Validation Of Risk Prediction Model Research Articles

Refining PREVENT prediction models for 10-year risk of cardiovascular disease using measures of anxiety and depression

Refining PREVENT prediction models for 10-year risk of cardiovascular disease using measures of anxiety and depression

Validation of Risk Prediction Models for Pneumothorax and Intercostal Catheter Insertion Following CT-Guided Lung Biopsy.

CT-guided percutaneous transthoracic needle biopsy is the primary method for diagnosing lung lesions. Widely accepted validated risk prediction models are yet to be developed. A recently published study conducted at Grampians Health Services (GHS) developed two risk prediction models for predicting pneumothorax and intercostal catheter (ICC) insertion. This study aims to validate these models. This is a single-centre, retrospective cohort study performed at GHS. Patients with a CT-guided lung biopsy between January 2020 and July 2023 were included, alongside target-lesion characteristics, procedural-related factors and complications. Predicted probabilities for pneumothorax and ICC insertion were generated for each patient, and the diagnostic accuracy of the previous risk prediction models was evaluated the area under the receiver operating characteristic. A Youden Index was used to determine the sensitivity and specificity at the optimal probability thresholds. The validation found the model published by GHS demonstrated a diagnostic accuracy of 0.695 (95% CI: 0.601-0.695) for predicting pneumothorax following CT-guided percutaneous biopsy. The model for predicting intercostal catheter insertion had a diagnostic accuracy of 0.762 (95% CI: 0.642-0.762). The sensitivity for predicting pneumothorax and ICC insertion was 81.97% and 92.86%, respectively, for their optimum probability thresholds. The findings suggest that the previously published models may be useful in predicting pneumothoraces and ICC insertion following CT-guided percutaneous biopsy. We recommend these models as an adjunctive tool to aid in clinical decision-making during the peri-procedural management of these patients pending further validation with an external cohort.

Risk prediction of implant loss following implant-based breast reconstruction: a population-based study.

Implant loss following implant-based breast reconstruction (IBBR) is a serious complication, resulting in re-operations, patient suffering, and a significant decrease in quality of life. This study aimed to create a validated risk prediction model for implant loss after IBBR using perioperative risk factors. Patients who had undergone either a two-stage or a direct-to-implant postmastectomy IBBR were identified from the Dutch Breast Implant Registry (DBIR). The cohort was divided in a training cohort (80%) and a validation cohort (20%). A multivariate logistic regression model was used to create a risk prediction model for implant loss in the training cohort, which was subsequently internally validated in the validation cohort. Implant loss was defined as explantation or replacement of the implant due to postoperative wound healing-related complications within 6 months after placement. A total of 5260 IBBRs were divided into a training cohort and validation cohort. Implant loss occurred after 354 reconstructions (6.7%). The risk prediction model included four significant risk factors: BMI, active smoking status, previous radiotherapy and prepectoral placement. The model was able to predict an increasing probability of implant loss from 4.5% without any risk factors to 38.0% if four risk factors were present. The calibration plot showed good agreement. Nationwide population-based data were extracted from the DBIR and used to create a risk assessment model for implant loss after IBBR. The model was accurately internally validated, making it applicable to general practice and a valuable aid in preoperative counseling of women who consider IBBR.

Advanced AI-Driven Prediction of Pregnancy-Related Adverse Drug Reactions.

Ensuring drug safety during pregnancy is critical due to the potential risks to both the mother and fetus. However, the exclusion of pregnant women from clinical trials complicates the assessment of adverse drug reactions (ADRs) in this population. This study aimed to develop and validate risk prediction models for pregnancy-related ADRs of drugs using advanced Machine Learning (ML) and Deep Learning (DL) techniques, leveraging real-world data from the FDA Adverse Event Reporting System. We explored three methods─Information Component, Reporting Odds Ratio, and 95% confidence interval of ROR─for classifying drugs into high-risk and low-risk categories. DL models, including Directed Message Passing Neural Networks (DMPNN), Graph Neural Networks, and Graph Convolutional Networks, were developed and compared to traditional ML models like Random Forest, Support Vector Machines, and XGBoost. Among these, the DMPNN model, which integrated molecular graph information and molecular descriptors, exhibited the highest predictive performance, particularly at the preferred term level. The model was validated against external data sets from SIDER and DailyMed, demonstrating strong generalizability. Additionally, the model was applied to assess the risk of 22 oral hypoglycemic drugs, and potential substructure alerts for pregnancy-related ADRs were identified. These findings suggest that the DMPNN model is a valuable tool for predicting ADRs in pregnant women, offering significant advancement in drug safety assessment and providing crucial insights for safer medication use during pregnancy.

