Bibliometric analysis of the application of deep learning in cancer from 2015 to 2023.

BACKGROUND: Recently, the application of deep learning (DL) has made great progress in various fields, especially in cancer research. However, to date, the bibliometric analysis of the application of DL in cancer is scarce. Therefore, this study aimed to explore the research status and hotspots of the application of DL in cancer. METHODS: We retrieved all articles on the application of DL in cancer from the Web of Science database Core Collection database. Biblioshiny, VOSviewer and CiteSpace were used to perform the bibliometric analysis through analyzing the numbers, citations, countries, institutions, authors, journals, references, and keywords. RESULTS: We found 6,016 original articles on the application of DL in cancer. The number of annual publications and total citations were uptrend in general. China published the greatest number of articles, USA had the highest total citations, and Saudi Arabia had the highest centrality. Chinese Academy of Sciences was the most productive institution. Tian, Jie published the greatest number of articles, while He Kaiming was the most co-cited author. IEEE Access was the most popular journal. The analysis of references and keywords showed that DL was mainly used for the prediction, detection, classification and diagnosis of breast cancer, lung cancer, and skin cancer. CONCLUSIONS: Overall, the number of articles on the application of DL in cancer is gradually increasing. In the future, further expanding and improving the application scope and accuracy of DL applications, and integrating DL with protein prediction, genomics and cancer research may be the research trends.

Long-term trends in cancer incidence and mortality among U.S. children and adolescents: a SEER database analysis from 1975 to 2018.

Background: Childhood and adolescent cancer represent a significant health burden in the United States. Current and precise epidemiological data are crucial to develop effective cancer control plans and ultimately reduce the burden of childhood and adolescent cancer. Methods: We analyzed data obtained from cancer registries in the National Cancer Institute's Surveillance, Epidemiology, and End Results Program. Age-standardized incidence and death rates, assessed using joinpoint analysis, were quantified as annual percentage changes (APC) and average percentage changes (AAPC). Results: The overall cancer incidence rate in 2008-2018 was 187.9 per 1,000,000 persons. Cancer incidence rates demonstrated a sustained upward trend, with an APC of 0.8 from 1975 to 2018. Incidence rates during 2008-2018 remained stable among non-Hispanic Black children but increased among other racial and ethnic groups. Leukemias, central nervous system tumors, and lymphomas were the most common cancer groups for patients aged 0-19 years. Cancer death rates decreased among children [AAPC, -1.3 (95% CI, -1.5 to -1.1)] during 2009-2019, while were stable among adolescents during that period. Conclusions: In this study, we analyzed cancer incidence and mortality rates and trends in children aged 0-19 years in the United States. Our findings revealed an overall increase in cancer incidence rates among children and adolescents, accompanied by a decline in cancer mortality rates over time. These rates and trends varied by age, sex, and particularly race and ethnicity, highlighting the significance of comprehending and addressing disparities and ultimately reducing the disease burden of childhood and adolescent cancer.

Partial molecular characterization, expression pattern and polymorphism analysis of MHC I genes in Chinese domestic goose (Anser cygnoides).

Major histocompatibility complex (MHC) allelic polymorphism is critically important for mediating antigen presentation in vertebrates. Presently, there are insufficient studies of MHC genetic diversity in domestic Anseriform birds. In this study, we analyzed the expression profile of MHC I genes and screened for MHC I exon 2 polymorphism in one domestic goose population from China using Illumina MiSeq sequencing. The results showed that four MHC I alleles (Ancy-IE2*09/*11/*13/*21) in one goose were identified based on cDNA cloning and sequencing using four primer combinations, and the varying number of cDNA clones implied that these four classical sequences showed differential expression patterns. Through next-generation sequencing, 27 alleles were obtained from 68 geese with 3-10 putative alleles per individual, indicating at least the existence of 5 MHC I loci in the goose. The marked excess of the non-synonymous over the synonymous substitution in the peptide-binding region (PBR) along 27 alleles and five positively selected sites (PSSs) detected around the PBR indicated that balancing selection might be the major force in shaping high MHC variation in the goose. Additionally, IA alleles displaying lower polymorphism were subject to less positive selection pressure than non-IA alleles with a higher level of polymorphism.

Comparison of the burden of digestive diseases between China and the United States from 1990 to 2019.

