A novel scoring model for predicting efficacy and guiding individualised treatment in immune thrombocytopaenia.

Despite diverse therapeutic options for immune thrombocytopaenia (ITP), drug efficacy and selection challenges persist. This study systematically identified potential indicators in ITP patients and followed up on subsequent treatment. We initially analysed 61 variables and identified 12, 14, and 10 candidates for discriminating responders from non-responders in glucocorticoid (N = 215), thrombopoietin receptor agonists (TPO-RAs) (N = 224), and rituximab (N = 67) treatments, respectively. Patients were randomly assigned to training or testing datasets and employing five machine learning (ML) models, with eXtreme Gradient Boosting (XGBoost) area under the curve (AUC = 0.89), Decision Tree (DT) (AUC = 0.80) and Artificial Neural Network (ANN) (AUC = 0.79) selected. Cross-validated with logistic regression and ML finalised five variables (baseline platelet, IP-10, TNF-α, Treg, B cell) for glucocorticoid, eight variables (baseline platelet, TGF-ß1, MCP-1, IL-21, Th1, Treg, MK number, TPO) for TPO-RAs, and three variables (IL-12, Breg, MAIPA-) for rituximab to establish the predictive model. Spearman correlation and receiver operating characteristic curve analysis in validation datasets demonstrated strong correlations between response fractions and scores in all treatments. Scoring thresholds SGlu ≥ 3 (AUC = 0.911, 95% CI, 0.865-0.956), STPO-RAs ≥ 5 (AUC = 0.964, 95% CI 0.934-0.994), and SRitu = 3 (AUC = 0.964, 95% CI 0.915-1.000) indicated ineffectiveness in glucocorticoid, TPO-RAs, and rituximab therapy, respectively. Regression analysis and ML established a tentative and preliminary predictive scoring model for advancing individualised treatment.

ABCD2-I Score Predicts Unplanned Emergency Department Revisits within 72 Hours Due to Recurrent Acute Ischemic Stroke.

BACKGROUND: the ABCD2 score is valuable for predicting early stroke recurrence after a transient ischemic attack (TIA), and Doppler ultrasound can aid in expediting stroke triage. The study aimed to investigate whether combining the ABCD2 score with carotid duplex results can enhance the identification of early acute ischemic stroke after TIA. METHODS: we employed a retrospective cohort design for this study, enrolling patients diagnosed with TIA who were discharged from the emergency department (ED). The modified ABCD2-I (c50) score, which incorporates a Doppler ultrasound assessment of internal carotid artery stenosis > 50%, was used to evaluate the risk of acute ischemic stroke within 72 h. Patients were categorized into three risk groups: low risk (with ABCD2 and ABCD2-I scores = 0-4), moderate risk (ABCD2 score = 4-5 and ABCD2-I score = 5-7), and high risk (ABCD2 score = 6-7 and ABCD2-I score = 8-9). RESULTS: between 1 January 2014, and 31 December 2019, 1124 patients with new neurological deficits were screened, with 151 TIA patients discharged from the ED and included in the analysis. Cox proportional hazards analysis showed that patients in the high-risk group, as per the ABCD2-I (c50) score, were significantly associated with revisiting the ED within 72 h due to acute ischemic stroke (HR: 3.12, 95% CI: 1.31-7.41, p = 0.0102), while the ABCD2 alone did not show significant association (HR: 1.12, 95% CI: 0.57-2.22, p = 0.7427). CONCLUSION: ABCD2-I (c50) scores effectively predict early acute ischemic stroke presentations to the ED within 72 h after TIA.

An early predictive model for Kawasaki disease shock syndrome in children in central China.

Introduction: This study aims to analyze the clinical features of Kawasaki disease (KD) shock syndrome (KDSS) and explore its early predictors. Methods: A retrospective case-control study was used to analyze KD cases from February 2016 to October 2023 in our hospital. A total of 28 children with KDSS and 307 children who did not develop KDSS were included according to matching factors. Baseline information, clinical manifestations, and laboratory indicators were compared between the two groups. Indicators of differences were analyzed based on univariate analysis; binary logistic regression analysis was used to identify the risk factors for KDSS, and then receiver operating characteristic analysis was performed to establish a predictive score model for KDSS. Results: Elevated neutrophil-to-lymphocyte ratio(NLR) and decreased fibrinogen (FIB) and Na were independent risk factors for KDSS; the scoring of the above risk factors according to the odds ratio value eventually led to the establishment of a new scoring system: NLR ≥ 7.99 (6 points), FIB ≤ 5.415 g/L (1 point), Na ≤ 133.05 mmol/L (3 points), and a total score of ≥3.5 points were high-risk factors for progression to KDSS; otherwise, they were considered to be low-risk factors. Conclusion: Children with KD with NLR ≥ 7.99, FIB ≤ 5.415 g/L, and Na ≤ 133.05 mmol/L, and those with two or more of the above risk factors, are more likely to progress to KDSS, which helps in early clinical diagnosis and treatment.

