Receiver Operating Research Articles

Pediatric Electrocardiogram-Based Deep Learning to Predict Secundum Atrial Septal Defects.

Secundum atrial septal defect (ASD2) detection is often delayed, with the potential for late diagnosis complications. Recent work demonstrated artificial intelligence-enhanced ECG analysis shows promise to detect ASD2 in adults. However, its application to pediatric populations remains underexplored. In this study, we trained a convolutional neural network (AI-pECG) on paired ECG-echocardiograms (≤ 2days apart) to detect ASD2 from patients ≤ 18years old without major congenital heart disease. Model performance was evaluated on the first ECG-echocardiogram pair per patient for Boston Children's Hospital internal testing and emergency department cohorts using area under the receiver operating (AUROC) and precision-recall (AUPRC) curves. The training cohort comprised of 92,377 ECG-echocardiogram pairs (46,261 patients; median age 8.2years) with an ASD2 prevalence of 6.7%. Test groups included internal testing (12,631 patients; median age 7.4years; 6.9% prevalence) and emergency department (2,830 patients; median age 7.5years; 4.9% prevalence) cohorts. Model performance was higher in the internal test (AUROC 0.84, AUPRC 0.46) cohort than the emergency department cohort (AUROC 0.80, AUPRC 0.30). In both cohorts, AI-pECG outperformed ECG findings of incomplete right bundle branch block. Model explainability analyses suggest high-risk limb lead features include greater amplitude P waves (suggestive of right atrial enlargement) and V1 RSR' (suggestive of RBBB). Our findings demonstrate the promise of AI-pECG to inexpensively screen and/or detect ASD2 in pediatric patients. Future multicenter validation and prospective trials to inform clinical decision making are warranted.

The application of dynamic contrast-enhanced ultrasonography in immediate distinguishing residual tumour from benign periablational enhancement after hepatocellular carcinoma radiofrequency ablation.

This study set out to access the performance of quantitative analysis of contrast-enhanced ultrasound (CEUS) indistinguishing between benign periablational enhancement (BPE) and residual tumor (RT) following radiofrequency ablation(RFA). 165 tumors from 124 patients with hepatocellular carcinoma between 2021 and 2023underwent RFA, contrast-enhanced computed tomography (CECT), and CEUS in less than 24 hours. Analysis was done onthe quantitative parameters from RT and BPE found by CEUS. Complete ablation was obtained in 89.1% of lesions.When compared to BPE, RT had significantly greater peak intensity (PI), time to peak (TTP), area under the curve (AUC),ratio of PI and base intensity (PI/BI), and enhanced intensity (EI) values (all p<0.05). PI, TTP, AUC, PI/BI, and EI had largeareas under the receiver operating (ROC) curves. A binary logistic regression analysis, respectively, demonstrated that PI andPI/BI were independent favorable prognostic variables. Multiple parameters of quantitative analysis of CEUScan aid in distinguishing immediately between RT and BPE lesions. PI and PI/BI may be a more promising parameter. ImmediateCEUS evaluation following RFA may allow immediate retreatment of RT during the same operation time, which reducespatients' hospital stays and financial costs.

Assessing renal interstitial fibrosis using compartmental, non-compartmental, and model-free diffusion MRI approaches

