the ensemble ELNET approach is recommended for accurate prediction of pearl millet yield, followed by the individual RF model. These performances underscore the importance of tailored model selection based on specific geographic and environmental conditions.

Retraction: GNB2L1 and its O-GlcNAcylation regulates metastasis via modulating epithelial-mesenchymal transition in the chemoresistance of gastric cancer

Comparative assessment of macrophage responses and antileishmanial efficacy in dynamic vs. Static culture systems utilizing chitosan-based formulations

The discovery of novel anti-leishmanial compounds is essential due to the limitations of current treatments and the lack of new drugs in development. In this study, we employed the Quasi Vivo 900 medium perfusion system (QV900, Kirkstall Ltd, UK) to simulate physiological fluid flow, allowing us to compare macrophage responses and therapeutic outcomes under dynamic versus static conditions. After 24 hours, phagocytosis and macropinocytosis decreased in all cell types under flow conditions compared to static cultures. Under slow (1.45 x 10-9 m/s) and faster (1.23 x 10-7 m/s) flow conditions ((simulating in vivo lymphatic flow), phagocytosis decreased by around 42.55% and 56.98% in peritoneal macrophages (PEMs), 42.21% and 56.11% in bone marrow-derived macrophages (BMMs), and 49.75% and 63.32% in THP-1 cells, respectively. Similarly, macropinocytosis decreased by approximately 40.7% and 62.2% in PEMs, 34.8% and 60.9% in BMMs, and 33.3% and 59.3% in THP-1 cell line under this same conditions. In this study, we further assessed the impact of medium perfusion on drug efficacy and macrophage functions using a Leishmania major amastigote-macrophage assay. We evaluated the performance of both standard and nanoparticle-based drug formulations within dynamic and static culture systems. After 72 hours of medium perfusion, chitosan solution, blank chitosan-sodium tripolyphosphate (TPP) nanoparticles, and amphotericin B (AmB)-loaded chitosan-TPP nanoparticles exhibited a statistically significant reduction in antileishmanial activity by approximately 30-50% under slow flow conditions and 60-80% under faster flow conditions. In comparison, pure AmB showed a 40% decrease in efficacy at slow flow and a 67% decrease at faster flow, both statistically significant. These results highlighted the importance of considering fluid flow dynamics in in vitro studies for a more accurate simulation of in vivo conditions, potentially leading to better therapeutic strategies for cutaneous leishmaniasis (CL).

Early warning strategies for corporate operational risk: A study by an improved random forest algorithm using FCM clustering

To enhance the accuracy and response speed of the risk early warning system, this study develops a novel early warning system that combines the Fuzzy C-Means (FCM) clustering algorithm and the Random Forest (RF) model. Firstly, based on operational risk theory, market risk, research and development risk, financial risk, and human resource risk are selected as the primary indicators for enterprise risk assessment. Secondly, the Criteria Importance Through Intercriteria Correlation (CRITIC) weight method is employed to determine the importance of these risk indicators, thereby enhancing the model’s prediction ability and stability. Following this, the FCM clustering algorithm is utilized for pre-processing sample data to improve the efficiency and accuracy of data classification. Finally, an improved RF model is constructed by optimizing the parameters of the RF algorithm. The data selected is mainly from RESSET/DB, covering the issuance, trading, and rating data of fixed-income products such as bonds, government bonds, and corporate bonds, and provides basic information, net value, position, and performance data of funds. The experimental results show that the model achieves an F1 score of 87.26%, an accuracy of 87.95%, an Area under the Curve (AUC) of 91.20%, a precision of 89.29%, and a recall of 87.48%. They are respectively 6.45%, 4.45%, 5.09%, 4.81%, and 3.83% higher than the traditional RF model. In this study, an improved RF model based on FCM clustering is successfully constructed, and the accuracy of risk early warning models and their ability to handle complex data are significantly improved.

