Good Discrimination Performance Research Articles

NEWS2, S/F-ratio and ROX-index at emergency department for the prediction of adverse outcomes in COVID-19 patients: An external validation study

BackgroundIn the context of the COVID-19 pandemic, the early and accurate identification of patients at risk of deterioration was crucial in overcrowded and resource-limited emergency departments. This study conducts an external validation for the evaluation of the performance of the National Early Warning Score 2 (NEWS2), the S/F ratio, and the ROX index at ED admission in a large cohort of COVID-19 patients from Colombia, South America, assessing the net clinical benefit with decision curve analysis. MethodsA prospective cohort study was conducted on 6907 adult patients with confirmed COVID-19 admitted to a tertiary care ED in Colombia. The study evaluated the diagnostic performance of NEWS2, S/F ratio, and ROX index scores at ED admission using the area under the receiver operating characteristic curve (AUROC) for discrimination, calibration, and decision curve analysis for the prediction of intensive care unit admission, invasive mechanical ventilation, and in-hospital mortality. ResultsWe included 6907 patients who presented to the ED with confirmed SARS-CoV-2 infection from March 2020 to November 2021. Mean age was 51 (35–65) years and 50.4% of patients were males. The rate of intensive care unit admission was 28%, and in-hospital death was 9.8%. All three scores have good discriminatory performance for the three outcomes based on the AUROC. S/F ratio showed miscalibration at low predicted probabilities and decision curve analysis indicated that the NEWS2 score provided a greater net benefit compared to other scores across at a 10% threshold to decide ED admission at a high-level of care facility. ConclusionsThe NEWS2, S/F ratio, and ROX index at ED admission have good discriminatory performances in COVID-19 patients for the prediction of adverse outcomes, but the NEWS2 score has a higher net benefit underscoring its clinical utility in optimizing patient management and resource allocation in emergency settings.

NEWS2, S/F-ratio and ROX-index at emergency department for the prediction of adverse outcomes in COVID-19 patients: An external validation study

BackgroundIn the context of the COVID-19 pandemic, the early and accurate identification of patients at risk of deterioration was crucial in overcrowded and resource-limited emergency departments. This study conducts an external validation for the evaluation of the performance of the National Early Warning Score 2 (NEWS2), the S/F ratio, and the ROX index at ED admission in a large cohort of COVID-19 patients from Colombia, South America, assessing the net clinical benefit with decision curve analysis. MethodsA prospective cohort study was conducted on 6907 adult patients with confirmed COVID-19 admitted to a tertiary care ED in Colombia. The study evaluated the diagnostic performance of NEWS2, S/F ratio, and ROX index scores at ED admission using the area under the receiver operating characteristic curve (AUROC) for discrimination, calibration, and decision curve analysis for the prediction of intensive care unit admission, invasive mechanical ventilation, and in-hospital mortality. ResultsWe included 6907 patients who presented to the ED with confirmed SARS-CoV-2 infection from March 2020 to November 2021. Mean age was 51 (35–65) years and 50.4% of patients were males. The rate of intensive care unit admission was 28%, and in-hospital death was 9.8%. All three scores have good discriminatory performance for the three outcomes based on the AUROC. S/F ratio showed miscalibration at low predicted probabilities and decision curve analysis indicated that the NEWS2 score provided a greater net benefit compared to other scores across at a 10% threshold to decide ED admission at a high-level of care facility. ConclusionsThe NEWS2, S/F ratio, and ROX index at ED admission have good discriminatory performances in COVID-19 patients for the prediction of adverse outcomes, but the NEWS2 score has a higher net benefit underscoring its clinical utility in optimizing patient management and resource allocation in emergency settings.

The Impact of Silent Liver Disease on Hospital Length of Stay Following Isolated Coronary Artery Bypass Grafting Surgery.

