The value of LCI-based modified Kyoto classification risk scoring system in predicting the risk of early gastric cancer.

OBJECTIVE: To study and compare the value of the Kyoto classification risk scoring system and the modified Kyoto classification risk scoring system based on linked color imaging (LCI) in predicting the risk of early gastric cancer. METHODS: One hundred and fifty patients with pathologically confirmed non-cardia early gastric cancer by endoscopic LCI and 150 non-gastric cancer patients matched for age and gender were included. Basic patient data and whole gastric endoscopic images under LCI were collected, and the images were scored according to the LCI-based Kyoto classification risk scoring system and the LCI-based modified Kyoto classification risk scoring system. RESULTS: Compared with the LCI-based Kyoto classification risk scoring system, the LCI-based modified Kyoto classification risk scoring system had a higher AUC for predicting the risk of early gastric cancer (0.723 vs. 0.784, p = 0.023), with a score of ≥3 being the best cutoff value for predicting the risk of early gastric cancer (sensitivity 61.33%, specificity 86.00%), and scores of 3 to 5 were significantly associated with early gastric carcinogenesis significantly (OR = 9.032, 95% CI: 4.995-16.330, p < 0.001). CONCLUSIONS: Compared with the LCI-based Kyoto classification risk scoring system, the LCI-based Kyoto modified classification risk scoring system has a better value for predicting the risk of early gastric cancer, and the score of 3 to 5 is a high-risk factor for the risk of early gastric cancer development, which is more strongly correlated with the risk of early gastric cancer.

Renal Outcomes in Older Adults with Antineutrophil Cytoplasmic Autoantibody-Associated Vasculitis: A New Prediction Model.

INTRODUCTION: Older patients with antineutrophil cytoplasmic autoantibody-associated vasculitis (AAV) commonly experience renal impairment and poor prognoses. This study aimed to establish a risk-scoring system for predicting composite renal outcomes in older patients with AAV. METHODS: This retrospective observational study included all patients with AAV hospitalized in a single-center tertiary hospital in China between January 2013 and April 2022. Patients aged ≥65 years were defined as older adults and short-term composite renal outcomes included a ≥25% reduction in estimated glomerular filtration rate (eGFR) (for AKI), renal replacement therapy, provision of renal replacement therapy (long-term dialysis, kidney transplant, or sustained eGFR <15 mL/min/1.73 m), or all-cause mortality. Patients were randomly divided into development and validation cohorts (2:1). Logistic regression analysis was performed in the development cohort to analyze risk factors. The scoring system was established accordingly and further validated in the validation cohort. RESULTS: 1,203 patients were enrolled in the study, among whom the older adult group accounted for 36% with a mean age of 71. The older adult group had a worse prognosis, a higher mortality rate, a higher rate of end-stage renal disease, and worsening renal function. Logistic regression showed that age >75 years, chronic heart disease, and elevated serum creatinine and D-dimer values were risk factors for poor prognosis in patients with AAV. The development and validation cohorts in patients with AAV produced area under the curve values of 0.82 (0.78-0.86) and 0.83 (0.77-0.89), respectively. CONCLUSION: We established a risk-scoring system based on baseline clinical characteristics to predict composite renal outcomes in patients with AAV. Our results suggest that more attention should be paid to older patients with severe renal impairment and active inflammation.

A risk scoring system for early diagnosis of anastomotic leakage after subtotal esophagectomy for esophageal cancer.