Failure mechanism of soft– hard- interbedded rock slopes in cold regions: Numerical simulation and theoretical analysis

The soft– hard- interbedded rock slope in cold regions generally undergo the differential weathering due to the freeze-thaw effects, for which the irregular rock fractures increase the risk of geological disasters occurrence. To investigate the failure mechanism of the rock slope, both the numerical simulation and theoretical analysis were adopted in the present research. The structural integrity of the soft– hard- interbedded rock slope subjected to three different conditions (e.g., freeze-thaw cycles, natural, and anchored surroundings) was evaluated. The results indicated that the stability of the rock slope is significantly affected by the freeze-thaw cycles, the performance of which is much different from that under the natural- and anchored conditions. The failure process of the soft– hard- interbedded rock slope in cold regions exhibited the unloading-tensile cracking-sliding characteristics. The damage of the irregular structural surfaces subjected to the long-term weathering and freeze-thaw cycles is the one of the main factor controlling the failure mode. As revealed by numerical simulation, the application of the anchor rods can effectively prevent and control the collapse of the soft– hard- interbedded rock slope. The findings obtained from this research provide an important guidance for the stability assessment and mitigation design of the soft– hard- interbedded rock slopes in cold regions.

The impact of postoperative glucocorticoids on complications after head and neck cancer surgery with free flap reconstruction: A retrospective study

Background After head and neck cancer surgery with free flap reconstruction, the use of glucocorticoids is often required to alleviate inflammation and edema. However, the impact of glucocorticoid on postoperative complications and cancer progression remains unclear. Methods This retrospective cohort study included 711 elderly patients who underwent head and neck cancer surgery with free flap reconstruction at Shanghai Ninth People’s Hospital from January 1, 2014, to December 31, 2022. Patients were categorized based on postoperative glucocorticoid usage into a high-dose steroid group (n = 307) and a control group (n = 404). The study focused on the impact of postoperative GC use on postoperative complications and long-term oncological outcomes. Results Multivariate analysis indicated that compared to the control group, the high-dose steroid group had a significant increase in postoperative complications, including atelectasis (OR: 3.83, 95% CI: 1.27–14.11, P = 0.025), postoperative hyperglycemia (OR: 1.54, 95% CI: 1.14–2.08, P = 0.006), and flap complications (OR: 4.61, 95% CI: 3.31–6.47, P < 0.001). These complications often required extended hospital stays (β: 1.656, 95% CI: 1.075-2.236, P <  0.001). Additionally, the high-dose steroid group had a higher rate of unplanned readmissions within one year (OR: 5.61, 95% CI: 3.87–8.25, P < 0.001). The increased readmission rates were notably due to difficulties swallowing requiring percutaneous gastrostomy (OR: 3.62, 95% CI: 1.97–6.98, P < 0.001), recurrence (OR: 9.34, 95% CI: 5.02–19.05, P < 0.001), and metastasis (OR: 4.78, 95% CI: 2.58-9.44, P < 0.001). Conclusion The use of high-dose postoperative glucocorticoids is associated with increased postoperative complications, higher readmission rates, and poorer oncological outcomes in patients. The results advocate for cautious use and dosage management of perioperative glucocorticoids in head and neck surgeries to optimize patient outcomes.

A fuzzy robust optimization model for dual objective forward and reverse logistics networks considering carbon emissions

The inherent unpredictability within the low-carbon integrated supply chain logistics network complicates its management. This paper endeavours to address the challenge of designing a low-carbon logistics network within a context of uncertainty and with consideration of low-carbon policies. It also endeavours to identify locations of facilities and appropriate transportation routes between nodes. Robust optimisation and fuzzy programming techniques are employed to examine the various attributes of the network. In addition, the strategic planning model of a multi-level forward/reverse integration logistics network is examined, with the aims of cost minimisation and emission reduction. Extensive computational simulations substantiate the efficacy of the proposed robust fuzzy programming model. Moreover, analytical results indicate the rationality and applicability of the decisions suggested by the proposed optimisation model and the solution approach. Furthermore, the results indicate that a decision maker can ascertain that the decisions derived from three cases considered have a 50% probability of being the most favourable outcomes.

Field size as a predictor of “excellence.” The selection of subject fields in Germany’s Excellence Initiative

We investigate the selection of subject fields in Germany’s “excellence initiative,” a two-phase funding scheme administered by the German Research Foundation (DFG) from 2005 to 2017 to increase international competitiveness of scientific research at German universities. While most empirical studies have examined the “excellence initiative’s” effects at the university level (“elite universities”), we focus on subject fields within universities. Based on both descriptive and logistic regression analyses, we find that the “excellence initiative” reveals a stable social order of public universities based on organizational size, that field selection is biased toward those fields with many professors and considerable grant funding, and that funding success in the second phase largely follows decisions from the first phase. We discuss these results and suggest avenues for future research.

