Discriminatory Capacity Research Articles

Assessing a prediction model for depression risk using an early adolescent sample with self‐reported depression

AbstractBackgroundMajor depressive disorder (MDD) in adolescence is a risk factor for poor physical and psychiatric outcomes in adulthood, with earlier age of onset associated with poorer outcomes. Identifying Depression Early in Adolescence Risk Score (IDEA‐RS) is a model for predicting MDD in youth aged >15 years, but replication in younger samples (<15 years) is lacking. Here, we tested IDEA‐RS in a younger sample (9–11 years) to assess whether IDEA‐RS could be applied to earlier onset depression.MethodsWe applied IDEA‐RS predictor weights to 9854 adolescents (9–11 years) from the Adolescent Brain Cognitive Development (ABCD) Study, United States. We derived incident depression outcomes from self‐reported data at 2‐year follow‐up (11–13 years): incident MDD and increase in depression symptoms (DS). Sensitivity analyses were conducted using parent‐reported data. We assessed accuracy and calibration in predicting self‐reported incident depression and compared this to a refitted model with predictor weights derived in ABCD. Lastly, we tested associations between IDEA‐RS predictors and self‐reported incident depression.ResultsExternal replication yielded better‐than‐chance discriminative capacity for self‐reported incident depression (MDD: AUC = 61.4%, 95% CI = 53.5%–69.4%; DS: AUC = 57.9%, 95% CI = 54.6%–61.3%) but showed poor calibration with overly extreme risk estimates. Re‐estimating predictor weights improved discriminative capacity (MDD: AUC = 75.9%, 95% CI = 70.3%–81.4%; DS: AUC = 64.8%, 95% CI = 61.9%–67.7%) and calibration. IDEA‐RS predictors ‘poorest level of relationship with the primary caregiver’ (OR = 4.25, 95% CI = 1.73–10.41) and ‘high/highest levels of family conflict’ (OR = 3.36 [95% CI = 1.34–8.43] and OR = 3.76 [95% CI = 1.50–9.38], respectively) showed greatest associations with self‐reported incident MDD.ConclusionsWhile IDEA‐RS yields better‐than‐chance predictions on external replication, accuracy is improved when differences between samples, such as case‐control mix, are adjusted for. IDEA‐RS may be more suited to research settings with sufficient data for refitting. Altogether, we find that IDEA‐RS can be generalisable to early adolescents after refitting and that family dysfunction may be especially impactful for this period of development.

Using MRI Texture Analysis Machine Learning Models to Assess Graft Interstitial Fibrosis and Tubular Atrophy in Patients with Transplanted Kidneys

Objective: Interstitial fibrosis/tubular atrophy (IFTA) is a common, irreversible, and progressive form of chronic kidney allograft injury, and it is considered a critical predictor of kidney allograft outcomes. The extent of IFTA is estimated through a graft biopsy, while a non-invasive test is lacking. The aim of this study was to evaluate the feasibility and accuracy of an MRI radiomic-based machine learning (ML) algorithm to estimate the degree of IFTA in a cohort of transplanted patients. Approach: Patients who underwent MRI and renal biopsy within a 6-month interval from 1 January 2012 to 1 March 2021 were included. Stable MRI sequences were selected, and renal parenchyma, renal cortex and medulla were segmented. After image filtering and pre-processing, we computed radiomic features that were subsequently selected through a LASSO algorithm for their highest correlation with the outcome and lowest intercorrelation. Selected features and relevant patients’ clinical data were used to produce ML algorithms using 70% of the study cases for feature selection, model training and validation with a 10-fold cross-validation, and 30% for model testing. Performances were evaluated using AUC with 95% confidence interval. Main results: A total of 70 coupled tests (63 patients, 35.4% females, mean age 52.2 years) were included and subdivided into a wider cohort of 50 for training and a smaller cohort of 20 for testing. For IFTA ≥ 25%, the AUCs in test cohort were 0.60, 0.59, and 0.54 for radiomic features only, clinical variables only, and a combined radiomic–clinical model, respectively. For IFTA ≥ 50%, the AUCs in training cohort were 0.89, 0.84, and 0.96, and in the test cohort, they were 0.82, 0.83, and 0.86, for radiomic features only, clinical variables only, and the combined radiomic–clinical model, respectively. Significance: An ML-based MRI radiomic algorithm showed promising discrimination capacity for IFTA > 50%, especially when combined with clinical variables. These results need to be confirmed in larger cohorts.