BACKGROUND: Anastomotic leakage (AL) is one of the most critical postoperative complications after subtotal esophagectomy in patients with esophageal cancer. This study attempted to develop an optimal scoring system for stratifying the risk for AL. METHODS: The study included 171 patients who underwent subtotal esophagectomy for esophageal cancer followed by esophagogastrostomy in the cervical region from January 2011 to April 2021 at Nagoya University Hospital. AL was defined by radiologic or endoscopic evidence of anastomotic breakdown using some modalities. A risk scoring system for an early diagnosis of AL was established using factors determined in the multivariate analysis. A score was calculated for each patient, and the patients were classified into three categories according to the risk for AL: low-, intermediate- and high-risk. The trend of the risk for AL among the categories was evaluated. RESULTS: Twenty-nine patients (17%) developed AL. Multivariate analysis demonstrated that sinistrous gross features of drain fluid (P < 0.001; odds ratio (OR), 10.2), radiologic air bubble sign (P < 0.001; OR, 15.0) and the level of drain amylase ≥280 U/L on postoperative Day 7 (P < 0.001; OR, 9.0) were significantly associated with AL. According to the matching number of the above three risk factors and categorization into three risk groups, the incidence of AL was 6.1% (8/131) in the low-risk group, 45.5% (15/33) in the intermediate-risk group and 85.7% (6/7) in the high-risk group (area under curve, 0.81; 95% confidence interval, 0.72-0.90). CONCLUSIONS: The present AL-risk scoring system may be useful in postoperative patient care after subtotal esophagectomy.

Analysis of factors affecting nonalcoholic fatty liver disease in Chinese steel workers and risk assessment studies.

BACKGROUND: The global incidence of nonalcoholic fatty liver disease (NAFLD) is rapidly escalating, positioning it as a principal public health challenge with significant implications for population well-being. Given its status as a cornerstone of China's economic structure, the steel industry employs a substantial workforce, consequently bringing associated health issues under increasing scrutiny. Establishing a risk assessment model for NAFLD within steelworkers aids in disease risk stratification among this demographic, thereby facilitating early intervention measures to protect the health of this significant populace. METHODS: Use of cross-sectional studies. A total of 3328 steelworkers who underwent occupational health evaluations between January and September 2017 were included in this study. Hepatic steatosis was uniformly diagnosed via abdominal ultrasound. Influential factors were pinpointed using chi-square (χ2) tests and unconditional logistic regression analysis, with model inclusion variables identified by pertinent literature. Assessment models encompassing logistic regression, random forest, and XGBoost were constructed, and their effectiveness was juxtaposed in terms of accuracy, area under the curve (AUC), and F1 score. Subsequently, a scoring system for NAFLD risk was established, premised on the optimal model. RESULTS: The findings indicated that sex, overweight, obesity, hyperuricemia, dyslipidemia, occupational dust exposure, and ALT serve as risk factors for NAFLD in steelworkers, with corresponding odds ratios (OR, 95% confidence interval (CI)) of 0.672 (0.487-0.928), 4.971 (3.981-6.207), 16.887 (12.99-21.953), 2.124 (1.77-2.548), 2.315 (1.63-3.288), 1.254 (1.014-1.551), and 3.629 (2.705-4.869), respectively. The sensitivity of the three models was reported as 0.607, 0.680 and 0.564, respectively, while the precision was 0.708, 0.643, and 0.701, respectively. The AUC measurements were 0.839, 0.839, and 0.832, and the Brier scores were 0.150, 0.153, and 0.155, respectively. The F1 score results were 0.654, 0.661, and 0.625, with log loss measures at 0.460, 0.661, and 0.564, respectively. R2 values were reported as 0.789, 0.771, and 0.778, respectively. Performance was comparable across all three models, with no significant differences observed. The NAFLD risk score system exhibited exceptional risk detection capabilities with an established cutoff value of 86. CONCLUSIONS: The study identified sex, BMI, dyslipidemia, hyperuricemia, occupational dust exposure, and ALT as significant risk factors for NAFLD among steelworkers. The traditional logistic regression model proved equally effective as the random forest and XGBoost models in assessing NAFLD risk. The optimal cutoff value for risk assessment was determined to be 86. This study provides clinicians with a visually accessible risk stratification approach to gauge the propensity for NAFLD in steelworkers, thereby aiding early identification and intervention among those at risk.

Role of risk scoring systems in predicting life expectancy after carotid endarterectomy in asymptomatic patients.