Genetic subtyping by Whole Exome Sequencing across Diffuse Large B Cell Lymphoma and Plasmablastic Lymphoma

Diffuse Large B-Cell Lymphoma (DLBCL) is a heterogeneous disease characterized by a limited number of molecularly defined subtypes. Recently, genomic-based algorithms have been proposed for the classification of this disease. The whole exome sequencing was conducted on 108 diagnostic samples of diffuse large B-cell lymphoma (DLBCL). Somatic variants, predicted copy number alterations (CNAs), and available fusion data were utilized to classify the cases. Additionally, the enrichment of mutations in the TP53, MYC, and MAPK/ERK pathways was analyzed. Genetic subtypes were identified in approximately 55% of the cases. Cases with a specific genetic subtype exhibited a significantly higher Tumor Mutation Burden compared to molecularly unclassified cases (Mann-Whitney U test, p =  0.024). The prevalence of subtypes varied according to the cell of origin phenotypes. GC-B type DLBCL NOS were classified as EZB (5 cases, 16%), ST2 (5 cases, 16%), and BN2 (1 case, 3%). Four cases (13%) were genetically composite. Three cases of HGBCL/DLBCL double-hit (MYC & BCL2) were classified as EZB-MYC. Forty-three non-GC-B type DLBCL cases were classified as ST2 (5 cases, 11%), BN2 (6 cases, 14%), and MCD (3 cases, 7%). Nine cases were genetically composite (20%). MYC pathway mutations were enriched in cases with EZB and ST2 genetic features, while they were absent in the MCD subtype. TP53 mutations were identified in 11% of the cases. Plasmablastic lymphomas exhibit genetic diversity, with 27% of tumors classified as ST2. Recurrent somatic mutations indicate dysregulation of the JAK/STAT, MAPK/ERK, and tyrosine kinase signaling pathways.

Enhancing patient-centered care: Evaluating quality of life in type 2 diabetes management

Aims To evaluate quality of life (QoL) in patients with type 2 diabetes mellitus (T2DM). Methods A cross-sectional study included 151 T2DM patients at the Clinical Centre of Montenegro. The Ferrans and Powers Quality of Life Index (QLI), validated for the Montenegrin population, assessed QoL across five domains. Participants rated items on a Likert scale from 1 (very dissatisfied) to 5 (very satisfied). Data were analysed using SPSS version 22. Results The cohort included 51% women, with a mean age of 60.05 ±  11.63 years. Of the patients, 42% had diabetes for over a decade, and 64% had no additional health conditions. Overall, patients reported satisfactory QoL, especially in self-care and glucose management, though dissatisfaction was high regarding sexual life. Emotional support from family, housing, and friendships significantly contributed to life satisfaction, while financial concerns and job dissatisfaction were common. QoL showed no significant gender differences but declined with age and was notably lower in patients with comorbidities. Conclusion Patients with T2DM report generally satisfactory QoL, with notable concerns in socio-economic and health-related areas. Routine QoL assessments in clinical practice can improve communication, aid in early complication detection, and enable timely interventions to enhance patient outcomes.

Metabolic versatility and nitrate reduction pathways of a new thermophilic bacterium of the Deferrivibrionaceae: Deferrivibrio metallireducens sp. nov isolated from hot sediments of Vulcano Island, Italy

