Receiver Operating Characteristic Research Articles

Lower uterine segment thickness to predict uterine rupture: a secondary analysis of PRISMA cluster randomized trial

BackgroundThird-trimester lower uterine segment thickness (LUST) is associated with uterine rupture during trial of labor after cesarean (TOLAC) but threshold values vary according to the approach used (lower values with vaginal ultrasound, higher values with abdominal ultrasound). ObjectiveTo estimate the optimal LUST cut-off value combining vaginal and abdominal ultrasound to predict uterine rupture during TOLAC. Study DesignWe performed a secondary analysis of PRISMA cluster randomized trial including women with a single previous cesarean who underwent ultrasound LUST measurement at 34-38 weeks using the thinnest measurement obtained by combining transvaginal and transabdominal measurements. Participants in the intervention group were informed about the risk of uterine rupture according to LUST reported in 3 categories [≥2.5 mm: low risk - TOLAC is safe; 2.0-2.4 mm: intermediate-risk - TOLAC is safe under specific conditions (e.g. Grobman estimate of vaginal delivery of at or above 70 percent and/or having a history of vaginal delivery; estimated fetal weight below 4000 grams; inter-delivery interval ≥18 months); <2.0 mm: high-risk for uterine rupture]. Delivery outcomes including uterine rupture were compared using non-parametric analyses and receiver operating characteristics (ROC) curves. ResultsAmong 3460 participants, 2809 (81%); 385 (11%); and 266 (8%) were identified at low-; intermediate-; and high-risk for uterine rupture, respectively. As expected, low-risk participants were more likely to undergo TOLAC (49% vs 46% vs 13%; p<0.001) and more likely to undergo labor induction (16% vs 12% vs 3%, respectively; p<0.001) than intermediate-risk and high-risk participants. Four (0.3%) cases of uterine rupture during TOLAC occurred among 1382 low-risk participants but none among the intermediate-risk (0/178) and high-risk (0/35) participants (p=0.73). Among low-risk participants, uterine rupture was associated with LUST combining vaginal and abdominal ultrasound (area under the ROC curve : 0.93; 95% confidence interval: 0.86 – 0.99; p<0.001) with all cases occuring among women with LUST between 2.5 and 3.0 mm (4/371 or 1.1%) compared to none (0/1011) among those with LUST ≥3.0 mm (p<0.01). ConclusionsThird-trimester LUST measurement influences the rates of TOLAC and uterine rupture. TOLAC appears to be associated with a low risk of uterine rupture with a LUST between 2.0 and 2.4 mm under specific conditions. However, these conditions should perhaps be extended to patients with a LUST of less than 3.0 mm, as we found an increase in uterine ruptures in this sub-group (between 2.5 and 3.0 mm) who had no special conditions to comply with. LUST ≥3.0 mm combining vaginal and abdominal ultrasound was associated with a very low risk for uterine rupture. A large-scale study using these new parameters would have the potential to demonstrate a reduction in uterine ruptures during TOLAC.

Glycemic Laboratory Values Are Associated With Increased Length of Stay and 90-Day Revision Risk Following Surgical Management of Adult Spinal Deformity

