Discriminative Ability Research Articles

Clinical Utility and Diagnostic Accuracy of ROMA, RMI, ADNEX, HE4, and CA125 in the Prediction of Malignancy in Adnexal Masses

Objective: We aimed to compare the clinical utility and diagnostic accuracy of the ADNEX model, ROMA score, RMI I, and RMI IV, as well as two serum markers (CA125 and HE4) in preoperative discrimination between benign and malignant adnexal masses (AMs). Methods: We conducted a retrospective study extracting all consecutive patients with AMs seen at our Institution between January 2015 and December 2020. Accuracy metrics included sensitivity (SE), specificity (SP), and area under the receiver operating characteristic curve (AUC), and their 95% confidence intervals (CI) were calculated for basic discrimination between AMs. Model performance was evaluated in terms of discrimination ability and clinical utility (net benefit, NB). Results: A total of 581 women were included; 481 (82.8%) had a benign ovarian tumor and 100 (17.2%) had a malignant tumor. The SE and SP of CA125, HE4, ROMA score, RMI I, RMI IV, and ADNEX model were 0.60 (0.54–0.66) and 0.80 (0.76–0.83); 0.39 (0.30–0.49) and 0.96 (0.94–0.98); 0.59 (0.50–0.68) and 0.92 (0.88–0.95); 0.56 (0.46–0.65) and 0.98 (0.96–0.99); 0.54 (0.44–0.63) and 0.96 (0.94–0.98); 0.82 (0.73–0.88) and 0.91 (0.89–0.94), respectively. The overall AUC was 0.76 (0.74–0.79) for CA125, 0.81 (0.78–0.83) for HE4, 0.82 (0.80–0.85) for ROMA, 0.86 (0.84–0.88) for RMI I, 0.83 (0.81–0.86) for RMI IV, and 0.92 (0.90–0.94) for ADNEX. The NB for ADNEX was higher than other biomarkers and models across all decision thresholds between 5% and 50%. Conclusions: The ADNEX model showed a better discrimination ability and clinical utility when differentiating malignant from benign Ams, compared to CA125, HE4, ROMA score, RMI I, and RMI IV.

Development and validation of a nomogram for predicting the risk of developing gastric cancer based on a questionnaire: a cross–sectional study

BackgroundDetection of gastric cancer (GC) at early stages is an effective strategy for decreasing mortality. This study aimed to construct a prediction nomogram based on a questionnaire to assess the risk of developing GC.MethodsOur study comprised a total of 4379 participants (2326 participants from outpatient at Fengqing People’s Hospital were considered for model development and internal validation, and 2053 participants from outpatients at the endoscopy center at the Seventh Affiliated Hospital of Sun Yat-Sen University were considered for independent external validation) and gastric mucosa status was determined by endoscopy and biopsies. The eligible participants in development cohort from Fengqing people’s Hospital were randomly separated into a training cohort (n=1629, 70.0%) and an internal validation cohort (n=697, 30.0%). The relevant features were selected by a least absolute shrinkage and selection operator (LASSO), and the ensuing features were evaluated through multivariable logistic regression analysis. Subsequently, the variables were selected to construct a prediction nomogram. The discriminative ability and predictive accuracy of the nomogram were evaluated by the C-index and calibration plot, respectively. Decision curve analysis (DCA) curves were used for the assessment of clinical benefit of the model. This model was developed to estimate the risk of developing neoplastic lesions according to the “transparent reporting of a multivariable prediction model for individual prognosis or diagnosis” (TRIPOD) statement.ResultsSix variables, including age, sex, alcohol consumption, cigarette smoking, education level, and Hp infection status, were independent risk factors for the development of neoplastic lesions. Thus, these variables were incorporated into the final nomogram. The AUC of the nomogram were 0.701, 0.657 and 0.699 in the training, internal validation, and external validation cohorts, respectively. The calibration curve showed that the nomogram was in good agreement with the observed outcomes. Compared to treatment of all patients or none, our nomogram showed a notably higher clinical benefit.ConclusionThis nomogram proved to be a convenient, cost-effective tool to effectively predict an individual’s risk of developing neoplastic lesions, and it can act as a prescreening tool before gastroscopy.