Clinical validated risk prediction model for development of heart failure after contemporary breast cancer treatment

Abstract Background Patients receiving breast cancer (BC) treatment are at risk for heart failure and cardiomyopathy (HF/CM). European Society of Cardiology (ESC) cardio-oncology guidelines recommend baseline cardiovascular (CV) assessment, however, there is limited data about cardiotoxicity risk specific to patients with BC. Our aim was to develop and validate model for prediction of HF/CM in women receiving contemporary treatment for invasive early-stage BC. Methods We assembled a cohort women diagnosed with Stage I-III BC from 2008-2020 and followed through 2021 in a large health care plan. Women age >80, with history of HF/CM, and women who received both anthracyclines and trastuzumab were excluded, leaving N=26,044 for analysis. Study cohort was randomly split into derivation (60%) and validation (40%) datasets. Elastic-net penalized Cox proportional hazard model was created using the derivation dataset to select risk factors and to calculate the panelized coefficient which defined the HF/CM risk score. Risk score system was assessed by Hosmer-Lemeshow goodness-of-fit test and area under the ROC curve (AUC). Event rates of <5% constituted low risk; 5-14% moderate; and >15% high risk category. Incident HF/CM events were examined using Kaplan-Meier approach in derivation and validation datasets. Results HF/CM risk score had high discrimination ability and sufficiently good model of fit regarding HF/CM events (P value=0.163 and 0.667 from Hosmer–Lemeshow test;AUC 0.751 and 0.764, in derivation and validation sets, respectively). There were 10% of women in the high risk; 30% in moderate; and 60% in low-risk group. Variables associated with the higher HF/CM risk score included age, receipt of anthracycline-based chemotherapy or anti-HER2 therapy, presence of hypertension, diabetes, or history of other CV conditions at baseline. The score pattern showed major effect of age, with anthracycline and anti-HER2 therapy increasing the risk across all age groups (Figure 1). Kaplan-Meier analysis of incident HF/CM over 14 years after BC diagnosis showed significantly lower number of HF/CM events in low risk compared to moderate and high-risk score groups (p<0.0001, Figure 2). Conclusion Our robust risk prediction model for HF/CM among women with early-stage BC provides a new tool to identify women at higher CV risk and inform cardiac function monitoring during and after BC treatment. Our findings may guide further validation studies and build evidence for the cardiotoxicity risk stratification in patients with BC.Risk Score for HF/CM by Age/ChemoTxK-M curves of freedom from HF/CM

Predicting Admission to Neonatal Care Unit at Mid-Pregnancy and Delivery Using Data from a General Obstetric Population.

Development and validation of risk prediction models at mid-pregnancy and delivery to predict admission to the neonatal care unit. We used data from all singleton deliveries at Cork University Maternity Hospital (CUMH), Ireland during 2019. Admission to the neonatal care unit was assumed if length of stay in the unit was > 24h. Multivariable logistic regression with backward stepwise selection was used to develop the models. Discrimination was assessed using the ROC curve C-statistic, and internal validation was assessed using bootstrapping techniques. We conducted temporal external validation using data from all singleton deliveries at CUMH during 2020. Out of 6,077 women, 5,809 (95.6%) with complete data were included in the analyses. A total of 612 infants (10.54%) were admitted to the neonatal care unit for > 24 hours. Six variables were informative at mid-pregnancy: male infants, maternal smoking, advancing maternal age, maternal overweight/obesity, nulliparity and history of gestational diabetes (C-statistic: 0.600, 95% CI: 0.567, 0.614). Seven variables were informative at delivery: male infants, nulliparity, public antenatal care, gestational age < 39 weeks', non-spontaneous vaginal delivery, premature rupture of membranes and time of birth between 17:01-07.59h (C-statistic: 0.738, 95% CI: 0.715, 0.760). Using these predictors, we developed nomograms to calculate individualised risk of neonatal care unit admission. Bootstrapping indicated good internal performance and external validation suggested good reproducibility. Our nomograms allow the user to quickly estimate individualised risk of neonatal care unit admission. Future research should aim to improve accuracy in early pregnancy to better assist counselling of parents.