Predicting nosocomial pneumonia risk in level-1 trauma patients: An external validation study using the trauma quality improvement program

BackgroundEarly identification of patients at risk of nosocomial pneumonia enables the opportunity for preventative measures, which may improve survival and reduce costs. Therefore, this study aimed to externally validate an existing prediction model (issued by Croce et al.) to predict nosocomial pneumonia in patients admitted to US level-1 trauma centers. MethodsA retrospective cohort study including patients admitted to level-1 trauma centers and registered in the TQIP, a US nationwide trauma registry, admitted between 2013–2015 and 2017–2019. The main outcome was total nosocomial pneumonia for the first period and ventilator-associated pneumonia (VAP) for the second. Model discrimination and calibration were assessed before and after recalibration. ResultsThe study comprised 902,231 trauma patients (N2013–2015 ​= ​180,601; N2017–2019 ​= ​721,630), with a median age of 52 in both periods, 64–65 ​% male, and approximately 90 ​% sustaining blunt traumatic injury. The median Injury Severity Scores were 13 (2013–2015) versus 9 (2017–2019); median Glasgow Coma Scale scores were 15. Nosocomial pneumonia incidence was 4.4 ​%, VAP incidence was 0.7 ​%. The original model demonstrated good to excellent discrimination for both periods (c-statistic2013–2015 0.84, 95%CI 0.83–0.84; c-statistic2017–2019 0.92, 95%CI 0.91–0.92). After recalibration, discriminatory capacity and calibration for the lower predicted probabilities improved. ConclusionsThe Croce model can identify patients admitted to US level-1 trauma centers at risk of total nosocomial pneumonia and VAP. Implementing (modified) Croce models in route trauma clinical practice could guide judicious use of preventative measures and prescription of additional non-invasive preventative measures (e.g., increased monitoring, pulmonary physiotherapy) to decrease the occurrence of nosocomial pneumonia in at-risk patients.

Association between vitamin D metabolism gene polymorphisms and schizophrenia.

Schizophrenia (SZ) is a multifactorial and neurodegenerative disorder that results from the interaction between genetic and environmental factors. Notably, hundreds of single nucleotide polymorphisms (SNPs) are associated with the susceptibility to SZ. Vitamin D (VD) plays an essential role in regulating several genes important for maintaining brain function and health. To the best of the authors' knowledge, no studies have yet been conducted on the association between the VD pathway and patients with SZ. Therefore, the present study aimed to assess the potential association between eight SNPs in genes related to the VD pathway, including CYP2R1, CYP27B1, CYP24A1 and VDR among patients with SZ. A case-control study was conducted, involving a total of 400 blood samples drawn from 200 patients and 200 healthy controls. Genomic DNA was extracted and variants were genotyped using the tetra-amplification refractory mutation system-polymerase chain reaction method. The present study revealed statistically significant differences between patients with SZ and controls regarding the genotypes and allele distributions of three SNPs [CYP2R1 (rs10741657), CYP27B1 (rs10877012) and CYP24A1 (rs6013897) (P<0.0001)]. The AA genotype of rs10741657 was identified to be associated with SZ (P<0.0001) and the frequency of the A allele was higher in patients with SZ (P<0.0001) compared with the control group. Similarly, the TT genotype of rs10877012 was revealed to be associated with SZ (P<0.0001) and the T allele was more frequent in patients with SZ (P<0.0001) than in the control group. Moreover, the AA genotype of rs6013897 was revealed to be associated with SZ (P<0.0001), although no significant difference was detected between the two groups regarding the A allele (P=0.055). VDR (rs2228570, rs1544410, rs731236 and rs7975232) and CYP27B1 (rs4646536) gene polymorphisms did not exhibit a significant association with SZ. While the studied SNPs revealed promising discriminatory capacity between patients with SZ and controls, the rs10741657 SNP exhibited the most optimal area under the curve value at 0.615. A logistic model was applied considering only the significant SNPs and VD levels, which revealed that rs6013897 (T/A) and VD may have protective effects (0.267, P<0.001; 0.888, P<0.001, respectively). Moreover, a low serum VD level was highly prevalent in patients with SZ compared with the controls. Based on this finding, an association between serum 25(OH)D and SZ could be demonstrated. The present study revealed that CYP2R1 (rs10741657), CYP27B1 (rs10877012) and CYP24A1 (rs6013897) gene SNPs may be associated with SZ susceptibility.

Predicting Non-Mass Breast Cancer Utilizing Ultrasound and Molybdenum Target X-Ray Characteristics.