ObjectiveTo assess renal interstitial fibrosis (IF) using diffusion MRI approaches, and explore whether corticomedullary difference (CMD) of diffusion parameters, combination among MRI parameters, or combination with estimated glomerular filtration rate (eGFR) benefit IF evaluation.MethodsForty-two patients with chronic kidney disease were included, undergoing MRI examinations. MRI parameters from apparent diffusion coefficient (ADC), intra-voxel incoherent motion (IVIM), diffusion kurtosis imaging (DKI), and diffusion-relaxation correlated spectrum imaging (DR-CSI) were obtained both for renal cortex and medulla. CMD of these parameters was calculated. Pathological IF scores (1–3) were obtained by biopsy. Patients were divided into mild (IF = 1, n = 23) and moderate-severe fibrosis (IF = 2–3, n = 19) groups. Group comparisons for MRI parameters were performed. Diagnostic performances were assessed by the receiver operator’s curve analysis for discriminating mild from moderate-severe IF patients.ResultsSignificant inter-group differences existed for cortical ADC, IVIM-D, IVIM-f, DKI-MD, DR-CSI VB, and DR-CSI VC. Significant inter-group differences existed in ΔADC, ΔMD, ΔVB, ΔVC, ΔQB, and ΔQC. Among the cortical MRI parameters, VB displayed the highest AUC = 0.849, while ADC, f, and MD also showed AUC > 0.8. After combining cortical value and CMD, the diagnostic performances of the MRI parameters were slightly improved except for IVIM-D. Combining VB with f brings the best performance (AUC = 0.903) among MRI bi-variant models. A combination of cortical VB, ΔADC, and eGFR brought obvious improvement in diagnostic performance (AUC 0.963 vs 0.879, specificity 0.826 vs 0.896, and sensitivity 1.000 vs 0.842) than eGFR alone.ConclusionOur study shows promising results for the assessment of renal IF using diffusion MRI approaches.Critical relevance statementOur study explores the non-invasive assessment of renal IF, an independent and effective predictor of renal outcomes, by comparing and combining diffusion MRI approaches including compartmental, non-compartmental, and model-free approaches.Key PointsSignificant difference exists for diffusion parameters between mild and moderate-severe IF.Generally, cortical parameters show better performance than corresponding CMD.Bi-variant model lifts the diagnostic performance for assessing IF.Graphical

Urban explosion and hotspots of forest loss in western Himalaya: Mapping land use/cover change trends since 1975

The Western Himalayan Region (WHR) is under constant threat from Land Use and Land Cover Change (LULCC) brought on by various socioeconomic activities such as urbanization, agricultural expansion, and population growth. Detailed research into the scope of these changes is necessary to comprehend the challenges they represent. This study aimed at (1) examining and quantifying spatiotemporal patterns of LULCC from 1975 to 2015, (2) mapping the hotspots of forest loss, and (3) modelling future LULCC for the year 2055 using medium spatial resolution multispectral satellite imagery (MSS, TM, LISS-I, LISS-III, AWiFS), field data, visual interpretation and logistic regression model in the WHR. Logistic regression integrated various drivers of LULCC, including climatic, topographic, and socio-economic factors and past LULCC trends to forecast potential LULC in the WHR by 2055. The results highlight an outrageous 184% increase in regional urbanization. Expansion of urban and cropland (12%) led to deforestation which reduced the area of natural habitats, specifically forests (−11%), water bodies (−8%) and scrubland (−6%). A significant rise in barren land by 30% was noted, while there was a decrease of 20% in glacier/snow melt. The future projection for 2055 anticipates continuing current trends, emphasizing an intensified urban expansion of 63% and an approximate 9% reduction in overall forest coverage. The accuracy of the predicted 2015 LULC map was assessed using ROC/AUC (Receiver Operating Characteristic/Area under Curve) which was found to be 0.79.

Energy‐efficient physical layer security schemes for low Earth orbit satellite systems

SummaryThis paper introduces four proposals to enhance physical layer security (PLS) in low Earth orbit (LEO) satellite systems. The first proposal leverages the Alamouti code aided by artificial noise (AN) and involves the collaborative use of two LEO satellites, ensuring secure downlink transmission. Its efficiency is further enhanced when implementing a power‐balanced Alamouti code. The second PLS proposal capitalizes on an reconfigurable intelligent surface (RIS) to introduce interference to potential eavesdroppers. As the RIS manages the reflected channel, this security measure is achieved without necessitating additional transmit power or receiver operations. The third proposal integrates the first and second solutions, resulting in improved secrecy rates compared to the individual proposals, nearly reaching the maximum achievable rate. The fourth proposal is based on a relay‐based method, securing all transmission links from the satellite to the relay and from the satellite and relay to the legitimate user. The secrecy performance simulation results presented in the paper demonstrate the remarkable effectiveness of the proposed solutions.