OBJECTIVE: The aim of this study is to compare and to test the performance of all available risk scoring systems (RSSs) designed to predict long-term survival rate in asymptomatic candidate patients for carotid endarterectomy (CEA) for significant carotid artery stenosis. METHODS: Data on asymptomatic patients who underwent CEA in three high-volume centers were prospectively recorded. Through literature research using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) recommendations, six RSSs were identified for the intent of the study. Primary endpoints were 3- and 5-year survival rates after CEA. All items used as variables to compose multiple RSSs were applied to every patient in the study population. The 3- and 5-year mortality prediction rates for each score were assessed by sensitivity, specificity, and predictive negative and positive value calculation, as well as univariable Cox proportional hazard models with the Harrell C index. RESULTS: During the study period, 825 CEAs in 825 asymptomatic patients were analyzed. All items used in RSSs were available in the dataset, with some concerns regarding their definition and application among RSSs. The 3- and 5-year survival rates of the study cohort were 94.5% and 90.3%, respectively. Among the six RSSs analyzed, no RSS demonstrated optimal results in terms of mortality rate prediction accuracy, although some scores had good diagnostic and risk of death precision. CONCLUSIONS: RSSs, when used alone, fail to optimally detect postoperative life expectancy in asymptomatic CEA patient candidates. Further prospective controlled studies are needed to compose and validate RSSs with better calibration to predict outcomes.

A preoperative risk prediction model for high malignancy potential gastrointestinal stromal tumors of the stomach.

BACKGROUND: Gastric gastrointestinal stromal tumors (GISTs) exhibit various degrees of aggression and malignant potential. However, no systematic preoperative evaluation strategy to predict the malignancy potential of gastric GISTs has yet been developed. This study aimed to develop a reliable and easy-to-use preoperative risk-scoring model for predicting high malignancy potential (HMP) gastric GISTs. METHODS: The data of 542 patients with pathologically confirmed gastric GISTs who underwent resection were reviewed. Multivariate logistic regression analysis was used to identify significant predictors of HMP. The risk-scoring system (RSS) was based on the predictive factors for HMP, and its performance was validated using a split-sample approach. RESULTS: A total of 239 of 542 (44.1%) surgically resected gastric GISTs had HMP. Multivariate analysis demonstrated that tumor size, location, and surface changes were independent risk factors for HMP. Based on the accordant regression coefficients, the presence of surface ulceration was assigned 1 point. Tumor sizes of 4-6 cm and > 6 cm were assigned 2 and 5 points, respectively. Two points were assigned to cardia or fundus locations. A score of 3 points was the optimal cut-off value for HMP prediction. HMP were found in 19.8% and 82.7% of the low and high-risk groups of the RSS, respectively. The area under the receiver-operating characteristic curve for predicting HMP was 0.81 (95% confidence interval (CI) 0.75-0.86). Discrimination was good after validation (0.75, 95% CI 0.69-0.81). CONCLUSION: This simple RSS could be useful for predicting the malignancy potential of gastric GISTs and may aid preoperative clinical decision making to ensure optimal treatment.

The risk scoring system for assessing the technical difficulty of endoscopic submucosal dissection in cases of remnant gastric cancer after distal gastrectomy.

BACKGROUND: Endoscopic submucosal dissection (ESD) for remnant gastric cancer (RGC) after distal gastrectomy (DG) is considered technically challenging due to the narrow working space, and severe fibrosis and staples from the previous surgery. Technical difficulties of ESD for RGC after DG have not been thoroughly investigated. This study aimed to develop and validate a risk-scoring system for assessing the technical difficulty of ESD for RGC after DG in a large multicenter cohort. METHODS: We investigated patients who underwent ESD for RGC after DG in 10 institutions between April 2008 and March 2018. A difficult case was defined as ESD lasting ≥ 120 min, involving piecemeal resection, or the occurrence of perforation during the procedure. A risk-scoring system for the technical difficulty of the procedure was developed based on multiple logistic regression analyses, and its performance was internally validated using bootstrapping. RESULTS: A total of 197 consecutive patients with 201 lesions were analyzed. There were 90 and 111 difficult and non-difficult cases, respectively. The scoring model consisted of four independent risk factors and points of risk scores were assigned for each as follows: tumor size > 20 mm: 2 points; anastomosis site: 2 points; suture line: 1 point; and non-expert endoscopist: 2 points. The C-statistics of the scoring system for technical difficulty was 0.72. CONCLUSIONS: We developed a validated risk-scoring model for predicting the technical difficulty of ESD for RGC after DG that can contribute to its safer and more reliable performance.