Objectives: Risk assessment models for cardiac surgery do not distinguish between degrees of liver dysfunction. We have previously shown that preoperative liver stiffness is associated with hospital length of stay following cardiac surgery. The authors hypothesized that a liver stiffness measurement (LSM) ≥ 9.5 kPa would rule out a short hospital length of stay (LOS < 6 days) following isolated coronary artery bypass grafting (CABG) surgery. Methods: A prospective observational study of one hundred sixty-four adult patients undergoing non-emergent isolated CABG surgery at a single university hospital center. Preoperative liver stiffness measured by ultrasound elastography was obtained for each participant. Multivariate logistic regression models were used to assess the adjusted relationship between LSM and a short hospital stay. Results: We performed multivariate logistic regression models using short hospital LOS (<6 days) as the dependent variable. Independent variables included LSM (< 9.5 kPa, ≥ 9.5 kPa), age, sex, STS predicted morbidity and mortality, and baseline hemoglobin. After adjusting for included variables, LSM ≥ 9.5 kPa was associated with lower odds of early discharge as compared to LSM < 9.5 kPa (OR: 0.22, 95% CI: 0.06-0.84, p = 0.03). The ROC curve and resulting AUC of 0.76 (95% CI: 0.68-0.83) suggest the final multivariate model provides good discriminatory performance when predicting early discharge. Conclusions: A preoperative LSM ≥ 9.5 kPa ruled out a short length of stay in nearly 80% of patients when compared to patients with a LSM < 9.5 kPa. Preoperative liver stiffness may be a useful metric to incorporate into preoperative risk stratification.

Ensemble modeling to identify high conservation value areas for endemic and elusive large-sized mammals of the Philippines

Bubalus mindorensis (tamaraw) and Sus oliveri (Mindoro warty pig) are emblematic of Mindoro Island as a faunal biodiversity hotspot in the Philippines. However, these endemic, red-listed mammals are of socioecological concern due to pressures within their contracting home ranges. Conservation efforts are logistically hindered by their elusive yet aggressive behavior and coexistence with indigenous tribes. This study aims to identify high conservation value areas (HCVAs), sites where both species are highly suitable. Ensemble species distribution modeling (SDM) based on nine algorithms was performed. For each species, three ensemble SDMs were calibrated following three proposed approaches in decreasing hyperparameter-based model complexity: standard, tuned, and limited. Across ensemble SDMs, complexity and True Skill Statistics (TSS)-based accuracy are positively associated. Still, the limited ensemble SDM of tamaraw (TSS = 0.740) and Mindoro warty pig (TSS = 0.855) retain good discriminatory performance. These coincidingly predict that known occurrence sites are areas of high suitability, which are spatially fragmented into four patches across the Mindoro Mountain Range: Mt. Calavite Wildlife Sanctuary, Upper Amnay Watershed, Aruyan-Malati, and Mts. Iglit-Baco National Park. In total, these prospective HCVAs cover 405.17 km2 (3.83%) of Mindoro Island, which represent areas of priority for the ongoing Mindoro Island Biodiversity (BD) Corridor Project. This study substantiates the need for strategic management of these HCVAs. Despite overarching study-specific limitations and uncertainties, this study advocates the informed use of ensemble SDMs for reserve selection, conservation planning, and wildlife-related policymaking in Mindoro Island.

Investigating protease-mediated peptides of inflammation and tissue remodeling as biomarkers associated with flares in psoriatic arthritis.

