Multivariable Prediction Model Research Articles

The Sensitivity and Specificity of Multiparametric Magnetic Resonance Imaging and Prostate-Specific Membrane Antigen Positron Emission Tomography/Computed Tomography for Predicting Seminal Vesicle Invasion in Clinically Significant Prostate Cancer: A Multicenter Retrospective Study.

Background/Objectives: The presence of seminal vesicle invasion (SVI) in prostate cancer (PCa) is associated with poorer postoperative outcomes. This study evaluates the predictive value of magnetic resonance imaging (MRI) and prostate-specific membrane antigen positron emission tomography/computed tomography (PSMA PET/CT) for SVI in PCa. Methods: This cohort study included consecutive robotic prostatectomy patients for PCa at three Australian tertiary referral centres between April 2016 and September 2022. MRI and PSMA PET/CT results, clinicopathological variables, including age, BMI, prostate-specific antigen (PSA), PSA density, DRE, Biopsy Gleason score, Positive biopsy cores, PIRADS v2.1 score, MRI volume and MRI lesion size were extracted. The sensitivity, specificity, and accuracy of MRI and PSMA PET/CT for predicting SVI were compared with the histopathological results by receiver operating characteristic (ROC) analysis. Subgroup univariate and multivariate analysis was performed. Results: Of the 528 patients identified, 86 had SVI on final pathology. MRI had a low sensitivity of 0.162 (95% CI: 0.088-0.261) and a high specificity of 0.963 (95% CI: 0.940-0.979). The PSMA PET/CT had a low sensitivity of 0.439 (95% CI: 0.294-0591) and a high specificity of 0.933 (95% CI: 0.849-0.969). When MRI and PSMA PET/CT were used in combination, the sensitivity and specificity improved to 0.514 (95%CI: 0.356-0.670) and 0.880 (95% CI: 0.813-0.931). The multivariate regression showed a higher biopsy Gleason score (p = 0.033), higher PSA (p < 0.001), older age (p = 0.001), and right base lesions (p = 0.003) to be predictors of SVI. Conclusions: MRI and PSMA PET/CT independently underpredicted SVI. The sensitivity and AUC improved when they were used in combination. Multiple clinicopathological factors were associated with SVI on multivariate regression and predictive models incorporating this information may improve oncological outcomes.

Skeleton density and ellipsoid zone loss are prognostic for progression in Macular Telangiectasia Type 2

Macular Telangiectasia Type 2 (MacTel) is a chronic, progressive disease of the central retina characterized by vascular and neurodegenerative changes. As there is currently no treatment for non-neovascular MacTel, there is a dearth for biomarkers identifying eyes with an increased risk for disease progression for patient counseling and clinical trial recruitment. Eyes were classified to be stable or progressive, defined by the fundus photography-based grading system by Gass and Blodi. First, structural differences between these two groups were assessed, employing optical coherence tomography (OCT) and OCT-angiography. Univariate regression analyses revealed evidence towards a lower superficial retinal layer (SRL) vessel density (VD), skeleton density (SD) and deep retinal layer (DRL) SD in progressing compared to stable eyes (p = 0.05, p = 0.05, p = 0.07). Second, a multivariable predictive model was employed to examine the predictive value of structural and functional parameters for disease progression. Baseline best corrected visual acuity (BCVA) and SRL SD are prognostic for disease progression (p < 0.001, p = 0.05). The presence of ellipsoid zone (EZ) loss is prognostic for future central retinal thickness (p < 0.01). We propose SRL SD, BCVA, and EZ loss as prognostic biomarkers and as possible outcome measures in future interventional studies in MacTel.

Gluten-Free Diet Adherence Tools for Individuals with Celiac Disease: A Systematic Review and Meta-Analysis of Tools Compared to Laboratory Tests.

