OBJECTIVE: To observe the correlation between the four limbs perfusion index (PI) and blood lactic acid in patients with neurosis, and evaluate the predictive value of PI on microcirculation perfusion metabolic disorder in patients with neurosis. METHODS: A prospective observational study was conducted. Adult patients admitted to the department of neurological intensive care unit (NICU) of the First Affiliated Hospital of Xinjiang Medical University from July 1 to August 20 in 2020 were enrolled. Under the condition of indoor temperature controlled at 25 centigrade, all patients were placed in the supine position, and the blood pressure, heart rate, PI of both fingers and thumb toes and arterial blood lactic acid were measured within 24 hours and 24-48 hours after NICU. The difference of four limbs PI at different time periods and its correlation with lactic acid were compared. Receiver operator characteristic curve (ROC curve) was used to evaluate the predictive value of four limbs PI on patients with microcirculatory perfusion metabolic disorder. RESULTS: A total of 44 patients with neurosis were enrolled, including 28 males and 16 females; average age (61.2±16.5) years old. There were no significant differences in PI of the left index finger and the right index finger [2.57 (1.44, 4.79) vs. 2.70 (1.25, 5.33)], PI of the left toe and the right toe [2.09 (0.85, 4.76) vs. 1.88 (0.74, 4.32)] within 24 hours after entering the NICU, and the PI of the left index finger and the right index finger [3.17 (1.49, 5.07) vs. 3.14 (1.33, 5.36)], PI of the left toe and the right toe [2.07 (0.75, 5.20) vs. 2.07 (0.68, 4.67)] at 24-48 hours after NICU admission (all P > 0.05). However, compared to the PI of the upper and lower limbs on the same side, except for the 24-48 hours after ICU of the PI difference between the left index finger and the left toe (P > 0.05), the PI of the toe was lower than that of the index finger at the other time periods (all P < 0.05). The correlation analysis showed that the PI value of four limbs of patients in both time periods were significantly negatively correlated with arterial blood lactic acid (the r values of the left index finger, the right index finger, the left toe and the right toe were -0.549, -0.482, -0.392 and -0.343 respectively within 24 hours after entering the NICU; the r values of the left index finger, the right index finger, the left toe and the right toe were -0.331, -0.292, -0.402 and -0.442 respectively after entering the NICU 24-48 hours, all P < 0.05). Taking lactic acid ≥ 2 mmol/L as the diagnostic standard for metabolic disorder of microcirculation perfusion (total 27 times, accounting for 30.7%). The efficacy of four limbs PI in predicting microcirculation perfusion metabolic disorder were compared. ROC curve analysis showed that the area under the curve (AUC) and 95% confidence interval (95%CI) of left index finger, right index finger, left toe and right toe predicting microcirculation perfusion metabolic disorder were 0.729 (0.609-0.850), 0.767 (0.662-0.871), 0.722 (0.609-0.835), 0.718 (0.593-0.842), respectively. There was no significant difference in AUC compare with each other (all P > 0.05). The cut-off value of PI of right index finger for predicting microcirculation perfusion metabolic disorder was 2.46, the sensitivity was 70.4%, the specificity was 75.4%, the positive likelihood ratio was 2.86, and the negative likelihood ratio was 0.30. CONCLUSIONS There are no significant differences in PI of bilateral index fingers, bilateral toes in patients with neurosis. However, unilateral upper and lower limbs showed lower PI in the toe than in the index finger. There is a significantly negatively correlation between PI and arterial blood lactic acid in all four limbs. PI can predict the metabolic disorder of microcirculation perfusion, and its cut-off value is 2.46.
Adult ; Female ; Male ; Humans ; Middle Aged ; Aged ; Lactic Acid ; Microcirculation ; Perfusion Index ; Lower Extremity ; Area Under Curve ; Nervous System Diseases