Psoriatic arthritis (PsA) is an inflammatory arthritis associated with psoriasis. PsA disease involves flares, which are associated with increased joint inflammation and tissue remodeling. There is a need for identifying biomarkers related to PsA disease activity and flares to improve the management of PsA patients and decrease flares. The tissue turnover imbalance that occurs during the inflammatory and fibro-proliferative processes during flares leads to an increased degradation and/or reorganization of the extracellular matrix (ECM), where increased proteolysis plays a key role. Hence, protease-mediated fragments of inflammatory and tissue-remodeling components could be used as markers reflecting flares in PsA patients. A broad panel of protease-mediated biomarkers reflecting inflammation and tissue remodeling was measured in serum and synovial fluid (SF) obtained from PsA patients experiencing flares (acutely swollen joint[s], PsA-flare). In serum, biomarker levels assessed in PsA-flare patients were compared to controls and in early-diagnosed PsA patients not experiencing flares (referred to as PsA without flare). Furthermore, the biomarker levels assessed in SF from PsA-flare patients were compared to the levels in SF of osteoarthritis (OA) patients. In serum, levels of the PRO-C3 and C3M, reflecting formation and degradation of the interstitial matrix, were found significantly elevated in PsA-flare compared to controls and PsA without flare. The remodeling marker of the basement membrane, PRO-C4, was significantly elevated in PsA-flare compared to PsA without flare. The inflammation and immune cell activity related markers, CRPM, VICM, and CPa9-HNE were significantly elevated in PsA-flare patients compared to controls and PsA without flare. In addition, VICM (AUC = 0.71), CPa9-HNE (AUC = 0.89), CRPM (AUC = 0.76), and PRO-C3 (AUC = 0.86) showed good discriminatory performance for separating PsA-flare from PsA without flare. In SF, the macrophage activity marker, VICM, was significantly elevated whereas the type II collagen formation marker, PRO-C2, was significantly reduced in the PsA-flare compared to OA. The combination of five serum markers reflecting type III and IV collagen degradation (C3M and C4M, respectively), type III and VI collagen formation (PRO-C3 and PRO-C6, respectively), and neutrophil activity (CPa9-HNE) showed an excellent discriminatory performance (AUC = 0.98) for separating PsA-flare from PsA without flares. The serum biomarker panel of C3M, C4M, PRO-C3, PRO-C6, and CPa9-HNE reflecting synovitis, enthesitis, and neutrophil activity may serve as novel tool for quantitatively monitoring flares in PsA patients.

A predictive model using MRI and clinicopathologic features for breast cancer recurrence in young women treated with upfront surgery.

To identify preoperative breast MR imaging and clinicopathological variables related to recurrence and develop a risk prediction model for recurrence in young women with breast cancer treated with upfront surgery. This retrospective study analyzed 438 consecutive women with breast cancer aged 35 years or younger between January 2007 and December 2016. Breast MR images before surgery were independently reviewed by breast radiologists blinded to patient outcomes. The clinicopathological data including patient demographics, clinical features, and tumor characteristics were reviewed. Univariate and multivariate logistic regression analyses were used to identify the independent factors associated with recurrence. The risk prediction model for recurrence was developed, and the discrimination and calibration abilities were assessed. Of 438 patients, 95 (21.7%) developed recurrence after a median follow-up of 65 months. Tumor size at MR imaging (HR = 1.158, p = 0.006), multifocal or multicentric disease (HR = 1.676, p = 0.017), and peritumoral edema on T2WI (HR = 2.166, p = 0.001) were identified as independent predictors of recurrence, while adjuvant endocrine therapy (HR = 0.624, p = 0.035) was inversely associated with recurrence. The prediction model showed good discrimination ability in predicting 5-year recurrence (C index, 0.707 in the development cohort; 0.686 in the validation cohort) and overall recurrence (C index, 0.699 in the development cohort; 0.678 in the validation cohort). The calibration plot demonstrated an excellent correlation (concordance correlation coefficient, 0.903). A prediction model based on breast MR imaging and clinicopathological features showed good discrimination to predict recurrence in young women with breast cancer treated with upfront surgery, which could contribute to individualized risk stratification. Our prediction model, incorporating preoperative breast MR imaging and clinicopathological features, predicts recurrence in young women with breast cancer undergoing upfront surgery, facilitating personalized risk stratification and informing tailored management strategies. Younger women with breast cancer have worse outcomes than those diagnosed at more typical ages. The described prediction model showed good discrimination performance in predicting 5-year and overall recurrence. Incorporating better risk stratification tools in this population may help improve outcomes.

Predicting tall-cell subtype of papillary thyroid carcinomas independently with preoperative multimodal ultrasound.

