Net Clinical Benefit Research Articles

Edoxaban dose, frailty, and outcomes in patients with atrial fibrillation: the ETNA-AF-Europe 4-year follow-up

Abstract Background Frailty is a common reason to choose non-recommended (non-rec) doses of non-vitamin-K-antagonist oral anticoagulants in patients with atrial fibrillation (AF); however, it is not known how this practice affects stroke and bleeding outcomes. Purpose To assess clinical outcomes in frail patients with AF receiving non-rec vs recommended (rec) doses of edoxaban using 4-yr follow-up data from ETNA-AF-Europe. Methods The prospective, observational ETNA-AF-Europe study followed patients with AF receiving edoxaban for up to 4 yrs. In ETNA-AF-Europe, perceived frailty was based on investigators’ own clinical binary judgement in each patient. Objective frailty was determined using a simplified adaptation of the Rockwood’s Frailty Index. For objective frailty, patients with missing index were categorised as non-frail. Patients with perceived or objective frailty were combined for this analysis. Baseline characteristics and hazard ratios (HRs) with 95% confidence intervals (CIs) assessing risk of outcomes in frail patients prescribed non-rec vs rec edoxaban doses (i.e., non-rec 60mg vs rec 30mg and non-rec 30mg vs rec 60mg) are presented. Data were adjusted for age, sex, and derived versions of the CHA2DS2-VASc and HAS-BLED scores. Net clinical benefit was defined as any stroke/systemic embolic event (SEE), transient ischaemic attack, venous thromboembolic event, major bleeding, or cardiovascular death, whichever came first. Results Of 13164 patients, 1786 were frail (13.6%; perceived frailty [n=1410], age [IQR]: 82.0 [78.0-86.0] yrs, women: 57.9%; objective frailty [n=540], age [IQR]: 77.0 [71.0-82.0] yrs, women: 31.9%; both, n=164). Baseline characteristics are reported in Table 1. Risk of all-cause death was higher in frail patients treated with non-rec 30mg vs rec 60mg (HR [95% CI]: 1.44 [1.06,1.96]). The annualised rate [CI] of any stroke/SEE was non-significantly higher (HR [95% CI]:1.60 [0.80,3.20]) with non-rec 30mg (n=169; 2.25 [1.25,4.06]) vs rec 60mg (n=622; 1.54 [1.08,2.20]). There was, however, no association between treatment received and risk (HR [95% CI]) of major bleeding (1.19 [0.58,2.43]) or net clinical benefit (1.26 [0.84,1.87]) (Figure 1). In frail patients who received non-rec 60mg (n=183) vs rec 30mg (n=695), risk of any stroke/SEE (HR [95% CI]) was higher (2.15 [1.03,4.49]), but there were no significant differences in the risk (HR [95% CI]) of major bleeding (1.03 [0.52,2.01]), net clinical benefit (1.15 [0.78,1.71]), or all-cause death (0.79 [0.59,1.05]) (Figure 1). Conclusions In this large European AF registry, the presence of frailty should not drive dosing recommendations for edoxaban. In particular, when compared with the rec 60mg dose, the non-rec 30mg (reduced) dose, was associated with more all-cause death and no benefits on major bleeding.Baseline Characteristics

Radiomics-based multimodality prediction of left atrial appendage thrombus using coronary computed tomography angiography

Abstract Background Timely detection of thrombus in the left atrial appendage (LAA) may help guide decision-making. However, existing models have challenges in extracting comprehensive image information. It has been shown that radiomics-based prediction models can be used for accurate identification. This study investigates potential radiomic markers and constructs a highly efficient multimodality prediction model for LAA thrombus in patients undergoing coronary computed tomography angiography (CCTA). Methods We retrospectively enrolled patients with nonvalvular atrial fibrillation (NVAF) who underwent CCTA and transesophageal echocardiography (TEE) from May 2015 to May 2020. These patients were classified into thrombus or non-thrombus groups based on TEE findings. The data were balanced by resampling and assigned to training or test sets. Radiomics was conducted on the extracted features, and a random forest algorithm was employed for feature selection and importance ranking. We constructed different multimodality thrombus prediction models and compared their performance using the area under the receiver operating characteristic curve (AUC) and other efficacy parameters. Results Among 670 patients (60.17±10.98 years, 70.1% male), 5.2% (n=35) had LAA thrombi. A total of 1232 radiomics features were extracted, with 25 features selected using a random forest for modeling. Two radiomics features (Ibp_3D_m1_firstorder Skewness and original_shape_Flatness) ranked the highest. The radiomics-based multimodality prediction model achieved an AUC of 0.964 (95% confidence interval [CI]: 0.947-0.982), an accuracy of 0.926 (95% CI: 0.925-0.926), and an F1 score of 0.924, outperforming other traditional prediction models. Decision curve analysis also indicated that this model provided the best net clinical benefit. Conclusions Radiomics facilitates a comprehensive exploration of predictors associated with LAA thrombi. A radiomics-based multimodality prediction model can significantly enhance the efficiency of non-invasively detecting thrombi.Receiver operating characteristic curveDecision curve analysis