This systematic review aimed to find the tool that best predicts celiac individuals' adherence to a gluten-free diet (GFD). The Transparent Reporting of Multivariable Prediction Models for Individual Prognosis or Diagnosis (TRIPOD-SRMA) guideline was used for the construction and collection of data from eight scientific databases (PubMed, EMBASE, LILACS, Web of Science, LIVIVO, SCOPUS, Google Scholar, and Proquest) on 16 November 2023. The inclusion criteria were studies involving individuals with celiac disease (CD) who were over 18 years old and on a GFD for at least six months, using a questionnaire to predict adherence to a GFD, and comparing it with laboratory tests (serological tests, gluten immunogenic peptide-GIP, or biopsy). Review articles, book chapters, and studies without sufficient data were excluded. The Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies (CHARMS) was used for data collection from the selected primary studies, and their risk of bias and quality was assessed using the Prediction Risk of Bias Assessment Tool (PROBAST). The association between the GFD adherence determined by the tool and laboratory test was assessed using the phi contingency coefficient. The studies included in this review used four different tools to evaluate GFD adherence: BIAGI score, Coeliac Dietary Adherence Test (CDAT), self-report questions, and interviews. The comparison method most often used was biopsy (n = 19; 59.3%), followed by serology (n = 14; 43.7%) and gluten immunogenic peptides (GIPs) (n = 4; 12.5%). There were no significant differences between the interview, self-report, and BIAGI tools used to evaluate GFD adherence. These tools were better associated with GFD adherence than the CDAT. Considering their cost, application time, and prediction capacity, the self-report and BIAGI were the preferred tools for evaluating GFD adherence.

“Long term speech outcomes after using the Sommerlad technique for primary palatoplasty: a retrospective study in the Wilhelmina Children’s Hospital, Utrecht.”

ObjectivesAfter cleft lip and/or palate (CL/P) repair, children may develop velopharyngeal insufficiency (VPI) leading to speech imperfections, necessitating additional speech correcting surgery. This study examines the incidence of VPI and speech correcting surgery after Sommerlad’s palatoplasty for CL/P, and its association with various clinical features.Materials and methodsA retrospective cohort study was performed in the Wilhelmina Children’s Hospital in Utrecht and child records from 380 individuals with CL/P registered from 2008 to 2017 were retrospectively reviewed. Inclusion criteria comprised the diagnosis of CL/P, primary palatoplasty according to Sommerlad’s technique, and speech assessment at five years or older. Association between cleft type and width, presence of additional genetic disorders and postoperative complications (palatal dehiscence, fistula) were assessed using odds ratios and chi squared tests.ResultsA total of 239 patients were included. The VPI rate was 52.7% (n = 126) and in 119 patients (49.8%) a speech correcting surgery was performed. Severe cleft type, as indicated by a higher Veau classification, was associated with a significant higher rate of speech correcting surgeries (p = 0.033). Significantly more speech correcting surgeries were performed in patients with a cleft width >10 mm, compared to patients with a cleft width ≤10 mm (p < 0.001). Patients with oronasal fistula underwent significantly more speech correcting surgeries than those without fistula (p = 0.004). No statistically significant difference was found in the incidence of speech correcting surgery between patients with and without genetic disorders (p = 0.890).Conclusions/clinical relevanceVariations in cleft morphology, cleft width and complications like oronasal fistula are associated with different speech outcomes. Future research should focus on creating a multivariable prediction model for speech correcting surgery in CL/P patients.

Outcome risk model development for heterogeneity of treatment effect analyses: a comparison of non-parametric machine learning methods and semi-parametric statistical methods