Enhancing prognostic prediction of invasive candidiasis among cancer patients with a serum C5a-based scoring model.

PURPOSE: Invasive candidiasis poses a life-threatening risk, and early prognosis assessment is vital for timely interventions to reduce mortality. Serum C5a levels have recently been linked to prognosis, but confirmation in cancer patients is pending. METHODS: We detected the concentrations of serum C5a in hospitalized cancer patients with invasive candidiasis from 2020 to 2023, and retrospectively analyzed the clinical data. RESULTS: 372 cases were included in this study, with a 90-day mortality rate of 21.8%. Candida albicans (48.7%) remained the predominant pathogen, followed by Candida glabrata (25.5%), Candida tropicalis (12.4%), and Candida parapsilosis (8.3%). Gastrointestinal cancer was the most diagnosed pathology type (37.6%). Serum C5a demonstrated a noteworthy correlation with 90-day mortality, and employing a cutoff value of 36.7 ng/ml revealed significantly higher 90-day mortality in low-C5a patients (41.2%) compared to high-C5a patients (6.3%) (p < 0.001). We also identified no source control, no surgery, metastasis, or chronic renal failure independently correlated with the 90-day mortality. Based on this, a prognostic model combining C5a and clinical parameters was constructed, which performed better than models built solely on C5a or clinical parameters. Furthermore, we weighted scores to each parameter in the model and presented diagnostic sensitivity and specificity corresponding to different score points calculated by the model. CONCLUSION: We constructed a prognostic scoring model including serum C5a and clinical parameters, which would contribute to precise prognosis assessment and benefit the outcome among cancer patients.

Prediction of neoplastic gallbladder polyps in patients with different age level based on preoperative ultrasound: a multi-center retrospective real-world study.

BACKGROUND: The prevalence of neoplastic polyps in gallbladder polyps (GPs) increases sharply with age and is associated with gallbladder carcinoma (GBC). This study aims to predict neoplastic polyps and provide appropriate treatment strategies based on preoperative ultrasound features in patients with different age level. METHODS: According to the age classification of WHO, 1523 patients with GPs who underwent cholecystectomy from January 2015 to December 2019 at 11 tertiary hospitals in China were divided into young adults group (n=622), middle-aged group (n=665) and elderly group (n=236). Linear scoring models were established based on independent risk variables screened by the Logistic regression model in different age groups. The area under ROC (AUC) to evaluate the predictive ability of linear scoring models, long- and short- diameter of GPs. RESULTS: Independent risk factors for neoplastic polyps included the number of polyps, polyp size (long diameter), and fundus in the young adults and elderly groups, while the number of polyps, polyp size (long diameter), and polyp size (short diameter) in the middle-aged groups. In different age groups, the AUCs of its linear scoring model were higher than the AUCs of the long- and short- diameter of GPs for differentiating neoplastic and non-neoplastic polyps (all P<0.05), and Hosmer-Lemeshow goodness of fit test showed that the prediction accuracy of the linear scoring models was higher than the long- and short- diameter of GPs (all P>0.05). CONCLUSION: The linear scoring models of the young adults, middle-aged and elderly groups can effectively distinguish neoplastic polyps from non-neoplastic polyps based on preoperative ultrasound features.

Combination of S100A12/TLR2 signaling molecules and clinical indicators in a new predictive model for IVIG-resistant Kawasaki disease.

Although intravenous immunoglobulin (IVIG)-resistant Kawasaki disease (KD) presents with persistent inflammatory stimulation of the blood vessels and an increased risk of coronary artery dilatation. However, the pathogenesis of this disease is unclear, with no established biomarkers to predict its occurrence. This study intends to explore the utility of S100A12/TLR2-related signaling molecules and clinical indicators in the predictive modeling of IVIG-resistant KD. The subjects were classified according to IVIG treatment response: 206 patients in an IVIG-sensitive KD group and 49 in an IVIG-resistant KD group. Real-time PCR was used to measure the expression of S100A12, TLR2, MYD88, and NF-κB in peripheral blood mononuclear cells of patients, while collecting demographic characteristics, clinical manifestations, and laboratory test results of KD children. Multi-factor binary logistic regression analysis identified procalcitonin (PCT) level (≥ 0.845 ng/mL), Na level (≤ 136.55 mmol/L), and the relative expression level of S100A12 (≥ 10.224) as independent risk factors for IVIG-resistant KD and developed a new scoring model with good predictive ability to predict the occurrence of IVIG-resistant KD.