Introduction: China has experienced unprecedented transformations unseen in a century and is gradually progressing toward an emerging superpower. The epidemiological trends of digestive diseases in the United States (the US) have significant prescient effects on China. Methods: We extracted data on 18 digestive diseases from the Global Burden of Diseases 2019 Data Resource. Linear regression analysis conducted by the JoinPoint software assessed the average annual percentage change of the burden. We performed subgroup analyses based on sex and age group. Results: In 2019, there were 836.01 and 180.91 million new cases of digestive diseases in China and the US, causing 1558.01 and 339.54 thousand deaths. The age-standardized incidence rates of digestive diseases in China and the US were 58417.87/100,000 and 55018.65/100,000 respectively, resulting in age-standardized mortality rates of 81.52/100,000 and 60.88/100,000. The rates in China annually decreased by 2.149% for mortality and 2.611% for disability-adjusted life of year (DALY). The mortality and DALY rates of the US, respectively, had average annual percentage changes of -0.219 and -0.251. Enteric infections and cirrhosis and other chronic liver diseases accounted for the highest incidence and prevalence in both counties, respectively. The burden of multiple digestive diseases exhibited notable sex disparities. The middle-old persons had higher age-standardized prevalence rates. Conclusion: China bore a greater burden of digestive diseases, and the evolving patterns were more noticeable. Targeted interventions and urgent measures should be taken in both countries to address the specific burden of digestive diseases based on their different epidemic degree.

Knowledge, attitude, and practice toward sleep disorders and sleep hygiene among perimenopausal women.

This cross-sectional study aimed to explore the knowledge, attitude and practice (KAP) toward sleep disorders and sleep hygiene among perimenopausal women, who were enrolled in Dezhou region of Shandong Province between July and September 2023. A total of 720 valid questionnaires were collected (mean age: 51.28 ± 4.32 years old), and 344 (47.78%) reported experiencing insomnia. The mean scores for knowledge, attitude, practice, and Dysfunctional Beliefs and Attitudes about Sleep (DBAS) were 15.73 ± 7.60 (possible range: 0-36), 29.35 ± 3.15 (possible range: 10-50), 28.54 ± 4.03 (possible range: 10-50), and 6.79 ± 1.90 (possible range: 0-10), respectively. Path analysis showed that knowledge had direct effects on attitude (ß = 0.04, 95% CI 0.01-0.07, P = 0.001), and DBAS (ß = 0.04, 95% CI 0.02-0.05, P < 0.001). Knowledge had direct effects (ß = 0.11, 95% CI 0.08-0.15, P < 0.001) and indirect (ß = 0.02, 95% CI 0.00-0.03, P = 0.002) effect on practice. Moreover, attitude also had a direct impact on practice (ß = 0.34, 95% CI 0.25-0.43, P < 0.001). In conclusion, perimenopausal women exhibited insufficient knowledge, negative attitude, inactive practice toward sleep disorders and sleep hygiene, and unfavorable DBAS, emphasizing the need for targeted healthcare interventions.

Development and validation of a nomogram for predicting in-hospital mortality of intensive care unit patients with liver cirrhosis.

BACKGROUND: Liver cirrhosis patients admitted to intensive care unit (ICU) have a high mortality rate. AIM: To establish and validate a nomogram for predicting in-hospital mortality of ICU patients with liver cirrhosis. METHODS: We extracted demographic, etiological, vital sign, laboratory test, comorbidity, complication, treatment, and severity score data of liver cirrhosis patients from the Medical Information Mart for Intensive Care IV (MIMIC-IV) and electronic ICU (eICU) collaborative research database (eICU-CRD). Predictor selection and model building were based on the MIMIC-IV dataset. The variables selected through least absolute shrinkage and selection operator analysis were further screened through multivariate regression analysis to obtain final predictors. The final predictors were included in the multivariate logistic regression model, which was used to construct a nomogram. Finally, we conducted external validation using the eICU-CRD. The area under the receiver operating characteristic curve (AUC), decision curve, and calibration curve were used to assess the efficacy of the models. RESULTS: Risk factors, including the mean respiratory rate, mean systolic blood pressure, mean heart rate, white blood cells, international normalized ratio, total bilirubin, age, invasive ventilation, vasopressor use, maximum stage of acute kidney injury, and sequential organ failure assessment score, were included in the multivariate logistic regression. The model achieved AUCs of 0.864 and 0.808 in the MIMIC-IV and eICU-CRD databases, respectively. The calibration curve also confirmed the predictive ability of the model, while the decision curve confirmed its clinical value. CONCLUSION: The nomogram has high accuracy in predicting in-hospital mortality. Improving the included predictors may help improve the prognosis of patients.