This study aimed to explore the differences between tall-cell subtype of papillary thyroid carcinoma (TCPTC) and classical papillary thyroid carcinoma (cPTC) using multimodal ultrasound, and identify independent risk factors for TCPTC to compensate the deficiency of preoperative cytological and molecular diagnosis on PTC subtypes. Forty-six TCPTC patients and 92 cPTC patients were included. Each patient received grey-scale ultrasound, colour Dopplor flow imaging (CDFI) and shear-wave elastography (SWE) preoperatively. Clinicopathologic information, grey-scale ultrasound features, CDFI features and SWE features of 98 lesions were compared using univariate analysis to find out predictors of TCPTC, based on which, a predictive model was built to differentiate TCPTC from cPTC and validated with 40 patients. Univariate and multivariate analyses identified that extra-thyroidal extension (odds ratio [OR], 15.12; 95% CI, 2.26-115.44), aspect ratio (≥0.91) (OR, 29.34; 95% CI, 1.29-26.23), and maximum diameter ≥14.6 mm (OR, 20.79; 95% CI, 3.87-111.47) were the independent risk factors for TCPTC. Logistic regression equation: P = 1/1+ExpΣ[-5.099 + 3.004 × (if size ≥14.6 mm) + 2.957 × (if aspect ratio ≥ 0.91) + 2.819 × (if extra-thyroidal extension). The prediction model had a good discrimination performance for TCPTC: the area under the receiver-operator-characteristic curve, sensitivity, and specificity were 0.928, 0.848, and 0.954 in cohort 1, and the corresponding values in cohort 2 were 0.943, 0.923, and 0.926, respectively. Ultrasound has the potential for differential diagnosis of TCPTC from cPTC. A prediction model based on ultrasound characteristics (extra-thyroidal extension, aspect ratio ≥0.91, and maximum diameter ≥14.6 mm) was useful in predicting TCPTC. Multimodal ultrasound prediction of TCPTC was a supplement to preoperative cytological diagnosis and molecular diagnosis of PTC subtypes.

Radiomics analysis for prediction and classification of submucosal tumors based on gastrointestinal endoscopic ultrasonography.

To identify and classify submucosal tumors by building and validating a radiomics model with gastrointestinal endoscopic ultrasonography (EUS) images. A total of 144 patients diagnosed with submucosal tumors through gastrointestinal EUS were collected between January 2019 and October 2020. There are 1952 radiomic features extracted from each patient's EUS images. The statistical test and the customized least absolute shrinkage and selection operator regression were used for feature selection. Subsequently, an extremely randomized trees algorithm was utilized to construct a robust radiomics classification model specifically tailored for gastrointestinal EUS images. The performance of the model was measured by evaluating the area under the receiver operating characteristic curve. The radiomics model comprised 30 selected features that showed good discrimination performance in the validation cohorts. During validation, the area under the receiver operating characteristic curve was calculated as 0.9203 and the mean value after 10-fold cross-validation was 0.9260, indicating excellent stability and calibration. These results confirm the clinical utility of the model. Utilizing the dataset provided curated from gastrointestinal EUS examinations at our collaborating hospital, we have developed a well-performing radiomics model. It can be used for personalized and non-invasive prediction of the type of submucosal tumors, providing physicians with aid for early treatment and management of tumor progression.

Predictors of systolic function recovery after atrial fibrillation ablation in heart failure patients

Introduction and ObjectivesAtrial fibrillation (AF) and heart failure (HF) often coexist. AF catheter ablation improves left ventricular ejection fraction (LVEF), but its impact varies between patients. We aimed to identify predictors of LVEF improvement in HF patients with impaired LVEF undergoing AF ablation. MethodsWe conducted a retrospective single-center study in HF patients with LVEF <50% undergoing AF catheter ablation between May 2016 and May 2022. The primary endpoint was the LVEF recovery rate (‘responders’). Secondary endpoints were one-year safety and effectiveness. We also aimed to validate a prediction model for LVEF recovery. ResultsThe study included 100 patients (79% male, median age 60 years, 70% with probable tachycardia-induced cardiomyopathy [TIC], mean LVEF 37%, 29% with paroxysmal AF). After a median follow-up of 12 months after catheter ablation, LVEF improved significantly (36±10% vs. 53±10%, p<0.001), with an 82% responder rate. A suspected diagnosis of TIC (OR 4.916 [95% CI 1.166–20.732], p=0.030), shorter QRS duration (OR 0.969 [95% CI 0.945–0.994], p=0.015), and smaller left ventricle (OR 0.893 [95% CI 0.799–0.999], p=0.049) were independently associated with LVEF improvement. Freedom from any documented atrial arrhythmia was 86% (64% under antiarrhythmic drugs), and the rate of adverse events was 2%. The prediction model had a good discriminative performance (AUC 0.814 [95% CI 0.681–0.947]). ConclusionIn AF patients with HF and impaired LVEF, suspected TIC, shorter QRS duration, and smaller LV diameter were associated with LVEF recovery following AF catheter ablation.