Utility of metabolic ratios in the diagnosis of tumor Thrombus on F-18 FDG PET/CT

BackgroundThis study aims to predict quantitative parameter in form of metabolic ratios to diagnose tumor thrombus on F-18 FDG PET/CT.MethodsThis is a retrospective study from Nuclear Medicine department at All India Institute of Medical Sciences, Jodhpur, India. Patients with malignancies who underwent F-18 FDG PET/CT in our department or images sent for review from February 2020 till September 2022 were screened for tumor thrombus that comprised study group. Control group had patients with malignancy and no imaging evidence of tumor thrombus. Metabolic activities (SUVmax) of tumor thrombus, liver and descending aorta in study group, and that of IVC, liver and descending aorta in control group were recorded. Metabolic ratios of tumor thrombus to liver (SUR L) and to aorta (SUR A) in study group, and IVC to liver (SUR* L) and to aorta (SUR*A) in control group were compared using receiver operator curves.ResultsOf 2277 studies screened, 12 had tumor thrombus. The most common primary malignant site and vessel involved were lung and IVC respectively. The median (IQR) SUR L, SUR A, SUR* L and SUR* A were 2.5 (3.25), 2.6 (6), 0.67 (0.18) and 1 (0.17) respectively. Area under ROC for SUR L and SUR A were 0.983 [95% CI: 0.955–1.0] and 0.958 [95% CI: 0.90–1.0] respectively. The ideal cut-off for SUR L was 0.953 (sensitivity 92.3%, specificity 98.0%) and for SUR A was 1.42 (sensitivity 84.6%, specificity 98.0%).ConclusionMetabolic ratios of tumor thrombus to liver (SUR L) and aorta (SUR A) have good diagnostic performance and can be useful in studies with non-iodinated contrast CT.

Assessing the use of the triglyceride-glycemic index (TyG), neutrophil-lymphocyte Ratio (NLR), and platelet-lymphocyte Ratio (PLR) in distinguishing benign and malignant tumors among patients with complaints of breast mass

IntroductionBreast cancer is a prevalent global health concern characterized by uncontrolled cell growth in breast tissue. In 2020, approximately 2.3 million cases were reported worldwide, with 162,468 new cases and 87,090 fatalities documented in India in 2018. Early diagnosis is crucial for reducing mortality. Our study focused on the use of markers such as the triglyceride-glycemic index and hematological markers to distinguish between benign and malignant breast masses. MethodsA prospective cross-sectional study included female patients with breast mass complaints. The target sample size was 200. Data collection included medical history, clinical breast examination, mammography, cytological assessment via fine-needle aspiration cytology (FNAC), and blood sample collection. The analyzed parameters included neutrophil-to-lymphocyte Ratio (NLR), platelet-to-lymphocyte Ratio (PLR), and triglyceride-glycemic index (TyG). Histopathological examination confirmed the FNAC results. Statistical analysis including propensity score matching, Kolmogorov–Smirnov tests, Mann–Whitney U tests, receiver's operator curve (ROC) analysis, and logistic regression models was conducted using SPSS and R Software. Additional validation was performed on 25 participants. ResultsThis study included 200 participants. 109 had benign tumors and 91 had malignant tumors. Propensity score matching balanced covariates. NLR did not significantly differ between the groups, while PLR and TyG index differed significantly. NLR correlated strongly with the breast cancer stage, but not with the BI-RADS score. PLR and TyG index showed moderate positive correlations with the BI-RADS score. ROC analysis was used to determine the optimal cutoff values for PLR and TyG index. Logistic regression models combining PLR and TyG index significantly improved malignancy prediction. ConclusionsTyG index and PLR show potential as adjunctive markers for distinguishing breast masses. NLR correlated with cancer stage but not lesion type. Combining TyG and PLR improves prediction, aiding clinical decisions, but large-scale multicenter trials and long-term validation are required for clinical implementation.

Assessment of nomogram model for the prediction of esophageal variceal hemorrhage in hepatitis B-induced hepatic cirrhosis.

Esophageal variceal (EV) hemorrhage is a life-threatening consequence of portal hypertension in hepatitis B virus (HBV) -induced cirrhotic patients. Screening upper endoscopy and endoscopic variceal ligation to find EVs for treatment have complications, contraindications, and high costs. We sought to identify the nomogram models (NMs) as alternative predictions for the risk of EV hemorrhage. In this case-control study, we retrospectively analyzed 241 HBV-induced liver cirrhotic patients treated for EVs at the Second People's Hospital of Fuyang City, China from January 2021 to April 2023. We applied univariate analysis and multivariate logistic regression to assess the accuracy of various NMs in EV hemorrhage. The area under the curve (AUC) and calibration curves of the receiver's operating characteristics were used to evaluate the predictive accuracy of the nomogram. Decision curve analysis (DCA) was used to determine the clinically relevant of nomograms. In the prediction group, multivariate logistic regression analysis identified platelet distribution and spleen length as independent risk factors for EVs. We applied NMs as the independent risk factors to predict EVs risk. The NMs fit well with the calibration curve and have good discrimination ability. The AUC and DCA demonstrated that NMs with a good net benefit. The above results were validated in the validation cohort. Our non-invasive NMs based on the platelet distribution width and spleen length may be used to predict EV hemorrhage in HBV-induced cirrhotic patients. NMs can help clinicians to increase diagnostic performance leading to improved treatment measures.