OBJECTIVE: To develop a noninvasive method for prediction of 1p/19q codeletion in diffuse lower-grade glioma (DLGG) based on multimodal magnetic resonance imaging (MRI) radiomics. METHODS: We collected MRI data from 104 patients with pathologically confirmed DLGG between October, 2015 and September, 2022. A total of 535 radiomics features were extracted from T₂WI, T₁WI, FLAIR, CE-T₁WI and DWI, including 70 morphological features, 90 first order features, and 375 texture features. We constructed logistic regression (LR), logistic regression least absolute shrinkage and selection operator (LRlasso), support vector machine (SVM) and Linear Discriminant Analysis (LDA) radiomics models and compared their predictive performance after 10-fold cross validation. The MRI images were reviewed by two radiologists independently for predicting the 1p/19q status. Receiver operating characteristic curves were used to evaluate classification performance of the radiomics models and the radiologists. RESULTS: The 4 radiomics models (LR, LRlasso, SVM and LDA) achieved similar area under the curve (AUC) in the validation dataset (0.833, 0.819, 0.824 and 0.819, respectively; P>0.1), and their predictive performance was all superior to that of resident physicians of radiology (AUC=0.645, P=0.011, 0.022, 0.016, 0.030, respectively) and similar to that of attending physicians of radiology (AUC=0.838, P>0.05). CONCLUSION Multiparametric MRI radiomics models show good performance for noninvasive prediction of 1p/19q codeletion status in patients with in diffuse lower-grade glioma.
Humans ; Magnetic Resonance Imaging ; Chromosome Aberrations ; Area Under Curve ; Glioma/genetics* ; ROC Curve

It is a significant challenge to improve the blood-brain barrier (BBB) permeability of central nervous system (CNS) drugs in their development. Compared with traditional pharmacokinetic property tests, machine learning techniques have been proven to effectively and cost-effectively predict the BBB permeability of CNS drugs. In this study, we introduce a high-performance BBB permeability prediction model named balanced-stacking-learning based BBB permeability predictor(BSL-B3PP). Firstly, we screen out the feature set that has a strong influence on BBB permeability from the perspective of medicinal chemistry background and machine learning respectively, and summarize the BBB positive(BBB+) quantification intervals. Then, a combination of resampling algorithms and stacking learning(SL) algorithm is used for predicting the BBB permeability of CNS drugs. The BSL-B3PP model is constructed based on a large-scale BBB database (B3DB). Experimental validation shows an area under curve (AUC) of 97.8% and a Matthews correlation coefficient (MCC) of 85.5%. This model demonstrates promising BBB permeability prediction capability, particularly for drugs that cannot penetrate the BBB, which helps reduce CNS drug development costs and accelerate the CNS drug development process.
Blood-Brain Barrier ; Algorithms ; Area Under Curve ; Databases, Factual ; Permeability

OBJECTIVE: Exosomal long noncoding RNAs (lncRNAs) are the key to diagnosing and treating various diseases. This study aimed to investigate the diagnostic value of plasma exosomal lncRNAs in white matter hyperintensities (WMH). METHODS: We used high-throughput sequencing to determine the differential expression (DE) profiles of lncRNAs in plasma exosomes from WMH patients and controls. The sequencing results were verified in a validation cohort using qRT-PCR. The diagnostic potential of candidate exosomal lncRNAs was proven by binary logistic analysis and receiver operating characteristic (ROC) curves. The diagnostic value of DE exo-lncRNAs was determined by the area under the curve (AUC). The WMH group was then divided into subgroups according to the Fazekas scale and white matter lesion site, and the correlation of DE exo-lncRNAs in the subgroup was evaluated. RESULTS: In our results, four DE exo-lncRNAs were identified, and ROC curve analysis revealed that exo-lnc_011797 and exo-lnc_004326 exhibited diagnostic efficacy for WMH. Furthermore, WMH subgroup analysis showed exo-lnc_011797 expression was significantly increased in Fazekas 3 patients and was significantly elevated in patients with paraventricular matter hyperintensities. CONCLUSION Plasma exosomal lncRNAs have potential diagnostic value in WMH. Moreover, exo-lnc_011797 is considered to be a predictor of the severity and location of WMH.
Humans ; RNA, Long Noncoding/genetics* ; White Matter ; Area Under Curve ; Exosomes/genetics* ; High-Throughput Nucleotide Sequencing