NIMG-17. PREDICTIVE VALUE OF THE BRAIN TUMOR REPORTING AND DATA SYSTEM SCORE (BT-RADS) ON FUNCTIONAL OUTCOMES AND PROGRESSION-FREE SURVIVAL IN GLIOBLASTOMA PATIENTS

Abstract The Brain Tumor Reporting and Data System Score (BT-RADS) is a novel eight-point classification system that standardizes magnetic resonance imaging (MRI) reporting in glioblastoma (GB) patients. While previous studies have demonstrated BT-RADS predictive value in the prognosis and overall survival of high-grade glioma patients, its association with functional outcomes and progression-free survival (PFS) in GB patients is unclear. We aim to evaluate the BT-RADS predictive value on functional outcomes assessed through the Karnofsky Performance Scale (KPS) at one year post-diagnosis and on PFS. BT-RADS from MRI ~3 months post-diagnosis after chemo-radiation therapy (BT-RADS_1), and ~6 months post-diagnosis after the 6-month maintenance temozolomide (TMZ) cycle (BT-RADS_2) were analyzed. BT-RADS was classified as low (BT-RADS score 0-3a) and high (BT-RADS score 3b-4). In a univariate logistic regression analysis, BT-RADS_1 was a significant predictor (p=0.04) in discriminating an unfavorable KPS from a favorable one. In a multivariate logistic regression, in which the best model fit was the model containing BT-RADS_1 and MGMT tumor status (model p value=0.03), the ROC analyses indicate that BT-RADS_1 is not better than chance in differentiating an unfavorable KPS from a favorable one (model AUC=0.65; 95% CI=0.55, 0.76). The discriminatory ability of BT-RADS scores alone in predicting KPS outcomes was modest, as indicated by the AUC. This underscores the need for larger sample sizes. In a final model of BTRADS_1 and BT-RADS_2, accounting for MGMT tumor status, the risk of tumor progression was 50% lower (p value=0.003) with a low BT-RADS (0-3a) in the BT-RADS _1 group and 38% lower (p value=0.03) with a low BT-RADS (0-3a) in the BT-RADS_2 group. Considering the above-discussed findings, BT-RADS may represent a new tool in the clinical management of glioblastoma patients by informing on disease progression, prognosis, and quality of life.

Predicting first-line VEGFR-TKI resistance and survival in metastatic clear cell renal cell carcinoma using a clinical-radiomic nomogram.

This study aims to construct predicting models using radiomic and clinical features in predicting first-line vascular endothelial growth factor receptor-tyrosine kinase inhibitor (VEGFR-TKI) early resistance in metastatic clear cell renal cell carcinoma (mccRCC) patients. We also aim to explore the correlation of predicting models with short and long-term survival of mccRCC patients. In this retrospective study, 110 mccRCC patients from 2009 to 2019 were included and assigned into training and test sets. Radiomic features were extracted from tumor 3D-ROI of baseline enhanced CT images. Radiomic features were selected by Lasso method to construct a radiomic score. A combined nomogram was established using the combination of radiomic score and clinical factors. The discriminative abilities of the radiomic, clinical and combined nomogram were quantified using ROC curve. Cox regression analysis was used to test the correlation of nomogram score with progression-free survival (PFS) and overall survival (OS). PFS and OS were compared between different risk groups by log-rank test. The radiomic, clinical and combined nomogram demonstrated AUCs of 0.81, 0.75, and 0.83 in training set; 0.79, 0.77, and 0.88 in test set. Nomogram score ≥ 1.18 was an independent prognostic factor of PFS (HR 0.22 (0.10, 0.47), p < 0.001) and OS (HR 0.38 (0.20, 0.71), p = 0.002), in training set. PFS in low-risk group were significantly longer than high-risk group in training (p < 0.001) and test (p < 0.001) set, respectively. OS in low-risk group were significantly longer than high-risk group in training (p = 0.003) and test (p = 0.009) set, respectively. A nomogram combining baseline radiomic signature and clinical factors helped detecting first-line VEGFR-TKI early resistance and predicting short and long-term prognosis in mccRCC patients.

Multimodal neuroimaging-based prediction of Parkinson's disease with mild cognitive impairment using machine learning technique.

This study aimed to identify potential markers that can predict Parkinson's disease with mild cognitive impairment (PDMCI). We retrospectively collected general demographic data, clinically relevant scales, plasma samples, and neuroimaging data (T1-weighted magnetic resonance imaging (MRI) data as well as resting-state functional MRI [Rs-fMRI] data) from 173 individuals. Subsequently, based on the aforementioned multimodal indices, a support vector machine was employed to investigate the machine learning (ML) classification of PD patients with normal cognition (PDNC) and PDMCI. The performance of 29 classifiers was assessed based on various combinations of indicators. Results demonstrated that the optimal classifier in the validation set was composed by clinical + Rs-fMRI+ neurofilament light chain, exhibiting a mean Accuracy of 0.762, a mean area under curve of 0.840, a mean sensitivity of 0.745, along with a mean specificity of 0.783. The ML algorithm based on multimodal data demonstrated enhanced discriminative ability between PDNC and PDMCI patients.