Optimal anticoagulant strategy for periprocedural management of atrial fibrillation ablation: a systematic review and network meta-analysis

Abstract Background This network meta-analysis was performed to rank the safety and efficacy of periprocedural anticoagulant strategies in patients undergoing atrial fibrillation ablation. Methods MEDLINE, EMBASE, CENTRAL, and Web of Science were searched to identify randomized controlled trials comparing anticoagulant regimens in patients undergoing atrial fibrillation ablation up to July 1, 2021. The primary efficacy and safety outcomes were thromboembolic and major bleeding events, respectively, and the net clinical benefit was investigated as the primary-outcome composite. Results Seventeen studies were included (n = 6950). The mean age ranged from 59 to 70 years; 74% of patients were men and 55% had paroxysmal atrial fibrillation. Compared with the uninterrupted vitamin-K antagonist strategy, the odds ratios for the composite of primary safety and efficacy outcomes were 0.61 (95%CI: 0.31–1.17) with uninterrupted direct oral anticoagulants, 0.63 (95%CI: 0.26–1.54) with interrupted direct oral anticoagulants, and 8.02 (95%CI: 2.35–27.45) with interrupted vitamin-K antagonists. Uninterrupted dabigatran significantly reduced the risk of the composite of primary safety and efficacy outcomes (odds ratio, 0.21; 95%CI, 0.08–0.55). Conclusion Uninterrupted direct oral anticoagulants are preferred alternatives to uninterrupted vitamin-K antagonists. Interrupted direct oral anticoagulants may be feasible as alternatives. Our results support the use of uninterrupted direct oral anticoagulants as the optimal periprocedural anticoagulant strategy for patients undergoing atrial fibrillation ablation.

Machine learning identification of risk factors for ischaemic stroke in patients with heart failure with reduced ejection fraction but without atrial fibrillation: A report from WARCEF trial

Abstract Background The prediction of ischaemic stroke in patients with heart failure with reduced ejection fraction (HFrEF) but without atrial fibrillation (AF) remains challenging and risk stratification based clinical factors alone has limited discrimination. Our aim was to evaluate the performance of machine learning (ML) to identify risk factors for ischaemic stroke in such HFrEF patients. Methods We performed a post-hoc analysis of the WARCEF trial, only including patients without prior history of AF, and censoring those who developed incident AF during follow-up. We evaluated the performance of 9 ML models to identify risk factors for incident stroke, using metrics including area under the curve (AUC), precision, specificity, and decision curve analysis. The importance of each feature in constructing the model was quantified using SHapley Additive exPlanations (SHAP) values. Results We included 2,213 patients with HFrEF but without AF (mean age 59±12 years; 79% male). Of these, 74 (3.3%) had an ischaemic stroke during mean follow-up of 3.5±1.8 years. Out of the 29 patient-demographics variables, 12 were selected for the ML training. All ML models demonstrated high AUC values, outperforming the CHA2DS2-VASc score (Figure 1). The logistic regression model exhibited a slight deviation from this trend. The XGBoost model achieved an AUC of 0.86 (95% confidence interval [CI]: 0.72-0.99), while the Random Forest model showed an AUC of 0.85 (95% CI: 0.74-0.96). Similarly, the Support Vector Machine and Light Gradient Boosting Machine models recorded AUCs of 0.85 (95% CI: 0.72-0.97) and 0.83 (95% CI: 0.70-0.96), respectively. Each of these models attained precision and specificity scores of 1.0, indicating high performance. These models consistently provided significant net clinical benefits. Key risk factors for stroke identified across these models were creatinine clearance and blood urea nitrogen. The use of warfarin appears to be protective. Conclusions Machine-learning models can identify risk factors for ischaemic stroke in patients with HFrEF but without AF. Worsening renal failure was predictive of an incident stroke, while warfarin use was protective against stroke (Figure 2).Figure 1Figure 2

Expression of cardiomyopathy-related genes in mononuclear blood cells predicts all-cause mortality in patients presenting with acute versus chronic coronary syndrome requiring revascularisation