BackgroundIn randomized clinical trials, treatment effects may vary, and this possibility is referred to as heterogeneity of treatment effect (HTE). One way to quantify HTE is to partition participants into subgroups based on individual’s risk of experiencing an outcome, then measuring treatment effect by subgroup. Given the limited availability of externally validated outcome risk prediction models, internal models (created using the same dataset in which heterogeneity of treatment analyses also will be performed) are commonly developed for subgroup identification. We aim to compare different methods for generating internally developed outcome risk prediction models for subject partitioning in HTE analysis.MethodsThree approaches were selected for generating subgroups for the 2,441 participants from the United States enrolled in the ASPirin in Reducing Events in the Elderly (ASPREE) randomized controlled trial. An extant proportional hazards-based outcomes predictive risk model developed on the overall ASPREE cohort of 19,114 participants was identified and was used to partition United States’ participants by risk of experiencing a composite outcome of death, dementia, or persistent physical disability. Next, two supervised non-parametric machine learning outcome classifiers, decision trees and random forests, were used to develop multivariable risk prediction models and partition participants into subgroups with varied risks of experiencing the composite outcome. Then, we assessed how the partitioning from the proportional hazard model compared to those generated by the machine learning models in an HTE analysis of the 5-year absolute risk reduction (ARR) and hazard ratio for aspirin vs. placebo in each subgroup. Cochran’s Q test was used to detect if ARR varied significantly by subgroup.ResultsThe proportional hazard model was used to generate 5 subgroups using the quintiles of the estimated risk scores; the decision tree model was used to generate 6 subgroups (6 automatically determined tree leaves); and the random forest model was used to generate 5 subgroups using the quintiles of the prediction probability as risk scores. Using the semi-parametric proportional hazards model, the ARR at 5 years was 15.1% (95% CI 4.0–26.3%) for participants with the highest 20% of predicted risk. Using the random forest model, the ARR at 5 years was 13.7% (95% CI 3.1–24.4%) for participants with the highest 20% of predicted risk. The highest outcome risk group in the decision tree model also exhibited a risk reduction, but the confidence interval was wider (5-year ARR = 17.0%, 95% CI= -5.4–39.4%). Cochran’s Q test indicated ARR varied significantly only by subgroups created using the proportional hazards model. The hazard ratio for aspirin vs. placebo therapy did not significantly vary by subgroup in any of the models. The highest risk groups for the proportional hazards model and random forest model contained 230 participants each, while the highest risk group in the decision tree model contained 41 participants.ConclusionsThe choice of technique for internally developed models for outcome risk subgroups influences HTE analyses. The rationale for the use of a particular subgroup determination model in HTE analyses needs to be explicitly defined based on desired levels of explainability (with features importance), uncertainty of prediction, chances of overfitting, and assumptions regarding the underlying data structure. Replication of these analyses using data from other mid-size clinical trials may help to establish guidance for selecting an outcomes risk prediction modelling technique for HTE analyses.

Remaining useful life prediction of slewing bearings using attention mechanism enabled multivariable gated recurrent unit network

It is difficult to obtain the damage information on large slewing bearings only from vibration signals. In addition, deep learning models trained on old samples do not achieve high accuracy in new tasks. Therefore, this paper uses vibration, temperature, and torque signals of slewing bearings to build a model. Meanwhile, we add attention mechanism to capture internal correlation of them to consider the related factors of remaining useful life (RUL) from multiple angles. The multivariable gated recurrent unit (GRU) based on attention mechanism gated recurrent unit (attention-MGRU) model is adopted to improve the prediction performance. On this foundation, a fine-tuning strategy is introduced to improve the generalization ability of the model. A full-life accelerated test is carried out on the slewing bearing test bench. The model proposed in this paper is compared with GRU prediction model, which utilizes vibration signals and multivariable GRU prediction model. Mean absolute error (MAE) and root-mean-square error (RMSE) are used as measurement indicators. Among different methods, three indicators generated by attention-MGRU show significant superiority. Moreover, the fine-tuned model performs better in new tasks compared with the original model.

Machine learning in the prediction of treatment response in rheumatoid arthritis: A systematic review

ObjectiveThis study aimed to investigate the current status and performance of machine learning (ML) approaches in providing reproducible treatment response predictions. MethodsThis systematic review was conducted in accordance with the PRISMA statement and the CHARMS checklist. We searched PubMed, Cochrane Library, Web of Science, Scopus, and EBSCO databases for cohort studies that derived and/or validated ML models focused on predicting rheumatoid arthritis (RA) treatment response. We extracted data and critically appraised studies based on the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) and Prediction Model Risk of Bias Assessment Tool (PROBAST) guidelines. ResultsFrom 210 unduplicated records identified by the literature search, we retained 29 eligible studies. Of these studies, 10 developed a predictive model and reported a mean adherence to the TRIPOD guidelines of 45.6 % (95 % CI: 38.3–52.8 %). The remaining 19 studies not only developed a predictive model but also validated it externally, with a mean adherence of 42.9 % (95 % CI: 39.1–46.6 %). Most of the articles had an unclear risk of bias (41.4 %), followed by a high risk of bias, which was present in 37.9 %. ConclusionsIn recent years, ML methods have been increasingly used to predict treatment response in RA. Our critical appraisal revealed unclear and high risk of bias in most of the identified models, suggesting that researchers can do more to address the risk of bias and increase transparency, including the use of calibration measures and reporting methods for handling missing data. FundingNone.