BACKGROUND: Since the diagnostic value of aldosterone to renin ratio (ARR) calculated by plasma renin concentration (PRC) or plasma renin activity (PRA) is still inconclusive, we conducted a meta-analysis by systematically reviewing relevant literature to explore the difference in the diagnostic efficacy of ARR calculated by PRC or PRA, so as to provide guidance for clinical diagnosis. METHODS: We searched PubMed, Embase, and Cochrane Library from the establishment of the database to March 2021. We included studies that report the true positive, false positive, true negative, and false negative values for the diagnosis of primary aldosteronism, and we excluded duplicate publications, research without full text, incomplete information, or inability to conduct data extraction, animal experiments, reviews, and systematic reviews. STATA 15.1 was used to analyze the data. RESULTS: The pooled results showed that ARR (plasma aldosterone concentration [PAC]/PRC) had a sensitivity of 0.82 (95% confidence interval [CI]: 0.78-0.86), a specificity of 0.94 (95% CI: 0.92-0.95), a positive-likelihood ratio (LR) of 12.77 (95% CI: 7.04-23.73), a negative LR of 0.11 (95% CI: 0.07-0.17), and symmetric area under the curve (SAUC) of 0.982, respectively. Furthermore, the diagnostic odds ratio (DOR) of ARR (PAC/PRC) was 180.21. Additionally, the pooled results showed that ARR (PAC/PRA) had a sensitivity of 0.91 (95% CI: 0.86-0.95), a specificity of 0.91 (95% CI: 0.90-0.93), a positive LR of 7.30 (95% CI: 2.99-17.99), a negative LR of 0.10 (95% CI: 0.04-0.26), and SAUC of 0.976, respectively. The DOR of ARR (PAC/PRA) was 155.52. Additionally, we conducted a subgroup analysis for the different thresholds (<35 or ≥35) of PAC/PRC. The results showed that the DOR of the cut-off ≥35 groups was higher than the cut-off <35 groups (DOR = 340.15, 95% CI: 38.32-3019.66; DOR = 116.40, 95% CI = 23.28-581.92). CONCLUSIONS The research results suggest that the determination of ARR (PAC/PRC) and ARR (PAC/PRA) was all effective screening tools for PA. The diagnostic accuracy and diagnostic value of ARR (PAC/PRC) are higher than ARR (PAC/PRA). In addition, within a certain range, the higher the threshold, the better the diagnostic value.
Aldosterone ; Area Under Curve ; Humans ; Hyperaldosteronism/diagnosis* ; Hypertension ; Renin

The goal of this study was to investigate the clinical application of free/total prostate-specific antigen (F/T PSA) ratio, considering the new broad serum total PSA (T-PSA) "gray zone" of 2.0-25.0 ng ml^-1 in differential diagnosis of prostate cancer (PCa) and benign prostate diseases (BPD) in men over 50 years in Western China. A total of 1655 patients were included, 528 with PCa and 1127 with BPD. Serum T-PSA, free PSA (F-PSA), and F/T PSA ratio were analyzed. Receiver operating characteristic curves were used to assess the efficiency of PSA and F/T PSA ratio. There were 47.4% of cancer patients with T-PSA of 2.0-25.0 ng ml^-1. When T-PSA was 2.0-4.0 ng ml^-1, 4.0-10.0 ng ml^-1, and 10.0-25.0 ng ml^-1, the area under the curve (AUC) of F/T PSA ratio was 0.749, 0.769, and 0.761, respectively. The best AUC of F/T PSA ratio was 0.811 when T-PSA was 2.0-25.0 ng ml^-1, with a specificity of 0.732, a sensitivity of 0.788, and an optimal cutoff value of 15.5%. The AUC of F/T PSA ratio in different age groups (50-59 years, 60-69 years, 70-79 years, and ≥80 years) was 0.767, 0.806, 0.815, and 0.833, respectively, and the best sensitivity (0.857) and specificity (0.802) were observed in patients over 80 years. The T-PSA trend was in accordance with the Gleason score, tumor node metastasis (TNM) stage, and American Joint Committee on Cancer prognosis group. Therefore, the F/T PSA ratio can facilitate the differential diagnosis of PCa and BPD in the broad T-PSA "gray zone". Serum T-PSA can be a Gleason score and prognostic indicator.
Area Under Curve ; Humans ; Male ; Middle Aged ; Prostate-Specific Antigen ; Prostatic Neoplasms/pathology* ; ROC Curve ; Sensitivity and Specificity