Abstract Objective Despite advances in the revascularisation techniques their net clinical benefit differs substantially between patients presenting with myocardial infarction (ACS) and chronic coronary syndrome (CCS) due to obstructive coronary atherosclerosis. Considering that leukocytes represents a key pathophysiological component of myocardial ischaemia, exploration of mononuclear blood cell (PBMC) gene expression profile in CCS and ACS setting could reveal clinically relevant transcriptomic signals. The aim of the present study was to identify differences in PBMC transcriptome between ACS and CCS patients which are linked to mortality after revascularisation. Methods and Results We analysed PBMC transcriptomes from719 ACS and 486 CCS patients creating discovery cohort. The results of transcriptomic analysis were verified in replication cohort (ACS: N=682 for CCS: N=489) generated based on propensity score matching. Median time from revascularisation to blood collection (IQR) was 15.68 (-4.52, 23.23) hrs. Patients with ACS showed consistent differential expression of 8173 genes (4544 upregulated, 3629 downregulated) when compared with CCS patients. The subsequent pathway analysis also showed significant enrichment of several canonical pathways involved in major cardiovascular pathologies i.e. atherosclerosis (p = 1.22-06, enrichment = 3.39), vascular endothelial growth factor production (p = 1.16-06, enrichment = 16.73), positive regulation of vascular development (p = 2.78-06, enrichment = 5.30) and heterotopic cell adhesion including gene desmocollin 2 (DSC2, p = 3.64-04, enrichment = 6.30). In der multivariate survival analysis with differentially expressed genes, increased expression of DCS2, lamin A/C (LMNA), and UGGT2, and decreased expression of SNRNP70 predicted poor survival over the median follow-up 11.35 yrs. Consistently, controlling the false discovery rate at ≤ 5% these genes enriched pathways involved in cardiomyopathies such as arrhythmogenic right-ventricular cardiomyopathy (p = 4.19x10-4, enrichment = 58.9) and collagen disease (p = 2.29x10-3, enrichment = 23.8). Conclusion We found altered PBMC expression of multiple genes in patients requiring revascularisation for ACS versus CCS. Several differentially expressed genes included in cardiomyopathy pathways predicted long-term all-cause mortality in these patients.

Clinical-radiomics nomogram based on the fat-suppressed T2 sequence for differentiating luminal and non-luminal breast cancer

ObjectiveTo establish and validate a new clinical-radiomics nomogram based on the fat-suppressed T2 sequence for differentiating luminal and non-luminal breast cancer.MethodsA total of 593 breast cancer patients who underwent preoperative breast MRI from Jan 2017 to Dec 2020 were enrolled, which were randomly divided into the training (n=474) and test sets (n=119) at the ratio of 8:2. Intratumoral region (ITR) of interest were manually delineated, and peritumoral regions of 3 mm and 5 mm (PTR-3 mm and PTR-5 mm) were automatically obtained by dilating the ITR. Intratumoral and peritumoral radiomics features were extracted from the fat-suppressed T2-weighted images, including first-order statistical features, shape features, texture features, and filtered features. The Mann-Whitney U Test, Z score normalization, K-best method, and least absolute shrinkage and selection operator (LASSO) algorithm were applied to select key features to construct radscores based on ITR, PTR-3 mm, PTR-5 mm, ITR+PTR-3 mm and ITR+ PTR-5 mm. Risk factors were selected by univariate and multivariate logistic regressions and were used to construct a clinical model and a clinical-radiomics model that presented as a nomogram. The performance of models was assessed by sensitivity, specificity, accuracy, the area under the curve (AUC) of receiver operating characteristic (ROC), calibration curves, and decision curve analysis (DCA).ResultsITR+PTR-3 mm radsore and histological grade were selected as risk factors. A clinical-radiomics model was constructed by adding ITR+PTR-3mm radscore to the clinical factor, which was presented as a nomogram. The clinical-radiomics nomogram showed the highest AUC (0.873), sensitivity (72.3%), specificity (78.9%) and accuracy (77.0%) in the training set and the highest AUC (0.851), sensitivity (71.4%), specificity (79.8%) and accuracy (77.3%) in the test set. DCA showed that the clinical-radiomics nomogram had the greatest net clinical benefit compared to the other models.ConclusionThe clinical-radiomics nomogram showed promising clinical application value in differentiating luminal and non-luminal breast cancer.