WP7.17 - Routine Use of Validated Risk Prediction Model in the Management of Acute Appendicitis in a District General Hospital

Abstract Aim Acute appendicitis is the most common general surgery emergency in the UK. Currently, there is no optimal diagnostic pathway for managing the right iliac fossa (RIF) pain. The right iliac fossa pain treatment (RIFT) study group has previously performed an analysis of different risk prediction models to search for the most specific one and made a website (appy-risk.org) to calculate risk scores on presentation. We aimed to look into our practice in a DGH and see how compliant we are in documenting risk scores on presentation with acute RIF pain. Method A list of patients presenting with acute RIF pain to the surgical assessment unit in September was prepared. Admission clerking notes were reviewed from the electronic patient record to look for the documentation of the appendicitis risk score. Standard statistical packages were used for data analysis. Results A total of 95 patients were presented with RIF pain. Of them, 17 were excluded from the analysis for being over 45 years old. Of the remaining 78 patients' records, only 7 (8.97%) had appendicitis risk scores documented in the clerking notes. Conclusions The RIFT study highlighted a high normal appendicectomy rate (NAR) in the UK in comparison to other European countries. In our hospital, NAR was 9.74% in the first six months of 2023. We are in the process of implementing a pathway to manage acute RIF pain using a risk prediction model as advised by the RIFT group to reduce our NAR to less than 5%.

Development and validation of risk prediction model for adverse outcomes in trauma patients

Background The prognosis of trauma patients is highly dependent on early medical diagnosis. By constructing a nomogram model, the risk of adverse outcomes can be displayed intuitively and individually, which has important clinical implications for medical diagnosis. Objective To develop and evaluate models for predicting patients with adverse outcomes of trauma that can be used in different data availability settings in China. Methods This was a retrospective prognostic study using data from 8 public tertiary hospitals in China from 2018. The data were randomly divided into a development set and a validation set. Simple, improved and extended models predicting adverse outcomes were developed, with adverse outcomes defined as in-hospital death or ICU transfer, and patient clinical characteristics, vital signs, diagnoses, and laboratory test values as predictors. The results of the models were presented in the form of nomograms, and performance was evaluated using area under the receiver operating characteristic curve (ROC-AUC), precision-recall (PR) curves (PR-AUC), Hosmer-Lemeshow goodness-of-fit test, calibration curve, and decision curve analysis (DCA). Results Our final dataset consisted of 18,629 patients (40.2% female, mean age of 52.3), 1,089 (5.85%) of whom resulted in adverse outcomes. In the external validation set, three models achieved ROC-AUC of 0.872, 0.881, and 0.903, and a PR-AUC of 0.339, 0.337, and 0.403, respectively. In terms of the calibration curves and DCA, the models also performed well. Conclusions This prognostic study found that three prediction models and nomograms including the patient clinical characteristics, vital signs, diagnoses, and laboratory test values can support clinicians in more accurately identifying patients who are at risk of adverse outcomes in different settings based on data availability.