Prediction of incident chronic kidney disease in community-based electronic health records: a systematic review and meta-analysis.

Chronic kidney disease (CKD) is a major global health problem and its early identification would allow timely intervention to reduce complications. We performed a systematic review and meta-analysis of multivariable prediction models derived and/or validated in community-based electronic health records (EHRs) for the prediction of incident CKD in the community. Ovid Medline and Ovid Embase were searched for records from 1947 to 31 January 2024. Measures of discrimination were extracted and pooled by Bayesian meta-analysis, with heterogeneity assessed through a 95% prediction interval (PI). Risk of bias was assessed using Prediction model Risk Of Bias ASsessment Tool (PROBAST) and certainty in effect estimates by Grading of Recommendations, Assessment, Development and Evaluation (GRADE). Seven studies met inclusion criteria, describing 12 prediction models, with two eligible for meta-analysis including 2173202 patients. The Chronic Kidney Disease Prognosis Consortium (CKD-PC) (summary c-statistic 0.847; 95% CI 0.827-0.867; 95% PI 0.780-0.905) and SCreening for Occult REnal Disease (SCORED) (summary c-statistic 0.811; 95% CI 0.691-0.926; 95% PI 0.514-0.992) models had good model discrimination performance. Risk of bias was high in 64% of models, and driven by the analysis domain. No model met eligibility for meta-analysis if studies at high risk of bias were excluded, and certainty of effect estimates was 'low'. No clinical utility analyses or clinical impact studies were found for any of the models. Models derived and/or externally validated for prediction of incident CKD in community-based EHRs demonstrate good prediction performance, but assessment of clinical usefulness is limited by high risk of bias, low certainty of evidence and a lack of impact studies.

Development and validation of risk prediction model for recurrent cardiovascular events among Chinese: the Personalized CARdiovascular DIsease risk Assessment for Chinese model.

Cardiovascular disease (CVD) is a leading cause of mortality, especially in developing countries. This study aimed to develop and validate a CVD risk prediction model, Personalized CARdiovascular DIsease risk Assessment for Chinese (P-CARDIAC), for recurrent cardiovascular events using machine learning technique. Three cohorts of Chinese patients with established CVD were included if they had used any of the public healthcare services provided by the Hong Kong Hospital Authority (HA) since 2004 and categorized by their geographical locations. The 10-year CVD outcome was a composite of diagnostic or procedure codes with specific International Classification of Diseases, Ninth Revision, Clinical Modification. Multivariate imputation with chained equations and XGBoost were applied for the model development. The comparison with Thrombolysis in Myocardial Infarction Risk Score for Secondary Prevention (TRS-2°P) and Secondary Manifestations of ARTerial disease (SMART2) used the validation cohorts with 1000 bootstrap replicates. A total of 48 799, 119 672 and 140 533 patients were included in the derivation and validation cohorts, respectively. A list of 125 risk variables were used to make predictions on CVD risk, of which 8 classes of CVD-related drugs were considered interactive covariates. Model performance in the derivation cohort showed satisfying discrimination and calibration with a C statistic of 0.69. Internal validation showed good discrimination and calibration performance with C statistic over 0.6. The P-CARDIAC also showed better performance than TRS-2°P and SMART2. Compared with other risk scores, the P-CARDIAC enables to identify unique patterns of Chinese patients with established CVD. We anticipate that the P-CARDIAC can be applied in various settings to prevent recurrent CVD events, thus reducing the related healthcare burden.

Proteomics identifies complement protein signatures in patients with alcohol-associated hepatitis.