The Risk Assessment Before Dose Tapering Among Methadone Maintenance Treatment Participants: Derivation and Validation of a Nomogram

ABSTRACT Many methadone maintenance treatment (MMT) participants experienced a tapering phase. The benefit of tapering is based on a balance between meeting the desire to reduce methadone dose and reduction in relapse. We aimed to develop and validate a nomogram to assess relapse risk after dose tapering. We developed and internally validated a nomogram for risk assessment before dose tapering in 432 participants with dose tapering in the non-Guangzhou region of Guangdong, China, and externally validated it in 117 participants with dose tapering in Guangzhou. Cox regression analysis showed that the taper start week (HR = 0.14, [0.08–0.22]) was an independent risk predictor of the relapse risk after tapering. The C-index of the nomogram was 0.76 (95%CI: 0.73–0.79) in the training cohort, 0.76 (95%CI: 0.72–0.80) in the testing cohort, and 0.84 (95%CI: 0.80–0.88) in the validation cohort. Decision curve analysis showed that the nomogram had better discriminative ability than other predictors. The nomogram was developed to assess the risk of relapse for MMT participants who volunteer a tapering phase and may help participants better make decisions about whether and how to reduce the dose to minimize the harm of relapse.

Attenuated Total Reflection Fourier Transform Infrared Spectroscopy and Chemometrics for the Discrimination of Animal Hair Fibers for the Textile Sector.

Analyzing the composition of animal hair fibers in textiles is crucial for ensuring the quality of yarns and fabrics made from animal hair. Among others, Fourier transform infrared (FT-IR) spectroscopy is a technique that identifies vibrations associated with chemical bonds, including those found in amino acid groups. Cashmere, mohair, yak, camel, alpaca, vicuña, llama, and sheep hair fibers were analyzed via attenuated total reflection FT-IR (ATR FT-IR) spectroscopy and scanning electron microscopy techniques aiming at the discrimination among them to identify possible commercial frauds. ATR FT-IR, being a novel approach, was coupled with chemometric tools (partial least squares discriminant analysis, PLS-DA), building classification/prediction models, which were cross-validated. PLS-DA models provided an excellent differentiation among animal hair of both camelids and eight animal species. In addition, the combination of ATR FT-IR and PLS-DA was used to discriminate the cashmere hair from different origins (Afghanistan, Australia, China, Iran, and Mongolia). The model showed very good discrimination ability (accuracy 87%), with variance expression of 94.88% and mean squared error of cross-validation of 0.1525.

Urinary interferon-γ-induced protein-10/creatinine ratio as a predictor of severe paediatric infections: A prospective pilot study.

This prospective pilot study evaluated urinary interferon-γ-induced protein-10 (IP-10)/creatinine and tumour necrosis factor-related apoptosis-inducing ligand (TRAIL)/creatinine ratios as non-invasive biomarkers for distinguishing bacterial from viral infections and assessing disease severity in febrile children. The study involved 85 febrile children and 29 healthy controls, measuring urinary IP-10/creatinine and TRAIL/creatinine ratios to determine their diagnostic utility. Both ratios were significantly elevated in infected patients compared to controls. The IP-10/creatinine ratio effectively assessed disease severity in the overall cohort and subgroups (AUC: 0.7324, 0.7192, 0.7277; p < 0.05). Serum C-reactive protein showed limited discriminatory ability in viral infections (AUC = 0.5385, p = 0.7257). Differentiation between bacterial and viral infections using IP-10/creatinine approached significance (p = 0.082). No significant differences in biomarker levels were observed across pathogens. The urinary IP-10/creatinine ratio shows promise as a biomarker for assessing paediatric infection severity, particularly when traditional markers are less effective. Larger studies are needed to validate these results and improve its discriminatory accuracy in clinical practice.

Development of a nomogram for predicting pancreatic portal hypertension in patients with acute pancreatitis: a retrospective study

IntroductionPancreatic portal hypertension (PPH) is a rare complication of acute pancreatitis (AP) that can lead to severe gastrointestinal bleeding. The risk factors associated with PPH, as well as the overall...

NT-proBNP improves prediction of cardiorenal complications in type 2 diabetes: the Hong Kong Diabetes Biobank.