Research on the economic loss prediction and vulnerability risk zoning of coastal erosion disaster: a case study from Liaoning, China

IntroductionCoastal erosion is widely distributed globally, with sandy coasts being particularly prominent, causing significant economic losses to coastal areas. This study focuses on the coastal areas of Liaoning Province, China, which represent typical sandy beach erosion.MethodsBased on the assessment of coastal erosion disaster losses, a multivariate variable-weight combination prediction model is utilized to predict the losses caused by coastal erosion disasters, providing an effective mathematical modeling approach for predicting such losses. Furthermore, the cluster analysis method is employed to delineate vulnerability risk zones for coastal erosion along the Liaoning Province coast.Results and discussionThe research findings indicate the following: (1) From 2023 to 2025, the losses due to coastal erosion disasters in Liaoning Province are projected to decrease significantly from a scale of 36 million RMB yuan to 5 million RMB yuan; (2) Based on the magnitude of disaster vulnerability risk, the coastal areas of Liaoning Province are categorized into four risk zones: high-risk zones (Jinzhou District), moderately high-risk zones (Zhuanghe City, Wafangdian City, Ganjingzi District), medium-risk zones (Lvshunkou District, Bayuquan), and low-risk zones (Gaizhou City, Suizhong County, Xingcheng City). Recommendations are proposed accordingly: (1) Effective measures should be implemented to mitigate the losses incurred by coastal erosion on land, buildings, infrastructure, agricultural output; (2) In the selection of disaster prevention and control measures,economic factors should be carefully considered in line with the specific circumstances of the losses. Specifically, the economic efficiency of disaster prevention and mitigation measures should be taken into account; (3) Precise efforts should be made to implement coastal erosion disaster prevention and control measures in different regions.

Diagnostic models to predict structural spinal osteoarthritis on lumbar radiographs in older adults with back pain: Development and internal validation

ObjectiveIt is difficult for health care providers to diagnose structural spinal osteoarthritis (OA), because current guidelines recommend against imaging in patients with back pain. Therefore, the aim of this study was to develop and internally validate multivariable diagnostic prediction models based on a set of clinical and demographic features to be used for the diagnosis of structural spinal OA on lumbar radiographs in older patients with back pain. DesignThree diagnostic prediction models, for structural spinal OA on lumbar radiographs (i.e. multilevel osteophytes, multilevel disc space narrowing (DSN), and both combined), were developed and internally validated in the ‘Back Complaints in Older Adults’ (BACE) cohort (N ​= ​669). Model performance (i.e. overall performance, discrimination and calibration) and clinical utility (i.e. decision curve analysis) were assessed. Internal validation was performed by bootstrapping. ResultsMean age of the cohort was 66.9 years (±7.6 years) and 59% were female. All three models included age, gender, back pain duration and duration of spinal morning stiffness as predictors. The combined model additionally included restricted lateral flexion and spinal morning stiffness severity, and exhibited the best model performance (optimism adjusted c-statistic 0.661; good calibration with intercept −0.030 and slope of 0.886) and acceptable clinical utility. The other models showed suboptimal discrimination, good calibration and acceptable decision curves. ConclusionAll three models for structural spinal OA displayed lesuboptimal discrimination and need improvement. However, these internally validated models have potential to inform primary care clinicians about a patient with risk of having structural spinal OA on lumbar radiographs. External validation before implementation in clinical care is recommended.

ICURE: Intensive care unit (ICU) risk evaluation for 30-day mortality. Developing and evaluating a multivariable machine learning prediction model for patients admitted to the general ICU in Sweden.