The aim of this study is to investigate the influence of ultrasound and molybdenum target X-ray characteristics in predicting non-mass breast cancer. A retrospective analysis was conducted on the clinical data of 185 patients presenting with non-mass breast lesions between September 2019 and 2021. The non-mass lesions were categorized into benign and malignant types based on ultrasonographic findings, which included lamellar hypoechoic, ductal alteration, microcalcification, and structural disorder types. Furthermore, an examination was undertaken to discern variances in molybdenum target X-ray parameters, ultrasonographic manifestations, and characteristics among individuals diagnosed with non-mass breast lesions. The ultrasonographic depiction of microcalcified lesions and the identification of suspicious malignancy through molybdenum target X-ray evaluation exhibited independent associations with non-mass breast cancer, yielding statistically significant differences (p < 0.05). Subsequently, the logistic regression model was formulated as follows: Logit (P) =-1.757+2.194* microcalcification type on ultrasound + 1.520* suspicious malignancy on molybdenum target X-ray evaluation. The respective areas under the receiver operating characteristic curves for microcalcification type on ultrasound, suspicious malignancy on molybdenum target X-ray, and the integrated diagnostic model were 0.733, 0.667, and 0.827, respectively, demonstrating discriminative capacities. Using both ultrasound and molybdenum target X-ray diagnostics can increase the accuracy of non-mass breast cancer detection. The findings of this study have the potential to augment the detection rate of non-lumpy breast cancer and provide an imaging basis for enhancing the prognosis of individuals with breast cancer.

Evaluating Handwritten Character Recognition with Hu Moments and K-Nearest Neighbors Algorithm

Handwritten character recognition remains a challenging task in various domains, including handwriting analysis and document digitization. This task poses a significant challenge because of the variability and complexity of handwriting. To address this, it is crucial to develop different methodologies that enhance accuracy and efficiency in recognition. This research evaluates the discrimination capacity of a classifier that combines together the Hu Moments features extraction technique and the k-nearest neighbors (KNN) algorithm for the purpose of handwritten character recognition. The authors worked with handwritten characters from the English alphabet where each character is represented in two handwritten forms. The average accuracy of recognition was 82.69%, that conforms the efficiency of the proposed classifier. This research contributes to the field of automated handwritten recognition and highlights the necessity for improved techniques in character analysis, which has implications for handwriting recognition in different contexts, linguistic studies, document digitization, and other applications where character recognition is crucial. This is the first study that aims to apply the combination of Hu Moments features extraction technique in combination with the KNN algorithm for purpose of handwritten character recognition.

The relationship between the expression of fibroblast growth factor 19 and insulin-like growth factor 1 in colorectal polyp tissues and the occurrence of colorectal adenomas

Objective: This investigation sought to delineate the associations among colorectal adenomatous polyps, diabetes, and biomolecules involved in glucose metabolism. Method: Data were collected from 40 patients who underwent endoscopic polypectomy at the Endoscopy Department of Shandong Cancer Hospital between June 2019 and September 2021. This cohort included 27 patients with inflammatory polyps and 13 with adenomatous polyps. We assessed fasting insulin (Fins), fasting blood glucose (FBG), and the mRNA expressions of fibroblast growth factor 19 (FGF-19) and insulin-like growth factor 1 (IGF-1) in the polyp tissues. Both univariate and multivariate logistic regression analyses were employed to ascertain the determinants influencing the emergence of adenomatous polyps. From these analyses, a predictive nomogram was constructed to forecast the occurrence of adenomatous polyps, and evaluations on the discriminative capacity, calibration, and clinical utility of the model were conducted. Results: The adenomatous polyp group exhibited markedly elevated levels of glucose, insulin, FGF-19, and IGF-1, with respective concentrations of (8.67±2.70) mmol/L, (12.72±7.69) μU/L, 2.20±1.88, and 1.36±0.69. These figures were significantly higher compared to the inflammatory polyp group, which showed levels of (5.51±0.72) mmol/L, (5.49±2.68) μU/L, 0.53±0.97, and 0.41±0.46, respectively, P=0.001. Multivariate logistic regression revealed that the relative expression of IGF-1 served as an independent risk factor for the development of colorectal adenomatous polyps (OR=5.622, 95% CI:1.085-29.126). The nomogram displayed a C-index of 0.849, indicating substantial discriminative capability. The calibration curve affirmed the model's accuracy in aligning predicted probabilities with actual outcomes, and the clinical decision curve demonstrated thepractical clinical applicability of the model. Conclusions: There was a significant correlation between the occurrence of colorectal adenomatous polyps and glucose metabolic pathways. Individuals with diabetes showed a higher propensity to develop such polyps.