Full Outline of Unresponsiveness Score versus Glasgow Coma Scale in Predicting Clinical Outcomes in Altered Mental Status.

Full outline of unresponsiveness (FOUR) score has advantages over Glasgow Coma Scale (GCS); as it can be used in intubated patients and provides greater neurological details. It has been studied mainly in the trauma and neuroscience setting. Our primary objective was to compare the FOUR versus GCS score as predictors of mortality at 30 days and poor functional outcome at 3 months among nontrauma patients in the emergency department (ED). This prospective observational study was conducted on adult patients presenting with altered mental status (duration <7 days) in the ED (March 2019-November 2020). Data collection included demographic and clinical features, the GCS and FOUR scores, the feasibility of acquiring and interpreting FOUR on a Likert scale, duration of hospital stay, 30-day mortality, and functional outcome at 3 months on the modified Rankin Scale. Trained emergency medicine residents managing the patient collected the data. The area under receiver's operating characteristics curve (AUROC) was used to compare the accuracy of the GCS and FOUR scores in predicting outcomes. The FOUR score equivalent of GCS cutoffs for categorizing neurological impairment (mild, moderate, and severe) was also investigated. Two hundred and ninety-one patients were included, with a mean age of 50.3 years and 67.4% males. Most patients (40.2%) had altered mental status for 1-3 days and hepatic encephalopathy was the most common ED diagnosis. The mortality at 30 days was 66.7% (194 of 291), and 88% (256 of 291) of patients had poor functional outcomes at 3 months. The AUROCs for predicting 30-day mortality were similar for both the scores (GCS: 0.70, FOUR: 0.71, and the P value for difference: 0.9). Similarly, the AUROCs for predicting 3-month poor functional outcome were 0.683 and 0.669 using GCS and FOUR, respectively, with a nonsignificant difference (P = 0.82). The FOUR score strata of 14-16, 11-13, and 0-10 were found to be equivalent to the GCS scores of 13-15 (mild), 9-12 (moderate), and 3-8 (severe). The feasibility of acquiring and interpreting GCS and FOUR scores on the Likert scale was found to be "easy." The FOUR score is similar to GCS in predicting mortality at 30 days and poor neurological outcomes at 3 months among nontrauma patients of ED. Moreover, it was found that the FOUR score is "easy" to assess and interpret by the emergency residents.

Application of machine learning methods for predicting under-five mortality: analysis of Nigerian demographic health survey 2018 dataset

BackgroundUnder-five mortality remains a significant public health issue in developing countries. This study aimed to assess the effectiveness of various machine learning algorithms in predicting under-five mortality in Nigeria and identify the most relevant predictors.MethodsThe study used nationally representative data from the 2018 Nigeria Demographic and Health Survey. The study evaluated the performance of the machine learning models such as the artificial neural network, k-nearest neighbourhood, Support Vector Machine, Naïve Bayes, Random Forest, and Logistic Regression using the true positive rate, false positive rate, accuracy, precision, F-measure, Matthew’s correlation coefficient, and the Area Under the Receiver Operating Characteristics.ResultsThe study found that machine learning models can accurately predict under-five mortality, with the Random Forest and Artificial Neural Network algorithms emerging as the best models, both achieving an accuracy of 89.47% and an AUROC of 96%. The results show that under-five mortality rates vary significantly across different characteristics, with wealth index, maternal education, antenatal visits, place of delivery, employment status of the woman, number of children ever born, and region found to be the top determinants of under-five mortality in Nigeria.ConclusionsThe findings suggest that machine learning models can be useful in predicting U5M in Nigeria with high accuracy. The study emphasizes the importance of addressing social, economic, and demographic disparities among the population in Nigeria. The study’s findings can inform policymakers and health workers about developing targeted interventions to reduce under-five mortality in Nigeria.

Higher serum Lp-PLA2 is associated with cognitive impairment in Parkinson's disease patients.