A prediction model that estimates mortality at admission to the intensive care unit (ICU) is of potential benefit to both patients and society. Logistic regression models like Simplified Acute Physiology Score 3 (SAPS 3) and APACHE are the traditional ICU mortality prediction models. With the emergence of machine learning (machine learning) and artificial intelligence, new possibilities arise to create prediction models that have the potential to sharpen predictive accuracy and reduce the likelihood of misclassification in the prediction of 30-day mortality. We used the Swedish Intensive Care Registry (SIR) to identify and include all patients ≥18 years of age admitted to general ICUs in Sweden from 2008 to 2022 with SAPS 3 score registered. Only data collected within 1 h of ICU admission was used. We had 153 candidate predictors including baseline characteristics, previous medical conditions, blood works, physiological parameters, cause of admission, and initial treatment. We stratified the data randomly on the outcome variable 30-day mortality and created a training set (80% of data) and a test set (20% of data). We evaluated several hundred prediction models using multiple ML frameworks including random forest, gradient boosting, neural networks, and logistic regression models. Model performance was evaluated by comparing the receiver operator characteristic area under the curve (AUC-ROC). The best performing model was fine-tuned by optimizing hyperparameters. The model's calibration was evaluated by a calibration belt. Ultimately, we simplified the best performing model with the top 1-20 predictors. We included 296,344 first-time ICU admissions. We found age, Glasgow Coma Scale, creatinine, systolic blood pressure, and pH being the most important predictors. The AUC-ROC was 0.884 in test data using all predictors, specificity 95.2%, sensitivity 47.0%, negative predictive value of 87.9% and positive predictive value of 70.7%. The final model showed excellent calibration. The ICU risk evaluation for 30-day mortality (ICURE) prediction model performed equally well to the SAPS 3 score with only eight variables and improved further with the addition of more variables. The ICURE prediction model predicts 30-day mortality rate at first-time ICU admission superiorly compared to the established SAPS 3 score.

Exploring capelin (Mallotus villosus) population dynamics using Empirical Dynamic Modelling (EDM)

Capelin (Mallotus villosus) populations on the Newfoundland shelf collapsed in the early 1990s, coinciding with a regime shift and greatly reduced capelin and groundfish biomasses which both persist to this day. The biphasic nature of this stock’s history suggest it may experience nonlinear dynamics, which are difficult to predict using linear models. This study explores the application of Empirical Dynamic Modelling (EDM) nonlinear, nonparametric time series forecasting tools to capelin biomass data, seeking to detect nonlinear dynamics, compare performance of linear and nonlinear multivariate predictive models, identify drivers of capelin biomass using convergent cross-mapping, and measure the sign and strength of capelin species interactions. We found capelin dynamics were nonlinear, and multivariate EDM predictive models returned equal or improved model diagnostics to linear models in most situations. We identified long-term climate dynamics and timing of sea ice retreat as the primary drivers of capelin dynamics, but some indications of potential top-down effects from Greenland halibut were also detected. Atlantic cod biomass, and capelin catch were investigated as potential drivers of capelin dynamics, but both were found more likely to be driven by capelin dynamics. Overall, our results support the idea that capelin dynamics are mostly bottom-up driven, and that capelin itself is a driver of its predators, suggesting that the overall ecosystem may be largely bottom-up driven. This study also clearly identifies the utilities of EDM as a complementary tool for stock assessments by detecting and forecasting nonlinear stock dynamics, and identifying and characterizing relationships between stock biomass and the factors which drive it.

Classification-Predictive Model Based on Artificial Neural Network Validated by Histopathology and Direct Immunofluorescence for the Diagnosis of Oral Lichen Planus.

The diagnosis of oral lichen planus (OLP) poses many challenges due to its nonspecific clinical symptoms and histopathological features. Therefore, the diagnostic process should include a thorough clinical history, immunological tests, and histopathology. Our study aimed to enhance the diagnostic accuracy of OLP by integrating direct immunofluorescence (DIF) results with clinical data to develop a multivariate predictive model based on the Artificial Neural Network. Eighty patients were assessed using DIF for various markers (immunoglobulins of classes G, A, and M; complement 3; fibrinogen type 1 and 2) and clinical characteristics such as age, gender, and lesion location. Statistical analysis was performed using machine learning techniques in Statistica 13. The following variables were assessed: gender, age on the day of lesion onset, results of direct immunofluorescence, location of white patches, locations of erosions, treatment history, medications and dietary supplement intake, dental status, smoking status, flossing, and using mouthwash. Four statistically significant variables were selected for machine learning after the initial assessment. The final predictive model, based on neural networks, achieved 85% in the testing sample and 71% accuracy in the validation sample. Significant predictors included stress at onset, white patches under the tongue, and erosions on the mandibular gingiva. In conclusion, while the model shows promise, larger datasets and more comprehensive variables are needed to improve diagnostic accuracy for OLP, highlighting the need for further research and collaborative data collection efforts.