Multicentre derivation and validation of a prognostic scoring system for mortality assessment in HIV-infected patients with talaromycosis.

BACKGROUND: Although the widespread use of modern antiretroviral therapy (ART) has reduced the incidence of talaromycosis in people living with HIV, mortality remains as high as 20% in this population, even after appropriate antifungal treatment. OBJECTIVES: The objective of our study was to develop a risk assessment system for HIV-infected patients with comorbid talaromycosis, in order to provide these patients with appropriate, effective and potentially life-saving interventions at an early stage of their illness. PATIENTS/METHODS: This was a multicentre, retrospective cohort study conducted in China. We built a predictive model based on data from 11 hospitals, and a validated model using the data of 1 hospital located in an endemic area. RESULTS: Forward stepwise multivariate statistical calculations indicated that age, aspartate aminotransferase/alanine transaminase ratio and albumin levels, and BUN levels were valid, independent predictors of the risk of death in HIV-infected patients with talaromycosis. Our developed and validated risk scoring system is effective for the identification of HIV-infected patients with talaromycosis at high risk of death at hospital admission (p < .001; AUC = 0.860). In our study, our risk prediction model provided functional and robust discrimination in the validation cohort (p < .001; AUC = 0.793). CONCLUSION: The prognostic scoring system for mortality assessment developed in the present study is an easy-to-use clinical tool designed to accurately assist clinicians in identifying high-risk patients with talaromycosis.

Development and validation of a questionnaire-based risk scoring system to identify individuals at high risk for gastric cancer in Chinese populations.

OBJECTIVE: This study aimed to develop and validate a risk scoring system to identify high-risk individuals carrying malignant lesions in stomach for tailored gastric cancer screening. METHODS: A gastric cancer risk scoring system (GC-RSS) was developed based on questionnaire-based predictors for gastric cancer derived from systematic literature review. To assess the capability of this system for discrimination, risk scores for 8,214 and 7,235 outpatient subjects accepting endoscopic examination in two endoscopy centers, and 32,630 participants in a community-based cohort in China were calculated to plot receiver operating characteristic curves and generate area under the curve (AUC). To evaluate the performance of GC-RSS, the screening proportion, sensitivity and detection rate ratio compared to universal screening were used under different risk score cutoff values. RESULTS: GC-RSS comprised nine predictors including advanced age, male gender, low body mass index (<18.5 kg/m2), family history of gastric cancer, cigarette smoking, consumption of alcohol, preference for salty food, irregularity of meals and consumption of preserved food. This tool performed well in determining the risk of malignant gastric lesions with AUCs of 0.763, 0.706 and 0.696 in three validation sets. When subjects with risk scores ≥5 were evaluated with endoscopy, nearly 50% of these endoscopies could be saved with a detection rate of over 1.5 times achieved. When the cutoff was set at 8, only about 10% of subjects with the highest risk would be offered endoscopy, and detection rates for gastric cancer could be increased 2-4 fold compared to universal screening. CONCLUSIONS: An effective questionnaire-based GC-RSS was developed and validated. This tool may play an important role in establishing a tailored screening strategy for gastric cancer in China.

Novel Risk Scoring System for Patients with Metastatic Renal Cell Carcinoma Treated with Immune Checkpoint Inhibitors.