A novel thermophilic (optimum growth temperature ~ 60 °C) anaerobic Gram-negative bacterium, designated strain V6Fe1T, was isolated from sediments heated by the hydrothermal circulation of the Aeolian Islands (Vulcano, Italy) on the seafloor. Strain V6Fe1T belongs to the recently described family Deferrivibrionaceae in the phylum Deferribacterota. It grows chemoorganotrophically by fermentation of proteinaceous substrates and organic acids or by respiration of organic compounds using fumarate, nitrate, Fe(III), S°, and Mn(IV) as electron acceptors. The strain V6Fe1T can also grow chemolithoautotrophically using H2 as an electron donor and nitrate, nitrous oxide, Fe(III), Mn(IV), or sulfur as an electron acceptor. Stable isotope probing showed that V6Fe1T performs denitrification with nitrate reduction to dinitrogen and Dissimilatory Nitrate Reduction to Ammonium (DNRA). Culture experiments with RT-qPCR analysis of target genes revealed that strain V6Fe1T performs DNRA with the nitrite reductase formate-dependent NrfA and denitrification with an Hcp protein and other redox partners yet to be identified. Genomic analysis and experimental data suggest that strain V6Fe1T performs autotrophic carbon fixation via the recently discovered reversed oxidative TCA cycle (roTCA cycle). Based on genomic (ANI) and phenotypic properties, strain V6Fe1T ( = DSM 27501T =  JCM 39088T) is proposed to be the type strain of a novel species named Deferrivibrio metallireducens.

Association of expenditure on ultra-processed foods and beverages and anthropometric indicators in Mexican children: A longitudinal study

The prevalence of obesity in Mexico has been rising dramatically from school age onward. The high consumption of ultra-processed food has been identified as a contributing factor. We explored the longitudinal association between household expenditure on ultra-processed foods and beverages (UPF) and changes in anthropometric indicators of obesity among Mexican children aged 5 to 10 years in 2002. We used data from the Mexican Family Life Survey (MxFLS), a longitudinal, probabilistic, multipurpose, and representative survey of the Mexican population conducted in 2002, which reports household expenditure on the main food and beverage groups, as well as anthropometric indicators and sociodemographic characteristics of household members, across three rounds surveyed between 2002 and 2012 (n = 2,677). The exposure variable was UPF expenditure, categorized into tertiles, and the outcomes studied were BMI z-score for age, waist circumference, and waist-to-height ratio. We estimated random effects models and generalized estimating equation models for longitudinal data. Using an interaction term between tertiles of UPF expenditure and survey rounds, we found that household membership in the middle and upper tertiles of UPF expenditure in 2002 was associated with an increase in waist circumference and waist-to-height ratio, particularly after three years of follow-up. For instance, the middle tertile of UPF expenditure was associated with an increase of 4.43 centimeters in waist circumference compared to the low tertile of UPF expenditure after three years of follow-up (p < 0.01). Our findings suggest that higher UPF expenditure in households with children aged 5–10 years drives abdominal obesity in the short and medium term, underscoring the need for comprehensive policies to limit the purchase and consumption of UPF from an early age.

Psychological stress associated with prognostic uncertainties in recently diagnosed Parkinson’s disease patients: A qualitative study

Background Parkinson’s disease (PD) is a common neurodegenerative disorder that negatively impacts thousands of patients in Canada. The unexpected nature of PD is associated with a decline in mental health. The highest level of psychological stress occurs during the early years following the diagnosis. Objectives To understand the psychological stress associated with prognostic uncertainties in recently diagnosed PD patients, uncover the gaps in the current support systems, and recommend areas for improvement in the support services that aim to decrease the psychological stress associated with receiving the PD diagnosis. Methods An exploratory qualitative study was conducted using semi-structured interviews with 13 PD patients diagnosed for more than 6 months and less than 5 years. Participants were recruited from the Toronto Western Hospital Movement Disorders Clinic, Toronto, Ontario, Canada until saturation of key themes was reached. Results Five major themes were identified capturing the lived experiences of PD patients following diagnosis: 1) the circumstances of receiving the diagnosis and its psychological impact on PD patients, 2) the impact of intrapersonal factors on the PD journey, 3) the role of social relationships in PD patient’s life, 4) the interaction of PD patients with different elements of the healthcare system, and 5) support services available for recently diagnosed PD patients. Conclusions This study uncovers the psychological burden faced by PD patients due to prognostic uncertainties and insufficient support systems. It emphasizes the importance of a patient-centered approach for improving their quality of life and healthcare experiences through personalized support services.