Diabetes mellitus (DM) is a common comorbidity among patients undergoing spinal fusion for adult spinal deformity (ASD) surgery. An elevated Hemoglobin A1c (HbA1c) and elevated postoperative glucose have been shown to increase the risk of complications following spine and other orthopaedic surgeries; however, data is limited for ASD. To investigate glycemic control and ASD surgery to inform surgical decision making, medical optimization, and patient education. Retrospective cohort. Total of 106 adult patients undergoing surgical correction for ASD with an HbA1c drawn within six months preoperatively or two weeks postoperatively and valid plasma glucose levels throughout postoperative hospital stay. Length of stay, 90-day wound complication, 90-day readmission, 90-day revision. All patients undergoing spinal fusion of seven or more levels between 2021 and 2023 at two large academic medical centers were identified using institutional data acquisition software. Medical charts were then manually reviewed to obtain and confirm demographic, laboratory, and surgical characteristics and outcomes. Laboratory characteristics included preoperative HbA1c, mean postoperative glucose (PG), and maximum PG. Surgical characteristics and outcomes included procedure time, estimated blood loss (EBL), length of inpatient stay (LOS), transfusion requirement, 90-day complications, 90-day revision, and 90-day readmission. Bivariate analysis was performed followed by simple and multiple regression analysis. Odds ratios were established relative to the laboratory threshold values informed by receiver operating characteristics. Of 872 original procedures identified, 106 patients (12.2%) were adults with preoperative HbA1c and postoperative plasma glucose measurements who underwent surgery for a diagnosis of ASD. Median patient age was 67 years (IQR 59-72 years), 59 (55.7%) were female, and 96 (90.6%) were of Caucasian race. Median LOS was 7 days (IQR 5-10 years) and median HbA1c was 5.9% (IQR 5.3%-6.5%). Higher preoperative HbA1c was correlated with increased LOS (R=0.22, P=0.023). The odds ratio for patients requiring extended LOS was 2.49 (95% CI 1.06-5.86, P=0.034) for those with HbA1c ≥6.3%. Multiple regression analysis of LOS identified HbA1c [B= 1.51 (95% CI 0.32-2.70), P=0.013] as a positive predictor of LOS and mean PG [B= -0.05 (95% CI -0.10-(-0.01), P=0.019] as a weakly negative predictor of LOS. Upon simple logistic regression, the odds ratio for 90-day revision was 1.81 (95% CI 1.02-3.19, P=0.042) for every unit increase in HbA1c. Patients with mean PG ≥165 mg/dL [OR=5.76 (95% CI 1.28-26.01), P=0.024] were at increased risk for 90-day revision. Glycemic laboratory values do not seem to predict 90-day wound complications or 90-day readmission following surgery for ASD. Elevated preoperative HbA1c is associated with increased LOS and risk for revision within 90 days of ASD surgery. Postoperative hyperglycemia is also associated with increased 90-day revision risk. To our knowledge, this study is the first to evaluate HbA1c and outcomes following ASD surgery. These findings can be leveraged to inform preoperative medical optimization and highlight the importance of glycemic control in ASD patients undergoing corrective surgical intervention.

Enhanced landslide susceptibility mapping in data-scarce regions via unsupervised few-shot learning

Given the critical need to assess landslide hazards, producing landslide susceptibility map (LSM) in regions with scarce historical landslide inventories poses significant challenges. This study introduces a novel landslide susceptibility assessment framework that combines unsupervised learning strategies with few-shot learning methods to increase the accuracy of LSM in these areas. The framework has been practically validated in a representative geological disaster-prone area along the West-East Gas Pipeline in Shaanxi Province, China. We employed three advanced few-shot learning models: a support vector machine, meta-learning, and transfer learning. These models implement feature representation learning for weakly correlated influencing factors through an unsupervised approach, thereby constructing an effective landslide susceptibility assessment model. We compared traditional learning methods and used the receiver operating characteristic (ROC) curve and SHAP values to quantify the effectiveness of the models. The results indicate that the meta-learning algorithm outperforms both the SVM and transfer learning in areas with limited landslide data. The integration of unsupervised strategies significantly improves performance, achieving area under the curve (AUC) values of 0.9385 and 0.9861, respectively. Compared with using meta-learning alone, incorporating unsupervised learning strategies increased the AUC by 4.76%, enhancing both the predictive power of the model and the interpretability of the features. Meta-learning under unsupervised conditions effectively mitigates the evaluation difficulties caused by insufficient landslide records, providing a viable path and empirical evidence for performance improvement in similar data- scarce regions worldwide.

Differential expression of ferroptosis-related proteins in urinary exosomes: potential indicators for monitoring acute gout attack

BackgroundGout is the most prevalent form of inflammatory arthritis, characterized by significant pain during acute episodes. Current diagnostic and monitoring techniques are invasive and fail to predict the onset of acute attacks. Recent studies have implicated ferroptosis-related proteins in the pathogenesis of inflammation and gout; however, their clinical relevance in gout patients remains largely unexplored. This study aimed to evaluate the expression of these proteins in urinary exosomes from gout patients and to investigate their potential as noninvasive biomarkers.MethodsUtilizing data-independent acquisition (DIA) mass spectrometry and advanced bioinformatics techniques, we assessed the expression of ferroptosis-related proteins in the urinary exosomes of three groups: acute gout patients (AD group), intermittent gout patients (ID group), and normal controls (NC group). We constructed receiver operating characteristic (ROC) curves to determine the clinical utility of these proteins in monitoring acute gout attacks.ResultsOur analysis of urinary exosome proteomics identified 13 ferroptosis-related proteins. Notably, in comparison to the ID group, the proteins ACSL4, VDAC2, GPX4, and GSS were significantly upregulated in the AD group. ROC curve analysis revealed that the presence of ACSL4, VDAC2, and GPX4 in urinary exosomes possesses substantial predictive value for acute gout attacks.ConclusionIn patients with gout, numerous protein alterations occur within urinary exosomes. Specifically, changes in ferroptosis-related proteins such as ACSL4, VDAC2, GPX4, and GSS may serve as promising biomarkers for the monitoring of acute gout attacks.