The predictive value of coronary computed tomography angiography-derived fractional flow reserve for perioperative cardiac events in lung cancer surgery.

As a non-invasive coronary functional examination, coronary computed tomography angiography (CCTA)-derived fractional flow reserve (CT-FFR) showed predictive value in several non-cardiac surgeries. This study aimed to evaluate the predictive value of CT-FFR in lung cancer surgery. We retrospectively collected 227 patients from January 2017 to June 2022 and used machine learning-based CT-FFR to evaluate the stable coronary artery disease (CAD) patients undergoing lung cancer surgery. The major adverse cardiac event (MACE) was defined as perioperative myocardial injury (PMI), myocardial infarction, heart failure, atrial and ventricular arrhythmia with hemodynamic disorder, cardiogenic shock and cardiac death. The multivariate logistic regression analysis was performed to identify risk factors for MACE and PMI. The discriminative capacity, goodness-of-fit, and reclassification improvement of prediction model were determined before and after the addition of CT-FFR≤0.8. The incidence of MACE was 20.7% and PMI was 15.9%. CT-FFR significantly outperformed CCTA in terms of accuracy for predicting MACE (0.737 vs 0.524). In the multivariate regression analysis, CT-FFR≤0.8 was an independent risk factor for both MACE [OR=10.77 (4.637, 25.016), P<0.001] and PMI [OR=8.255 (3.372, 20.207), P<0.001]. Additionally, we found that the performance of prediction model for both MACE and PMI improved after the addition of CT-FFR. CT-FFR can be used to assess the risk of perioperative MACE and PMI in patients with stable CAD undergoing lung cancer surgery. It adds prognostic information in the cardiac evaluation of patients undergoing lung cancer surgery.

ACAN: A plug-and-play Adaptive Center-Aligned Network for unsupervised domain adaptation

Domain adaptation is an important topic due to its capability in transferring knowledge from source domain to target domain. However, many existing domain adaptation methods primarily concentrate on aligning the data distributions between the source and target domains, often neglecting discriminative feature learning. As a result, target samples with low confidence are embedded near the decision boundary, where they are susceptible to being misclassified, resulting in negative transfer. To address this problem, a novel Adaptive Center-Aligned Network dubbed ACAN is proposed for unsupervised domain adaptation in this work. The main innovations of ACAN are fourfold. Firstly, it is a plug-and-play module and can be easily incorporated into any domain alignment methods without increasing the model complexity and computational burden. Secondly, in contrast to conventional softmax plus cross-entropy loss, angular margin loss is called to enhance the discrimination power for classifier. Thirdly, entropy regularization is exploited to highlight the probability of potential related class, which renders our learned feature representation far away from the decision boundary. Fourthly, to improve the discriminative capacity of model to the target domain, we propose to align the target domain samples to the corresponding class center via pseudo labels. Incorporating ACAN, the performance of baseline domain alignment methods is significantly improved. Extensive ablation and comparison experiments on four widely adopted databases demonstrate the effectiveness of our ACAN. Code is available at: https://github.com/Cloudfly-Z/ACAN

Prospective Study: Utility of Anterior Segment Optical Coherence Tomography to Identify Predictive Factors of Recurrence in Pterygium Surgery.

Background/Objectives: The main purpose of this study is to determine, by anterior segment optical coherence tomography (AS-OCT), the anatomical characteristics, both preoperatively and postoperatively, that correlate with a higher rate of pterygium recurrence after surgery with exeresis and conjunctival autograft with biological glue. Methods: A total of 50 eyes which were listed for primary pterygium surgery at an ophthalmology tertiary centre were treated with standard pterygium excision and a conjunctival autograft with tissue glue. Ten variables were measured with AS-OCT (Casia 2; Tomey Corp., Nagoya, Japan) during six control visits with all patients. Finally, statistical analysis was performed using SPSS (SPSS stadistics®, IBM®, version 21.0.0.0) for descriptive variables and R-project (The R foundation©, version 3.0.2) for the rest of the analyses, including a descriptive analysis and an inferential analysis studying prognostic factors of recurrence and their predictive capacity. Results: Among the 50 patients who underwent surgery, recurrence was detected in 8 cases (rate 16%; 95% CI: 5.8-26.2%). Most cases (n = 6) were detected 3 months after surgery. The pattern of recurrences was atrophic in two thirds of the cases; none required reintervention. Preoperative total conjunctival thickness at 3 mm was significantly increased in patients who developed recurrence. One week after surgery, epithelial and stromal thickness at 1 mm and total thickness at 3 mm proved to be useful for predicting recurrence. Both models have significant discriminant capacity. Conclusions: By imaging the graft with AS-OCT preoperatively and 7 days after surgery, the risk of future recurrence can be predicted.