Due to the low specificity and sensitivity of biomarkers in sepsis diagnostics, the prognosis of sepsis patient outcomes still relies on the assessment of clinical symptoms. Inflammatory response is crucial to sepsis onset and progression; however, the significance of inflammatory response-related genes (IRRGs) in sepsis prognosis is uncertain. This study developed an IRRG-based signature for sepsis prognosis and immunological function. The Gene Expression Omnibus (GEO) database was retrieved for two sepsis microarray datasets, GSE64457 and GSE69528, followed by gene set enrichment analysis (GSEA) comparing sepsis and healthy samples. A predictive signature for IRRGs was created using least absolute shrinkage and selection operator (LASSO). To confirm the efficacy and reliability of the new prognostic signature, Cox regression, Kaplan-Meier (K-M) survival, and receiver operating characteristic (ROC) curve analyses were performed. Subsequently, we employed the GSE95233 dataset to independently validate the prognostic signature. A single-sample GSEA (ssGSEA) was conducted to quantify the immune cell enrichment score and immune-related pathway activity. We found that more gene sets were enriched in the inflammatory response in sepsis patient samples than in healthy patient samples, as determined by GSEA. The signature of nine IRRGs permitted the patients to be classified into two risk categories. Patients in the low-risk group showed significantly better 28-d survival than those in the high-risk group. ROC curve analysis corroborated the predictive capacity of the signature, with the area under the curve (AUC) for 28-d survival reaching 0.866. Meanwhile, the ssGSEA showed that the two risk groups had different immune states. The validation set and external dataset showed that the signature was clinically predictive. In conclusion, a signature consisting of nine IRRGs can be utilized to predict prognosis and influence the immunological status of sepsis patients. Thus, intervention based on these IRRGs may become a therapeutic option in the future.
Humans ; Reproducibility of Results ; Sepsis/genetics* ; Leukocyte Count ; Area Under Curve ; ROC Curve

BACKGROUND: The current deep learning diagnosis of breast masses is mainly reflected by the diagnosis of benign and malignant lesions. In China, breast masses are divided into four categories according to the treatment method: inflammatory masses, adenosis, benign tumors, and malignant tumors. These categorizations are important for guiding clinical treatment. In this study, we aimed to develop a convolutional neural network (CNN) for classification of these four breast mass types using ultrasound (US) images. METHODS: Taking breast biopsy or pathological examinations as the reference standard, CNNs were used to establish models for the four-way classification of 3623 breast cancer patients from 13 centers. The patients were randomly divided into training and test groups (n = 1810 vs. n = 1813). Separate models were created for two-dimensional (2D) images only, 2D and color Doppler flow imaging (2D-CDFI), and 2D-CDFI and pulsed wave Doppler (2D-CDFI-PW) images. The performance of these three models was compared using sensitivity, specificity, area under receiver operating characteristic curve (AUC), positive (PPV) and negative predictive values (NPV), positive (LR+) and negative likelihood ratios (LR-), and the performance of the 2D model was further compared between masses of different sizes with above statistical indicators, between images from different hospitals with AUC, and with the performance of 37 radiologists. RESULTS: The accuracies of the 2D, 2D-CDFI, and 2D-CDFI-PW models on the test set were 87.9%, 89.2%, and 88.7%, respectively. The AUCs for classification of benign tumors, malignant tumors, inflammatory masses, and adenosis were 0.90, 0.91, 0.90, and 0.89, respectively (95% confidence intervals [CIs], 0.87-0.91, 0.89-0.92, 0.87-0.91, and 0.86-0.90). The 2D-CDFI model showed better accuracy (89.2%) on the test set than the 2D (87.9%) and 2D-CDFI-PW (88.7%) models. The 2D model showed accuracy of 81.7% on breast masses ≤1 cm and 82.3% on breast masses >1 cm; there was a significant difference between the two groups (P < 0.001). The accuracy of the CNN classifications for the test set (89.2%) was significantly higher than that of all the radiologists (30%). CONCLUSIONS: The CNN may have high accuracy for classification of US images of breast masses and perform significantly better than human radiologists. TRIAL REGISTRATION Chictr.org, ChiCTR1900021375; http://www.chictr.org.cn/showproj.aspx?proj=33139.
Area Under Curve ; Breast/diagnostic imaging* ; Breast Neoplasms/diagnostic imaging* ; China ; Deep Learning ; Humans ; ROC Curve ; Sensitivity and Specificity