Diagnostic challenges continue to impede development of effective therapies for successful management of alcohol-associated hepatitis (AH), creating an unmet need to identify noninvasive biomarkers for AH. In murine models, complement contributes to ethanol-induced liver injury. Therefore, we hypothesized that complement proteins could be rational diagnostic/prognostic biomarkers in AH. Here, we performed a comparative analysis of data derived from human hepatic and serum proteome to identify and characterize complement protein signatures in severe AH (sAH). The quantity of multiple complement proteins was perturbed in liver and serum proteome of patients with sAH. Multiple complement proteins differentiated patients with sAH from those with alcohol cirrhosis (AC) or alcohol use disorder (AUD) and healthy controls (HCs). Serum collectin 11 and C1q binding protein were strongly associated with sAH and exhibited good discriminatory performance among patients with sAH, AC, or AUD and HCs. Furthermore, complement component receptor 1-like protein was negatively associated with pro-inflammatory cytokines. Additionally, lower serum MBL associated serine protease 1 and coagulation factor II independently predicted 90-day mortality. In summary, meta-analysis of proteomic profiles from liver and circulation revealed complement protein signatures of sAH, highlighting a complex perturbation of complement and identifying potential diagnostic and prognostic biomarkers for patients with sAH.

Investigating the Impact of Xylella Fastidiosa on Olive Trees by the Analysis of MODIS Terra Satellite Evapotranspiration Time Series by Using the Fisher Information Measure and the Shannon Entropy: A Case Study in Southern Italy

Xylella Fastidiosa has been recently detected for the first time in southern Italy, representing a very dangerous phytobacterium capable of inducing severe diseases in many plants. In particular, the disease induced in olive trees is called olive quick decline syndrome (OQDS), which provokes the rapid desiccation and, ultimately, death of the infected plants. In this paper, we analyse about two thousands pixels of MODIS satellite evapotranspiration time series, covering infected and uninfected olive groves in southern Italy. Our aim is the identification of Xylella Fastidiosa-linked patterns in the statistical features of evapotranspiration data. The adopted methodology is the well-known Fisher–Shannon analysis that allows one to characterize the time dynamics of complex time series by means of two informational quantities, the Fisher information measure (FIM) and the Shannon entropy power (SEP). On average, the evapotranspiration of Xylella Fastidiosa-infected sites is characterized by a larger SEP and lower FIM compared to uninfected sites. The analysis of the receiver operating characteristic curve suggests that SEP and FIM can be considered binary classifiers with good discrimination performance that, moreover, improves if the yearly cycle, very likely linked with the meteo-climatic variability of the investigated areas, is removed from the data. Furthermore, it indicated that FIM exhibits superior effectiveness compared to SEP in discerning healthy and infected pixels.

External validity of frailty discrimination using the Questionnaire for Medical Checkup of Old-Old-15 and -12

BackgroundIn this study, we aimed to establish the external validity of the cutoff values for frailty identification using both the 15-item and 12-item Questionnaire for Medical Checkups of the Old-Old (QMCOO-15 and QMCOO-12) and the frailty screening index (FSI). MethodThis cross-sectional study was conducted in Takasaki, Gunma Prefecture, Japan. Data from 114 participants aged ≥65 years were analyzed. The frailty assessment was based on the Revised Japanese version of the Cardiovascular Health Study (J-CHS) criteria. The QMCOO-15, QMCOO-12, and FSI were also examined. The cutoff value for frailty discrimination using these three scales was set at 3/4. The frailty discrimination performance of the three scales was validated using receiver operating characteristic (ROC) analysis, sensitivity, and specificity. ResultsThe average age of the participants was 76.4 years, and there were 79 female participants (69.3 %). According to the J-CHS criteria, nine participants (7.9 %) were identified as frail. The areas under the ROC curves were 0.878 for QMCOO-15, 0.853 for QMCOO-12, and 0.912 for FSI. The QMCOO-15 exhibited the highest sensitivity (0.778), whereas the FSI exhibited the highest specificity (0.943). The FSI also achieved the highest accuracy of 0.912. ConclusionsThis study revealed the external validity of frailty discrimination using the QMCOO-15, QMCOO-12, and FSI based on the J-CHS frailty assessment criteria. ROC analysis showed that all three tools exhibited good frailty discrimination performance. Hence, we demonstrated the validity of frailty assessments using questionnaires that did not involve physical measurements.

Comparison of the Discrimination Performance of AI Scoring and the Brixia Score in Predicting COVID-19 Severity on Chest X-Ray Imaging: Diagnostic Accuracy Study.