N-terminal pro B-type natriuretic peptide (NT-proBNP) is a natriuretic peptide that is strongly associated with congestive heart failure (CHF). The utility of NT-proBNP for prediction of cardiovascular events and renal endpoints, compared with clinical risk factors, has not been evaluated in detail. We hypothesise that NT-proBNP can improve risk stratification and prediction of cardiorenal events in type 2 diabetes, beyond that provided by clinical risk factors. NT-proBNP was measured in 1993 samples from the Hong Kong Diabetes Biobank, a multicentre prospective diabetes cohort and biobank. A cut-off of ≥125 pg/ml was used to define elevated NT-proBNP. Associations between elevated NT-proBNP and incident cardiovascular and renal endpoints were examined using Cox regression, adjusted for sex, age and duration of diabetes, as well as other covariates. Prognostic and incremental predictive values of NT-proBNP in diabetes cardiorenal complications, compared with those of the Joint Asia Diabetes Evaluation risk equations for CHD, CHF and kidney failure, were evaluated using the concordance index (C index), net reclassification improvement index, integrated discrimination improvement index and relative integrated discrimination improvement index. A total of 24.7% of participants had elevated NT-proBNP. Participants with elevated NT-proBNP at baseline had a more adverse cardiometabolic profile, with 2-4-fold higher frequency of complications at baseline. Adjusting for age at baseline, sex and duration of diabetes, elevated NT-proBNP was associated with incident atrial fibrillation (HR 4.64 [95% CI 2.44, 8.85]), CHD (HR 4.21 [2.46, 7.21]), CVD (HR 3.32 [2.20, 5.01]) and CHF (HR 4.18 [2.18, 8.03]; all p<0.001). All these associations remained significant after further adjustment for additional covariates. Elevated NT-proBNP had good discriminative ability for various cardiorenal endpoints, with C index of 0.83 (95% CI 0.76, 0.90) for CHD, 0.88 (0.81, 0.94) for atrial fibrillation, 0.89 (0.83, 0.95) for CHF, 0.81 (0.77, 0.84) for 40% drop in eGFR and 0.88 (0.84, 0.92) for kidney failure. Models incorporating NT-proBNP had improved prediction compared with established clinical risk models. Sensitivity analyses including alternative cut-off of NT-proBNP, as well as use of other risk engines of CHD, yielded similar results. NT-proBNP demonstrated a promising ability to serve as a prognostic marker for a variety of cardiorenal complications in type 2 diabetes. Considering NT-proBNP in clinical assessments could potentially help identify high-risk individuals who may benefit from more intensive therapies.

Diagnostic Performance of a Newly-Launched Canadian Fast-Track Ultrasound Clinic by Rheumatologists for the Diagnosis of Giant Cell Arteritis.

Giant Cell Arteritis (GCA) can present diagnostic challenges and early diagnosis is crucial due to potential ischemic complications. Recent guidelines suggest that a suspected diagnosis should be confirmed with temporal artery biopsy or imaging, including ultrasound (US). In our Canadian setting, point-of-care temporal artery US was near unavailable, and biopsy remains the standard of care. We hypothesize that launching a fast-track US clinic by rheumatologists may spare the need for a temporal artery biopsy. Therefore, this study aimed to assess the diagnostic performance of US in this newly-launched fast-track clinic. In this single-center retrospective cross-sectional analysis, 99 visits were identified from the fast-track clinic between January 2020 and July 2022. Each subject had an US according to a standard protocol for suspicion of either new-onset or relapse of GCA. Ultrasonographers were rheumatologists who acquired training on vascular US techniques before launching the clinic. For each patient presenting with suspected new-onset GCA, the pre-test probability was calculated using the Southend GCA probability score. The sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) were calculated using the rheumatologist clinical diagnosis as the gold standard for GCA diagnosis. A total of 22 subjects had a diagnostic of GCA and 77 had another diagnostic. Patients with and without GCA were, respectively, 81.8% vs 72.7% females, had a mean age of 76.6 ± 7.7 vs. 74.8 ± 9.8 years and a mean CRP of 73.4 ± 57.8 vs 38.3 ± 59.9 mg/L. Temporal artery US demonstrated a a sensitivity of 86.3% [95% confidence interval (CI), 65.1%-97.1%], a specificity of 90.9% (95% CI, 82.2%-96.3%), a PPV of 73.1% (95% CI, 56.8%-84.9%) and a NPV of 95.9% (95% CI, 89.0%-98.5%). 14 patients had a suspicion of relapse and were all correctly identified by the US. Among those with suspicion of new-onset 27, 34 and 24 US were performed for high, intermediate, and low pretest probability of GCA, respectively. The high-risk subgroup demonstrated higher PPV while similar sensitivity/specificity were observed between all three subgroups. Our results highlights the benefits of US as a key diagnostic tool for GCA, particularly when combined with clinical evaluations. An excellent discriminative ability for diagnosis of GCA was shown in this newly-launched clinic suggesting that the role of TAB may need to be redefined. These findings will guide on broader implementation of US programs for GCA.