Duration of Anticoagulation for Venous Thromboembolism in Pediatric Patients: Kids-DOTT Trial Outcomes at Two Years

The Kids-DOTT multinational randomized clinical trial (RCT) revealed non-inferiority of a six-week versus three-month duration of anticoagulation for the treatment of provoked venous thromboembolism (VTE) in patients <21 years old, in regard to net clinical benefit at one year. To evaluate non-inferiority at two years. Patients whose repeat imaging six weeks after VTE diagnosis did not show complete veno-occlusion were randomized to discontinue anticoagulation versus receive a total three-month course and followed for two years for the occurrence of symptomatic recurrent (SR-) VTE (efficacy outcome) and clinically-relevant bleeding (CRB, safety outcome). Outcomes were centrally adjudicated and net clinical benefit was compared between treatment arms via a pre-specified bivariate non-inferiority boundary, using 95% confidence intervals (CIs) in absolute risk differences (ARDs) between treatment arms. Kaplan-Meier estimates of two-year cumulative incidences in the six-week and three-months arms of the intention-to-treat (ITT) population (n=417) were 1.7% (95% CI: 0%, 3.7%) and 2.9% (95% CI: 0.3%, 5.4%) for SR-VTE and 1.1% (95% CI: 0%, 2.5%) and 3.2% (95% CI: 0.6%, 5.7%) for CRB. Bivariate analysis of the ARDs in the ITT population demonstrated that a six-week anticoagulation duration was non-inferior to a three-month course. These findings support durability of the Kids-DOTT RCT findings of net clinical benefit at two years.

Optimal antithrombotic therapy in ischemic stroke patients with non-valvular atrial fibrillation and atherothrombosis: study protocol for a randomized controlled trial

BackgroundThe addition of antiplatelet therapy to anticoagulant therapy in patients with stroke with non-valvular atrial fibrillation (NVAF) and atherothrombotic disease may increase bleeding risk without reducing recurrent stroke risk.AimsTo evaluate the clinical benefits of anticoagulant monotherapy compared to combination therapy with anticoagulants and antiplatelet agents.Methods and designThis is an investigator-initiated prospective multicenter, randomized, open-label, parallel-group clinical trial. Patients with NVAF and atherothrombotic disease who have had a recent ischemic stroke or transient ischemic attack will be eligible to participate in this trial.Study outcomesThe primary outcome is a composite of ischemic cardiovascular events, including cardiovascular death, ischemic stroke, myocardial infarction, systemic embolism, ischemic events requiring urgent revascularization, and major bleeding events within 2 years after randomization.Sample size estimatesThis study will enroll 400 patients, 200 receiving anticoagulant monotherapy and 200 receiving combination therapy. This sample size will provide 90% power (one-sided p = 0.025) to detect a risk reduction in outcome events within 2 years, assuming event rates of 13 and 27% for each group, respectively, and a 10% loss to follow-up at a 2.5% significance level with one-sided log-rank tests at an interim analysis and a final analysis.DiscussionThis will be the first study to assess the net clinical benefit of oral anticoagulant monotherapy in ischemic stroke patients with NVAF and atherothrombosis.Clinical trial registrationhttps://clinicaltrials.gov/study/NCT03062319, NCT03062319; https://center6.umin.ac.jp/cgi-open-bin/ctr/ctr_view.cgi?recptno=R000029222, UMIN000025392; https://jrct.niph.go.jp/latest-detail/jRCTs051180202, jRCTs051180202.

Optimizing risk stratification for intermediate-risk prostate cancer – the prognostic value of baseline health-related quality of life

ObjectiveTo investigate the prognostic value of baseline health-related quality of life (HRQOL) for patients with intermediate-risk localized prostate cancer (IR-PCa) undergoing radical prostatectomy (RP).Methods4780 patients with IR-PCa according to NCCN risk stratification were identified from a prospectively maintained database. All patients were treated with RP and had prospectively assessed baseline HRQOL. Main outcomes were oncologic endpoints metastasis-free survival (MFS); biochemical recurrence free survival (BRFS) and overall survival (OS). Multivariable Cox regression models assessed prognostic significance of baseline global health status (GHS) on survival outcomes. Harrell’s discrimination C-index was applied to calculate the predictive accuracy of the model. Decision curve analysis (DCA) tested the clinical net benefit associated with adding the GHS domain to our multivariable model (p < 0.05).ResultsMedian follow-up was 51 months. Multivariable analysis confirmed baseline GHS as an independent predictor for increased MFS (HR 0.976, 95%CI 0.96–0.99; p < 0.001), increased BRFS (HR 0.993, 95%CI 0.99–1.00; p = 0.027) and increased OS (HR 0.969, 95%CI 0.95–0.99; p = 0.002), indicating a relative risk reduction of 2.4% for MFS, 0.7% for BRFS and 3.1% for OS per 1-point increase of baseline GHS. Baseline HRQOL improved discrimination in predicting MFS, BRFS and OS. DCA revealed a net benefit over all threshold probabilities.ConclusionsWe found baseline HRQOL to substantially improve risk stratification for the heterogeneous cohort of IR-PCa. Baseline HRQOL accurately predicts increased MFS, BRFS and OS. Our findings therefore support the role of preoperative HRQOL as an adjunct to established prognosticators for IR-PCa, potentially facilitating guidance of therapy.