The artificial intelligence (AI) analysis of chest x-rays can increase the precision of binary COVID-19 diagnosis. However, it is unknown if AI-based chest x-rays can predict who will develop severe COVID-19, especially in low- and middle-income countries. The study aims to compare the performance of human radiologist Brixia scores versus 2 AI scoring systems in predicting the severity of COVID-19 pneumonia. We performed a cross-sectional study of 300 patients suspected with and with confirmed COVID-19 infection in Jakarta, Indonesia. A total of 2 AI scores were generated using CAD4COVID x-ray software. The AI probability score had slightly lower discrimination (area under the curve [AUC] 0.787, 95% CI 0.722-0.852). The AI score for the affected lung area (AUC 0.857, 95% CI 0.809-0.905) was almost as good as the human Brixia score (AUC 0.863, 95% CI 0.818-0.908). The AI score for the affected lung area and the human radiologist Brixia score had similar and good discrimination performance in predicting COVID-19 severity. Our study demonstrated that using AI-based diagnostic tools is possible, even in low-resource settings. However, before it is widely adopted in daily practice, more studies with a larger scale and that are prospective in nature are needed to confirm our findings.

Nomogram for predicting the risk of nonalcoholic fatty liver disease in older adults in Qingdao, China: A cross-sectional study.

To explore the risk factors for non-alcoholic fatty liver disease (NAFLD) and to establish a non-invasive tool for the screening of NAFLD in an older adult population. A total of 131,161 participants were included in this cross-sectional study. Participants were randomly divided into training and validation sets (7:3). The least absolute shrinkage and selection operator method was used to screen risk factors. Multivariate logistic regression was employed to develop a nomogram, which was made available online. Receiver operating characteristic curve analysis, calibration plots, and decision curve analysis were used to validate the discrimination, calibration, and clinical practicability of the nomogram. Sex and age subgroup analyses were conducted to further validate the reliability of the model. Nine variables were identified for inclusion in the nomogram (age, sex, waist circumference, body mass index, exercise frequency, systolic blood pressure, fasting plasma glucose, alanine aminotransferase, and low-density lipoprotein cholesterol). The area under the receiver operating characteristic curve values were 0.793 and 0.790 for the training set and the validation set, respectively. The calibration plots and decision curve analyses showed good calibration and clinical utility. Subgroup analyses demonstrated consistent discriminatory ability in different sex and age subgroups. This study established and validated a new nomogram model for evaluating the risk of NAFLD among older adults. The nomogram had good discriminatory performance and is a non-invasive and convenient tool for the screening of NAFLD in older adults.

A tool to predict the risk of lower extremity amputation in patients starting dialysis.

Non-traumatic lower extremity amputation (LEA) is a severe complication during dialysis. To inform decision-making for physicians, we developed a multivariable prediction model for LEA after starting dialysis. Data from the Swedish Renal Registry (SNR) between 2010 and 2020 were geographically split into a development and validation cohort. Data from NECOSAD between 1997 and 2009 were used for validation targeted at Dutch patients. Inclusion criteria were no previous LEA and kidney transplant and age≥40 years at baseline. A Fine-Gray model was developed with LEA within 3 years after starting dialysis as outcome of interest. Death and kidney transplant were treated as competing events. One coefficient, ordered by expected relevance, per 20 events was estimated. Performance was assessed with calibration and discrimination. SNR was split into an urban development cohort with 4771 individuals experiencing 201 (4.8%) events and a rural validation cohort with 4.876 individuals experiencing 155 (3.2%) events. NECOSAD contained 1658 individuals experiencing 61 (3.7%) events. Ten predictors were included: female sex, age, diabetes mellitus, peripheral artery disease, cardiovascular disease, congestive heart failure, obesity, albumin, haemoglobin and diabetic retinopathy. In SNR, calibration intercept and slope were -0.003 and 0.912 respectively. The C-index was estimated as 0.813 (0.783-0.843). In NECOSAD, calibration intercept and slope were 0.001 and 1.142 respectively. The C-index was estimated as 0.760 (0.697-0.824). Calibration plots showed good calibration. A newly developed model to predict LEA after starting dialysis showed good discriminatory performance and calibration. By identifying high-risk individuals this model could help select patients for preventive measures.