External validation of the natriuretic response prediction equation to discriminate diuretic response in heart failure.

Incomplete decongestion due to lack of titration of diuretics to effective doses is a common reason for readmission in patients with acute decompensated heart failure (ADHF). The natriuretic response prediction equation (NRPE) is a novel tool that proved to be rapid and accurate to predict natriuretic response and does not need urine collection. However, the NRPE has not been externally validated. The goal of this study was to externally validate the discrimination capacity of the NRPE in patients with ADHF and fluid overload. Patients admitted with ADHF who required intravenous loop diuretics were included. A spot urine sample was obtained ~2h following diuretic administration, and a timed 6-h urine collection by study staff was carried out. Urine sodium and urine creatinine from the spot urine sample were used to predict the 6-h natriuretic response using the NRPE. The primary goal was to validate the NRPE to discriminate poor loop diuretic natriuretic response (sodium output <50 mmol in the 6h following diuretic administration). The NRPE was compared with urine sodium and measured urine output which are the methods currently recommended by international guidelines to assess diuretic response. Eighty-seven diuretic administrations from 49 patients were analysed. Mean age of patients was 57±17 years and 67% were male. Mean estimated glomerular filtration rate was 65±28mL/min/1.73m2, and ejection fraction was 35±15%. Median dose of intravenous furosemide equivalents administered the day of the study was 80 mg (IQR 40 - 160). Poor natriuretic response occurred in 39% of the visits. The AUC of the NRPE to predict poor natriuretic response during the 6-h urine collection was 0.91 (95% CI 0.85-0.98). Compared with the NRPE, spot urine sodium concentration (AUC 0.75) and urine output during the corresponding nursing shift (AUC 0.74) showed lower discrimination capacity. In this cohort of patients with ADHF, the NRPE outperformed spot urine sodium concentration and all other metrics related to diuretic response to predict poor natriuretic response. Our findings support the use of this equation at other settings to allow rapid and accurate prediction of natriuretic response.

Changes of intracardiac flow dynamics measured by HyperDoppler in patients with aortic stenosis.

Assessment of intracardiac flow dynamics has recently acquired significance due to the development of new measurement methods based on echocardiography. Recent studies have demonstrated that cardiac abnormalities are associated with changes in intracardiac vortical flows. Yet, no previous study assessed the impact of aortic stenosis (AS) on intracardiac vortices. This study aims to explore the clinical potential of additional information provided by quantifying intracardiac flow dynamics in patients with AS. One hundred and twenty patients with severe AS, sixty patients with concentric ventricular remodelling (VR), and hundred controls (CTRL) were prospectively included and underwent non-invasive evaluation of intracardiac flow dynamics. In addition to standard echocardiography, fluid dynamics were assessed by means of HyperDoppler. Vortex depth (P < 0.001), vortex length (P = 0.003), vortex intensity (P < 0.001), and vortex area (P = 0.049) were significantly increased in AS compared with CTRL. In addition, mean energy dissipation was significantly higher in AS compared with CTRL (P < 0.001) and VR (P = 0.002). At receiver operating characteristic analysis, vortex depth showed the best discrimination capacity for AS (P < 0.001). Changes in fluid dynamics-based HyperDoppler indices can be reliably assessed in patients with AS. Significant changes in vortex depth and intensity can selectively differentiate AS from both concentric remodelling and healthy CTRLs, suggesting that the assessment of intracardiac flow dynamics may provide complementary information to standard echocardiography to better characterize patients' subsets.

Metabolic dysfunction-associated steatotic liver disease (SLD) and alcohol-associated liver disease, but not SLD without metabolic dysfunction, are independently associated with new onset of chronic kidney disease during a 10-year follow-up period.