Construction and verification of the prediction model for risk of sleep disturbance in elderly patients with hypertension: a cross-sectional survey based on NHANES database from 2005 to 2018

ObjectiveTo construct and verify a risk prediction model for sleep disturbance in elderly patients with hypertension, aiming to offer guidance for sleep management in this demographic.MethodsA cohort of 6,708 elderly hypertensive patients from the NHANES database, spanning 2005 to 2018, met the inclusion criteria and were selected for this study. Participants were randomly assigned to a development group (n = 4,696) and a verification group (n = 2,012) in a 7:3 ratio. The occurrence of sleep disturbance was assessed across the subjects. Independent risk factors for sleep disturbance were analyzed using weighted multivariate logistic regression within the development group. A predictive model for sleep disturbance risk in elderly hypertensive patients was developed and verified using Stata 17.0. The model's predictive accuracy and stability were evaluated using the verification group's data.ResultsOf the 6,708 subjects, 2,014 (30.02%) were identified with sleep disturbance, and the weighted prevalence of sleep disturbance among elderly hypertensive patients was 33.283%. Weighted multivariate logistic regression analysis in the development group revealed that six factors were independently associated with sleep disturbance: higher total depression scores, higher education level, asthma, overweight, arthritis, and work restriction (OR > 1 and P < 0.05). The area under the receiver operating characteristic (ROC) curve (AUC) for the nomogram prediction model was 0.709 in the development group and 0.707 in the verification group, indicating good discrimination ability. Brier scores for the nomogram model were 0.185 in the development group and 0.189 in the verification group, both below 0.25, suggesting good calibration. Decision Curve Analysis (DCA) determined that the nomogram's clinical net benefit was maximized when the threshold probability for sleep disturbance in elderly hypertensive patients was 0.13–0.67 in the development group and 0.14–0.61 in the verification group, highlighting the model's clinical utility.LimitationsThis study is not without its limitations, including issues with data collection, the absence of external validation, and the non-extrapolation of results.ConclusionThe prevalence of sleep disturbance among elderly hypertensive patients stands at 33.283%. The nomogram model, based on identified risk factors for sleep disturbance in this population, has demonstrated good predictive efficiency and clinical relevance. It serves as a valuable tool to assist healthcare providers in identifying elderly hypertensive patients at high risk for sleep disturbance.

Modification, validation and comparison of Naples prognostic score to determine in-hospital mortality in ST-segment elevation myocardial infarction.

The relationship between inflammatory status and poor outcomes in acute coronary syndromes is a significant area of current research. This study investigates the association between in-hospital mortality and the modified Naples prognostic score (mNPS) as well as other inflammatory biomarkers in STEMI patients. This single-centre, cross-sectional study included 2576 consecutive STEMI patients who underwent primary percutaneous coronary intervention between January 2022 and November 2023. Participants were randomly divided into derivation and validation cohorts in a 6:4 ratio. The following inflammatory indices were calculated: pan-immune-inflammation value (PIV), systemic immune-inflammation-index (SII), systemic inflammation-response index (SIRI) and conventional NPS. The mNPS was derived by integrating hs-CRP into the conventional NPS. The performance of these indices in determining in-hospital mortality was assessed using regression, calibration, discrimination, reclassification and decision curve analyses. Inflammatory biomarkers, including PIV, SII, SIRI, NPS and mNPS, were significantly higher in patients who died during in-hospital follow-up compared to those discharged alive in both the derivation and validation cohorts. Multivariable logistic regression analyses were performed separately for the derivation and validation cohorts. In the derivation cohort, mNPS was associated with in-hospital mortality (aOR = 1.490, p < .001). Similarly, in the validation cohort, mNPS was associated with in-hospital mortality (aOR = 2.023, p < .001). mNPS demonstrated better discriminative and reclassification power than other inflammatory markers (p < .05 for all). Additionally, regression models incorporating mNPS were well-calibrated and showed net clinical benefit in both cohorts. mNPS may be a stronger predictor of in-hospital mortality in STEMI patients compared to the conventional scheme and other inflammatory indices.

Delta-CT radiomics based model for predicting postoperative anastomotic leakage following radical resection of esophageal squamous cell carcinoma.