Development of a weighted scoring model for social activities to predict disability incidents among older Japanese adults.

BACKGROUND: Social activities contribute to health improvements in older adults, but methods for evaluating these activities are not yet established. We developed a scoring model for social activity, weighted by specific activities, to assess the association between disability incidence in older adults and social activities. METHODS: Data were obtained from Japan's National Center for Geriatrics and Gerontology Study of Geriatric Syndromes (NCGG-SGS). Social activity was evaluated across 16 domains. Disability was determined using data extracted from Japan's long-term care insurance system. RESULTS: Data from 4998 older adults were analyzed; among them, 422 (8.4 %) developed a disability within 35 months (Interquartile range: 32-39). The Cox proportional hazards model was used to assess 16 domains of social activity. The results yielded risk factors for disability incidence in six social activity domains: work, travel, hobbies, babysitting, family caregiving, and events. The coefficients for these activities were assigned weights of 3, 3, 2, 1, 1, and 1, respectively. The weighted social activity scoring model significantly improved the ability to predict disability incidence when the number of social activities in which individuals participated was considered (social activity score: area under the curve [AUC] 0.691, 95 % confidence interval [CI] 0.664-0.717; number of social activities: AUC 0.681, 95 % CI 0.654-0.707, P = 0.042). CONCLUSIONS: The composite score derived from the weighted social activity scoring model serves as a valuable tool due to its enhanced predictability, which complements established background factors associated with the incidence of disability in older adults.

Construction and validation of a risk-scoring model to predict lymph node metastasis in T1b-T2 esophageal cancer.

BACKGROUND: Lymph node status is an important factor in determining preoperative treatment strategies for stage T1b-T2 esophageal cancer (EC). Thus, the aim of this study was to investigate the risk factors for lymph node metastasis (LNM) in T1b-T2 EC and to establish and validate a risk-scoring model to guide the selection of optimal treatment options. METHODS: Patients who underwent upfront surgery for pT1b-T2 EC between January 2016 and December 2022 were analyzed. On the basis of the independent risk factors determined by multivariate logistic regression analysis, a risk-scoring model for the prediction of LNM was constructed and then validated. The area under the receiver operating characteristic curve (AUC) was used to assess the discriminant ability of the model. RESULTS: The incidence of LNM was 33.5% (214/638) in our cohort, 33.4% (169/506) in the primary cohort and 34.1% (45/132) in the validation cohort. Multivariate analysis confirmed that primary site, tumor grade, tumor size, depth, and lymphovascular invasion were independent risk factors for LNM (all P < 0.05), and patients were grouped based on these factors. A 7-point risk-scoring model based on these variables had good predictive accuracy in both the primary cohort (AUC, 0.749; 95% confidence interval 0.709-0.786) and the validation cohort (AUC, 0.738; 95% confidence interval 0.655-0.811). CONCLUSION: A novel risk-scoring model for lymph node metastasis was established to guide the optimal treatment of patients with T1b-T2 EC.

Early Identification of Patients with Potential Failure of Nonoperative Management for Gastroduodenal Peptic Ulcer Perforation.

INTRODUCTION: We aimed to identify objective factors associated with failure of nonoperative management (NOM) of gastroduodenal peptic ulcer perforation (GDUP) and establish a scoring model for early identification of patients in whom NOM of GDUP may fail. METHODS: A total of 71 patients with GDUP were divided into NOM (cases of NOM success) and operation groups (cases requiring emergency operation or conversion from NOM to operation). Using logistic regression analysis, a scoring model was established based on the independent factors. The patients were stratified into low-risk and high-risk groups according to the scores. RESULTS: Of the 71 patients, 18 and 53 were in the NOM and operation groups, respectively. Ascites in the pelvic cavity on computed tomography (CT) and sequential organ failure assessment (SOFA) score at admission were identified as independent factors for NOM failure. The scoring model was established based on the presence of ascites in the pelvic cavity on CT and SOFA score ≥2 at admission. The operation rates for GDUP were 28.6% and 86.0% in the low-risk (score, 0) and high-risk groups (scores, 2 and 4), respectively. CONCLUSION: Our scoring model may help determine NOM failure or success in patients with GDUP and make decisions regarding initial treatment.