Prediction models for skin tears in the elderly: A systematic review and meta-analysis

BackgroundThe prevalence of risk prediction models for skin tears in the elderly is growing; however, there is still debate regarding the usefulness and suitability of these models for clinical use and additional study. ObjectiveThe purpose of this work is to perform a systematic review and meta-analysis of published research on skin tear risk prediction models in the elderly. MethodsWe conducted a comprehensive search of various databases, including Cumulative Index to Nursing and Allied Health Literature (CINAHL), Embase, PubMed, Web of Science, MEDLINE, Scopus, The Cochrane Library, Wanfang Database, China Science and Technology Journal Database (VIP), and China National Knowledge Infrastructure (CNKI), from the beginning until November 27, 2023. Data extraction from the chosen studies encompassed various elements, such as study design, sample size, outcome definition, data source, predictors, model development, and performance. The assessment of bias and applicability was conducted using the Prediction Model Risk of Bias Assessment Tool (PROBAST) checklist. The Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) checklist was utilized to assess the transparency in reporting the prediction models—a meta-analysis of the most common predictors to assess predictor reliability. In addition, a narrative synthesis was carried out to provide an overview of the qualities, bias risk, and effectiveness of the current models. The reporting procedures of this meta-analysis conformed to the 2020 Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) statement. ResultsOut of the initially retrieved 1499 studies, this review included eight prediction models from eight selected studies. All the studies employed logistic regression to develop prediction models for skin tears. The prevalence of skin tears in the elderly varied from 3.0% to 33.3%. Senile purpura and a history of previous skin tears were the most commonly utilized predictors. The reported values for the area under the curve (AUC) ranged from 0.765 to 0.854. All the studies exhibited a high risk of bias, primarily due to inadequate reporting in the outcome and analysis domains. Furthermore, serious questions concerning their applicability were highlighted by four studies. ConclusionBased on the PROBAST checklist, the current models for predicting skin tears in the elderly showed a high risk of bias. The development of new prediction models with bigger sample sizes, appropriate study designs, and external validation from multiple sources ought to be the primary focus of future research. Patient or public contributionThere was no patient or public contribution to this systematic review. RegistrationPROSPERO registration number: CRD42023494387.

Reliability of predictive models based on the mesiodistal and buccolingual diameters of permanent canine teeth for sex estimation in forensic contexts: A systematic review and meta-analysis

This study aimed to assess the reliability of predictive models for sex estimation based on permanent canine size. A systematic literature review was performed by following the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA). Six electronic databases were searched as the primary source of information. As a secondary source of information, a manual search was performed to identify additional relevant studies not captured in the initial search. After assessing the methodological quality and risk of bias with the Joanna Briggs Institute Critical Appraisal Tools for Systematic Reviews, the data were subjected to statistical tests for a meta-analysis of diagnostic test accuracy and Higgin’s I2 statistic to evaluate the heterogeneity between the eligible studies. The systematic search resulted in 21 studies for qualitative synthesis, and 13 of them were selected for quantitative analysis. The analysis of 25 univariate predictive models showed an estimated sensitivity of 77.2 % and specificity of 67.1 %. Meta-regression analyses were performed for dental arch, the type of diameter and dental region outcomes for these univariate predictive models. Dental arch (p = 0.029) and the dental region of measurement (p = 0.001) were significant modifiers. The analysis of 25 multivariate predictive models showed an estimated sensitivity of 82.6 % and specificity of 70.1 %. There were significant methodological limitations and substantial heterogeneity among the included studies. Based on the results, there is insufficient high-quality scientific evidence to support the safe use of predictive models based on permanent canine measurements as the exclusive method for sex estimation in forensic settings.