Development and validation of a risk score model for predicting autism based on pre- and perinatal factors.

The use of pre- and perinatal risk factors as predictive factors may lower the age limit for reliable autism prediction. The objective of this study was to develop a clinical model based on these risk factors to predict autism. A stepwise logistic regression analysis was conducted to explore the relationships between 28 candidate risk factors and autism risk among 615 Han Chinese children with autism and 615 unrelated typically developing children. The significant factors were subsequently used to create a clinical risk score model. A chi-square automatic interaction detector (CHAID) decision tree was used to validate the selected predictors included in the model. The predictive performance of the model was evaluated by an independent cohort. Five factors (pregnancy influenza-like illness, pregnancy stressors, maternal allergic/autoimmune disease, cesarean section, and hypoxia) were found to be significantly associated with autism risk. A receiver operating characteristic (ROC) curve indicated that the risk score model had good discrimination ability for autism, with an area under the curve (AUC) of 0.711 (95% CI=0.679-0.744); in the external validation cohort, the model showed slightly worse but overall similar predictive performance. Further subgroup analysis indicated that a higher risk score was associated with more behavioral problems. The risk score also exhibited robustness in a subgroup analysis of patients with mild autism. This risk score model could lower the age limit for autism prediction with good discrimination performance, and it has unique advantages in clinical application.

Markers of imminent myocardial infarction

Myocardial infarction is a leading cause of death globally but is notoriously difficult to predict. We aimed to identify biomarkers of an imminent first myocardial infarction and design relevant prediction models. Here, we constructed a new case–cohort consortium of 2,018 persons without prior cardiovascular disease from six European cohorts, among whom 420 developed a first myocardial infarction within 6 months after the baseline blood draw. We analyzed 817 proteins and 1,025 metabolites in biobanked blood and 16 clinical variables. Forty-eight proteins, 43 metabolites, age, sex and systolic blood pressure were associated with the risk of an imminent first myocardial infarction. Brain natriuretic peptide was most consistently associated with the risk of imminent myocardial infarction. Using clinically readily available variables, we devised a prediction model for an imminent first myocardial infarction for clinical use in the general population, with good discriminatory performance and potential for motivating primary prevention efforts.

Deep learning in computed tomography to predict endotype in chronic rhinosinusitis with nasal polyps

BackgroundAs treatment strategies differ according to endotype, rhinologists must accurately determine the endotype in patients affected by chronic rhinosinusitis with nasal polyps (CRSwNP) for the appropriate management. In this study, we aim to construct a novel deep learning model using paranasal sinus computed tomography (CT) to predict the endotype in patients with CRSwNP.MethodsWe included patients diagnosed with CRSwNP between January 1, 2020, and April 31, 2023. The endotype of patients with CRSwNP in this study was classified as eosinophilic or non-eosinophilic. Sinus CT images (29,993 images) were retrospectively collected, including the axial, coronal, and sagittal planes, and randomly divided into training, validation, and testing sets. A residual network-18 was used to construct the deep learning model based on these images. Loss functions, accuracy functions, confusion matrices, and receiver operating characteristic curves were used to assess the predictive performance of the model. Gradient-weighted class activation mapping was performed to visualize and interpret the operating principles of the model.ResultsAmong 251 included patients, 86 and 165 had eosinophilic or non-eosinophilic CRSwNP, respectively. The median (interquartile range) patient age was 49 years (37–58 years), and 153 (61.0%) were male. The deep learning model showed good discriminative performance in the training and validation sets, with areas under the curves of 0.993 and 0.966, respectively. To confirm the model generalizability, the receiver operating characteristic curve in the testing set showed good discriminative performance, with an area under the curve of 0.963. The Kappa scores of the confusion matrices in the training, validation, and testing sets were 0.985, 0.928, and 0.922, respectively. Finally, the constructed deep learning model was used to predict the endotype of all patients, resulting in an area under the curve of 0.962.ConclusionsThe deep learning model developed in this study may provide a novel noninvasive method for rhinologists to evaluate endotypes in patients with CRSwNP and help develop precise treatment strategies.