The expression of autophagy markers in IVIG-resistant Kawasaki disease and the establishment of prediction model.

BACKGROUND: The aim of this study was to find early predictors of Intravenous Immunoglobulin (IVIG)-Resistant Kawasaki Disease. METHODS: Patients diagnosed with Kawasaki disease were enrolled in this study. Univariate analysis and multiple logistic regression were used to analyze the clinical characteristics and laboratory findings of patients in both groups before IVIG treatment. Independent predictors of Intravenous Immunoglobulin-Resistant Kawasaki Disease were analyzed, and a prediction model for children with Intravenous Immunoglobulin-Resistant Kawasaki Disease was constructed. RESULTS: A total of 108 children (67 males and 41 females) with IVIG-sensitive Kawasaki disease and 31 children (20 males and 11 females) with IVIG-resistant Kawasaki disease participated in this study. Compared with the IVIG-sensitive group, the duration of hospitalization, ALT, AST, GLB, r-GT, IgG, PCT, and ESR was elevated in the IVIG-resistant KD group, and ATG16L1, LC3II, BECN1, RBC, HGB, ALB, A/G, and CK were significantly lower (P < 0.05). mRNA expression of ESR, BECN1, and LC3II were independent risk factors for IVIG-resistant Kawasaki disease. A logistic regression model and scoring system were established, and the cut-off values of independent risk factors were derived from ROC curves: ESR ≥ 79.5 mm/h, BECN1 ≤ 0.645, LC3II ≤ 0.481. A new scoring system was established according to the respective regression coefficients as follows: ESR ≥ 79.5 mm/h (1 point), BECN1 ≤ 0.645 (1 point). LC3II ≤ 0.481 (2 points), 0-1 as low risk for IVIG non-response, and ≥ 2 as high risk. Applied to this group of study subjects, the sensitivity was 87.10%, specificity 83.33%, Youden index 0.70, AUC 0.9. CONCLUSIONS: Autophagy markers ATG16L1, BECN1, and LC3II are down-regulated in the expression of IVIG -resistant KD. ESR, BECN1, and LC3II mRNAs are independent risk factors for IVIG-resistant KD and may be involved in the development of IVIG-resistant KD. This study established a new model that can be used to predict IVIG-resistant KD, and future validation in a larger population is needed.

PIVKA-II combined with tumor burden score to predict long-term outcomes of AFP-negative hepatocellular carcinoma patients after liver resection.

BACKGROUND: This study aimed to establish a simple prognostic scoring model based on tumor burden score (TBS) and PIVKA-II to predict long-term outcomes of α-fetoprotein (AFP)-negative hepatocellular carcinoma (HCC) patients. METHODS: 511 patients were divided into the training cohort (n = 305) and the validation cohort (n = 206) at a ratio of 6:4. Receiver operating characteristic curves (ROC) were established to identify cutoff values of TBS and PIVKA-II. Kaplan-Meier curves were used to analyze survival outcomes. The multivariable Cox regression was used to identify variables independently associated with survival outcomes. The predictive performance of the TBS-PIVKA II score (TPS) model was compared with Barcelona clinic liver cancer (BCLC) stage and American Joint Committee on Cancer (AJCC TNM) stage. RESULTS: The present study established the TPS model using a simple scoring system (0, 1 for low/high TBS [cutoff value: 4.1]; 0, 1 for low/high PIVKA-II [cutoff value: 239 mAU/mL]). The TPS scoring model was divided into three levels according to the summation of TBS score and PIVKA-II score: TPS 0, TPS 1, and TPS 2. The TPS scoring model was able to stratify OS (training: p < 0.001, validation: p < 0.001) and early recurrence (training: p < 0.001; validation: p = 0.001) in the training cohort and the validation cohort. The TPS score was independently associated with OS (TPS 1 vs. 0, HR: 2.28, 95% CI: 1.01-5.17; TPS 2 vs. 0, HR: 4.21, 95% CI: 2.01-8.84) and early recurrence (TPS 1 vs. 0, HR: 3.50, 95% CI: 1.71-7.16; TPS 2 vs. 0, HR: 3.79, 95% CI: 1.86-7.75) in the training cohort. The TPS scoring model outperformed BCLC stage and AJCC TNM stage in predicting OS and early recurrence in the training cohort and the validation cohort. But the TPS scoring model was unable to stratify the late recurrence in the training cohort (p = 0.872) and the validation cohort (p = 0.458). CONCLUSIONS: The TPS model outperformed the BCLC stage and AJCC TNM stage in predicting OS and early recurrence of AFP-negative HCC patients after liver resection, which might better assist surgeons in screening AFP-negative HCC patients who may benefit from liver resection.