BACKGROUND: The International Metastatic Renal Cell Carcinoma Database Consortium (IMDC) criteria are the gold standard for risk-stratifying patients with metastatic renal cell cancer (mRCC). We developed a novel risk scoring system for patients with mRCC treated with immune checkpoint inhibitors (ICIs). METHODS: We performed a retrospective analysis of 100 ICI-treated patients with mRCC at Winship Cancer Institute from 2015 to 2018. Several baseline variables were collected, including markers of inflammation, body mass index (BMI), and sites of metastatic disease, and all were considered for inclusion in our risk scoring system. Upon variable selection in multivariable model, monocyte-to-lymphocyte ratio (MLR), BMI, and number and sites of metastases at baseline were used for risk score calculation. Patients were categorized using four-level risk groups as good (risk score = 0), intermediate (risk score = 1), poor (risk score = 2), or very poor (risk score = 3-4). Cox's proportional hazard model and the Kaplan-Meier method were implemented for survival outcomes. RESULTS: Most patients were male (66%) with clear cell renal cell carcinoma (72%). The majority (71%) received anti-programmed cell death protein-1 monotherapy. Our risk scoring criteria had higher Uno's concordance statistics than IMDC in predicting overall survival (OS; 0.71 vs. 0.57) and progression-free survival (0.61 vs. 0.58). Setting good risk (MLR <0.93, BMI ≥24, and D_Met = 0) as the reference, the OS hazard ratios were 29.5 (95% confidence interval [CI], 3.64-238.9), 6.58 (95% CI, 0.84-51.68), and 3.75 (95% CI, 0.49-28.57) for very poor, poor, and intermediate risk groups, respectively. CONCLUSION: Risk scoring using MLR, BMI, and number and sites of metastases may be an effective way to predict survival in patients with mRCC receiving ICI. These results should be validated in a larger, prospective study. IMPLICATIONS FOR PRACTICE: A risk scoring system was created for patients with metastatic renal cell carcinoma treated with immune checkpoint inhibitors. The results of this study have significant implications for practicing oncologists in the community and academic setting. Importantly, these results identify readily available risk factors that can be used clinically to risk-stratify patients with metastatic renal cell carcinoma who are treated with immune checkpoint inhibitors.

Development of a risk scoring system for evaluating the prognosis of patients with Her2-positive breast cancer.

BACKGROUND: As one of the many breast cancer subtypes, human epidermal growth factor receptor 2 (Her2)-positive breast cancer has higher invasiveness and poor prognosis, although the advent of anti-Her2 drugs has brought good news to patients. However, the emergence of drug resistance still limits its clinical efficacy, so there is an urgent need to explore new targets and develop a risk scoring system to improve treatments and evaluate patient prognosis. METHODS: Differentially expressed mRNAs associated with Her2-positive breast cancer were screened from a TCGA cohort. The prognostic risk scoring system was constructed according to univariate and Lasso Cox regression model analyses and combined with clinical factors (such as age and TNM) for univariate and multivariate analyses to verify the specificity and sensitivity of the risk scoring system. Finally, based on correlation and CNV mutation analyses, we explored the research value of the mRNAs involved in the system as key genes of the model. RESULTS: In this study, six mRNAs were screened and identified to construct a prognostic risk scoring system, including four up-regulated mRNA (RDH16, SPC25, SPC24, and SCUBE3) and two down-regulated mRNA (DGAT2 and CCDC69). The risk scoring system can divide Her2-positive breast cancer samples into high-risk and low-risk groups to evaluate patient prognosis. In addition, whether through the time-dependent receiver operating characteristics curve or compared with clinical factors, the risk scoring system showed high predictive sensitivity and specificity. Moreover, some CNV mutations in mRNA increase patient risk by influencing expression levels. CONCLUSION: The risk scoring system constructed in this study is helpful to improve the screening of high-risk patients with Her2-positive breast cancer and is beneficial for implementing early diagnosis and personalized treatment. It is suggested that these mRNAs may play an important role in the progression of Her2-positive breast cancer.

Development of a risk scoring system for prognostication in HIV-related toxoplasma encephalitis.