Patient-centred composite scores as tools for assesment of response to biological therapy for paediatric and adult severe asthma.

We have previously developed Core Outcome Measures sets for Severe Asthma (COMSA) by multi-stakeholder consensus. There are no patient-centred tools to quantify response to biologics for severe asthma. We aimed to develop paediatric and adult CompOsite iNdexes For Response in asthMa (CONFiRM) incorporating clinical parameters and patient-reported quality of life (QoL). International expert healthcare professionals (HCPs) and patients with severe asthma were invited to: 1) develop consensus levels of clinically relevant changes for each outcome measure within COMSA; 2) use multicriteria decision analysis to develop the CONFiRM scores and 3) assess their internal validity. A separate group of HCPs evaluated CONFiRM's external validity. Five levels of change for each COMSA outcome were agreed. Severe exacerbations and maintenance oral corticosteroids use were rated as most important in determining both paediatric and adult CONFiRM scores. There was strong agreement between HCPs and patients, although patients assigned greater importance to QoL. The CONFiRM score quantified response to a biological from -31 (deterioration) to 69 (best possible response). Paediatric and adult CONFiRMs had good discriminative ability for a sufficient (AUC≥0.92) and a substantial (AUC≥0.95) response to biologics. Both CONFiRMs demonstrated excellent external validity (Spearman correlation coefficients 0.9 and 0.8 for paediatric and adult respectively (p<0.0001)). We have developed novel patient-centred paediatric and adult CONFiRMs which include QoL measures. CONFiRMs should allow a more holistic understanding of response for the patient and a standardised assessment of the effectiveness of biologics between studies. Further research is needed to prospectively validate CONFiRM scores.

Societal costs of older adults with low back pain seeking chiropractic care: findings from the BACE-C cohort study

BackgroundTo describe the societal costs during one year of follow-up among older adults seeking chiropractic care due to a new episode of low back pain (LBP), and to determine what factors predict high societal costs in this population.MethodsProspective cohort study, within chiropractic private practices (n = 38) in the Netherlands. 223 people ≥ 55 years of age with a new episode of LBP seeking chiropractic care participated. The primary outcome was total societal costs. High societal costs were defined as patients with costs in the top 20th percentile. The final prediction models were obtained using forward selection. Results were presented for the total population and stratified for retirement status. The model’s prognostic accuracy (Hosmer–Lemeshow X2, Nagelkerke’s R2) and discriminative ability [area under the receiver operating curve (AUC)] were assessed, and the models were internally validated using bootstrapping.ResultsThe mean total annual societal cost per patient was €5297 [95% confidence interval (CI): 4191–6403]. The biggest cost driver was presenteeism (65% of total costs), and costs were higher among non-retired participants (€7759; 95% CI 6047–9470) than retired participants (€1892; 95% CI 1088–2695). In the total population, younger age [odds ratio (OR): 0.87 for each additional year; 95% CI 0.80–0.95], being male instead of female (OR 2.96; 95% CI 1.19–7.44), less alcohol intake (OR 0.49; 95% CI 0.20–1.19), working instead of retirement (OR 9.37; 95% CI 1.83–48.04), and more disability at baseline (OR 1.08; 95% CI 1.00–1.16) were found to be predictive of high societal costs. Working was found to be the strongest predictor for high societal costs. After internal validation, the model’s fit was good, it’s explained variance was moderate (28%) and their AUCs could be interpreted as moderate (0.85). For non-pensioners, the same predictive factors were identified as for the entire population. The costs for the retired participants showed too little variation to be able to predict high costs.ConclusionsThis study estimated the mean total annual societal cost of older adults seeking chiropractic care due to a new episode of LBP at €5297 (95% CI 4191–6403).These costs were mainly due to high levels of presenteeism, and extensively differed based upon work status.