Construction of 11 metabolic-related lncRNAs to predict the prognosis in lung adenocarcinoma.

OBJECTIVE: To explore the metabolism-related lncRNAs in the tumorigenesis of lung adenocarcinoma. METHODS: The transcriptome data and clinical information about lung adenocarcinoma patients were acquired in TCGA (The Cancer Genome Atlas). Metabolism-related genes were from the GSEA (Gene Set Enrichment Analysis) database. Through differential expression analysis and Pearson correlation analysis, lncRNAs about lung adenocarcinoma metabolism were identified. The samples were separated into the training and validation sets in the proportion of 2:1. The prognostic lncRNAs were determined by univariate Cox regression analysis and LASSO (Least absolute shrinkage and selection operator) regression. A risk model was built using Multivariate Cox regression analysis, evaluated by the internal validation data. The model prediction ability was assessed by subgroup analysis. The Nomogram was constructed by combining clinical indicators with independent prognostic significance and risk scores. C-index, calibration curve, DCA (Decision Curve Analysis) clinical decision and ROC (Receiver Operating Characteristic Curve) curves were obtained to assess the prediction ability of the model. Based on the CIBERSORT analysis, the correlation between lncRNAs and tumor infiltrating lymphocytes was obtained. RESULTS: From 497 lung adenocarcinoma and 54 paracancerous samples, 233 metabolic-related and 11 prognostic-related lncRNAs were further screened. According to the findings of the survival study, the low-risk group had a greater OS (Overall survival) than the high-risk group. ROC analysis indicated AUC (Area Under Curve) value was 0.726. Then, a nomogram with T, N stage and risk ratings was developed according to COX regression analysis. The C-index was 0.743, and the AUC values of 3- and 5-year survival were 0.741 and 0.775, respectively. The above results suggested the nomogram had a good prediction ability. The results based on the CIBERSORT algorithm demonstrated the lncRNAs used to construct the model had a strong correlation with the polarization of immune cells. CONCLUSIONS: The study identified 11 metabolic-related lncRNAs for lung adenocarcinoma prognosis, on which basis a prognostic risk scoring model was created. This model may have a good predictive potential for lung adenocarcinoma.

A Modified NAR Scoring Model Incorporating Immune Infiltration Characteristics to Better Predict Long-Term Survival Following Neoadjuvant Radiotherapy in Rectal Cancer.

(1) Background: The neoadjuvant rectal (NAR) score has been developed as a prognostic tool for survival in locally advanced rectal cancer (LARC). However, the NAR score only incorporates weighted cT, ypT, and ypN categories. This long-term follow-up study aims to modify a novel prognostic scoring model and identify a short-term endpoint for survival. (2) Methods: The prognostic factors for overall survival (OS) were explored through univariate and multivariate analyses. Based on Cox regression modeling, nomogram plots were constructed. Area under the curve (AUC) and concordance indices were used to evaluate the performance of the nomogram. Receiver operating characteristic (ROC) analysis was conducted to compare the efficiency of the nomogram with other prognostic factors. (3) Results: After a long-term follow-up, the 5-year OS was 67.1%. The mean NAR score was 20.4 ± 16.3. Multivariate analysis indicated that CD8+ T-cell, lymphovascular invasion, and the NAR score were independent predictors of OS. The modified NAR scoring model, incorporating immune infiltration characteristics, exhibited a high C-index of 0.739 for 5-year OS, significantly outperforming any individual factor. Moreover, the predictive value of the nomogram was superior to the AJCC stage and pathological complete regression at 3-year, 5-year, and 10-year time points, respectively. Over time, the model's predictions of long-term survival remained consistent and improved in accuracy. (4) Conclusions: The modified NAR scoring model, incorporating immune infiltration characteristics, demonstrates high accuracy and consistency in predicting OS.

A pyroptosis gene-based prognostic model for predicting survival in low-grade glioma.