Development and validation of a risk prediction model for short-term progression of carotid atherosclerosis among early middle age adults

AimWe aimed at creating and validating a prognostic model incorporating easily accessible clinical and laboratory parameters to forecast the likelihood of short-term progression of carotid atherosclerosis. MethodsA prediction model was developed and validated for carotid plaque progression within 2 years in an early middle-age population in China. Progression was defined as the new appearance of carotid plaque or stenosis among participants who had normal carotid status at baseline. Leveraging data from a health check-up chain, predictors were identified using statistical methods including stepwise logistic regression, Markov Chain Monte Carlo (MCMC) simulation, random forest analysis and least absolute shrinkage selection operator (Lasso). Model performance was assessed. Bootstrap internal validation, validation on another check-up population and subgroup analysis were also conducted. ResultsAmong 7765 participants, predictors including age, diastolic blood pressure, uric acid levels, high-density lipoprotein cholesterol (HDL-C), and low-density lipoprotein cholesterol (LDL-C) were identified for carotid plaque progression in 2 years. The developed prediction model demonstrated good discrimination (AUC = 0.755, 95%CI:0.736–0.774) and calibration ability (slope = 0.922 and interception = 0.007) among development data, as well as among validation data (AUC = 0.759, 95%CI:0.674–0.770; slope = 1.076 and intercept = −0.014). Internal validation using bootstrap method yielded an adjusted AUC of 0.753. The model's performance remained consistent across different subgroups. ConclusionsOur study presents a validated risk prediction model for carotid plaque progression in an early middle age population, offering a valuable tool for early identification and monitoring of cardiovascular risks. The model's robustness and applicability across different subgroups highlight its potential utility in preemptive cerebrovascular and cardiovascular disease management.

Establishment and Validation of Risk Prediction Models for Postoperative Pain After Endoscopic Submucosal Dissection: A Retrospective Clinical Study.

Postoperative pain is a common complication in endoscopic submucosal dissection (ESD) patients. This study aimed to develop and validate predictive models for postoperative pain associated ESD. We retrospectively constructed a development cohort comprising 2162 patients who underwent ESD at our hospital between January 2015 and April 2022. The dataset was randomly divided into a training set (n = 1541) and a validation set (n = 621) in a 7:3 ratio. The bidirectional stepwise regression with Akaike's information criterion (AIC) and multivariate logistic regression analysis were used to screen the predictors of post-ESD pain and construct three nomograms. We evaluated the model's discrimination, precision and clinical benefit through receiver operating characteristic (ROC) curves, calibration plots, Hosmer-Lemeshow (HL) goodness-of-fit test and decision curve analysis (DCA) in internal validation. The proportion of patients developing postoperative pain in the training and testing data set was 25.6% and 28.5%, respectively. Three nomograms were constructed according to the final logistic regression models. The clinical prediction models for preoperative risks, preoperative and intraoperative risks, and perioperative risks consisted of seven, nine and six independent predictors, respectively, after bidirectional stepwise elimination. The models demonstrated the AUC of 0.794 (95% CI 0.768-0.820), 0.823 (95% CI 0.799-0.847) and 0.817 (95% CI 0.792-0.842) in the training cohort and 0.702 (95% CI 0.655-0.748), 0.705 (95% CI 0.659-0.752) and 0.747 (95% CI 0.703-0.790) in the validation cohort. The calibration plot, HL and DCA demonstrated the model's favorable clinical applicability. We developed and validated three robust nomogram models, which might identify patients at risk of post-ESD pain and promising for clinical applications.

Symptom-triggered testing detects early stage and low volume resectable advanced stage ovarian cancer

ObjectiveSymptom-triggered testing for ovarian cancer was introduced to the UK whereby symptomatic women undergo an ultrasound scan and serum CA125, and are referred to hospital within 2 weeks if these...

Development and validation of risk prediction model for post-donation renal function in living kidney donors

This study aimed to create and validate a predictive model for renal function following live kidney donation, using pre-donation factors. Accurately predicting remaining renal function post live kidney donation is currently insufficient, necessitating an effective assessment tool. A multicenter retrospective study of 2318 live kidney donors from two independent centers (May 2007–December 2019) was conducted. The primary endpoint was the reduction in eGFR to below 60 mL/min/m2 6 months post-donation. The primary endpoint was achieved in 14.4% of the training cohort and 25.8% of the validation cohort. Sex, age, BMI, hypertension, preoperative eGFR, and remnant kidney proportion (RKP) measured by computerized tomography (CT) volumetry were found significant in the univariable analysis. These variables informed a scoring system based on multivariable analysis: sex (male: 1, female: 0), age at operation (< 30: 0, 30–39: 1, 40–59: 2, ≥ 60: 3), preoperative eGFR (≥ 100: 0, 90–99: 2, 80–89: 4, < 80: 5), and RKP (≥ 52%: 0, < 52%: 1). The total score ranged from 0 to 10. The model showed good discrimination for the primary endpoint in both cohorts. The prediction model provides a useful tool for estimating post-donation renal dysfunction risk, factoring in the side of the donated kidney. It offers potential enhancement to pre-donation evaluations.