With the number of cases of coronavirus disease-2019 (COVID-19) increasing rapidly, the World Health Organization (WHO) has recommended that patients with mild or moderate symptoms could be released from quarantine without nucleic acid retesting, and self-isolate in the community. This may pose a potential virus transmission risk. We aimed to develop a nomogram to predict the duration of viral shedding for individual COVID-19 patients. This retrospective multicentric study enrolled 135 patients as a training cohort and 102 patients as a validation cohort. Significant factors associated with the duration of viral shedding were identified by multivariate Cox modeling in the training cohort and combined to develop a nomogram to predict the probability of viral shedding at 9, 13, 17, and 21 d after admission. The nomogram was validated in the validation cohort and evaluated by concordance index (C-index), area under the curve (AUC), and calibration curve. A higher absolute lymphocyte count (
Aged ; Aged, 80 and over ; Antibodies, Viral/blood* ; Area Under Curve ; COVID-19/virology* ; Female ; Humans ; Lymphocyte Count ; Male ; Middle Aged ; Nomograms ; Proportional Hazards Models ; Retrospective Studies ; Viral Load ; Virus Shedding

INTRODUCTION: An antenatal scoring system for vaginal birth after caesarean section (VBAC) categorises patients into a low or high probability of successful vaginal delivery. It enables counselling and preparation before labour starts. The current study aims to evaluate the role of Grobman nomogram and the Kalok scoring system in predicting VBAC success in Singapore. METHODS: This is a retrospective study on patients of gestational age 37 weeks 0 day to 41 weeks 0 day who underwent a trial of labour after 1 caesarean section between September 2016 and September 2017 was conducted. Two scoring systems were used to predict VBAC success, a nomogram by Grobman et al. in 2007 and an additive model by Kalok et al. in 2017. RESULTS: A total of 190 patients underwent a trial of labour after caesarean section, of which 103 (54.2%) were successful. The Kalok scoring system (area under curve [AUC] 0.740) was a better predictive model than Grobman nomogram (AUC 0.664). Patient's age (odds ratio [OR] 0.915, 95% CI [confidence interval] 0.844-0.992), body mass index at booking (OR 0.902, 95% CI 0.845-0.962), and history of successful VBAC (OR 4.755, 95% CI 1.248-18.120) were important factors in predicting VBAC. CONCLUSION Neither scoring system was perfect in predicting VBAC among local women. Further customisation of the scoring system to replace ethnicity with the 4 races of Singapore can be made to improve its sensitivity. The factors identified in this study serve as a foundation for developing a population-specific antenatal scoring system for Singapore women who wish to have a trial of VBAC.
Area Under Curve ; Cesarean Section ; Female ; Humans ; Infant ; Pregnancy ; Retrospective Studies ; Trial of Labor ; Vaginal Birth after Cesarean