To explore the association between lipoprotein-associated phospholipase A2 (Lp-PLA2) and the risk of cognitive impairment in Parkinson's disease (PD-CI). A case-control study involving 100 hospitalized PD patients and 60 healthy controls was carried out. Serum Lp-PLA2 level was detected by automatic biochemical analyzer. Based on whether Parkinson's patients have cognitive impairment, PD patients were subdivided to analyze the clinical value of Lp-PLA2. Relationship between Lp-PLA2 and PD-CI risk was analyzed by logistic regression. Diagnostic value of Lp-PLA2 in PD-CI patients was investigated using receiver's operator characteristic curves. The levels of serum Lp-PLA2 activity in Parkinson's disease with normal cognition (PD-NC) and PD-CI patients were significantly higher than those in healthy controls (HCs), respectively. Furthermore, compared to the PD-NC group, the serum Lp-PLA2 activity level was significantly higher in PD-CI patients. Multivariable logistic regression analysis indicated that higher Lp-PLA2 level was an independent risk factor for PD patients with cognitive impairment. Moreover, the area under the efficacy curve of Lp-PLA2 for predicting PD-CI is 0.659. Our study shows that higher levels of Lp-PLA2 activity in PD patients are associated with the risk of developing cognitive impairment. Therefore, given the wide availability, safety, and convenience of monitoring serum Lp-PLA2 activity, it may serve as an early biomarker for cognitive impairment in PD patients.

Modelling climate change impacts on the spatial distribution of anthrax in Zimbabwe

BackgroundIn Zimbabwe, anthrax is endemic with outbreaks being reported almost annually in livestock, wildlife, and humans over the past 40 years. Accurate modelling of its spatial distribution is key in formulating effective control strategies. In this study, an Ensemble Species Distribution Model was used to model the current and future distribution of anthrax occurrence in Zimbabwe.MethodsBioclimatic variables derived from the Beijing Climate Centre Climate System Model were used to model the disease. Collinearity testing was conducted on the 19 bioclimatic variables and elevation to remove redundancy. Variables that had no collinearity were used for anthrax habitat suitability modelling. Two future climate change scenarios for different Representative Concentration Pathways (RCP), RCP4.5 and RCP8.5 were used. Model evaluation was done using true skill, Kappa statistics and receiver operating characteristics.ResultsThe results showed that under current bioclimatic conditions, eastern and western districts of Zimbabwe were modelled as highly suitable, central districts moderately suitable and southern parts marginally suitable for anthrax occurrence. Future predictions demonstrated that the suitable (8%) and highly suitable (7%) areas for anthrax occurrence would increase under RCP4.5 scenario. In contrast, a respective decrease (11%) and marginal increase (0.6%) of suitable and highly suitable areas for anthrax occurrence were predicted under the RCP8.5 scenario. The percentage contribution of the predictors varied for the different scenarios; Bio6 and Bio18 for the current scenario, Bio2, Bio4 and Bio9 for the RCP4.5 and Bio3 and Bio15 for the RCP8.5 scenarios.ConclusionsThe study revealed that areas currently suitable for anthrax should be targeted for surveillance and prevention. The predicted future anthrax distribution can be used to guide and prioritise surveillance and control activities and optimise allocation of limited resources. In the marginally to moderately suitable areas, effective disease surveillance systems and awareness need to be put in place for early detection of outbreaks. Targeted vaccinations and other control measures including collaborative ‘One Health’ strategies need to be implemented in the predicted highly suitable areas. In the southern part where a high decrease in suitability was predicted, continued monitoring would be necessary to detect incursions early.

Opportunistic hand radiographs to screen for low forearm bone mineral density: a prospective and retrospective cohort study