Spatiotemporal distribution of oxidative potential in PM2.5 and its key components across six Chinese cities

Increasing evidence has supported that oxidative potential (OP) serves as a crucial indicator of health risk of exposure to PM2.5 over mass concentration. However, there is a lack of comparative studies across multiple cities, particularly on a fine temporal scale. In this study, we aim to investigate daily variation of ambient PM2.5 OP through simultaneous samplings in six Chinese cities for one year. Results showed that more than 60 % of the sampling days exhibited non-zero ranking difference between volume-normalized oxidative potential (OPv) and mass concentration among the six cities. Key components contributing to OPv inculde Mn, NO3-, and K+, followed by Ca2+, Al, SO42-, Cl-, Fe, and NH4+. Based on these chemical components, we developed a stepwise multivariable linear regression model (R2: 0.71) for OPv prediction. The performance of the model is comparable to both species- and sources-based ones in the literature. These findings suggest that a relatively lower daily-averaged mass concentration of PM2.5 does not necessarily indicate a lower oxidative risk. Future studies and policy developments on health benefits should also consider OPv rather than mass concentration alone. Priority could be given to sources/species that contribute significantly to oxidative potential of ambient PM2.5. SynopsisThis study highlights inclusion of oxidative potential as a complementary metric for air pollution assessment and control.

Exploratory analysis of predictors of ventricular aneurysm in a cohort of 291 patients with acute myocardial infarction

ObjectiveIn this study, we explored the determinants of ventricular aneurysm development following acute myocardial infarction (AMI), thereby prompting timely interventions to enhance patient prognosis.MethodsIn this retrospective cohort analysis, we evaluated 297 AMI patients admitted to the First People’s Hospital of Changzhou. The study was structured as follows. Comprehensive baseline data collection included hematological evaluations, ECG, echocardiography, and coronary angiography upon admission. Within 3 months post-AMI, cardiac ultrasounds were administered to detect ventricular aneurysm development. Univariate and multivariate logistic regression analysis were employed to pinpoint the determinants of ventricular aneurysm formation. Subsequently, a predictive model was formulated for ventricular aneurysm post-AMI. Moreover, the diagnostic efficacy of this model was appraised using the ROC curves.ResultsIn our analysis of 291 AMI patients, spanning an age range of 32–91 years, 247 were male (84.9%). At the conclusion of a 3-month observational period, the cohort bifurcated into two subsets: 278 patients without ventricular aneurysm and 13 with evident ventricular aneurysm. Distinguishing features of the ventricular aneurysm subgroup were markedly higher values for age, B-type natriuretic peptide(BNP), Left atrium(LA), Left ventricular end-diastolic dimension (LEVDD), left ventricular end systolic diameter (LVEWD), E-wave velocity (E), Left atrial volume (LAV), E/A ratio (E/A), E/e ratio (E/e), ECG with elevated adjacent four leads(4 ST-Elevation), and anterior wall myocardial infarction(AWMI) compared to their counterparts (p < 0.05). Among the singular predictive factors, total cholesterol (TC) emerged as the most significant predictor for ventricular aneurysm development, exhibiting an AUC of 0.704. However, upon crafting a multifactorial model that incorporated gender, TC, an elevated ST-segment in adjacent four leads, and anterior wall infarction, its diagnostic capability: notably surpassed that of the standalone TC, yielding an AUC of 0.883 (z = -9.405, p = 0.000) as opposed to 0.704. Multivariate predictive model included gender, total cholesterol, ST elevation in 4 adjacent leads, anterior myocardial infarction, the multivariate predictive model showed better diagnostic efficacy than single factor index TC (AUC: 0. 883 vs. 0.704,z =-9.405, p = 0.000), it also improved predictive power for correctly reclassifying ventricular aneurysm occurrence in patients with AMI, NRI = 28.42% (95% CI: 6.29-50.55%; p = 0.012). Decision curve analysis showed that the use of combination model had a positive net benefit.ConclusionLipid combined with ECG model after myocardial infarction could be used to predict the formation of ventricular aneurysm and aimed to optimize and adjust treatment strategies.