Body Habitus vs. Hepatic Steatosis: Understanding the Drivers of Non-Diagnostic Shear Wave Elastography

PurposeShear Wave Elastography (SWE) is frequently non-diagnostic in obese patients, a key cohort at risk for liver disease. Subcutaneous fat and hepatic steatosis are suspected drivers, but their relative contribution is unknown. We compare ultrasound-guided attenuation parameter (UGAP), a marker of steatosis, body mass index (BMI), and skin-to-liver capsule distance (SCD) to predict non-diagnostic SWE. Materials and MethodsThis IRB approved, single center retrospective study included adults with SWE and diagnostic UGAP exams between June and December 2023. Fasting patients were imaged in supine position with right arm abducted, via an intercostal window during neutral breath hold. The median of 10 measurements in the right lobe was analyzed for SWE and UGAP. SWE measurements were ≥ 2 cm from the capsule while UGAP depth was fixed at 4 cm from the probe. Exams were considered non-diagnostic for SWE (measured in m/s) if the Interquartile Range/Median Ratio (IQR/M) was > 15% or if diagnostic measurements could not be obtained. UGAP IQR/M > 30% or complete measurement failure was considered non-diagnostic. Univariate Receiver Operating Characteristic (ROC) curves compared UGAP (dB/cm/MHz), BMI (kg/m2), and SCD (mm) prediction of non-diagnostic SWE by the DeLong test. Results87 participants (48 male) with mean age of 54.7 ± 15.7 years were analyzed. UGAP [OR: 1.63 per 0.1 dB/cm/MHz, p=0.02, AUC=0.66], BMI [OR: 1.23, p<0.001, AUC=0.77], and SCD [OR: 1.27, p<0.001, AUC=0.81) were predictors of non-diagnostic SWE. UGAP prediction of non-diagnostic SWE was similar in subgroups with the measurement region at least 1 cm (OR: 1.64, n = 68), and 2 cm (OR: 1.54, n = 16) from the liver capsule. UGAP was a worse predictor than SCD (p = 0.04), while not significantly different than BMI (p = 0.15). BMI and SCD did not differ in predicting non-diagnostic SWE (p = 0.44). ConclusionOur small preliminary study demonstrated that body habitus and hepatic attenuation, a marker of steatosis, both contribute to non-diagnostic SWE exams, however body wall thickness is the key driver. This informs patient selection for SWE exams and guides future research to mitigate these technical shortcomings. Clinical Relevance/ApplicationPatients with hepatic steatosis and large body habitus are at increased risk of non-diagnostic ultrasound shear wave elastography (SWE) exams. These patients, particularly those with increased body wall thickness, may benefit from liver fibrosis evaluation with alternative approaches following an initial non-diagnostic SWE exam. Researchers working to improve SWE technique should pay particular attention to mitigating attenuation and phase aberration from the body wall as this is the key driver of non-diagnostic exams.

Identification of immune-related hub genes in chronic obstructive pulmonary disease

ObjectiveAs a prevalent persistent respiratory disease, chronic obstructive pulmonary disease (COPD) is featured by airflow limitation and chronic inflammation. This study focused on the identification of immune-related hub genes in COPD. MethodsWe employed the GSE38974 dataset to analyze differentially expressed genes (DEGs) of COPD. Then, we obtained COPD immune-related DEGs (COPD-IMDEGs) based on the intersection of DEGs and immune-related genes. Subsequently, we carried out Gene ontology and Kyoto Encyclopedia of Genes and Genomes enrichment analyses on COPD-IMDEGs. We established a protein-protein interaction network based on COPD-IMDEGs. The hub genes were determined by utilizing the Maximal Clique Centrality method. We utilized receiver operating characteristic (ROC) curves to analyze the clinical significance of hub genes in COPD. In addition, potential drugs targeting hub genes were predicted based on interactions between hub gene-corresponding proteins and drugs. ResultsA total of 45 COPD-IMDEGs were obtained through differential analysis. Enrichment analyses showed that COPD-IMDEGs were associated with cytokines, growth factors, and receptor ligands. Ten COPD-IMDEGs were identified as hub genes. As shown by ROC curves, these genes had potential value in identifying COPD patients. Drug prediction results showed that simvastatin and other drugs targeted hub genes. ConclusionThis study analyzed the potential biological functions enriched by COPD-IMDEGs, identified ten genes as biological markers for diagnosing COPD, and predicted potential drugs for treating COPD.