Research on gut microbiota characteristics of PBC patients at different ALBI grades based on machine learning

BackgroundThe Albumin-Bilirubin (ALBI) score and grade are widely used to stratify patients with primary biliary cholangitis (PBC) into different disease statuses and risk levels. Recent studies have increasingly highlighted the role of gut microbiota in autoimmune liver diseases. This study aimed to investigate the differences in gut microbiota among PBC patients with varying ALBI grades.MethodsClinical data and stool samples were collected from outpatient and inpatient PBC patients between 2019 and 2022. Gut microbiota profiles were obtained using 16S rDNA sequencing of stool samples. We analyzed alpha diversity, beta diversity, LEfSe analysis and pathway function prediction. Additionally, various machine learning methods—including random forest (RF), lasso, gradient boosting machine (GBM) and support vector machine (SVM)—were employed to identify key features and to build and validate predictive models using bootstrap techniques.ResultsClinical characteristics of ALBI grade 1 patients were comparatively better than those of ALBI grade 2 and 3 patients, including multiple laboratory indices. Gut microbiota analysis revealed that species richness and balance were higher in ALBI grade 1 patients. Both the comparison of the most abundant genera and the linear discriminant analysis (LDA) in LEfSe demonstrated that Lachnospira had a higher abundance and better discriminative ability in ALBI grade 1. Pathway function prediction indicated that sulfur metabolism was upregulated in higher ALBI grades. Furthermore, RF identified 10 specific genera, which were then used to build and validate models for discriminating PBC patients according to their ALBI grades. All three models, developed using different machine learning methods, demonstrated good discrimination ability (mean AUC 0.75–0.80).ConclusionThis study highlights significant differences in gut microbiota profiles among PBC patients with different ALBI grades. The increased abundance of Lachnospira and upregulation of sulfur metabolism pathways are notable in patients with lower ALBI grades. The machine learning models developed based on gut microbiota features offer promising tools for discriminating between PBC patients with varying disease severities, which could enhance the precision of treatment strategies.

Predictive modeling of preoperative acute heart failure in older adults with hypertension: a dual perspective of SHAP values and interaction analysis

BackgroundIn older adults with hypertension, hip fractures accompanied by preoperative acute heart failure significantly elevate surgical risks and adverse outcomes, necessitating timely identification and management to improve patient outcomes.Research objectiveThis study aims to enhance the early recognition of acute heart failure in older hypertensive adults prior to hip fracture surgery by developing a predictive model using logistic regression (LR) and machine learning methods, optimizing preoperative assessment and management.MethodsEmploying a retrospective study design, we analyzed hypertensive older adults who underwent hip fracture surgery at Hebei Medical University Third Hospital from January 2018 to December 2022. Predictive models were constructed using LASSO regression and multivariable logistic regression, evaluated via nomogram charts. Five additional machine learning methods were utilized, with variable importance assessed using SHAP values and the impact of key variables evaluated through multivariate correlation analysis and interaction effects.ResultsThe study included 1,370 patients. LASSO regression selected 18 key variables, including sex, age, coronary heart disease, pulmonary infection, ventricular arrhythmias, acute myocardial infarction, and anemia. The logistic regression model demonstrated robust performance with an AUC of 0.753. Although other models outperformed it in sensitivity and F1 score, logistic regression’s discriminative ability was significant for clinical decision-making. The Gradient Boosting Machine model, notable for a sensitivity of 95.2%, indicated substantial capability in identifying patients at risk, crucial for reducing missed diagnoses.ConclusionWe developed and compared efficacy of predictive models using logistic regression and machine learning, interpreting them with SHAP values and analyzing key variable interactions. This offers a scientific basis for assessing preoperative heart failure risk in older adults with hypertension and hip fractures, providing significant guidance for individualized treatment strategies and underscoring the value of applying machine learning in clinical settings.

Analysis of risk factors and establishment of early warning model for recent postoperative complications of colorectal cancer