To predict postoperative anastomotic leakage (AL) following radical resection of esophageal squamous cell carcinoma (ESCC) based on clinical data and preoperative enhanced Computed tomography(CT) radiomics of the esophagus. We retrospectively analyzed the clinicopathological and radiological data of 213 patients with ESCC who received radical resection at Xiangyang No.1 People's Hospital from July 2011 to February 2024. 3D slicer software was used in combination with Lasso extraction and 10-fold cross-validation to extract texture parameters from contrast-enhanced CT images and generate Delta-Radscores. Several models were built using logistic regression to predict postoperative AL in ESCC. In the training set, the univariate analysis confirmed that duration of surgery, surgical method, delta radscore 1, delta radscore 2, contrast enhancement patterns, peripheral lymph node metastasis, post thoracotomy pulmonary infection(PTPI), and hot pot were risk factors for ESCC-AL (P<0.05 for both). The multivariate analysis showed that delta radscore 1, delta radscore 2, PTPI, and hot pot were independent risk factors for AL (P<0.05 for all). These results were verified by the XGboost machine learning model. The combinational model based on all of the above risk factors [AUC 0.900, OR 0.0282, 95%CI 0.841-0.943] outperformed either the clinical model[AUC 0.759, OR 0.0392, 95%0.683-0.825,P<0.05] or the imaging model[AUC 0.869, OR 0.0335, 95%0.804-0.918,P=0.1277] alone in predictive efficacy. The decision curve proved that the combinational model had a higher clinical net benefit. The nomogram generated via the combinational model simplified the predictive process. The same predictions were verified in the testing set. Delta radscore 1, delta radscore 2, PTPI, and hot pot were related to ESCC-AL. The novel nomogram created using enhanced CT radiomics informed perioperative management and improved the survival quality of ESCC patients.

Development and Validation of a Prediction Model for Dysphagia in Community-Dwelling Older Adults.

Objectives. Dysphagia is a geriatric syndrome, which may lead to complications such as dehydration, malnutrition, aspiration, pneumonia, and a significant reduction in quality of life. The purpose of this study was to construct and validate a prediction model for dysphagia in community-dwelling older adults and provide an assessment tool for the prevention and control of dysphagia. Design. Cross-sectional study. Setting. The community-dwelling Chinese older adults. Participants. 3655 participants aged 65 years and older were involved, who were randomly divided into the training set and the validation set. Methods. Data were collected and analyzed from June 2022 to September 2022. Univariate and multivariate logistic regression analysis were used to identify independent risk factors for dysphagia. We applied R software to develop a nomogram model to predict dysphagia in community-dwelling older adults. The predictive value of the model was assessed by the area under the ROC curve (AUC), the calibration curve was used to evaluate the reliability of the nomogram model for predicting dysphagia in community-dwelling older adults. The model's clinical utility was further evaluated using a Decision Curve Analysis (DCA). Results. The incidence of dysphagia was 11.8% (320/3655). Maximum tongue pressure, number of molars, pneumonia, ADL, sarcopenia, age, neurological diseases, and rheumatic immune diseases were selected as risk predictors for dysphagia. The prediction model demonstrated fair discriminative ability with the AUC was 0.709 (95%CI: 0.679-0.739) in the training set and 0.693 (95%Cl: 0.640-0.747) in the validation set, the calibration is adequate, and the Hosmer and Lemeshow test showed p values of 0.163 and 0.415, respectively. The DCA curve of our model shows a positive clinical net benefit. Conclusions. The prediction model established in this study was of a certain predictive value for the risk of dysphagia in community-dwelling older adults. By estimating the likelihood of future outcomes or the onset of certain diseases, it can assist medical personnel in formulating preventive strategies, lessening the workload of nurses, and also diminishing the financial burden on patients, thereby enhancing their overall quality of life.

Development of a novel nomogram for patients with SCLC and comparison with other models

BackgroundThough several nomograms have been established to predict the survival probability of patients with small-cell lung cancer (SCLC), none involved enough variables. This study aimed to construct a novel prognostic nomogram and compare its performance with other models.MethodsSeven hundred twenty-two patients were pathologically diagnosed with SCLC in Shanxi Province Cancer Hospital, Shanxi Hospital Affiliated to Cancer Hospital, Chinese Academy of Medical Sciences, Cancer Hospital Affiliated to Shanxi Medical University from January 2016 to December 2018. We input Forty-one factors by reviewing the medical records. The nomogram was constructed based on the variables identified by univariate and multivariate analyses in the training set and validated in the validation set. Then we compared the performance of the models in terms of discrimination, calibration, and clinical net benefit.ResultsThere were eight variables involved in the nomogram: gender, monocyte (MON), neuron-specific enolase (NSE), cytokeratin 19 fragments (Cyfra211), M stage, radiotherapy (RT), chemotherapy cycles (CT cycles), and prophylactic cranial irradiation (PCI). The calibration curve showed a good correlation between the nomogram prediction and actual observation for overall survival (OS). The area under the curve (AUC) of the nomogram was higher, and the Integrated Brier score (IBS) was lower than other models, indicating a more accurate prediction. Decision curve analysis (DCA) showed a significant improvement in the clinical net benefit compared to the other models.ConclusionsWe constructed a novel nomogram to predict OS for patients with SCLC using more comprehensive and objective variables. It performed better than existing models and would assist clinicians in individually estimating risk and making a therapeutic regimen.