BackgroundLow bone mineral density affects 53% of women over age 65 in the US, yet many are unaware and remain untreated. Underdiagnosis of forearm osteoporosis and related fragility fractures represent missed warning signs of more deadly, future fractures. This study aimed to determine if hand radiographs could serve as early, simple screening tools for predicting low forearm bone mineral density (BMD).MethodsWe evaluated posterior-anterior (PA) hand radiographs (x-rays) and Dual-energy X-ray absorptiometry (DXA) scans of 43 participants. The ratio of the intramedullary cavity to total cortical diameter of the second metacarpal (second metacarpal cortical percentage (2MCP)) was used as a potential diagnostic marker. Mixed-effects linear regression was performed to determine correlation of 2MCP with BMD from various anatomic regions. Repeated measures ANOVAs were used to compare BMD across sites. An optimal 2MCP cutoff for predicting forearm osteopenia and osteoporosis was found using Receiver Operating Curves.Results2MCP is directly correlated with BMD in the forearm. The optimal 2MCP of 48.3% had 80% sensitivity for detecting osteoporosis of the 1/3 distal forearm. An 2MCP cutoff of 50.8% had 84% sensitivity to detect osteoporosis of the most distal forearm. Both 2MCP cutoffs were more sensitive at predicting forearm osteoporosis than femoral neck T-scores.ConclusionsThese findings support the expansion of osteoporosis screening to include low-cost hand x-rays, aiming to increase diagnosis and treatment of low forearm BMD and fractures. Proposed next steps include confirming the optimal 2MCP cutoff at scale and integrating automatic 2MCP measurements into PAC systems.

A falling particle receiver thermal model for system-level analysis of solar tower plants

Falling particle receivers are one of the most promising new generation solar tower technologies. They have the advantage of being directly heated, thus relaxing flux limitations associated with conventional receivers, and being able to achieve very high temperatures (>1000 °C) without degradation. The goal of this work is the development of a thermal model able to describe the behaviour of a falling particle receiver under different operating conditions, to provide the value of its thermal efficiency within reasonable computational time so that the model can be applied for optimization of solar tower plants at system-level. The thermal model was developed starting from models described in literature, upgrading them with various features (e.g., 2D/3D discretization, drag force effect, etc.) to describe more in detail the heat transfer phenomena occurring during receiver operation. The obtained model results were verified against CFD showing better agreement than the original model. Furthermore, the thermal model was employed in a case study with the goal of optimizing the receiver size for a given solar field and performing off-design and annual performance analyses. Results showed that the adoption of multiple stages increases performance compared to a free-falling particle receiver both under nominal and off-design conditions, and the higher the number of stages the better is the performance. A free-falling particle receiver showed a yearly thermal efficiency of 72.0 %, while the five stages one achieved 75.3 %. In addition, recirculation was investigated as part load strategy for improving performance of the free-falling receiver, but the benefits in terms of performance were limited.

Evaluation of liver segmental dose threshold for hepatocyte regeneration following liver stereotactic body radiation therapy.

There is limited evidence studying the relationship of liver segmental dose and segmental volume changes. The segmental dose thresholds could potentially allow for segmental regeneration after liver stereotactic body radiation therapy (SBRT). Given improved survival in hepatocellular cancer (HCC) and liver metastases and more salvage therapy options, this has become an important clinical question to explore. This study assesses the impact of liver segmental dose on segmental volume changes (gain or loss) after SBRT. Liver segmental contours were delineated on baseline and serial follow up triphasic computed tomography scans. The volumes of total liver and doses to total liver, uninvolved liver and individual segments were noted. A correlation was evaluated between liver/segmental volume and dose using Pearson's correlation. Furthermore, receiver operator's curve (ROC) analysis was performed to find the segmental dose, i.e . predictive for liver volume loss. A total of 140 non-tumour liver segments were available for analysis in 21 participants. Overall, 13 participants showed loss of overall liver volume and eight showed gain of overall liver volume. The median dose in segments reporting an increase in volume was 9.1 Gy (7-36 Gy). The median dose in segments losing volume was 15.5 Gy (1-49 Gy). On ROC analysis, segmental dose >11 Gy was associated with volume loss. On univariate analysis, only liver segmental dose contributed to a significant segmental volume loss. We propose from the findings of this study that in SBRT for large hepatocellular cancer or liver metastases, liver segments should be individually delineated. Furthermore, 3-5 liver segments may be preferentially subjected to <9 Gy to facilitate hepatocyte regeneration. Preferential sparing of uninvolved liver segments may improve outcomes in liver stereotaxyas lower segmental doses were associated with liver regeneration. This may have implications on future liver SBRT planning where segmental doses may be as important as the mean dose.