ObjectiveThis study aimed to analyze factors associated with recent complications after colorectal cancer surgery, constructing a nomogram to aid gastrointestinal surgeons in preoperative decision-making for patients at risk of such complications.MethodsIn this retrospective study, clinical data were collected from patients undergoing radical colorectal cancer surgery at the Department of Gastrointestinal Surgery of the Affiliated Cancer Hospital of Guizhou Medical University and the Second People’s Hospital of Chengdu from November 1, 2021, to January 26, 2024. Univariable and multivariable logistic regression analyses were conducted to assess risk factors for recent postoperative complications and develop a prediction model. External validation was performed using data from 48 postoperative colorectal cancer patients in the Second People’s Hospital of Chengdu City from January 1, 2023, to May 30, 2023. Evaluation included receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis using R4.2.2 statistical software.ResultsA total of 324 patients who underwent radical colorectal cancer surgery were enrolled. The training cohort (n=176) identified four independent risk factors for recent complications: PNI ≥45 (OR=4.17, P&amp;lt;0.001), Albumin &amp;lt;40 g/L (OR=3.9, P&amp;lt;0.001), ASA score III-IV (OR=6.29, P&amp;lt;0.001), and Tumor diameter ≥5 cm (OR=4.24, P&amp;lt;0.001). A nomogram was constructed incorporating these factors. The AUC of the nomogram model in the training cohort was 0.835, with subsequent internal and external validation cohort AUCs of 0.815 and 0.819, respectively, indicating strong discriminatory ability. The calibration curve demonstrated good consistency, and decision curve analysis indicated high clinical utility.ConclusionPNI ≥45, Albumin &amp;lt;40 g/L, ASA score III-IV, and Tumor diameter ≥5 cm emerged as independent risk factors for recent complications following colorectal cancer surgery. We developed a nomogram model for these complications, potentially aiding gastrointestinal surgeons in preoperative patient evaluation and treatment planning for colorectal cancer surgery.

Development and validation of a risk prediction model for postpartum urinary incontinence in primiparas with singleton pregnancies: a multicenter clinical investigation

BackgroundPostpartum urinary incontinence (UI) is a serious condition that significantly affects the quality of life. Several studies have demonstrated that it is associated with pelvic floor dysfunction. This study aimed to develop and validate a UI risk prediction model to identify primiparas with singleton pregnancies at high risk.MethodsA multistage stratified random sampling process was used. UI was measured using the International Standard Consultation on Incontinence Questionnaire Form (a modified Bristol questionnaire, ICIQ-FLUTS). Records of 1,340 primiparas with singleton pregnancies were reviewed, and data were collected from January 2014 to December 2014 in multiple centers. A univariate logistic regression analysis was performed, followed by a multivariable logistic regression analysis of the data. Using bootstrap resampling, we constructed a nomogram to assess postpartum UI risk.ResultsA total of 1,340 patients were enrolled, including 345 with postpartum UI and 995 with non-postpartum UI. The occurrence of postpartum UI was significantly related to the mode of delivery, family history of UI, coffee or tea consumption, antenatal UI, and frequent cough. The nomogram exhibited good discriminatory ability with a C-index of 0.718 (95% confidence interval: 0.684–0.752) and a bootstrap-corrected C-index of 0.716. Additionally, the calibration curve demonstrated that the predicted outcomes aligned well with the actual observations. Ultimately, the decision curve analysis indicated that the nomogram exhibited favorable clinical applicability.ConclusionThe decision curve analysis suggests that the nomogram could provide clinical value. The clinician will then feel more confident about making clinical recommendations regarding postpartum UI screening for primiparous women with singleton pregnancies.

Persistent Airflow Limitation Prediction and Risk Factor Analysis Among Asthmatic Children: A Retrospective Cohort Study.

A minority of asthmatic children develop persistent airflow limitation (PAL), associated with an increased risk of chronic airflow obstruction and poor prognosis. This study aimed to identify risk factors for PAL and develop a prediction model to identify high-risk asthmatic children. This retrospective study included 2072 children (5-16 years) with asthma. After a 2-year follow-up, patients were categorized into non-PAL, reversible PAL (RPAL), and irreversible PAL (IPAL) groups. Logistic regression (LR) was used to identify independent risk factors for RPAL and IPAL. A prediction model based on multivariate LR was developed and validated to identify asthmatic children at high risk of developing PAL. A nomogram was created for visualization. Among the 2072 asthmatic patients, 14.72% (n = 305) developed PAL. Asthma exacerbation history (OR 1.80, 95% CI 1.03-3.01) and poor adherence (OR 1.83, 95% CI 1.26-2.65) were independent risk factors of RPAL. Independent risk factors for IPAL were BMI over 19.0 kg/m2 (OR: 1.81, 95% CI: 1.03-3.21) and a history of pneumonia (OR: 2.40, 95% CI: 1.30-4.26). The prediction model incorporated nine variables and showed good discriminatory ability, with AUC values of 0.79 (95% CI: 0.76-0.81) for the training set, 0.76 (95% CI: 0.76-0.77) for internal validation, and 0.73 (95% CI: 0.64-0.81) for temporal validation. Asthma exacerbation history and poor adherence were independent risk factors for developing RPAL. BMI over 19.0 kg/m2 and a history of pneumonia were risk factors for IPAL. Our prediction model effectively identified asthmatic children at high risk of developing PAL.