Significant elevation of serum CA19-9 and CA242 levels induced by dulaglutide.

The use of dulaglutide, a common medication for managing type 2 diabetes, rarely causes elevated pancreatic tumour markers. Here, we report the case of a woman in her mid-60s with diabetes for over 10 years. The patient presented with markedly elevated serum CA19-9 and CA242 levels revealed during a routine health examination despite being asymptomatic. She had been receiving dulaglutide injections for 16 months. Imaging and interventional assessments did not reveal any hepatobiliary, gastrointestinal or pancreatic neoplasm. After excluding alternate diagnoses, the patient was determined to exhibit an adverse reaction to dulaglutide use. Management involved the discontinuation of dulaglutide, which resulted in normalisation of serum CA19-9 and CA242 levels within 6 weeks. This case underscores the importance of discontinuing dulaglutide and monitoring changes in the biomarker levels in asymptomatic patients receiving dulaglutide, rather than immediately resorting to imaging and endoscopic examinations.

Global, regional, and national burdens of cancer in children aged zero to nine years from 1990 to 2019.

Background: The description of long-term trends in the cancer burden among children aged zero to nine years from 1990 to 2019 reveals significant changes in children's health. It helps in resource allocation and health policy planning. We analysed data on the incidence, mortality, and disability-adjusted life years (DALYs) by sex and age group in children aged zero to nine. Methods: Estimates of DALYs for children aged zero to nine years, appeared as part of the Global Burden of Diseases, Injuries, and Risk Factor Study 2019, by age, sex, and location for 1990-2019. We also provided estimations by the sociodemographic index (SDI) quintile, a systematic measure to indicate educational attainment, income per capita, and total fertility rate for those younger than 25 years. We used age-period-cohort models to investigate paediatric cancers prevalence, incidence, mortality, and DALYs rates and auto-regressive integrated moving average models to predict cancer in children of different age groups in males and females. Results: A total of 6 224 010 DALY numbers for cancer cases occurred globally in 2019 among children aged zero to nine years. Additionally, the incidence of paediatric cancers in 2019 in the middle SDI countries was the highest, including 60 662 cases, and the highest mortality and DALYs cases of paediatric cancers were in the low SDI countries (25 502 and 2 199 790). The joinpoint regression analysis revealed that the trend of total cancer burden in age-standardised mortality rates and age-standardised DALYs rates showed a significant decrease with an average annual percentage change of -2.10 and -2.03 from 1990 to 2019. Furthermore, the paediatric cancer spectrum was changing. Other malignant neoplasms and other leukaemia were the major components of cancer in all age groups of children. Conclusions: The disease burden in children aged zero to nine years decreased significantly globally from 1990 to 2019. However, the overall prediction of childhood cancer increased slightly from 2020 to 2040. Our findings may help guide investments and inform policies. This highlights the necessity to improve current treatment measures and establish effective prevention strategies to reduce the cancer burden among children aged zero to nine years.

Performance Evaluation of Newly-Developed Tumor Markers Assay Kit Based on Flow Fluorescence Assay.

BACKGROUND: The purpose of this study is to evaluate the performance of recently developed tumor marker clinical kits in China, with the aim of encouraging local medical technology innovation and thus narrowing the research and development gap with foreign kits. METHODS: The newly established reagent kits were analyzed on the TESMI F3999-Luminex200 flow lattice instrument to verify precision, sensitivity (blank limit), linearity, anti-interference ability, carry-over contamination rate, hook effect, and reference interval verification. Additionally, the newly established reagent kits were compared to other commercially available detection kits (reference reagent kits) to analyze the correlation between the two types of kits. RESULTS: The intra-assay and inter-assay precision had coefficients of variations (CVs) less than 3.50% and 6.91%, respectively. The tumor marker blank limits were lower than the manufacturer's statement. The newly established reagent kits demonstrated excellent linearity (r > 0.99). Rheumatoid factor, triglycerides, bilirubin, and hemoglobin did not have significant interference with the determination of tumor markers. The carry-over contamination rates were all much lower than 3%. At extremely high concentrations of AFP (277,335 ng/mL and 1,031,424 ng/mL), the measured tumor marker values were higher than the upper limit of the linear range and no hook effect occurred. The reference interval was suitable for use in clinical laboratory settings. Correlation analysis indicated a satisfactory relevance and consistency between the newly developed reagent kits and reference reagent kits, with correlation coefficients of r > 0.967 among 654 patients and healthy individuals. CONCLUSIONS: The newly developed reagent kits for tumor markers performed well in all evaluated parameters, having the potential for clinical promotion and application.