The new nomenclature of steatotic liver disease (SLD) including metabolic dysfunction-associated SLD (MASLD), MASLD and increased alcohol intake (MetALD), and alcohol-associated liver disease (ALD) has recently been proposed. We aimed to elucidate the relationship between each category of SLD and chronic kidney disease (CKD). We investigated the effects of various SLDs on the development of CKD, defined as estimated glomerular filtration rate (eGFR)<60mL/min/1.73m2 or positive for urinary protein, during a 10-year period in 12138 Japanese subjects (men/women, 7984/4154; mean age, 48years) who received annual health examinations including abdominal ultrasonography. The prevalences of SLD without metabolic dysfunction (SLD-MD[-]), MASLD, MetALD, and ALD were 1.7%, 26.3%, 4.9%, and 1.9%, respectively. During the follow-up period, 1963 subjects (16.2%) (men/women, 1374 [17.2%]/589 [14.2%]) had new onset of CKD. Multivariable Cox proportional hazard model analyses after adjustment of age, sex, eGFR, current smoking habit, diabetes mellitus, hypertension, and dyslipidemia showed that the hazard ratios (HR [95% confidence interval]) for the development of CKD in subjects with MASLD (1.20 [1.08-1.33], p=0.001) and those with ALD (1.41 [1.05-1.88], p=0.022), but not those with MetALD (1.11 [0.90-1.36], p=0.332), were significantly higher than the HR in subjects with non-SLD. Interestingly, subjects with SLD-MD[-] had a significantly lower HR (0.61 [0.39-0.96], p=0.034) than that in subjects with non-SLD. The addition of the novel classification of SLDs into traditional risk factors for the development of CKD significantly improved the discriminatory capacity. MASLD and ALD, but not SLD-MD[-], are independently associated with the development of CKD.

Right anterior insula ASL hypoperfusion as a diagnostic biomarker of prodromal and mild dementia with Lewy bodies: preliminary evidence using a Bayesian approach.

Identifying and validating a biomarker with high specificity in early-stage dementia with Lewy bodies (DLB) using a feasible method is crucial to enhance the current suboptimal diagnostic procedure. Previous research revealed abnormalities, including hypoperfusion in the right anterior insular cortex at group level, in prodromal DLB. Exploring hypoperfusion of the right anterior insula, at an individual-level and assessing its relevance as a potential imaging biomarker in early DLB, has, to our knowledge, not been investigated. Our preliminary study aims to assess the feasibility of the technique and to provide a methodological framework for further investigation. We assessed the feasibility and accuracy of the hypoperfusion of the right anterior insula per arterial spin labelling magnetic resonance imaging (ASL-MRI) as a diagnostic biomarker in early DLB and provided rough estimates of its sensitivity and specificity. Defining the region of interest based on previous research, we established the biomarker as the hypoperfusion of the right anterior insula. Discriminative and analytical performances were assessed in comparison to a control group of treatment-resistant depression patients. Bayesian diagnostic reasoning was employed to assess the biomarker diagnostic usability in early DLB in two scenarios: healthy elderly controls and mild cognitive impairment. Additionally, we updated probabilities by integrating data from the Mayo-clinic cognitive fluctuations scale and real-time quaking-induced conversion (RT-QuIC) α-synuclein data. Lastly, a whole-brain perfusion analysis of DLB patients was conducted to identify further brain regions with discriminative abilities. We successfully replicated the right anterior insular hypoperfusion (RAI-Hypo) in all DLB patients at the individual level. The overall sensitivity of the biomarker was 96%, and the specificity was 92%. Bayesian testing revealed the biomarker's highest performance in early-stage DLB with cognitive fluctuations, showcasing a diagnostic potential associated with a high precision and moderate accuracy. In a cognitively non-impaired population, the RAI-Hypo showed a limited usability and lacked in selectivity to qualify as a screening tool. The exploratory whole-brain analysis revealed perfect discriminative capacities in the bilateral anterior insulae and the left inferior parietal lobule. Further studies are needed to confirm our preliminary results. If performance is maintained in subsequent studies and is compared to a more suitable control population, the proposed biomarker may be eventually sufficient to discriminate early-stage DLB from non-DLB.

External validation of Finnish diabetes risk score (FINDRISC) and Latin American FINDRISC for screening of undiagnosed dysglycemia: Analysis in a Peruvian hospital health care workers sample.

To evaluate the external validity of Finnish diabetes risk score (FINDRISC) and Latin American FINDRISC (LAFINDRISC) for undiagnosed dysglycemia in hospital health care workers. We carried out a cross-sectional study on health workers without a prior history of diabetes mellitus (DM). Undiagnosed dysglycemia (prediabetes or diabetes mellitus) was defined using fasting glucose and two-hour oral glucose tolerance test. LAFINDRISC is an adapted version of FINDRISC with different waist circumference cut-off points. We calculated the area under the receptor operational characteristic curve (AUROC) and explored the best cut-off point. We included 549 participants in the analysis. The frequency of undiagnosed dysglycemia was 17.8%. The AUROC of LAFINDRISC and FINDRISC were 71.5% and 69.2%; p = 0.007, respectively. The optimal cut-off for undiagnosed dysglycemiaaccording to Index Youden was ≥ 11 in LAFINDRISC (Sensitivity: 78.6%; Specificity: 51.7%) and ≥12 in FINDRISC (Sensitivity: 70.4%; Specificity: 53.9%). The discriminative capacity of both questionnaires is good for the diagnosis of dysglycemia in the healthcare personnel of the María Auxiliadora hospital. The LAFINDRISC presented a small statistical difference, nontheless clinically similar, since there was no difference by age or sex. Further studies in the general population are required to validate these results.