Urine lipoarabinomannan concentrations among HIV-negative adults with pulmonary or extrapulmonary tuberculosis disease in Vietnam.

Lipoarabinomannan (LAM) is a promising target biomarker for diagnosing subclinical and clinical tuberculosis (TB). Urine LAM (uLAM) testing using rapid diagnostic tests (RDTs) has been approved for people living with HIV (PLWH), however there is limited data regarding uLAM levels in HIV-negative (HIV-ve) adults with clinical TB. We conducted a clinical study of adults presenting with clinical TB-related symptoms at the National Lung Hospital in Hanoi, Vietnam. The uLAM concentrations were measured using electrochemiluminescent (ECL) immunoassays and compared to a microbiological reference standard (MRS) using GeneXpert Ultra and TB culture testing. Estimated uLAM concentrations above plate specific calculated limit of detection (LOD) were considered uLAM positive. Additional microbiological testing was conducted for possible extrapulmonary TB (EPTB). Among 745 participants enrolled, 335 (44.9%) participants with presumptive pulmonary TB (PTB) and 6 (11.3%) participants with presumptive EPTB had confirmed TB disease. Overall, the S/A antibody pair had a sensitivity of 39% (95% Confidence Interval [CI] 0.33, 0.44) and a specificity of 97% (95% CI 0.96, 0.99) compared to the MRS. The F/A antibody pair had a sensitivity of 41% (95% CI 0.35, 0.47) and a specificity of 79% (95% CI 0.75, 0.84). S/A provided greater discriminatory ability compared to F/A for both individuals with presumptive PTB (AUROC: 0.74 vs 0.63, p<0.0001) and presumptive EPTB (0.76 vs 0.54, p = 0.045) when using the MRS. Among HIV-ve participants in an adult cohort in Vietnam, the concentrations of uLAM remained relatively low for people with clinical TB, which may present challenges for improving RDT sensitivity.

Potential biomarkers in Behçet’s disease: monocyte, neutrophil, platelet, and C-reactive protein to albumin ratios

IntroductionThe objective of this cross-sectional study was to evaluate the monocyte to albumin ratio (MAR), neutrophil to albumin ratio (NAR), platelet to albumin ratio (PAR), and C-reactive protein to albumin ratio (CAR) as potential biomarkers for disease activity in patients with Behçet’s disease (BD).Material and methodsBoth BD cases and healthy controls were enrolled in this study. Demographic characteristics, disease duration, and current medications were recorded for all participants. The BD Current Activity Form (BDCAF) was utilized to assess the activity of BD. Additionally, ery­throcyte sedi­mentation rate, CRP, and serum albumin levels were measured. The MAR, NAR, PAR, and CAR were compared between the two groups. Correlation analysis and receiver operating characteristic curves (ROC) were employed to establish cut-off points for these biomarkers.ResultsIn the study, both BD cases and 45 controls were included, totaling 90 participants. Significant differences were observed in the mean ±SD values of ESR, MAR, PAR, CAR, and albumin between the BD cases and controls (&lt;i&gt;p&lt;/i&gt; = 0.008, &lt;i&gt;p&lt;/i&gt; = 0.009, &lt;i&gt;p&lt;/i&gt; = 0.029, &lt;i&gt;p&lt;/i&gt; = 0.034, &lt;i&gt;p&lt;/i&gt; = 0.006, respectively). However, despite these differences, no significant correlation was detected between BDCAF and the parameters under investigation. The cutoff point was determined as 150.59 (sensitivity 46.67%, specificity 82.22%, &lt;i&gt;p&lt;/i&gt; = 0.008, AUC = 0.655) for MAR; as 62,013.73 (sensitivity 60.00%, specificity 66.67%, &lt;i&gt;p&lt;/i&gt; = 0.03, AUC = 0.629) for PAR; and as 1.16 (sensitivity 35.56%, specificity of 95.567%, &lt;i&gt;p&lt;/i&gt; = 0.03, AUC = 0.629) for CAR. The results were not able to define any cut-off points for active-inactive BD.ConclusionsSignificantly higher levels of MAR, PAR, and CAR were observed in patients with BD than controls. Monocyte to albumin ratio, PAR, and CAR were notably elevated in patients with active BD. This finding suggests that these parameters possess discriminative ability and could potentially serve as biomarkers to aid in the clinical evaluation of BD.