Background: Pyroptosis, a lytic form of programmed cell death initiated by inflammasomes, has been reported to be closely associated with tumor proliferation, invasion and metastasis. However, the roles of pyroptosis genes (PGs) in low-grade glioma (LGG) remain unclear. Methods: We obtained information for 1,681 samples, including the mRNA expression profiles of LGGs and normal brain tissues and the relevant corresponding clinical information from two public datasets, TCGA and GTEx, and identified 45 differentially expressed pyroptosis genes (DEPGs). Among these DEPGs, nine hub pyroptosis genes (HPGs) were identified and used to construct a genetic risk scoring model. A total of 476 patients, selected as the training group, were divided into low-risk and high-risk groups according to the risk score. The area under the curve (AUC) values of the receiver operating characteristic (ROC) curves verified the accuracy of the model, and a nomogram combining the risk score and clinicopathological characteristics was used to predict the overall survival (OS) of LGG patients. In addition, a cohort from the Gene Expression Omnibus (GEO) database was selected as a validation group to verify the stability of the model. qRT-PCR was used to analyze the gene expression levels of nine HPGs in paracancerous and tumor tissues from 10 LGG patients. Results: Survival analysis showed that, compared with patients in the low-risk group, patients in the high-risk group had a poorer prognosis. A risk score model combining PG expression levels with clinical features was considered an independent risk factor. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses indicated that immune-related genes were enriched among the DEPGs and that immune activity was increased in the high-risk group. Conclusion: In summary, we successfully constructed a model to predict the prognosis of LGG patients, which will help to promote individualized treatment and provide potential new targets for immunotherapy.

Personal data protection compliance assessment: A privacy policy scoring approach and empirical evidence from Thailand's SMEs.

Privacy policies, intended to provide information to individuals regarding how their personal data is processed, are often complex and challenging for users to understand. Businesses often demonstrate non-compliance with personal data protection laws, ranging from the absence of privacy policies to the existence of policies that do not adhere to legal requirements. This paper aims to (1) develop a quantitative and systematic tool for evaluating privacy policies' compliance with the Personal Data Protection Act (PDPA), (2) assess compliance among Small and Medium Enterprises (SMEs) in Thailand, and (3) provide recommendations for enhancing compliance practices. To achieve this, we proposed a multi-criteria privacy policy scoring model integrated with comprehensive statistical data analyses. The privacy policy scoring model consists of ten privacy principles and 31 privacy criteria, providing a structured framework for evaluating privacy policies. During a two-year postponement period for enforcing the PDPA law, we conducted a stratified random-sampling survey of 384 SMEs to evaluate their privacy policies using the proposed scoring model. The accomplished results revealed significantly lower scores than anticipated, with the nationwide average score of SMEs reaching only 6.1909 out of 100 points. More than half of the SMEs collected personal data without announcing privacy policies, and those with privacy policies adhered to an average of only 12.15 out of 31 privacy criteria. These findings highlight the pressing need to improve compliance practices among SMEs in Thailand. The proposed methodology can be customized and applied to align with the requirements of personal data protection laws in other countries. Additionally, our findings indicate that compliance with the PDPA is influenced by the Thailand Standard Industrial Classification (TSIC) sections, suggesting the adoption of tailored approaches by policymakers to address the specific needs of different TSIC sections.

A predictive scoring model to select suitable patients for surgery on primary tumor in metastatic esophageal cancer.

BACKGROUND: Surgery on primary tumor (SPT) has been a common treatment strategy for many types of cancer. AIMS: This study aimed to investigate whether SPT could be considered a treatment option for metastatic esophageal cancer and to identify the patient population that would benefit the most from SPT. METHODS: Data from 18 registration sites in the Surveillance, Epidemiology, and End Results Program database (SEER database) were analyzed to select patients with metastatic esophageal cancer. Multivariate Cox regression analysis was used to identify potential risk factors for pre-treatment survival. Variables with a p-value of less than 0.05 were used to construct a pre-treatment nomogram. A pre-surgery predictive model was then developed using the pre-surgery factors to score patients, called the "pre-surgery score". The optimal cut-off value for the "pre-surgery score" was determined using X-tile analysis, and patients were divided into high-risk and low-risk subsets. It was hypothesized that patients with a low "pre-surgery score" risk would benefit the most from SPT. RESULTS: A total of 3793 patients were included in the analysis. SPT was found to be an independent risk factor for the survival of metastatic esophageal cancer patients. Subgroup analyses showed that patients with liver or lung metastases derived more benefit from SPT compared to those with bone or brain metastases. A pre-treatment predictive model was constructed to estimate the survival rates at one, two, and three years, which showed good accuracy (C-index: 0.705 for the training set and 0.701 for the validation set). Patients with a "pre-surgery score" below 4.9 were considered to have a low mortality risk and benefitted from SPT (SPT vs. non-surgery: median overall survival (OS): 24 months vs. 4 months, HR = 0.386, 95% CI: 0.303-0.491, p < 0.001). CONCLUSION: This study demonstrated that SPT could improve the OS of patients with metastatic esophageal cancer. The pre-treatment scoring model developed in this study might be useful in identifying suitable candidates for SPT. The strengths of this study include the large patient sample size and rigorous statistical analyses. However, limitations should be noted due to the retrospective study design, and prospective studies are needed to validate the findings in the future.