Acute Pancreatitis in Pregnancy: A Propensity Score Matching Analysis and Dynamic Nomogram for Risk Assessment.

BACKGROUND: Acute pancreatitis is easily confused with abdominal pain symptoms, and it could lead to serious complications for pregnant women and fetus, the mortality was as high as 3.3% and 11.6-18.7%, respectively. However, there is still lack of sensitive laboratory markers for early diagnosis of APIP and authoritative guidelines to guide treatment. OBJECTIVE: The purpose of this study was to explore the risk factors of acute pancreatitis in pregnancy, establish, and evaluate the dynamic prediction model of risk factors in acute pancreatitis in pregnancy patients. STUDY DESIGN: Clinical data of APIP patients and non-pregnant acute pancreases patients who underwent regular antenatal check-ups during the same period were collected. The dataset after propensity matching was randomly divided into training set and verification set at a ratio of 7:3. The model was constructed using Logistic regression, least absolute shrinkage and selection operator regression, R language and other methods. The training set model was used to construct the diagnostic nomogram model and the validation set was used to validate the model. Finally, the accuracy and clinical practicability of the model were evaluated. RESULTS: A total of 111 APIP were included. In all APIP patients, hyperlipidemic pancreatitis was the most important reason. The levels of serum amylase, creatinine, albumin, triglyceride, high-density lipoprotein cholesterol, and apolipoprotein A1 were significantly different between the two groups. The propensity matching method was used to match pregnant pancreatitis patients and pregnant non-pancreatic patients 1:1 according to age and gestational age, and the matching tolerance was 0.02. The multivariate logistic regression analysis of training set showed that diabetes, triglyceride, Body Mass Index, white blood cell, and C-reactive protein were identified and entered the dynamic nomogram. The area under the ROC curve of the training set was 0.942 and in validation set was 0.842. The calibration curve showed good predictive in training set, and the calibration performance in the validation set was acceptable. The calibration curve showed the consistency between the nomogram model and the actual probability. CONCLUSION: The dynamic nomogram model we constructed to predict the risk factors of acute pancreatitis in pregnancy has high accuracy, discrimination, and clinical practicability.

Antibiotic resistance genes profile in the surface sediments of typical aquaculture areas across 15 major lakes in China.

Aquatic farming is considered as a major source of antibiotic resistant bacteria (ARB) and antibiotic resistance genes (ARGs) for the natural environment of the lakes. ARB and ARGs in the natural environment have increased quickly because of the human activities. Here, we have profiled the diversity and abundance of ARGs in sediments from the typical aquaculture areas around 15 major lakes in China using PCR and qPCR, and further assessed the risk factor shaping the occurrence and distribution of ARGs. And class 1, 2 and 3 integrons were initially detected by PCR with specific primers. ARGs were widely distributed in the lakes: Weishan Lake and Poyang Lake showed high diversity of ARGs, followed by Dongting Lake, Chao Lake and Tai Lake. Generally, the ARGs in the Middle-Lower Yangtze Plain were more abundant than those in the Qinghai-Tibet Plateau. Tetracycline resistance genes (tet(C), tet(A) & tet(M)) were prominent in sediments, and the next was AmpC ß-lactamase gene group BIL/LAT/CMY, and the last was the genes resistance to aminoglycoside (strA-strB). Partial least squares path modeling analysis (PLS-PMA) revealed that livestock had a significant direct effect on the distribution of ARGs in lakes, and population might indirectly influence the profiles of ARGs by affecting the scale of livestock and aquaculture. The detectable rate of class 1, 2 and 3 integrons were 80%, 100% and 46.67%, respectively. The prevalence of integrons might play a key role in promoting more frequent horizontal gene transfer (HGT) events, resulting in the environmental mobilization and dissemination of ARGs between bacteria.

The burden of mental disorders in Asian countries, 1990-2019: an analysis for the global burden of disease study 2019.