Improvement of RT-DETR model for ground glass pulmonary nodule detection

Currently, pulmonary nodules detection work mostly focus on recognition and diagnosis of solid nodules. However, ground glass nodules have higher probability of malignancy, posing greater identification challenges and thus greater value for detection. To achieve rapid and accurate detection of ground glass nodules. This article proposed an algorithm based on RT-DETR model with the following enhancement: 1) optimize the backbone network with FCGE blocks to increase the detection accuracy of small-sized and blurred edge nodules; 2) replace the AIFI module with HiLo-AIFI module to reduce redundant computation and improve the detection accuracy of pure ground glass pulmonary nodules and mixed ground glass pulmonary nodules; 3) replace the DGAK module with CCFF module to address the issue of capturing complex features and recognition of irregularly shaped ground glass nodules. To obtain a more lightweight model, modules are designed for smaller number of parameters and higher computational efficiency. Model are tested on mixed dataset composed of LIDC-IDRI data and clinical data from cooperating hospitals. Compared to the baseline model, it shows an average precision improvement (mAP50/mAP50:95) of 2.1% and 1.7%, with a reduction parameters by 5.2 million. On a specialized dataset containing both pure and mixed ground glass nodules, our model outperformed the baseline model in all evaluation metrics. In general, the model proposed in this paper achieves improvement on lightweightness and detection accuracy. However, the model exhibits poor noise resistance and robustness, suggesting optimization in future work.

Lung cancer associated autoantibody responses are detectable years before clinical presentation

The EarlyCDT-Lung® test detects elevated levels of tumour-associated autoantibodies generated in response to immune recognition of cancerous cells, and these autoantibodies have previously been shown to precede clinical presentation of lung cancer. Using a longitudinal cohort from the United Kingdom Collaborative Trial of Ovarian Cancer Screening (UKCTOCS) study, we have established that elevated autoantibodies can be detected an average of four years in advance of clinical presentation, and in some cases up to 8 years prior to clinical presentation. This is the first study to establish pre-diagnostic elevation of autoantibodies using samples from a longitudinal prospective clinical trial using a clinically validated and commercially available biomarker panel.

Intraindividual variability differentiated older adults with physical frailty and the role of education in the maintenance of cognitive intraindividual variability

Objectives Physical frailty is associated with increased risk of cognitive impairment. However, its impact on sustained cognitive processing as evaluated by intraindividual variability (IIV), and factors beneficial to IIV in physically frail older adults remain unexplored. This study aimed to quantify differences in IIV between older adults with and without physical frailty, and examine whether education facilitated maintenance of IIV. Methods This cross-sectional study included 121 community-dwelling older adults 65-90 years with/without physical frailty (PF and non-PF; n = 41 and n = 80 respectively). Physical frailty was determined via Short Physical Performance Battery. Dispersion across the seven components of the Montreal Cognitive Assessment (MoCA) was computed to ascertain IIV. Multivariate analysis of covariance was used to determine group differences in total score and IIV. Four moderation models were constructed to test the effects of education on age-total score and age-IIV relationships in PF and non-PF. Results Compared with non-PF, PF showed greater IIV ( p = .022; partial η² =  0.044). Among PF, education moderated age-total score (R-sq =  0.084, F =  5.840, p <  0.021) and age-IIV (R-sq =  0.101, F =  7.454, p =  0.010) relationships. IIV increased with age for those with five years (β =  0.313, p =  0.006) or no formal education (β =  0.610, p =  0.001). Greater than seven years of education (β =  0.217, p =  0.050) may be required to maintain IIV at older age. Conclusion IIV may be a sensitive method to differentiate physically frail older adults. Additionally, perceived cognitive benefits of education may be dependent on physical functioning.

An optimized informer model design for electric vehicle SOC prediction

SOC prediction is of great value to electric vehicle status assessment. Informer model is better than other models in SOC prediction, but there is still a gap in practical application. Therefore, based on the health assessment algorithm, a new optimized Informer model is proposed to predict SOC. Firstly, the health assessment is carried out through the historical running data of the electric vehicle to obtain the health matrix. Then, the health matrix is used to improve Encoder and Decoder modules and improve the prediction accuracy and speed of Informer model. Subsequently, the health matrix is utilized to optimize the prediction logic, reduce the influence of truncation error, and further improve the SOC prediction accuracy. Finally, using the Informer model before and after optimization, SOC prediction is performed using four different datasets. The results indicate that after optimizing the En-De module of Informer, prediction accuracy improved by approximately 15%, with prediction speed increasing by about 100%. Furthermore, optimizing the prediction logic to reduce truncation error further enhanced Informer’s prediction accuracy by around 20%.