Simple Scoring Model Based on Enhanced CT in Preoperative Prediction of Biological Risk of Gastrointestinal Stromal Tumor.

Objective: To construct a simple scoring model for predicting the biological risk of gastrointestinal stromal tumors based on enhanced computed tomography (CT) features. Methods: The clinicopathological and imaging data of 149 patients with primary gastrointestinal stromal tumor were retrospectively analyzed in our hospital. According to the risk classification, the patients were divided into low-risk group and high-risk group. The features of enhanced CT were observed and recorded. Univariate and multivariate logistic regression models were used to determine the predictors of high-risk biological behaviors of gastrointestinal stromal tumor, and then a simple scoring model was constructed according to the regression coefficients of each predictor. The receiver operating characteristic curve was used to evaluate the predictive ability of the model. Results: There was no significant difference between the risk classification of gastrointestinal stromal tumor with gender and age (P = .168, .320), while significant difference was found between the tumor size and location (P < .001). Univariate and multivariate logistic regression analyses showed that tumor size, enlarged vessels feeding or draining the mass, peritumoral lymph node enlargement, and venous phase contrast enhancement rate were independent predictors of the biological risk of gastrointestinal stromal tumor (P < .05). The area under the curve value of tumor size, enlarged vessels feeding or draining the mass, peritumoral lymph node enlargement, and venous phase contrast enhancement rate as the high-risk predictor of gastrointestinal stromal tumor were 0.955, 0.729, 0.680, and 0.807, respectively. Receiver operating characteristic curve results showed that the area under the curve of the scoring model constructed based on enhanced CT features was 0.941 (95% confidence interval: 0.891-0.973). When the total score was >1, the sensitivity of the scoring model in diagnosing gastrointestinal stromal tumor was 85.58%, the specificity was 88.89%, the positive predictive value was 88.51%, the negative predictive value was 86.04%, and the accuracy was 86.18%. The results of DeLong test showed that the area under the curve of the scoring model was better than that of the receiver operating characteristic curve of tumor size, enlarged vessels feeding or draining the mass, peritumoral lymph node enlargement, venous phase contrast enhancement rate, and other indicators alone in predicting the high risk of gastrointestinal stromal tumor, and the differences were statistically significant (Z = 26.510, P < .001; Z = 3.992, P < .001; Z = 6.353, P < .001; Z = 4.052, P = .013). Conclusion: The simple scoring model based on enhanced CT features is a simple and practical clinical prediction model, which is helpful to make preoperative individualized treatment plan and improve the prognosis of gastrointestinal stromal tumor patients.

Development of a scoring model based on objective factors to predict gangrenous/perforated appendicitis.

BACKGROUND: The mortality rate of gangrenous/perforated appendicitis is higher than that of uncomplicated appendicitis. However, non-operative management of such patients is ineffective. This necessitates their careful exam at presentation to identify gangrenous/perforated appendicitis and aid surgical decision-making. Therefore, this study aimed to develop a new scoring model based on objective findings to predict gangrenous/perforated appendicitis in adults. METHODS: We retrospectively analyzed 151 patients with acute appendicitis who underwent emergency surgery between January 2014 and June 2021. We performed univariate and multivariate analyses to identify independent objective predictors of gangrenous/perforated appendicitis, and a new scoring model was developed based on logistic regression coefficients for independent predictors. Receiver operating characteristic (ROC) curve analysis and the Hosmer-Lemeshow test were performed to assess the discrimination and calibration of the model. Finally, the scores were classified into three categories based on the probability of gangrenous/perforated appendicitis. RESULTS: Among the 151 patients, 85 and 66 patients were diagnosed with gangrenous/perforated appendicitis and uncomplicated appendicitis, respectively. Using the multivariate analysis, C-reactive protein level, maximal outer diameter of the appendix, and presence of appendiceal fecalith were identified as independent predictors for developing gangrenous/perforated appendicitis. Our novel scoring model was developed based on three independent predictors and ranged from 0 to 3. The area under the ROC curve was 0.792 (95% confidence interval, 0.721-0.863), and the Hosmer-Lemeshow test showed a good calibration of the novel scoring model (P = 0.716). Three risk categories were classified: low, moderate, and high risk with probabilities of 30.9%, 63.8%, and 94.4%, respectively. CONCLUSIONS: Our scoring model can objectively and reproducibly identify gangrenous/perforated appendicitis with good diagnostic accuracy and help in determining the degree of urgency and in making decisions about appendicitis management.