Residential building and sub-building level flood damage analysis using simple and complex models

AbstractFlood damage assessment is critical for optimal risk management investments. Damage models evaluate physical damage or monetary loss from direct building exposure to flood hazard processes. Traditional models represent a simple relationship whereby physical damage increases with water depth. More complex models offer an improved understanding of vulnerability, analysing interactions between multiple hazard and exposure variables that drive damage. Our study investigates whether increasing model complexity and explanatory damage variables improves prediction precision and reliability at residential building and sub-building (component) levels. We evaluate simple and complex empirical univariable and multivariable models for flood damage prediction. The Random Forest algorithm learned on multiple hazard and exposure explanatory variables outperformed linear and non-linear univariable regression approaches. Random Forest model predictive precision was highest when learning was limited to water depth and several important explanatory damage variables (flow velocity, area and floor height). Component damage models demonstrated high predictive precision for internal finishes and services. Precision reduced for structure and external finishes as damage samples for model learning were limited. High performing but complex multivariable models require further spatio-temporal transfer investigation to determine opportunities for accurate and reliable object-specific flood damage prediction in data scarce locations.

A systematic review of fall prediction models for community-dwelling older adults: comparison between models based on research cohorts and models based on routinely collected data.

Prediction models can identify fall-prone individuals. Prediction models can be based on either data from research cohorts (cohort-based) or routinely collected data (RCD-based). We review and compare cohort-based and RCD-based studies describing the development and/or validation of fall prediction models for community-dwelling older adults. Medline and Embase were searched via Ovid until January 2023. We included studies describing the development or validation of multivariable prediction models of falls in older adults (60+). Both risk of bias and reporting quality were assessed using the PROBAST and TRIPOD, respectively. We included and reviewed 28 relevant studies, describing 30 prediction models (23 cohort-based and 7 RCD-based), and external validation of two existing models (one cohort-based and one RCD-based). The median sample sizes for cohort-based and RCD-based studies were 1365 [interquartile range (IQR) 426-2766] versus 90441 (IQR 56442-128157), and the ranges of fall rates were 5.4% to 60.4% versus 1.6% to 13.1%, respectively. Discrimination performance was comparable between cohort-based and RCD-based models, with the respective area under the receiver operating characteristic curves ranging from 0.65 to 0.88 versus 0.71 to 0.81. The median number of predictors in cohort-based final models was 6 (IQR 5-11); for RCD-based models, it was 16 (IQR 11-26). All but one cohort-based model had high bias risks, primarily due to deficiencies in statistical analysis and outcome determination. Cohort-based models to predict falls in older adults in the community are plentiful. RCD-based models are yet in their infancy but provide comparable predictive performance with no additional data collection efforts. Future studies should focus on methodological and reporting quality.

CT-based radiogenomics of intrahepatic cholangiocarcinoma

BackgroundIntrahepatic cholangiocarcinoma (ICC) is an aggressive disease with increasing incidence and its genetic alterations could be the target of systemic therapies. AimsTo elucidate if radiomics extracted from computed tomography (CT) may non-invasively predict ICC genetic alterations. MethodsAll consecutive patients with a diagnosis of a mass-forming ICC (01/2016–06/2022) were considered. Inclusion criteria were availability of a high-quality contrast-enhanced CT and molecular profiling by NGS or FISH for FGFR2 fusion/rearrangement. The CT scan at diagnosis was considered. Genetic analyses were performed on surgical specimens (resectable patients) or biopsies (unresectable ones). The radiomic features were extracted using the LifeX software. Multivariate predictive models of the commonest genetic alterations were built. ResultsIn the 90 enrolled patients (58 NGS/32 FISH, median age 65 years), the most common genetic alterations were FGFR2 (20/90), IDH1 (10/58), and KRAS (9/58). At internal validation, the combined clinical-radiomic models achieved the best performance for the prediction of FGFR2 (AUC = 0.892) and IDH1 status (AUC = 0.819), outperforming the pure clinical and radiomic models. The radiomic model for predicting KRAS mutations achieved an AUC = 0.767 (vs. 0.660 of the clinical model) without further improvements with the addition of clinical features. ConclusionsCT-based radiomics provides a reliable non-invasive prediction of ICC genetic status with a major impact on therapeutic strategies.

Development of the DONOR prediction model on the risk of hypertensive complications in oocyte donation pregnancy: study protocol for a multicentre cohort study in the Netherlands

IntroductionOocyte donation (OD) pregnancy is accompanied by a high incidence of hypertensive complications, with serious consequences for mother and child. Optimal care management, involving early recognition, optimisation of suitable treatment...