International External Validation of Risk Prediction Model of 90-Day Mortality after Gastrectomy for Cancer Using Machine Learning.

Radical gastrectomy remains the main treatment for gastric cancer, despite its high mortality. A clinical predictive model of 90-day mortality (90DM) risk after gastric cancer surgery based on the Spanish EURECCA registry database was developed using a matching learning algorithm. We performed an external validation of this model based on data from an international multicenter cohort of patients. A cohort of patients from the European GASTRODATA database was selected. Demographic, clinical, and treatment variables in the original and validation cohorts were compared. The performance of the model was evaluated using the area under the curve (AUC) for a random forest model. The validation cohort included 2546 patients from 24 European hospitals. The advanced clinical T- and N-category, neoadjuvant therapy, open procedures, total gastrectomy rates, and mean volume of the centers were significantly higher in the validation cohort. The 90DM rate was also higher in the validation cohort (5.6%) vs. the original cohort (3.7%). The AUC in the validation model was 0.716. The externally validated model for predicting the 90DM risk in gastric cancer patients undergoing gastrectomy with curative intent continues to be as useful as the original model in clinical practice.

Analysis of risk factors and construction of a prediction model for posttraumatic stress disorder among Chinese college students during the COVID-19 pandemic

BackgroundTo explore the risk factors of post-traumatic stress disorder (PTSD) among Chinese college students during the COVID-19 pandemic and the construction and validation of risk prediction models. MethodsA total of 10,705 university students were selected for the study. The questionnaire included the Generalized Anxiety Disorder 7 (GAD-7), Patient Health Questionnaire 9 (PHQ-9), PTSD Checklist for DSM-5 (PCL-5), and self-designed questionnaire. These assessments were conducted to facilitate the survey, construct the predictive model and validate the model's validity. ResultsSex, left-behind experience, poverty status, anxiety score, and depression score were identified as independent risk factors influencing psychological trauma among Chinese college students during the COVID-19 pandemic, while COVID-19 infection emerged as a protective factor against psychological trauma. A column chart was constructed to visualize the six independent risk factors derived from logistic regression analysis. The Hosmer–Lemeshow test results (χ2 = 13.021, P = 0.111) indicated that the risk prediction model fitted well. The receiver operating characteristic (ROC) curve showed an area under the curve (AUC) of 0.864 in the model group and 0.855 in the validation group. The calibration curves of the model closely resembled the ideal curve. Decision curve analysis (DCA) revealed that the model provided net benefit and demonstrated good clinical utility. LimitationsThe validation of the model is currently restricted to internal assessments. However, further confirmation through larger sample sizes, multicenter investigations, and prospective studies is necessary. ConclusionsThe model effectively predicted PTSD risk among Chinese college students during the COVID-19 pandemic, indicating strong clinical applicability.

Risk of emergency hospital admission related to adverse events after antibiotic treatment in adults with a common infection: impact of COVID-19 and derivation and validation of risk prediction models