Comparative Evaluation of Lipid Accumulation Product, and Triglyceride-Glucose Indices in Apparently Healthy Subjects in Predicting Cardiovascular Risks in Port-Harcourt

Lipid accumulation product is a novel biomarker of central lipid accumulation related to the risk of diabetes and cardiovascular diseases. In certain metabolic diseases, insulin resistance is often present which could be attributed to an abnormality in the insulin-specific receptors in various tissues, obesity, or visceral adiposity. This study aimed at determining the triglyceride–glucose index and lipid accumulation product index of apparently healthy individuals in Port Harcourt. A total of 150 healthy individuals were assessed for anthropometric and biochemical measurement, lipid accumulation production (LAP), and triglyceride --glucose index TyG. Comparison of mean values of biophysical variables body mass index (BMI), lipid accumulation product indices, cardiovascular, triglyceride–glucose index, insulin, C-peptide, glycated haemoglobin (HbAIC), Fasting blood sugar (FBS), and Body Mass Index (BMI) of male and female subjects were measured using standard procedures. A detailed comparison of mean values of biophysical variables of male and female subjects shows that the mean age for the male subjects (41.55±6.99 years) was significantly higher (p=0.0159) when compared to the mean age for female subjects (39.04±5.6 years. There was no significant difference in the mean weight, height, BMI, waist circumference, SBP, DBP, T. Chol, triglyceride, HDL, LDL, C-peptide level, HbAIc, FBS level, T. CHOL/HDL ratio, T. CHOL/LDL ratio, and TyG index between the male and female subjects. However, there was a significantly higher level of insulin for male than female subjects and higher LAP for female than male subjects. Also, there was a higher HOMA-R for male subjects than female subjects. Additionally, there was a positive correlation between BMI and the following; mean age, systolic blood pressure (SBP), diastolic blood pressure (DBP), waist circumference (WC), and insulin levels. The Receiver's Operating Characteristics (ROC) curve for the LAP test had a high AUC value of 0.9970. Similarly, the ROC curve analysis of the TyG test had a high AUC of 0.8344. However, these findings emphasize the LAP test has a stronger discriminatory ability than TyG. Healthy individuals may have the cardiovascular risk of being evaluated by LAP, which is very cost-effective.

Machine-learning vs. logistic regression for preoperative prediction of medical morbidity after fast-track hip and knee arthroplasty—a comparative study

BackgroundMachine-learning models may improve prediction of length of stay (LOS) and morbidity after surgery. However, few studies include fast-track programs, and most rely on administrative coding with limited follow-up and information on perioperative care. This study investigates potential benefits of a machine-learning model for prediction of postoperative morbidity in fast-track total hip (THA) and knee arthroplasty (TKA).MethodsCohort study in consecutive unselected primary THA/TKA between 2014–2017 from seven Danish centers with established fast-track protocols. Preoperative comorbidity and prescribed medication were recorded prospectively and information on length of stay and readmissions was obtained through the Danish National Patient Registry and medical records. We used a machine-learning model (Boosted Decision Trees) based on boosted decision trees with 33 preoperative variables for predicting “medical” morbidity leading to LOS > 4 days or 90-days readmissions and compared to a logistical regression model based on the same variables. We also evaluated two parsimonious models, using the ten most important variables in the full machine-learning and logistic regression models. Data collected between 2014–2016 (n:18,013) was used for model training and data from 2017 (n:3913) was used for testing.Model performances were analyzed using precision, area under receiver operating (AUROC) and precision recall curves (AUPRC), as well as the Mathews Correlation Coefficient. Variable importance was analyzed using Shapley Additive Explanations values.ResultsUsing a threshold of 20% “risk-patients” (n:782), precision, AUROC and AUPRC were 13.6%, 76.3% and 15.5% vs. 12.4%, 74.7% and 15.6% for the machine-learning and logistic regression model, respectively. The parsimonious machine-learning model performed better than the full logistic regression model. Of the top ten variables, eight were shared between the machine-learning and logistic regression models, but with a considerable age-related variation in importance of specific types of medication.ConclusionA machine-learning model using preoperative characteristics and prescriptions slightly improved identification of patients in high-risk of “medical” complications after fast-track THA and TKA compared to a logistic regression model. Such algorithms could help find a manageable population of patients who may benefit most from intensified perioperative care.

Novel nomogram for predicting survival in advanced non-small cell lung cancer receiving anti-PD-1 plus chemotherapy with or without antiangiogenic therapy.