Whole tumour- and subregion-based radiomics of contrast-enhanced mammography in differentiating HER2 expression status of invasive breast cancers: A double-centre pilot study.

To explore the value of whole tumour- and subregion-based radiomics of contrast-enhanced mammography (CEM) in differentiating the HER2 expression status of breast cancers. 352 patients underwent preoperative CEM from two centres were consecutively enroled and divided into the training, internal validation, and external validation cohorts. The lesions were divided into HER2-positive and HER2-negative groups. Besides the radiological features, radiomics features capturing the whole tumour-based (wITH) and subregion-based intratumoral heterogeneity (sITH) were extracted from the craniocaudal view of CEM recombined images. The XGBoost classifier was applied to develop the radiological, sITH, and wITH models. A combined model was constructed by fusing the prediction results of the three models. The mean age of the patients was 51.1 ± 10.7 years. Two radiological features, four wITH features, and three sITH features were selected to establish the models. The combined model significantly improved the AUC to 0.80 ± 0.03 (95% CI: 0.73-0.86), 0.79 ± 0.06 (95% CI: 0.67-0.90), and 0.79 ± 0.05 (95% CI: 0.69-0.89) in the training, internal validation, and external validation cohorts, respectively (All P < 0.05). The combined model showed good agreement between the predicted and observed probabilities and favourable net clinical benefit in the validation cohorts. Both whole tumour- and subregion-based ITH radiomics features of CEM exhibited potential for differentiating the HER2 expression status. Combining conventional radiological features and ITH features can improve the model's performance.

Development and validation of a predictive model for failure of ureteral access sheath placement in patients with ureteral calculi

ObjectiveThe Ureteral Access Sheath (UAS) has notable benefits but may fail to traverse the ureter in some cases. Our objective was to develop and validate a dynamic online nomogram for patients with ureteral stones who experienced UAS placement failure during retrograde intrarenal surgery (RIRS).MethodsThis study is a retrospective cohort analysis using medical records from the Second Hospital of Tianjin Medical University. We reviewed the records of patients with ureteral stones who underwent RIRS in 2022 to identify risk factors associated with UAS placement failure. Lasso combined logistic regression was utilized to identify independent risk factors associated with unsuccessful UAS placement in individuals with ureteral stones. Subsequently, a nomogram model was developed to predict the likelihood of failed UAS placement in this patient cohort. The model’s performance was assessed through Receiver Operating Characteristic Curve (ROC) analysis, calibration curve assessment, and Decision Curve Analysis (DCA).ResultsSignificant independent risk factors for unsuccessful UAS placement in patients with ureteral stones included age (OR = 0.95, P < 0.001), male gender (OR = 2.15, P = 0.017), body mass index (BMI) (OR = 1.12, P < 0.001), history of stone evacuation (OR = 0.35, P = 0.014), and ureteral stone diameter (OR = 0.23, P < 0.001). A nomogram was constructed based on these variables. Model validation demonstrated an area under the ROC curve of 0.789, indicating good discrimination. The calibration curve exhibited strong agreement, and the decision curve analysis revealed a favorable net clinical benefit for the model.ConclusionsYoung age, male sex, high BMI, no history of stone evacuation, and small diameter of ureteral stones were independent risk factors for failure of UAS placement in patients with ureteral stones, and the dynamic nomogram established with these 5 factors was clinically effective in predicting the outcome of UAS placement.

Machine learning models for diagnosing Alzheimer's disease using brain cortical complexity.