Mental disorders are the leading contributors to the globally nonfatal burden of disease. This study was aimed to estimate the burden of mental disorders in Asian countries. Based on GBD 2019, the prevalence and disability-adjusted life of years (DALYs) rates with 95% uncertainty intervals (UI) were estimated in Asian countries. Predictions for the future burden of 8 selected countries, ranks of the burden of mental disorders and correlations with Sociodemographic Index (SDI) were also estimated. During the past 3 decades, while the number of DALYs of mental disorders increased from 43.9 million (95% UI: 32.5-57.2) to 69.0 million (95% UI: 51.0-89.7), the age-standardized rates of DALYs of mental disorders remained largely consistent from 1452.2 (95% UI: 1080.16-1888.53) per 100,000 population in 1990 to 1434.82 (95% UI: 1065.02-1867.27) per 100,000 population in 2019, ranked as the eighth most significant disease burden in Asia in 2019. Depressive disorders (37.2%) were the leading contributors to the age-standardized DALY rates of mental disorders in Asia, followed by anxiety disorders (21.5%). The age-standardized DALY rates in females were higher than their male counterparts, both peaked at 30-34 years. The age-standardized DALY rates were predicted to remain stable, with the number of DALYs presented an upward trend in the future. There was no significant correlation between the burden of mental disorders and SDI. All mental disorders ranked higher in 2019, compared in 1990. To reduce this burden, urgent measures for prevention, treatment, and rehabilitation for mental disorders need to be taken by Asian governments.

Trends of hospitalisation among new admission inpatients with oesophagogastric variceal bleeding in cirrhosis from 2014 to 2019 in the Affiliated Hospital of Southwest Medical University: a single-centre time-series analysis.

OBJECTIVES: This study aimed to assess the internal law and time trend of hospitalisation for oesophagogastric variceal bleeding (EGVB) in cirrhosis and develop an effective model to predict the trend of hospitalisation time. DESIGN: We used a time series covering 72 months to analyse the hospitalisation for EGVB in cirrhosis. The number of inpatients in the first 60 months was used as the training set to establish the autoregressive integrated moving average (ARIMA) model, and the number over the next 12 months was used as the test set to predict and observe their fitting effect. SETTING AND DATA: Case data of patients with EGVB between January 2014 and December 2019 were collected from the Affiliated Hospital of Southwest Medical University. OUTCOME MEASURES: The number of monthly hospitalised patients with EGVB in our hospital. RESULTS: A total of 877 patients were included in the analysis. The proportion of EGVB in patients with cirrhosis was 73% among men and 27% among women. The peak age at hospitalisation was 40-60 years. The incidence of EGVB varied seasonally with two peaks from January to February and October to November, while the lowest number was observed between April and August. Time-series analysis showed that the number of inpatients with EGVB in our hospital increased annually. The sequence after the first-order difference was a stationary series (augmented Dickey-Fuller test p=0.02). ARIMA (0,1,0) (0,1,1)12 with a minimum Akaike Information Criterion value of 260.18 could fit the time trend of EGVB inpatients and had a good short-term prediction effect. The root mean square error and mean absolute error were 2.4347 and 1.9017, respectively. CONCLUSIONS: The number of hospitalised patients with EGVB at our hospital is increasing annually, with seasonal changes. The ARIMA model has a good prediction effect on the number of hospitalised patients with EGVB in cirrhosis.

Bortezomib modulated the autophagy-lysosomal pathway in a TFEB-dependent manner in multiple myeloma.

OBJECTIVE: To explore the involvement of TFEB-mediated autophagy-lysosomal mechanisms in multiple myeloma (MM) during bortezomib treatment. METHODS: MM cells were exposed to bortezomib or subjected to TFEB knockdown. CCK assay was used to assess the cell proliferation. Western blotting and fluorescent staining were conducted to examine autophagy and lysosomes. The TFEB expression pattern was analyzed, and whole transcriptome sequencing was carried out. Additionally, TFEB target genes were predicted using the GTRD(http://gtrd.biouml.org/) website, and pathway analysis was performed. RESULTS: Bortezomib demonstrated a dose-dependent and time dependent inhibition of cell proliferation. In MM cells treated with bortezomib, LC3B, Beclin-1, TFEB, and Lamp1 exhibited upregulation in a time- and concentration-dependent manner. LysoTracker dye labeling showed an increase in lysosomes in the bortezomib-treated group. Moreover, bortezomib elevated the expression of lysosome-associated factor Lamp1. Bortezomib promoted the nuclear translocation of TFEB, leading to decreased cytoplasmic TFEB and increased nuclear TFEB. TFEB gene silencing reversed bortezomib's inhibitory effect on MM cell lines, significantly reducing autophagosome expression and lysosome numbers. Furthermore, bioinformatic analysis identified the MAPK pathway as a potential downstream target of TFEB. CONCLUSION: Bortezomib effectively inhibits MM cell proliferation and induces autophagy, partly through TFEB-mediated mechanisms, with potential involvement of the MAPK pathway.