Accuracy of second and third molar maturity indices, Olze, Haavikko, and Demirjian methods for 14- and 16-year-old age thresholds assessment in Croatian children and adolescents.

This study explores the reliability of four established legal age threshold estimation approaches in a Croatian sample. We applied Haavikko stages, Demirjian stages, Olze's third molar eruption stages, and second and third molar maturity indices measurement in 593 orthopantomograms of Croatian children and adolescents aged 11.00-20.99years old. The left mandibular second and third molar were assessed. Logistic regression analysis was conducted to test the significance of predictive variables. Logistic Receiver operating characteristic (ROC) curves were performed to evaluate the classification ability of variables for estimating 14- and 16-year-old thresholds. The areas under the ROC curve (AUC), accuracy (Acc), sensitivity (Se), specificity (Sp), Positive Likelihood Ratio (LR +), Negative Likelihood Ratio (LR-), and Bayes post-test probability (Bayes PTP) were calculated to evaluate classification performance. Results suggest that the combination of I2M&I3M is the best classifier for the 14-year-old threshold (AUC = 0.879); for males alone, I2M is an even better classifier (AUC = 0.881). The highest Acc 80.1% (95%CI, 75.9%-83.9%), Bayes PTP 86.5% (95%CI, 82.8%-89.7%) and Sp 88.9% (95%CI, 83.0%-93.3%) were by I3M < 0.81 & I2M < 0.03 in total samples; the highest Acc 86.1% (80.6%- 90.6%), Bayes PTP 87.2% (95%CI, 81.7%- 91.4%) and Sp 87.8% (95%CI, 78.2%- 94.3%) were by I2M < 0.01 in males, Acc of Haavikko Ac and Demirjian H stage in second molar is very close with slightly lower Bayes PTP and Sp. I3M is a good classifier for 16-year-old threshold (AUC = 0.889). The cut-off value I3M < 0.34 can be used to classify the 16-year-old threshold with Acc of 80.6% (95%CI, 77.2%-83.7%), Sp of 83.4% (95%CI, 79.0%-87.3%), and 81.7% (95%CI, 78.4%-84.8%) Bayes PTP. In conclusion, to classify the 14-year-old threshold, a pair of cut-off values I3M < 0.81 & I2M < 0.03 can be used in Croatian females; I2M < 0.01, Demirjian H stage, Haavikko Ac stage in second molar, and the pair I3M < 0.81 & I2M < 0.03 can all be used in Croatian males. I3M < 0.34 can classify the 16-year-old threshold in Croatian populations.

Discovery of novel metabolic biomarkers in blood serum for diagnosis of Alzheimer's disease.

Blood metabolites have emerged as promising candidates in the search for biomarkers for Alzheimer's disease (AD), as evidence shows that various metabolic derangements contribute to neurodegeneration in AD. We aim to identify metabolic biomarkers for AD diagnosis. We conducted an in-depth analysis of the serum metabolome of AD patients and age, sex-matched cognitively unimpaired older adults using ultra-high-performance liquid chromatography-high resolution mass spectrometry. The biomarkers associated with AD were identified using machine learning algorithms. Using the discovery dataset and support vector machine (SVM) algorithm, we identified a panel of 14 metabolites predicting AD with a 1.00 area under the curve (AUC) of receiver operating characteristic (ROC). The SVM model was tested against the verification dataset using an independent cohort and retained high predictive accuracy with a 0.97 AUC. Using the random forest (RF) algorithm, we identified a panel of 13 metabolites that predicted AD with a 0.96 AUC when tested against the verification dataset. These findings pave the way for an efficient, blood-based diagnostic test for AD, holding promise for clinical screenings and diagnostic procedures.

Associations between anthropometric indices as complementary predictors and incidence of type 2 diabetes; Panasonic Cohort Study 21

AimsTo compare the predictive abilities of body mass index (BMI), waist circumference (WC), waist-corrected BMI (wBMI), a body shape index (ABSI), and waist-to-height ratio (WHtR) for the incidence of type 2 diabetes and determine the practical cut-off values for the Japanese population. MethodsThis study used data from 155,623 participants who had medical checkups with Panasonic Corporation between 2008 and 2021. Predictive abilities of anthropometric indices were evaluated at 13 years using time-dependent receiver operating characteristic (ROC) curve analyses. Results8,800 developed type 2 diabetes during the study period. The area under the ROC curve for the WHtR was high (0.717, 95 % confidence interval [CI]: 0.710–0.724), with cut-off value of 0.497 in men, while those for wBMI (0.829, 95 % CI: 0.808–0.848) and WHtR (0.826, 95 % CI: 0.806–0.845) were high in women, with cut-off values of 18.6 kg/m and 0.510, respectively. It was also showed WHtR was the most effective in men, while WHtR and wBMI outperformed WC and were comparable to BMI in women for predicting type 2 diabetes. ConclusionsWHtR demonstrated superior effectiveness in predicting type 2 diabetes in men, while both WHtR and wBMI showed higher effectiveness than WC and were almost equivalent to BMI in women.