This study aimed to develop and validate machine learning models (MLMs) to diagnose Alzheimer's disease (AD) using cortical complexity indicated by fractal dimension (FD). A total of 296 participants with normal cognitive (NC) function and 182 with AD from the AD Neuroimaging Initiative database were randomly divided into training and internal validation cohorts. Then, FDs, demographic characteristics, baseline global cognitive function scales [Montreal Cognitive Assessment (MoCA), Functional Activities Questionnaire (FAQ), Global Deterioration Scale (GDS), Neuropsychiatric Inventory (NPI)], phospho-tau (p-tau 181), amyloidβ-42/40, apolipoprotein E (APOE) and polygenic hazard score (PHS) were collected to establish multiple MLMs. Receiver operating characteristic curves were used to evaluate model performance. Participants from our institution (n = 66; 33 with NC and 33 with AD) served as external validation cohorts to validate the MLMs. Decision curve analysis was used to estimate the models' clinical values. The FDs from 30 out of 69 regions showed significant alteration. All MLMs were conducted based on the 30 significantly different FDs. The FD model had good accuracy in predicting AD in three cohorts [area under the receiver operating characteristic (ROC) curve (AUC) = 0.842, 0.808, and 0.803]. There were no statistically significant differences in AUC values between the FD model and the other combined models in the training and internal validation cohorts except MoCA + FD and FAQ + FD models. Among MLMs, the MoCA + FD model showed the best predictive efficiency in three cohorts (AUC = 0.951, 0.931, and 0.955) and had the highest clinical net benefit. The FD model showed favorable diagnostic performance for AD. Among MLMs, the MoCA + FD model can predict AD with the highest efficiency and could be used as a non-invasive diagnostic method.

Dual-energy computed tomography-based radiomics for differentiating patients with and without gout flares.

There is a current lack of data pertaining to the potential link between gout flares and dual-energy computed tomography radiomic features. This study aimed to construct and validate a comprehensive dual-energy computed tomography-based radiomics model for differentiating patients with and without gout flares. The analysis included 200 patients, of whom 150 were confirmed to have experienced at least one flare in the past 12months; the remaining 50 patients did not experience flares. The radiomic features of the tophi at the bilateral first metatarsophalangeal joints were extracted and analyzed. Optimal radiomic features were selected using the least absolute shrinkage and selection operator method, and logistic regression analysis was used to screen clinical characteristics and establish a clinical model. The optimal radiomic features were then combined with the identified independent clinical variables to develop a comprehensive model. The performances of the radiomic, clinical, and comprehensive models were evaluated using receiver operating characteristic curve analysis, calibration curves, and decision curve analysis. Four radiomic features distinguished patients with at least one flare from those without flares and were used to establish the radiomic model. Disease duration and hypertension were independent factors that differentiated flare occurrences. The radiomic, clinical, and comprehensive models showed favorable discrimination, with areas under the receiver operating characteristic curves of 0.76 (95% CI, 0.69-0.83), 0.72(95% CI, 0.63-0.80), and 0.79(95% CI, 0.73-0.86), respectively. The calibration curves (P > 0.05) showed that the differentiated values of the comprehensive model agreed well with the actual values. Decision curve analysis demonstrated that the comprehensive model achieved higher net clinical benefits than the use of either the radiomic or clinical model alone. The results of this study suggest that a radiomics model can distinguish patients with and without gout flares. Our proposed clinical radiomics nomogram can increase the efficacy of differentiating flare occurrence, which may facilitate the clinical decision-making process.

Machine learning derived model for the prediction of bleeding in dual antiplatelet therapy patients.

This study aimed to develop a predictive model for assessing bleeding risk in dual antiplatelet therapy (DAPT) patients. A total of 18,408 DAPT patients were included. Data on patients' demographics, clinical features, underlying diseases, past history, and laboratory examinations were collected from Affiliated Dongyang Hospital of Wenzhou Medical University. The patients were randomly divided into two groups in a proportion of 7:3, with the most used for model development and the remaining for internal validation. LASSO regression, multivariate logistic regression, and six machine learning models, including random forest (RF), k-nearest neighbor imputing (KNN), decision tree (DT), extreme gradient boosting (XGBoost), light gradient boosting machine (LGBM), and Support Vector Machine (SVM), were used to develop prediction models. Model prediction performance was evaluated using area under the curve (AUC), calibration curves, decision curve analysis (DCA), clinical impact curve (CIC), and net reduction curve (NRC). The XGBoost model demonstrated the highest AUC. The model features were comprised of seven clinical variables, including: HGB, PLT, previous bleeding, cerebral infarction, sex, Surgical history, and hypertension. A nomogram was developed based on seven variables. The AUC of the model was 0.861 (95% CI 0.847-0.875) in the development cohort and 0.877 (95% CI 0.856-0.898) in the validation cohort, indicating that the model had good differential performance. The results of calibration curve analysis showed that the calibration curve of this nomogram model was close to the ideal curve. The clinical decision curve also showed good clinical net benefit of the nomogram model. This study successfully developed a predictive model for estimating bleeding risk in DAPT patients. It has the potential to optimize treatment planning, improve patient outcomes, and enhance resource utilization.

Net Clinical Benefit of 12-Month Over 3-Month Edoxaban in Cancer-Associated Isolated Distal Deep Vein Thrombosis

Net Clinical Benefit of 12-Month Over 3-Month Edoxaban in Cancer-Associated Isolated Distal Deep Vein Thrombosis