BACKGROUND: This study aims to evaluate specific risk factors influencing prognosis of HIV-infected patients with toxoplasma encephalitis (TE) in order to develop a prognostic risk scoring system for them. METHODS: This is a six-center retrospective study of hospitalized HIV/TE patients. Data including six-week mortality after diagnosis, baseline characteristics, clinical features, laboratory tests and radiological characteristics of eligible patients were assimilated for risk model establishing. RESULTS: In this study, the six-week mortality among 94 retrospective cases was 11.7% (11/94). Seven specific risk factors, viz. time from symptom onset to presentation, fever, dizziness, CD4+ T-cell counts, memory deficits, patchy brain lesions, and disorders of consciousness were calculated to be statistically associated with mortality. A criterion value of '9' was selected as the optimal cut-off value of the established model. The AUC of the ROC curve of this scoring model was 0.976 (p < 0.001). The sensitivity and specificity of the risk scoring model was 100.0 and 86.9%, respectively, which were 81.8 and 94.1% of this scoring model in the verification cohort, respectively. CONCLUSIONS: The developed scoring system was established with simple risk factors, which also allows expeditious implementation of accurate prognostication, and appropriate therapeutic interventions in HIV-infected patients with TE.

An innovative risk-scoring system of dental procedures and safety protocols in the COVID-19 era.

BACKGROUND: The aim of this paper is to assess an innovative risk score for common dental procedures, based on the most recent contaminant SARS-CoV-2. After scoring the level of infection risk, safety procedures, advice and personal protective equipment (PPE) are recommended for the dental team in each dental practice. METHODS: The authors of this research analysed 42 common dental procedures on the basis of known transmission risks. In increasing order, many consider the parameters leading to different risk scores for the dental team and patients for each procedure to be: direct contact with saliva (score 1), direct contact with blood (score 2), production of low levels of spray/aerosol via air-water syringes (score 3), the production of high levels of spray/aerosol from rotating, ultrasound and piezoelectric tools (score 4); and the duration of the procedure, which may increase the risk of procedures producing droplets and aerosols. RESULTS: Using this innovative risk-scoring system, the authors classified the different dental procedures according to low, medium or high risk: low (1-3), medium (4-5), high (≥ 6). A safety protocol for each procedure was thereafter matched with the calculated risk level. CONCLUSIONS: The innovative risk-scoring system presented in this research permits the reclassification of dental procedures according to the infection risk level. Consequently, specific procedures, previously considered as entry level, will now merit revision. This paper also highlighted an effective and routine clinical tool for general dentists and oral medicine practitioners.

Risk scoring system for predicting breast conservation after neoadjuvant chemotherapy.

We developed a risk scoring system (RSS) for predicting breast conservative surgery (BCS) in women receiving neoadjuvant chemotherapy(NAC) for breast cancer. BCS rate in the training set was 32.6%, associated with five variables: age < 50years, primary radiological tumor diameter < 60mm, absence of multifocality, absence of breast inflammation and hormone receptor status. These variables were assigned scores ranging from 0 to 9. The discrimination of the RSS was 0.78(95%CI 0.69-0.86) in the training set. The area under the curve of the receiver operating characteristics for predicting BCS after internal and external validation was 0.77(95%CI 0.68-0.85) and 0.75(95%CI 0.66-0.84), respectively.

Development of a Genetic and Clinical Data-Based (GC) Risk Score for Predicting Survival of Hepatocellular Carcinoma Patients After Tumor Resection.

BACKGROUND/AIMS: Carnitine palmitoyltransferase 1A (CPT1A) is a rate-limiting enzyme in the transport of long-chain fatty acids for ß-oxidation. Increasing evidence has indicated that CPT1A plays an important role in carcinogenesis. However, the expression and prognostic value of CPT1A in hepatocellular carcinoma (HCC) have not been extensively studied. METHODS: Here, we collected 66 post-operative liver cancer tissue samples. Gene profile expression was tested by RT-PCR. Receiver operating characteristic (ROC) analysis was performed and multivariate analysis with Cox's Proportional Hazard Model was used for confirming the selected markers' predictive efficiency for HCC patients' survival. A simple risk scoring system was created based on Cox's regression modeling and bootstrap internal validation. RESULTS: Cox multivariate regression analysis demonstrated that CPT1A, tumor size, intrahepatic metastasis, TNM stage and histological grade were independent risk factors for the prognosis of HCC patients after surgery. Our genetic and clinical data-based (GC) risk scoring system revealed that HCC patients whose total score≥3 are more likely to relapse and die than patients whose total score < 3. Finally, the good discriminatory power of our risk scoring model was validated by bootstrap internal validation. CONCLUSIONS: The genetic and clinical data-based risk scoring model can be a promising predictive tool for liver cancer patients' prognosis after operation.