Minimum Fascia-Tumour Distance for Differentiating Deep Lobe From Superficial Lobe Benign Parotid Tumours: A Retrospective Study and Meta-Analysis.

This study was designed to evaluate the diagnostic efficacy of the minimum fascia-tumour distance (MFTD) in distinguishing deep-lobe benign parotid tumours from superficial-lobe tumours through both an original study and a meta-analysis. In this study, we performed a retrospective analysis of data from 91 patients who had been diagnosed with benign parotid tumours. The MFTD values were sourced from preoperative ultrasound examinations. The locations of these tumours were confirmed through surgical findings. We assessed the diagnostic accuracy of MFTD by utilising receiver operating characteristic (ROC) curves. Additionally, we conducted a systematic review of the pertinent literature and performed a diagnostic meta-analysis to ascertain the overall diagnostic efficacy of MFTD in identifying benign parotid tumours. Patients with tumours in the deep lobe had a significantly greater MFTD than patients with tumours in the superficial lobe. Using a cutoff value of 3.50 mm for MFTD, we found an AUC of 0.93, a sensitivity of 81.8%, and a specificity of 98.8%. Our meta-analysis included seven studies covering a total of 1689 tumours. The pooled values for sensitivity, specificity, and diagnostic odds ratio (OR) of MFTD were 81.0%, 89.0%, and 32.2, respectively. The AUC of the summarised ROC curve of MFTD was 0.90. The MFTD demonstrated reliable diagnostic accuracy in identifying deep-lobe benign parotid tumours and may be incorporated into standard evaluations before parotidectomy.

Combination of plasma-based lipidomics and machine learning provides a useful diagnostic tool for ovarian cancer

Ovarian cancer (OC), the second leading cause of death among gynecologic cancers, is often diagnosed at an advanced stage due to its asymptomatic nature at early stages. This study aimed to explore the diagnostic potential of plasma-based lipidomics combined with machine learning (ML) in OC. Non-targeted lipidomics analysis was conducted on plasma samples from participants with epithelial ovarian cancer (EOC), benign ovarian tumor (BOT), and healthy control (HC). The samples were randomly divided into a train set and a test set. Differential lipids between groups were selected using two-tailed Student’s t-test and partial least squares discriminant analysis (PLS-DA). Both single lipid-based receiver operating characteristic (ROC) model, and multiple lipid-based ML model, were constructed to investigate the diagnostic value of the differential lipids. The results showed several lipids with significant diagnostic potential. ST 27:2;O achieved the highest prediction accuracy of 0.92 in distinguishing EOC from HC. DG 42:2 had the highest prediction accuracy of 0.96 in diagnosing BOT from HC. Cer d18:1/18:0 had the highest prediction accuracy of 0.65 in differentiating EOC from BOT. Furthermore, multiple lipid-based ML models illustrated better diagnostic performance. K-nearest neighbors (k-NN), partial least squares (PLS), and random forest (RF) models achieved the highest prediction accuracy of 0.96 in discriminating EOC from HC. The support vector machine (SVM) model reached the highest prediction accuracy both in distinguishing BOT from HC, and in differentiating EOC from BOT, with accuracies of 1.00 and 0.74, respectively. In conclusion, this study revealed that the combination of plasma-based lipidomics and ML algorithms is an effective method for diagnosing OC.