Establishing the utility of multi-platform liquid biopsy by integrating the CSF methylome and proteome in CNS tumours.

Liquid biopsy represents a major development in cancer research, with significant translational potential. Similarly, it is increasingly recognized that multi-omic molecular approaches are a powerful avenue through which to understand complex and heterogeneous disease biology. We hypothesize that merging these two promising frontiers of cancer research will improve the discriminatory capacity of current models and allow for improved clinical utility. We have compiled a cohort of patients with glioblastoma, brain metastasis, and primary central nervoussystem lymphoma. Cell-free methylated DNA immunoprecipitation (cfMeDIP) and shotgun proteomic profiling wasobtained from the cerebrospinal fluid (CSF) of each patient and used to build tumour-specific classifiers. We show that the DNA methylation and protein profiles of cerebrospinal fluid can be integrated to fully discriminate lymphoma from its diagnostic counterparts with perfect AUC of 1 (95% confidence interval 1-1) and 100% specificity, significantly outperforming single-platform classifiers. We present the most specific and accurate CNS lymphoma classifier to date and demonstrates the synergistic capability of multi-platform liquid biopsies. This has far-reaching translational utility for patients with newly diagnosed intra-axial brain tumours.

Effect of Plasma Epstein-Barr Virus Nucleic Acid Loads on the Clinical Features and Prognosis in Adult Secondary Hemophagocytic Lymphohistiocytosis

To investigate the effect of pre-treatment plasma Epstein-Barr virus (EBV) DNA copy number on the clinical features and prognosis of patients with adult secondary hemophagocytic lymphohistiocytosis(sHLH). The clinical characteristics, survival rate, and prognostic factors of 171 patients with adult sHLH treated at Jiangsu Province Hospital from June 2017 to January 2022 were retrospectively analyzed in this study. Patients were divided into three groups, including the EBV DNA-negative group(<5.0×102 copies/ml), lower EBV-DNA loads group(5.0×102-8.51×104 copies/ml), and higher EBV-DNA loads group(＞8.51×104 copies/ml), according to pre-treatment plasma EBV-DNA copy number. Cox regression model was established for screening prognostic factors. Adult sHLH survival prediction model was constructed and realized through the nomogram based on EBV-DNA load after adjusted the factors affecting survival of etiology and treatment strategy.Concordance index (C-index) and calibration curves were calculated to verify model predictive and discriminatory capacity. Among 171 adult sHLH patients, 84 patients were not infected with EBV (EBV DNA-negative group), and 87 with EBV (EBV DNA-positive group, 48 lower EBV-DNA loads group and 39 higher EBV-DNA loads group). Consistent elevations in the levels of liver enzymes (ALT and AST), LDH, TG, β 2-microglobulin and ferritin across the increasing of EBV-DNA load (all P <0.05), while the levels of fibrinogen decrease (P <0.001). The median follow-up time was 52 days (range 20-230 days), and 123 patients died. The overall survival (OS) rate of patients in EBV DNA-positive group was lower than that in EBV DNA-negative group (median OS: 40 days vs 118 days, P <0.001). Higher EBV-DNA loads had worse OS (median OS: 24 days vs 45 days vs 118 days, P <0.0001 for trend) compared to lower EBV-DNA loads and EBV DNA-negative group. Multivariate Cox analysis revealed that higher EBV-DNA loads (P =0.005), fibrinogen≤1.5 g/L (P ＝0.012), ferritin (P ＝0.041), associated lymphoma (P ＝0.002), and anti-tumor based strategy (P ＝0.001) were independent prognostic factors for OS. The C-indexes of 30 day, 90 days, 365 days survival rate were all greater than 0.8 of the nomogram model and calibration curves provided credibility to their predictive capability. Subgroup analysis showed that patients with higher EBV-DNA loads had a significantly worse prognosis in adult sHLH who were women, ferritin＞5 000 μg/L, β2-microglobulin＞7.4 mmol/L and regardless of age, etiologies, HScore points. The EBV-DNA load is a strong and independent predictor for survival in patients with sHLH. The prognostic nomogram based on EBV-DNA loads was dependable and provides a visual tool for evaluating the survival of adult sHLH.