Improving the clinical management of women with borderline tumours: a recurrence risk scoring system from a French multicentre study.

OBJECTIVE: To develop a risk scoring system (RSS) for predicting recurrence in women with borderline ovarian tumours (BOTs). DESIGN: Cohort study of women with BOTs. SETTING: French multicentre tertiary care centres. POPULATION: A cohort of 360 women with BOTs who received primary surgical treatment between January 2000 and December 2013. METHODS: Clinical and pathological factors affecting recurrence in women with BOTs. MAIN OUTCOME MEASURE: The development of a model for the prediction of recurrence in women with BOTs. RESULTS: Overall the recurrence rate was 20.0% (72/360). Recurrence was associated with five variables: age < 45 years; preoperative serum tumour marker CA125 > 150 IU/mL; a serous histological subtype; International Federation of Gynecology and Obstetrics (FIGO) stage other than IA; and ovarian surgery other than bilateral salpingo-oophorectomy (BSO; i.e. cystectomy and unilateral salpingo-oophorectomy). These variables were included in the RSS and assigned scores ranging from 0 to 6. The discrimination of the RSS was 0.82 (95% confidence interval, 95% CI 0.79-0.85). A total score of 8 points corresponded to the optimal threshold of the RSS, with a rate of recurrence of 11.8% (35/297) and 58.7% (37/63) for women at low risk (<8 points) and women at high risk (≥8 points), respectively. The diagnostic accuracy was 85.0%. CONCLUSIONS: This study shows that the risk of BOT recurrence can be accurately predicted so that women at high risk can benefit from adapted surgical treatment. TWEETABLE ABSTRACT: Our RSS permitted women with BOTs at low risk to be distinguished from women with BOTs at high risk of recurrence.

Development and validation of a relatively accurate gastric cancer high-risk group screening scoring system in urban residents.

PURPOSE: Our study aimed to develop a relatively accurate gastric cancer (GC) screening score system for urban residents and to validate the screening efficacy. METHODS: The present study included a derivation cohort (n = 3406) and a validation cohort (n = 868) of urban residents. Applying the full-stack engineering intelligent system platform of Hualian Health Big Data of Shandong University, the clinical physical examination data of subjects were collected. Univariate and multivariate analyses were used to identify risk factors for GC, and subsequently, an optimal prediction rule was established to create three distinct scoring systems. RESULTS: In the GC-risk scoring system I, age, plateletocrit (PCT), carcinoembryonic antigen (CEA), glucose, albumin, creatinine were independent risk factors of GC, with scores ranging from 0 to 28 and optimal cut-off was 15.5. The second scoring system consisted of age, PCT, RDW-CV, CEA, glucose, albumin, and creatinine, with scores ranging from 0 to 31. The optimal cut-off point was determined to be 15.5. The scoring system III comprise of age, sex, PCT, RDW CV, CEA, glucose, with scores ranging from 0 to 21 and optimal cut-off was 10.5. All three scoring systems demonstrated excellent discrimination for GC, achieving an AUC of 0.884, 0.89, and 0.876, respectively. In external validation, the AUC values were 0.654, 0.658, and 0.714. Notably, the GC-risk scoring system III exhibited the highest screening efficiency. CONCLUSIONS: Urban residents benefited from the effective and verified GC-risk scoring systems, which demonstrated excellent performance in identifying individuals with an elevated risk of GC.

Machine learning-based survival analysis approaches for predicting the risk of pneumonia post-stroke discharge.