Integrating Machine Learning with Web-Based Tools for Personalized Prognosis in Oral Adenoid Cystic Carcinoma

BackgroundAdenoid cystic carcinoma (ACC) of the oral cavity is a rare head and neck cancer. This rarity contributes to the paucity of comprehensive research on this cancer thereby complicating the development of evidence-based treatment strategies. This study aims to use machine learning (ML) techniques to analyze survival outcomes and optimize treatment approaches of ACC. MethodsThe SEER database (2000-2020) was used in this study. Cox regression analysis was used to identify the prognostic variables; prognostic models using five ML algorithms were constructed to predict the 5-year survival rates. A validation method incorporating the area under the curve (AUC) of the receiver operating characteristic (ROC) curve was used to validate the accuracy and reliability of ML models. Also, Kaplan-Meier survival analysis was performed. ResultsThis study's sample included 645 patients. The most common primary site for ACC was the hard palate, followed by the cheek mucosa. Survival rates varied across treatment groups, with the highest rates observed in patients who underwent surgery only. ML models revealed that the most significant prognostic factors were age, metastasis, and surgery. ConclusionsThis study contributes evidence and knowledge to the limited literature on ACC and emphasizes the importance of adjuvant radiotherapy. This study highlights that metastasis and age are key prognostic factors. Furthermore, the developed ML-based web tool offers a novel approach for the personalized prognosis of these rare cancer types.

Value of 18F-FDG PET/CT in the Diagnosis and Grading of Incidental Colorectal Adenomas

PurposeColorectal adenomas (CRAs) are at a higher risk of progressing to colorectal cancer (CRC) as their histological grade increases. Herein, this study investigated the relationship between the maximum standardized uptake value (SUVmax) on 18F-fluorodeoxyglucose positron emission tomography-computed tomography (18F-FDG PET/CT) and the histological grades of CRAs and constructed the optimal regression model for distinguishing between different histological grades. MethodsThis study retrospectively analyzed the data of 153 patients with CRAs who had colorectal 18F-FDG uptake incidentally found on PET/CT. The patients were categorized into low-grade intraepithelial neoplasia (LGIN) and high-grade intraepithelial neoplasia (HGIN) groups based on their histological grade. After the analysis of the relationship between SUVmax measured on preoperative 18F-FDG PET/CT scans and histological grades, receiver-operating characteristic (ROC) curves were analyzed to determine the optimal cut-off values for distinguishing between the two groups. Common clinical and pathological factors were included and subjected to univariate and multivariate logistic regression analyses to identify independent risk factors. A diagnostic model integrating SUVmax and several risk factors was developed with the multivariate logistic regression analysis. ResultsSUVmax was significantly different between the two groups (P < 0.001) and increased with an elevation in the malignancy degree. The area under the ROC curve (AUC) for identifying LGIN and HGIN was 0.796, and the AUC of the combination model was 0.822. Furthermore, SUVmax was an independent risk factor for distinguishing between different histological grades in pairwise comparisons. ConclusionThe regression model involving SUVmax on 18F-FDG PET/CT can distinguish between histological grades of CRAs, which therefore can be used as a noninvasive tool for the accurate diagnosis of CRAs and assist in developing patient-specific treatment strategies before surgery.

Cardiac motion correction with a deep learning network for perfusion defect assessment in SPECT myocardial perfusion imaging

BackgroundIn myocardial perfusion imaging (MPI) with SPECT ungated studies are used for evaluation of perfusion defects despite motion blur. We investigate the potential benefit of motion correction using a deep-learning (DL) network for evaluating perfusion defects. MethodsWe employed a DL network for cardiac motion correction in ECG-gated SPECT-MPI images, wherein the image data from different cardiac phases are combined with respect to a reference gate to reduce motion blur. For training the DL network 197 cases were used. Given the variability of gated images during the cardiac cycle, we investigated the detectability of perfusion defects in two distinct reference gates. To assess perfusion defect detection, we performed receiver-operating-characteristic (ROC) analyses on the motion-corrected images using a separate test dataset of clinical 194 subjects, in which studies were created from actual patient data with inserted simulated-lesions as ground truth. The reconstructed images were assessed by the quantitative-perfusion SPECT (QPS) software. We also evaluated the performance on reduced-count studies (by two and four folds). ResultsThe quantitative results, measured by area-under-the-ROC curve (AUC), demonstrated that DL motion correction improves the detectability of perfusion defects significantly on both standard- and reduced-count studies, and that the detectability can vary with reference cardiac phases. A joint assessment from two reference-phases achieved AUC=0.841 on the quarter-count data, higher than with ungated full-count data (AUC=0.795, p-value=0.0054). ConclusionsDL motion correction can benefit assessment of perfusion defects in standard- and reduced-count SPECT-MPI studies. It can also be beneficial to evaluate perfusion images over multiple cardiac phases.

Interobserver reliability and accuracy of the visual assessment of interventricular septal flattening in pulmonary hypertension.