BackgroundWith the global challenge of antimicrobial resistance intensified during the COVID-19 pandemic, evaluating adverse events (AEs) post-antibiotic treatment for common infections is crucial. This study aims to examines the changes in incidence rates of AEs during the COVID-19 pandemic and predict AE risk following antibiotic prescriptions for common infections, considering their previous antibiotic exposure and other long-term clinical conditions.MethodsWith the approval of NHS England, we used OpenSAFELY platform and analysed electronic health records from patients aged 18–110, prescribed antibiotics for urinary tract infection (UTI), lower respiratory tract infections (LRTI), upper respiratory tract infections (URTI), sinusitis, otitis externa, and otitis media between January 2019 and June 2023. We evaluated the temporal trends in the incidence rate of AEs for each infection, analysing monthly changes over time. The survival probability of emergency AE hospitalisation was estimated in each COVID-19 period (period 1: 1 January 2019 to 25 March 2020, period 2: 26 March 2020 to 8 March 2021, period 3: 9 March 2021 to 30 June 2023) using the Kaplan–Meier approach. Prognostic models, using Cox proportional hazards regression, were developed and validated to predict AE risk within 30 days post-prescription using the records in Period 1.ResultsOut of 9.4 million patients who received antibiotics, 0.6% of UTI, 0.3% of URTI, and 0.5% of LRTI patients experienced AEs. UTI and LRTI patients demonstrated a higher risk of AEs, with a noted increase in AE incidence during the COVID-19 pandemic. Higher comorbidity and recent antibiotic use emerged as significant AE predictors. The developed models exhibited good calibration and discrimination, especially for UTIs and LRTIs, with a C-statistic above 0.70.ConclusionsThe study reveals a variable incidence of AEs post-antibiotic treatment for common infections, with UTI and LRTI patients facing higher risks. AE risks varied between infections and COVID-19 periods. These findings underscore the necessity for cautious antibiotic prescribing and call for further exploration into the intricate dynamics between antibiotic use, AEs, and the pandemic.

849 Routine Use of Validated Risk Prediction Model in the Management of Acute Appendicitis in a District General Hospital

849 Routine Use of Validated Risk Prediction Model in the Management of Acute Appendicitis in a District General Hospital

Construction and validation of risk prediction models for pulmonary embolism in hospitalized patients based on different machine learning methods.

This study aims to apply different machine learning (ML) methods to construct risk prediction models for pulmonary embolism (PE) in hospitalized patients, and to evaluate and compare the predictive efficacy and clinical benefit of each model. We conducted a retrospective study involving 332 participants (172 PE positive cases and 160 PE negative cases) recruited from Guangdong Medical University. Participants were randomly divided into a training group (70%) and a validation group (30%). Baseline data were analyzed using univariate analysis, and potential independent risk factors associated with PE were further identified through univariate and multivariate logistic regression analysis. Six ML models, namely Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Support Vector Machine (SVM), and AdaBoost were developed. The predictive efficacy of each model was compared using the receiver operating characteristic (ROC) curve analysis and the area under the curve (AUC). Clinical benefit was assessed using decision curve analysis (DCA). Logistic regression analysis identified lower extremity deep venous thrombosis, elevated D-dimer, shortened activated partial prothrombin time, and increased red blood cell distribution width as potential independent risk factors for PE. Among the six ML models, the RF model achieved the highest AUC of 0.778. Additionally, DCA consistently indicated that the RF model offered the greatest clinical benefit. This study developed six ML models, with the RF model exhibiting the highest predictive efficacy and clinical benefit in the identification and prediction of PE occurrence in hospitalized patients.

External validation and comparison of magnetic resonance imaging-based risk prediction models for prostate biopsy stratification.

Magnetic resonance imaging (MRI) is a promising tool for risk assessment, potentially reducing the burden of unnecessary prostate biopsies. Risk prediction models that incorporate MRI data have gained attention, but their external validation and comparison are essential for guiding clinical practice. The aim is to externally validate and compare risk prediction models for the diagnosis of clinically significant prostate cancer (csPCa). A cohort of 4606 patients across fifteen European tertiary referral centers were identified from a prospective maintained database between January 2016 and April 2023. Transrectal or transperineal image-fusion MRI-targeted and systematic biopsies for PI-RADS score of ≥ 3 or ≥ 2 depending on patient characteristics and physician preferences. Probabilities for csPCa, defined as International Society of Urological Pathology (ISUP) grade ≥ 2, were calculated for each patients using eight models. Performance was characterized by area under the receiver operating characteristic curve (AUC), calibration, and net benefit. Subgroup analyses were performed across various clinically relevant subgroups. Overall, csPCa was detected in 2154 (47%) patients. The models exhibited satisfactory performance, demonstrating good discrimination (AUC ranging from 0.75 to 0.78, p < 0.001), adequate calibration, and high net benefit. The model described by Alberts showed the highest clinical utility for threshold probabilities between 10 and 20%. Subgroup analyses highlighted variations in models' performance, particularly when stratified according to PSA level, biopsy technique and PI-RADS version. We report a comprehensive external validation of risk prediction models for csPCa diagnosis in patients who underwent MRI-targeted and systematic biopsies. The model by Alberts demonstrated superior clinical utility and should be favored when determining the need for a prostate biopsy.