Global trends and hotspots in the field of mitochondrial dynamics and hepatocellular carcinoma: A bibliometric analysis from 2007 to 2023.

Background: Mitochondria are dynamic organelles, and mitochondrial dynamics are important for the maintenance of mitochondrial inheritance and function. Recently, an increasing number of studies have shown that mitochondrial dynamics play an important role in the occurrence and development of hepatocellular carcinoma (HCC). However, bibliometric analyses of mitochondrial dynamics in HCC are scarce. Therefore, we conducted a bibliometric analysis to explore the current global research status and trends in mitochondrial dynamics and HCC. Methods: Global publications on mitochondrial dynamics and HCC published between 2007 and May 2023 were retrieved from the Web of Science Core Collection (WoSCC) database. Bibliometric analysis was performed using Bibliometrix, VOSviewer, and CiteSpace to analyze the numbers, citations, countries, institutions, authors, journals, references, and keywords. Results: A total of 518 publications were retrieved fromthe WoSCC database. China and The Fourth Military Medical University were the most productive countries and institutions. Zorzano, A published the most literature whereas Chen, HC was the author with the highest number of co-citations. Plos One was the most popular journal, whereas the Journal of Biological Chemistry had the highest number of co-citations. The most frequently used keyword was "mitochondria". Further analysis of the references and keywords showed that the molecular mechanisms linking them to drug therapy targets should be the focus of future studies. Conclusions: Research on mitochondrial dynamics in HCC has received much attention, and many studies have been published. However, research on mitochondrial dynamics and HCC has been limited by insufficient regional development imbalances and global cooperation. Nevertheless, future research on mitochondrial dynamics and HCC is promising, especially regarding the molecular mechanisms of mitochondrial fission and fusion and how to link the currently known molecular mechanisms with drug therapy targets for HCC.

Role of sestrins in metabolic and aging-related diseases.

Sestrins are a type of highly conserved stress-inducing protein that has antioxidant and mTORC1 inhibitory functions. Metabolic dysfunction and aging are the main risk factors for development of human diseases, such as diabetes, neurodegenerative diseases, and cancer. Sestrins have important roles in regulating glucose and lipid metabolism, anti-tumor functions, and aging by inhibiting the reactive oxygen species and mechanistic target of rapamycin complex 1 pathways. In this review, the structure and biological functions of sestrins are summarized, and how sestrins are activated and contribute to regulation of the downstream signal pathways of metabolic and aging-related diseases are discussed in detail with the goal of providing new ideas and therapeutic targets for the treatment of related diseases.

Application of a Machine Learning Predictive Model for Recurrent Acute Pancreatitis.

BACKGROUND AND AIM: Acute pancreatitis is the main cause of hospitalization for pancreatic disease. Some patients tend to have recurrent episodes after experiencing an episode of acute pancreatitis. This study aimed to construct predictive models for recurrent acute pancreatitis (RAP). METHODS: A total of 531 patients who were hospitalized for the first episode of acute pancreatitis at the Affiliated Hospital of Southwest Medical University from January 2018 to December 2019 were enrolled in the study. We confirmed whether the patients had a second episode until December 31, 2021, through an electronic medical record system and telephone or WeChat follow-up. Clinical and follow-up data of patients were collected and randomly allocated to the training and test sets at a ratio of 7:3. The training set was used to select the best model, and the selected model was tested with the test set. The area under the receiver operating characteristic curves, sensitivity, specificity, positive predictive value, negative predictive value, accuracy, decision curve, and calibration plots were used to assess the efficacy of the models. Shapley additive explanation values were used to explain the model. RESULTS: Considering multiple indices, XGBoost was the best model. The area under the receiver operating characteristic curves, accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the XGBoost model in the test set were 0.779, 0.763, 0.883, 0.647, 0.341, and 0.922, respectively. According to the Shapley additive explanation values, drinking, smoking, higher levels of triglyceride, and the occurrence of ANC are associated with RAP. CONCLUSION: The XGBoost model shows good performance in predicting RAP, which may help identify high-risk patients.