Interventricular septal (IVS) flattening is a key echocardiographic feature of pulmonary hypertension (PH) that is associated with worse outcomes. The accuracy and interobserver reliability of visual and quantitative measures of IVS in PH patients are poorly described. This single-center, retrospective analysis included 173 PH patients. All echocardiograms were independently interpreted by two board-certified echocardiographers, and IVS flattening was judged to be present visually and by calculating the eccentricity index (EI). A receiver operating characteristics analysis was conducted to determine the EI with the highest combination of sensitivity and specificity for visual IVS flattening. The agreement between the two echocardiographers for calculation of EI was assessed using Bland-Altman analysis. The overall percent agreement for visual IVS flattening was 72% with a Kappa coefficient of 0.27. Agreement was highest for patients with pre-capillary PH and lowest for those with isolated post-capillary PH. An EI cut-off of 1.5 had the highest combination of specificity (80%) and sensitivity (32%) to distinguish visual septal flattening. Bland-Altman analysis showed wide 95% limits of agreement between echocardiographers for EI measured during systole and diastole. There was a fair degree of agreement between two echo readers for the presence or absence of IVS flattening, which differed based on the hemodynamic subgroup of PH. Compared to the quantitative measure EI, visual assessment had a moderately high specificity but very low sensitivity for the presence of IVS flattening. Automated measures of IVS flattening should be considered to improve the accuracy and reliability of this key metric.

Critical analysis of Parkinson’s disease detection using EEG sub-bands and gated recurrent unit

Parkinson’s disease, the second most common neurodegenerative disorder in the world. A progressive disease, which can worsen over time and lead to complications like mild cognitive impairments and dementia. The accurate diagnosis of Parkinson’s Disease (PD) remains a critical challenge in medical engineering. This study explores the potential of brain wave patterns for PD detection in healthy and unhealthy patients. The Power Spectral Density (PSD) and proposed PD detection model based on the Gated Recurrent Unit (GRU) is used to analyze brain activities. It was found that the detection of PD in patients was improved by classifying the RAW EEG in conjunction with the sub-bands using PSD as a feature and GRU as a classifier. The performance matrices including accuracy, precision, recall, and F1-score fall within a range of 90% to 98% for alpha, beta, and gamma sub-bands, while the area under the curve in the case of receiver operating characteristics curve achieved the maximum value of 1.00. To assess the differences between the groups with Parkinson’s disease and the healthy group, a statistical significance test was performed. The power spectral density of the two groups differed statistically significantly, according to the results, indicating that they could be useful as biomarkers for the identification of Parkinson’s disease. The results are compared and validated with the standard performance measures.

Boston Naming Test as a Screening Tool for Early Postoperative Cognitive Dysfunction in Elderly Patients After Major Noncardiac Surgery.

The Boston naming test (BNT), as a simple, fast, and easily administered neuropsychological test, was demonstrated to be useful in detecting language function. In this study, BNT was investigated whether it could be a screening tool for early postoperative cognitive dysfunction (POCD). This prospective observational cohort study included 132 major noncardiac surgery patients and 81 nonsurgical controls. All participants underwent a mini-mental state examination (MMSE) and BNT 1 day before and 7 days after surgery. Early POCD was assessed by reliable change index and control group results. Seven days after surgery, among 132 patients, POCD was detected in 30 (22.7%) patients (95% CI, 15.5%-30.0%) based on MMSE, and 45 (34.1%) patients (95% CI, 26.3%-41.9%) were found with postoperative language function decline based on BNT and MMSE. Agreement between the BNT spontaneous naming and MMSE total scoring was moderate (Kappa .523), and the sensitivity of BNT spontaneous naming for detecting early POCD was .767. Further analysis showed that areas under receiver operating characteristics curves (AUC) did not show statistically significant differences when BNT spontaneous naming (AUC .862) was compared with MMSE language functional subtests (AUC .889), or non-language functional subtests (AUC .933). This study indicates the feasibility of implementing the BNT spontaneous naming test to screen early POCD in elderly patients after major noncardiac surgery.

Utilizing Saliva Metabolomics for Diagnosing Gastric Cancer and Exploring the Changes in Saliva Metabolites After Surgery.