This study aimed to develop and validate a novel nomogram to predict survival in advanced non-small cell lung cancer (NSCLC) receiving programmed cell death 1 (PD-1) inhibitor plus chemotherapy with or without antiangiogenic therapy. A total of 271 patients with advanced NSCLC who received anti-PD-1 plus chemotherapy with or without antiangiogenic therapy were enrolled in our center and randomized into the training cohort (n = 133) and the internal validation cohort (n = 138). Forty-five patients from another center were included as an independent external validation cohort. The nomogram was created based on the multivariate Cox regression analysis to predict overall survival (OS) and progression-free survival (PFS). The performance of the nomogram was assessed using the concordance index (C-index), the time-dependent area under the receiver operating (ROC) curves (AUCs), calibration curves, and decision curve analysis (DCA). Four factors significantly associated with OS were utilized to create a nomogram to predict OS: Eastern Cooperative Oncology Group performance status (ECOG PS), programmed cell death-ligand 1 (PD-L1) expression, chemotherapy cycle, and pretreatment lactate dehydrogenase-albumin ratio (LAR). Six variables significantly associated with PFS were incorporated into the development of a nomogram for predicting PFS: ECOG PS, histology, PD-L1 expression, chemotherapy cycle, pretreatment platelet to lymphocyte (PLR), and pretreatment LAR. The C-indexes of the nomogram for predicting OS and PFS were 0.750 and 0.747, respectively. The AUCs for predicting the 6-month, 12-month, and 18-month OS and PFS were 0.847, 0.791, and 0.776 and 0.810, 0.787, and 0.861, respectively. The calibration curves demonstrated a good agreement between predictions and actual observations. The DCA curves indicated that the nomograms had good net benefits. Furthermore, the nomogram model was well-validated in the internal and external cohorts. The novel nomogram for predicting the prognosis of advanced NSCLC receiving anti-PD-1 plus chemotherapy with or without antiangiogenic therapy may help guide clinical treatment decisions.

Impact of a short online course on the accuracy of non-ophthalmic diabetic retinopathy graders in recognising glaucomatous optic nerves in Vietnam

PurposeTo test an online training course for non-ophthalmic diabetic retinopathy (DR) graders for recognition of glaucomatous optic nerves in Vietnam.MethodsThis was an uncontrolled, experimental, before-and-after study in which 43 non-ophthalmic...

Comparison of the measurement properties of the EQ-5D-5L and SF-6Dv2 among overweight and obesity populations in China

ObjectiveTo evaluate and compare the measurement properties of the EQ-5D-5L and SF-6Dv2 among Chinese overweight and obesity populations.MethodsA representative sample of Chinese overweight and obesity populations was recruited stratified by age, gender, body mass index (BMI), and area of residence. Social-demographic characteristics and self-reported EQ-5D-5L and SF-6Dv2 responses were collected through the online survey. The agreement was assessed using intraclass correlation coefficients (ICC). Convergent validity and known-group validity were examined using Spearman’s rank correlation and effect sizes, respectively. The test-retest reliability was assessed using among a subgroup of the total sample. Sensitivity was compared using relative efficiency and receiver operating characteristic.ResultsA total of 1000 respondents (52.0% male, mean age 51.7 years, 67.7% overweight, 32.3% obesity) were included in this study. A higher ceiling effect was observed in EQ-5D-5L than in SF-6Dv2 (30.6% vs. 2.1%). The mean (SD) utility was 0.851 (0.195) for EQ-5D-5L and 0.734 (0.164) for SF-6Dv2, with the ICC of the total sample was 0.639 (p < 0.001). The Spearman’s rank correlation (range: 0.186–0.739) indicated an acceptable convergent validity between the dimensions of EQ-5D-5L and SF-6Dv2. The EQ-5D-5L showed basically equivalent discriminative capacities with the SF-6Dv2 (ES: 0.517–1.885 vs. 0.383–2.329). The ICC between the two tests were 0.939 for EQ-5D-5L and 0.972 for SF-6Dv2 among the subgroup (N = 150). The SF-6Dv2 had 3.7–170.1% higher efficiency than the EQ-5D-5L at detecting differences in self-reported health status, while the EQ-5D-5L was found to be 16.4% more efficient at distinguishing between respondents with diabetes and non-diabetes.ConclusionsBoth the EQ-5D-5L and SF-6Dv2 showed comparable reliability, validity, and sensitivity when used in Chinese overweight and obesity populations. The two measures may not be interchangeable given the systematic difference in utility values between the EQ-5D-5L and SF-6Dv2. More research is needed to compare the responsiveness.