FANCD2 as a novel prognostic biomarker correlated with immune and drug therapy in Hepatitis B-related hepatocellular carcinoma.

BACKGROUND: Ferroptosis is related to the immunosuppression of tumors and plays a critical role in cancer progression. Fanconi anemia complementation group D2 (FANCD2) is a vital gene that regulates ferroptosis. However, the mechanism of action of FANCD2 in Hepatitis B-related hepatocellular carcinoma (HCC) remains unknown. In this study, we investigated the prognostic significance and mechanism of action of FANCD2 in Hepatitis B-related HCC. METHODS: The expression of FANCD2 in Hepatitis B-related HCC was explored using The Cancer Genome Atlas (TCGA) and validated using the Gene Expression Omnibus (GEO) database. Univariate and multivariate Cox regression analyses and Kaplan-Meier survival curves were used to analyze the relationship between FANCD2 expression and the overall survival of patients with Hepatitis B-related HCC. Protein-protein interaction networks for FANCD2 were built using the STRING website. In addition, correlations between FANCD2 expression and the dryness index, tumor mutational burden, microsatellite instability (MSI), immune pathways, genes involved in iron metabolism, and sorafenib chemotherapeutic response were analyzed. RESULTS: Our results indicated that FANCD2 was significantly overexpressed in Hepatitis B-related HCC and demonstrated a strong predictive ability for diagnosis (Area Under Curve, 0.903) and prognosis of the disease. High FANCD2 expression was associated with poor prognosis, high-grade tumors, high expression of PDL-1, high MSI scores, and low sorafenib IC50 in Hepatitis B-related HCC. BRCA1, BRCA2, FAN1, and FANCC were vital proteins interacting with FANCD2. The expression level of FANCD2 significantly correlated with the infiltration levels of Treg cells, B cells, CD8 + T cells, CD4 + T cells, neutrophils, macrophages, myeloid dendritic cells, and NK cells in Hepatitis B-related HCC. FANCD2 was positively correlated with the tumor proliferation signature pathway, DNA repair, and cellular response to hypoxia. CONCLUSION: Our study indicated that FANCD2 was a potential novel biomarker and immunotherapeutic target against Hepatitis B-related HCC, which might be related to the chemotherapeutic response to sorafenib.

Prediction of in-hospital Mortality of Intensive Care Unit Patients with Acute Pancreatitis Based on an Explainable Machine Learning Algorithm.

BACKGROUND AND AIM: Acute pancreatitis (AP) is potentially fatal. Therefore, early identification of patients at a high mortality risk and timely intervention are essential. This study aimed to establish an explainable machine-learning model for predicting in-hospital mortality of intensive care unit (ICU) patients with AP. METHODS: Data on patients with AP, including demographics, vital signs, laboratory tests, comorbidities, treatment, complication, and severity scores, were extracted from the Medical Information Mart for Intensive Care IV (MIMIC-IV) and the eICU collaborative research database (eICU-CRD). Based on the data from MIMIC-IV, we used the least absolute shrinkage and selection operator algorithm to select variables and then established 9 machine-learning models and screened the optimal model. Data from the eICU-CRD were used for external validation. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, decision curve, and calibration plots were used to assess the models' efficacy. Shapley's additive explanation values were used to explain the model. RESULTS: Gaussian naive Bayes (GNB) model had the best performance on the data from MIMIC-IV, with an AUC, accuracy, sensitivity, and specificity of 0.840, 0.787, 0.839, and 0.792, respectively. The GNB model also performed well on the data from the eICU-CRD, with an AUC, accuracy, sensitivity, and specificity of 0.862, 0.833, 0.848, and 0.763, respectively. According to Shapley's additive explanation values, the top 4 predictive factors were maximum red cell distribution width, minimum saturation of blood oxygen, maximum blood urea nitrogen, and the Sequential Organ Failure Assessment score. CONCLUSION: The GNB model demonstrated excellent performance and generalizability in predicting mortality in ICU patients with AP. Therefore, it can identify patients at a high mortality risk.