Direct Bilirubin, but not Indirect Bilirubin, is Associated with Short-term Adverse Events in HFpEF.

Abnormal live function tests have been identified as independent risk factors for ominous prognosis in patients with heart failure. However, most of the previous studies have failed to determine the contribution of direct bilirubin (DBIL) and indirect bilirubin (IBIL) separately. Hence, we aimed to explore whether DBIL or IBIL is correlated with the prognosis of heart failure with preserved ejection fraction (HFpEF). A total of 19837 patients were hospitalized for HFpEF between January 2012 and January 2022 in Fuqing City Hospital affiliated with Fujian Medical University. The primary endpoint was in-hospital all-cause mortality. Secondary endpoints included in-hospital cardiovascular mortality and 30-day re-admission for heart failure. Univariable analysis indicated that patients with elevated DBIL or IBIL were exposed to a higher risk of mortality and re-admission. However, in multivariable models, both ln-transformed DBIL and TBIL, but not IBIL, were independent risk factors for in-hospital all-cause mortality (hazard ratio (HR)=1.796, 95% confidential interval (CI)=1.477-2.183, P<0.001; HR=1.854, 95% CI=1.461-2.352, P.0.001; HR=1.161, 95% CI=0.959-1.407, P=0.126) and in-hospital cardiovascular mortality (HR=1.831, 95% CI=1.345-2.492, P.0.001; HR=1.899, 95% CI=1.300-2.773, P=0.001; HR=1.145, 95% CI=0.841-1.561, P=0.389). Only DBIL remained independently associated with 30-day readmission for heart failure (HR=1.361, 95% CI=1.036-1.787, P=0.027). Adding ln-transformed DBIL to model 1 increased its discriminatory capacity (C-statistic: 0.851 to 0.869, respectively), whereas adding ln-transformed IBIL yielded little increment (C-statistic: 0.851 to 0.852, respectively). DBIL, but not IBIL, was associated with short-term ominous prognosis in patients with HFpEF. Hence, DBIL may be the superior predictor for prognosis in HFpEF.

Overall prognosis of index lung cancer recurrence or of second primary lung cancer in people with non-small cell lung cancer operated with complete resection.

This is a protocol for a Cochrane Review (prognosis). The objectives are as follows: We aim to compare overall survival in people with recurrence and second primary lung cancer (SPLC) after lung cancer surgery. If survival differs between those people categorised as having index lung cancer recurrence and those categorised as having SPLC, it might be possible to identify the definition that has the best discriminatory capacity from the various published definitions of these conditions, so that it can be used in future.

A machine learning-based approach for individualized prediction of short-term outcomes after anterior cervical corpectomy.

A retrospective machine learning (ML) classification study for prognostic modeling after anterior cervical corpectomy (ACC). To evaluate the effectiveness of ML in predicting ACC outcomes and develop an accessible, user-friendly tool for this purpose. Based on our literature review, no study has examined the capability of ML algorithms to predict major shortterm ACC outcomes, such as prolonged length of hospital stay (LOS), non-home discharge, and major complications. The American College of Surgeons' National Surgical Quality Improvement Program database was used to identify patients who underwent ACC. Prolonged LOS, non-home discharges, and major complications were assessed as the outcomes of interest. ML models were developed with the TabPFN algorithm and integrated into an open-access website to predict these outcomes. The models for predicting prolonged LOS, non-home discharges, and major complications demonstrated mean areas under the receiver operating characteristic curve (AUROC) of 0.802, 0.816, and 0.702, respectively. These findings highlight the discriminatory capacities of the models: fair (AUROC >0.7) for differentiating patients with major complications from those without, and good (AUROC >0.8) for distinguishing between those with and without prolonged LOS and non-home discharges. According to the SHapley Additive Explanations analysis, single- versus multiple-level surgery, age, body mass index, preoperative hematocrit, and American Society of Anesthesiologists physical status repetitively emerged as the most important variables for each outcome. This study has considerably enhanced the prediction of postoperative results after ACC surgery by implementing advanced ML techniques. A major contribution is the creation of an accessible web application, highlighting the practical value of the developed models. Our findings imply that ML can serve as an invaluable supplementary tool to stratify patient risk for this procedure and can predict diverse postoperative adverse outcomes.