Gastric cancer (GC) is a disease with high prevalence and mortality, but we lack convenient and accurate methods to screen for this disease. Thus, we aimed to search for some salivary biomarkers and explore changes in metabolites in patients' saliva after radical gastrectomy. A total of 152 subjects were divided into three groups (healthy group, GC group, and one-week postoperative group). After simple processing, saliva samples were analyzed by liquid chromatography-mass spectrometry. First, we used total ion chromatography and principal component analysis to determine the metabolite profiles. Next, t-test, partial least squares discriminant analysis, support vector machine, and receiver operating characteristics curve analysis were performed to identify biomarkers. Then, Fisher discriminant analysis and hierarchical clustering analysis were performed to determine the discriminating ability of biomarkers. Finally, we established a generalized linear model to predict GC based on biomarkers, and used bootstrapping for internal validation. Between the healthy and GC groups, we identified four biomarkers: lactic acid, kynurenic acid, 3-hydroxystachydrine, and S-(1,2,2-trichlorovinyl)-L-cysteine. We used stepwise regression to select five metabolites and develop a model with areas under the curve equal to 0.973 in the training dataset and 0.924 in the validation dataset. Between the GC and one-week postoperative groups, we found two differential metabolites: 19-hydroxyprostaglandin E2 and DG (14:0/0:0/18:2n6). Differential metabolites were observed among the three groups. GC could be initially diagnosed on the basis of detection of these biomarkers. Moreover, changes in salivary metabolites in postoperative patients could provide important insights for basic studies.

Concomitant detection of serum ATF4 levels and MAGE is helpful to predict the occurrence of osteoporosis in patients with type 2 diabetes mellitus

BackgroundActivating transcription factor 4 (ATF4) and mean amplitude of glycemic excursion (MAGE) have been implicated in the pathogenesis of osteoporosis (OP) and type 2 diabetes mellitus (T2DM). This retrospective cohort study assessed the predictive value of serum ATF4 and MAGE for the occurrence of OP in T2DM patients. MethodsA total of 162 patients with T2DM were assigned to T2DM and T2DM + OP groups. All participants underwent serum ATF4 level detection and 72-h blood glucose monitoring (MAGE measurement). The correlations of ATF4 and MAGE with glucose and bone metabolism indicators and bone mineral density (BMD) were analyzed. A multivariate logistic regression model was developed to evaluate the correlations of ATF4 and MAGE with T2DM-associated OP. The diagnostic performance of concomitant detection of ATF4 and MAGE was assessed based on the area under the receiver-operating characteristics curve (AUC). ResultsT2DM patients with OP had higher serum ATF4 levels and MAGE than T2DM patients. ATF4 and MAGE were correlated positively with FINS, HbA1c, HOMA-IR, β-CTX, and TRACP-5b and negatively with BALP, PINP, PICP, and BMD. Elevated levels of ATF4 and MAGE were independent risk factors but increased BMD at the hip, femoral neck, and lumbar spine was a protective factor for T2DM patients with OP. More importantly, the AUC of concomitant ATF4 and MAGE was considerably higher than that of ATF4 or MAGE alone. ConclusionConcomitant detection of ATF4 and MAGE potentially aids in predicting the occurrence of OP in patients with T2DM.

Grading of clear cell renal cell carcinoma by using monoexponential, biexponential, and stretched exponential diffusion-weighted MR imaging.

To evaluate the diagnostic accuracy of monoexponential, biexponential and stretched-exponential diffusion-weighted imaging (DWI) models in the grading of clear cell renal cell carcinoma (ccRCC). Fifty-one patients with pathologically proven ccRCC underwent DWI with fifteen b factors (0, 10, 30, 50, 70, 100, 150, 200, 300, 400, 600, 800, 1000, 1500, 2000 sec/mm²) on a 3.0T MR scanner. The isotropic apparent diffusion coefficient (ADC), true diffusion coefficient (ADCslow), pseudodiffusion coefficient (ADCfast), and fraction of perfusion (f) were derived from DWI using a biexponential model. The water diffusion heterogeneity index (α) and distributed diffusion coefficient (DDC) were derived from DWI using a stretched-exponential model. All values were calculated for the solid area of tumors and compared between high-grade and low-grade ccRCC. The Mann-Whitney U test and receiver operating characteristic (ROC) analysis were used for statistical analysis. The DeLong test was performed to compare the ROC curves. The mean ADC, DDC, ADCslow and α values were significantly lower in high-grade ccRCC than in low-grade ccRCC (P< 0.01). However, the ADCfast and f were not significantly different between the two groups (P > 0.05). According to the ROC analyses, the AUC for α was 0.941, which was significantly greater than those of the other parameters, with a sensitivity of 100% and a specificity of 84.2%. The DeLong test showed that there were significant differences in the ROCs among ADCfast/ADC, ADCfast/α, f/ADCslow, ADCfast/ADCslow, f/α, DDC/α, and f/ADC. Diffusion-related parameters (ADC, DDC, ADCslow and α) could be used to distinguish between low- and high-grade ccRCC. The α derived from the stretched-exponential model may be the most promising parameter for grading ccRCC.