#1584 Development and validation of risk prediction models according to different clinical settings of IgA nephropathy: nationwide multicenter cohort study

Abstract Background and Aims IgA nephropathy (IgAN) is the most common glomerulonephritis with a high risk of progression to end-stage renal disease (ESRD). Because machine learning models developed for research have limited use in clinical settings, this study developed and validated prediction models for IgAN according to different clinical settings. Method In this study, we analyzed data from 1,174 patients in the Japanese Nationwide Retrospective Cohort Study in IgAN, focusing on a 10-year observation period. We defined the derivation data from January 2002 to April 2004, and temporal validation data from May 2004 to December 2004. The composite renal outcome was defined as a 1.5-fold increase in creatinine or progression to ESRD. We developed and evaluated the three prediction models according to the different clinical settings: the primary care model for general physicians in primary care settings, the tertiary care model for specialists in tertiary care hospitals, and the research institute model, a machine learning-based approach for academic research institute settings. Results After excluding 82 patients for missing data, 114 and 14 patients experienced the composite renal outcome in the derivation (n = 874) and validation (n = 218) cohorts, respectively. The primary care model identified three variables—eGFR &amp;lt;45 mL/min/1.73 m², proteinuria ≥0.5 g/day, and non-use of corticosteroids—as significant predictors (C-statistic: 0.796; 95% CI: 0.686-0.895). The tertiary care model composed of three variables including glomerular number, histological severity and tubular/interstitial severity showed a slightly higher C-statistic (0.807; 95% CI: 0.713-0.886). When stratifying patients into risk groups, the primary care model showed a higher incidence of composite renal events in high-risk patients, and the tertiary care model effectively discriminated outcomes in all groups. The research institute model, which included 38 variables including proteinuria level, hypertension, eGFR, and non-use of corticosteroids as key predictors, showed comparable performance (C-statistic: 0.808; 95% CI: 0.689-0.886). Conclusion The primary care and tertiary care models provide simple yet effective predictive tools, competitive with the machine learning-based research institution model. These models are critical for predicting renal outcomes in patients with IgA nephropathy and for patient management according to different clinical settings.

Development and validation of risk prediction model for bacterial infections in acute liver failure patients.

Infections significantly increase mortality in acute liver failure (ALF) patients, and there are no risk prediction models for early diagnosis and treatment of infections in ALF patients. This study aims to develop a risk prediction model for bacterial infections in ALF patients to guide rational antibiotic therapy. The data of ALF patients admitted to the Second Hospital of Hebei Medical University in China from January 2017 to January 2022 were retrospectively analyzed for training and internal validation. Patients were selected according to the updated 2011 American Association for the Study of Liver Diseases position paper on ALF. Serological indicators and model scores were collected within 24 h of admission. New models were developed using the multivariate logistic regression analysis. An optimal model was selected by receiver operating characteristic (ROC) analysis, Hosmer-Lemeshow test, the calibration curve, the Brier score, the bootstrap resampling, and the decision curve analysis. A nomogram was plotted to visualize the results. A total of 125 ALF patients were evaluated and 79 were included in the training set. The neutrophil-to-lymphocyte ratio and sequential organ failure assessment (SOFA) were integrated into the new model as independent predictive factors. The new SOFA-based model outperformed other models with an area under the ROC curve of 0.799 [95% confidence interval (CI): 0.652-0.926], the superior calibration and predictive performance in internal validation. High-risk individuals with a nomogram score ≥26 are recommended for antibiotic therapy. The new SOFA-based model demonstrates high accuracy and clinical utility in guiding antibiotic therapy in ALF patients.