Identifying individuals satisfying the termination of resuscitation rule but having potential to achieve favourable neurological outcome following out-of-hospital cardiac arrest.

AIM: To develop a simple scoring model that identifies individuals satisfying the termination of resuscitation (TOR) rule but having potential to achieve favourable neurological outcome following out-of-hospital cardiac arrest (OHCA). METHODS: This study analysed the All-Japan Utstein Registry from 1 January 2010 to 31 December 2019. We identified patients satisfying basic life support (BLS) and advanced life support (ALS) TOR rules and determined factors associated with favourable neurological outcome (cerebral performance category scale of 1 or 2) for each cohort using multivariable logistic regression analysis. Scoring models were derived and validated to identify patient subgroups that might benefit from continued resuscitation efforts. RESULTS: Among 1,695,005 eligible patients, 1,086,092 (64.1%) and 409,498 (24.2%) satisfied BLS and ALS TOR rules, respectively. One month post-arrest, 2038 (0.2%) and 590 (0.1%) patients in the BLS and ALS cohorts, respectively, achieved favourable neurological outcome. A scoring model derived for the BLS cohort (2 points for age <17 years or ventricular fibrillation/ventricular tachycardia rhythm; 1 point for age <80 years, pulseless electrical activity rhythm, or transport time <25 min) effectively stratified the probability of achieving 1-month favourable neurological outcome, with patients scoring <4 having a probability of <1%, whereas those scoring 4, 5, and 6 having probabilities of 1.1%, 7.1%, and 11.1%, respectively. In the ALS cohort, the probability increased with scores; however, it remained <1%. CONCLUSION: A simple scoring model comprising age, first documented cardiac rhythm, and transport time effectively stratified the likelihood of achieving favourable neurological outcome in patients satisfying the BLS TOR rule.

GraphGPSM: a global scoring model for protein structure using graph neural networks.

The scoring models used for protein structure modeling and ranking are mainly divided into unified field and protein-specific scoring functions. Although protein structure prediction has made tremendous progress since CASP14, the modeling accuracy still cannot meet the requirements to a certain extent. Especially, accurate modeling of multi-domain and orphan proteins remains a challenge. Therefore, an accurate and efficient protein scoring model should be developed urgently to guide the protein structure folding or ranking through deep learning. In this work, we propose a protein structure global scoring model based on equivariant graph neural network (EGNN), named GraphGPSM, to guide protein structure modeling and ranking. We construct an EGNN architecture, and a message passing mechanism is designed to update and transmit information between nodes and edges of the graph. Finally, the global score of the protein model is output through a multilayer perceptron. Residue-level ultrafast shape recognition is used to describe the relationship between residues and the overall structure topology, and distance and direction encoded by Gaussian radial basis functions are designed to represent the overall topology of the protein backbone. These two features are combined with Rosetta energy terms, backbone dihedral angles and inter-residue distance and orientations to represent the protein model and embedded into the nodes and edges of the graph neural network. The experimental results on the CASP13, CASP14 and CAMEO test sets show that the scores of our developed GraphGPSM have a strong correlation with the TM-score of the models, which are significantly better than those of the unified field score function REF2015 and the state-of-the-art local lDDT-based scoring models ModFOLD8, ProQ3D and DeepAccNet, etc. The modeling experimental results on 484 test proteins demonstrate that GraphGPSM can greatly improve the modeling accuracy. GraphGPSM is further used to model 35 orphan proteins and 57 multi-domain proteins. The results show that the average TM-score of the models predicted by GraphGPSM is 13.2 and 7.1% higher than that of the models predicted by AlphaFold2. GraphGPSM also participates in CASP15 and achieves competitive performance in global accuracy estimation.