BACKGROUND: Post-stroke pneumonia (PSP) is common among stroke patients. PSP occurring after hospital discharge continues to increase the risk of poor functional outcomes and death among stroke survivors. Currently, there is no prediction model specifically designed to predict the occurrence of PSP beyond the acute stage of stroke. This study aimed to explore the use of machine learning (ML) methods in predicting the risk of PSP after hospital discharge. METHODS: This study analyzed data from 5,754 hospitalized stroke patients. The dataset was randomly divided into a training set and a holdout test set, with a ratio of 80:20. Several clinical and laboratory variables were utilized as predictors and different ML algorithms were employed to model time-to-event data. The ML model's predictive performance was compared to existing risk-scoring systems. A model-agnostic method based on Shapley additive explanations was utilized to interpret the ML model. RESULTS: The study found that 5.7% of the study patients experienced pneumonia within one year after discharge. Based on repeated 5-fold cross-validation on the training set, the random survival forest (RSF) model had the highest C-index among the various ML algorithms and traditional Cox regression analysis. The final RSF model achieved a C-index of 0.787 (95% confidence interval: 0.737-0.840) on the holdout test set, outperforming five existing risk-scoring systems. The top three important predictors were the Glasgow Coma Scale score, age, and length of hospital stay. CONCLUSIONS: The RSF model demonstrated superior discriminative ability compared to other ML algorithms and traditional Cox regression analysis, suggesting a non-linear relationship between predictors and outcomes. The developed ML model can be integrated into the hospital information system to provide personalized risk assessments.

Development of antepartum risk prediction model for postpartum hemorrhage in Lagos, Nigeria: A prospective cohort study (Predict-PPH study).

OBJECTIVES: There is currently a limited ability to accurately identify women at risk of postpartum hemorrhage (PPH). We conducted the "Predict-PPH" study to develop and evaluate an antepartum prediction model and its derived risk-scoring system. METHODS: This was a prospective cohort study of healthy pregnant women who registered and gave birth in five hospitals in Lagos, Nigeria, from January to June 2023. Maternal antepartum characteristics were compared between women with and without PPH. A predictive multivariable model was estimated using binary logistic regression with a backward stepwise approach eliminating variables when P was greater than 0.10. Statistically significant associations in the final model were reported when P was less than 0.05. RESULTS: The prevalence of PPH in the enrolled cohort was 37.1%. Independent predictors of PPH such as maternal obesity (adjusted odds ratio [aOR] 3.25, 95% confidence interval [CI] 2.47-4.26), maternal anemia (aOR 1.32, 95% CI 1.02-1.72), previous history of cesarean delivery (aOR 4.24, 95% CI 3.13-5.73), and previous PPH (aOR 2.65, 95% CI 1.07-6.56) were incorporated to develop a risk-scoring system. The area under the receiver operating characteristic curve (AUROC) for the prediction model and risk scoring system was 0.72 (95% CI 0.69-0.75). CONCLUSION: We recorded a relatively high prevalence of PPH. Our model performance was satisfactory in identifying women at risk of PPH. Therefore, the derived risk-scoring system could be a useful tool to screen and identify pregnant women at risk of PPH during their routine antenatal assessment for birth preparedness and complication readiness.

Prognostic aging gene-based score for colorectal cancer: unveiling links to drug resistance, mutation burden, and personalized treatment strategies.

OBJECTIVE: Colorectal cancer (CRC) is characterized by high incidence and mortality rates worldwide. In this study, we present a novel aging-related gene-based risk scoring system (Aging score) as a predictive tool for CRC prognosis. METHOD: We identified prognostic aging-related genes using univariate Cox regression analysis, revealing key biological processes in CRC progression. We then constructed a robust prognostic model using LASSO and multivariate Cox regression analyses, including four critical genes: CAV1, FOXM1, MAD2L1, and WT1. RESULT: The Aging score demonstrated high prognostic performance across the training, testing, and entire TCGA-CRC datasets, proving its reliability. High-risk patients identified by the Aging score had significantly shorter overall survival times than low-risk patients, indicating its potential for patient stratification and personalized treatment. The Aging score remained an independent prognostic factor compared to age, gender, and tumor stage. Additionally, the score was linked to tumor mutation burden and microsatellite instability, indicators of immune checkpoint inhibitor response. High-risk patients also showed higher estimated IC50 values for common chemotherapeutic drugs, suggesting possible treatment resistance. CONCLUSION: Our findings highlight the Aging score's potential to enhance clinical decision-making and pave the way for personalized CRC management.