scholarly journals Non-Invasive Preoperative Imaging Differential Diagnosis of Intracranial Hemangiopericytoma and Angiomatous Meningioma: A Novel Developed and Validated Multiparametric MRI-Based Clini-Radiomic Model

2022 ◽  
Vol 11 ◽  
Author(s):  
Yanghua Fan ◽  
Panpan Liu ◽  
Yiping Li ◽  
Feng Liu ◽  
Yu He ◽  
...  
Keyword(s):  
Differential Diagnosis ◽  
Clinical Features ◽  
Area Under The Curve ◽  
High Sensitivity ◽  
Recursive Feature Elimination ◽  
Preoperative Imaging ◽  
Multivariable Logistic Regression Analysis ◽  
Clinical Model ◽  
Non Invasive ◽  
Model Combining

BackgroundAccurate preoperative differentiation of intracranial hemangiopericytoma and angiomatous meningioma can greatly assist operation plan making and prognosis prediction. In this study, a clini-radiomic model combining radiomic and clinical features was used to distinguish intracranial hemangiopericytoma and hemangioma meningioma preoperatively.MethodsA total of 147 patients with intracranial hemangiopericytoma and 73 patients with angiomatous meningioma from the Tiantan Hospital were retrospectively reviewed and randomly assigned to training and validation sets. Radiomic features were extracted from MR images, the elastic net and recursive feature elimination algorithms were applied to select radiomic features for constructing a fusion radiomic model. Subsequently, multivariable logistic regression analysis was used to construct a clinical model, then a clini-radiomic model incorporating the fusion radiomic model and clinical features was constructed for individual predictions. The calibration, discriminating capacity, and clinical usefulness were also evaluated.ResultsSix significant radiomic features were selected to construct a fusion radiomic model that achieved an area under the curve (AUC) value of 0.900 and 0.900 in the training and validation sets, respectively. A clini-radiomic model that incorporated the radiomic model and clinical features was constructed and showed good discrimination and calibration, with an AUC of 0.920 in the training set and 0.910 in the validation set. The analysis of the decision curve showed that the fusion radiomic model and clini-radiomic model were clinically useful.ConclusionsOur clini-radiomic model showed great performance and high sensitivity in the differential diagnosis of intracranial hemangiopericytoma and angiomatous meningioma, and could contribute to non-invasive development of individualized diagnosis and treatment for these patients.

scholarly journals Efficacy of Monocyte Distribution Width in the Early Diagnosis of Sepsis: A Diagnostic Meta-Analysis

2021 ◽  
Author(s):  
Jiahao Chen ◽  
Qiang Guo
Keyword(s):  
Early Diagnosis ◽  
Large Scale ◽  
Meta Analysis ◽  
Delayed Diagnosis ◽  
Area Under The Curve ◽  
High Sensitivity ◽  
Inexpensive Method ◽  
Diagnostic Efficacy ◽  
Distribution Width ◽  
Non Invasive

Abstract Background: Delayed diagnosis of sepsis urgently requires a fast, convenient, and inexpensive method to improve the early diagnosis of sepsis. Increasing evidence showed that monocyte distribution width (MDW) could be used as a non-invasive biomarker with high sensitivity and specificity for the early diagnosis of sepsis. However, the accuracy and reliability of its diagnosis are still controversial in different studies. Method: A meta-analysis of all available studies regarding the association between MDW and the diagnosis of sepsis was performed to systematically evaluate the diagnostic efficacy of MDW in the prediction of sepsis. Results: The estimated results of all eight studies are as follows: sensitivity, 0.84 (95% CI 0.77, 0.90); specificity, 0.68 (95% CI 0.54, 0.80); PLR, 2.7 (95% CI 1.8, 4.1); NLR, 0.23 (95% CI 0.15, 0.35); DOR is 12 (95% CI 5, 25). The corresponding overall area under the curve is 0.85 (95% CI 0.82, 0.88). Conclusion: In conclusion, this meta-analysis demonstrates that MDW has high accuracy in distinguishing patients with sepsis from healthy controls for early diagnosis of sepsis. However, large-scale prospective studies and joint diagnosis with other indicators are urgently required to confirm our findings and their utilization for routine clinical diagnosis in the future.

scholarly journals Hyperglycemia Identification Using ECG in Deep Learning Era

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6263
Author(s):  
Renato Cordeiro ◽  
Nima Karimian ◽  
Younghee Park
Keyword(s):  
Deep Learning ◽  
Blood Glucose Concentration ◽  
Area Under The Curve ◽  
High Sensitivity ◽  
Physiological Signals ◽  
Ecg Signals ◽  
Non Invasive ◽  
Learning Classifier ◽  
Electrocardiogram Ecg ◽  
Smart Wearable

A growing number of smart wearable biosensors are operating in the medical IoT environment and those that capture physiological signals have received special attention. Electrocardiogram (ECG) is one of the physiological signals used in the cardiovascular and medical fields that has encouraged researchers to discover new non-invasive methods to diagnose hyperglycemia as a personal variable. Over the years, researchers have proposed different techniques to detect hyperglycemia using ECG. In this paper, we propose a novel deep learning architecture that can identify hyperglycemia using heartbeats from ECG signals. In addition, we introduce a new fiducial feature extraction technique that improves the performance of the deep learning classifier. We evaluate the proposed method with ECG data from 1119 different subjects to assess the efficiency of hyperglycemia detection of the proposed work. The result indicates that the proposed algorithm is effective in detecting hyperglycemia with a 94.53% area under the curve (AUC), 87.57% sensitivity, and 85.04% specificity. That performance represents an relative improvement of 53% versus the best model found in the literature. The high sensitivity and specificity achieved by the 10-layer deep neural network proposed in this work provide an excellent indication that ECG possesses intrinsic information that can indicate the level of blood glucose concentration.

scholarly journals P13.12 Development and validation of a radiomic model for the preoperative prediction of transsphenoidal surgical response in patients with acromegaly

2019 ◽  
Vol 21 (Supplement_3) ◽  
pp. iii65-iii65
Author(s):  
Y Fan ◽  
M Feng ◽  
R Wang
Keyword(s):  
Clinical Features ◽  
Validation Cohort ◽  
Treatment Strategies ◽  
Area Under The Curve ◽  
Support Vector ◽  
Individual Treatment ◽  
Multivariable Logistic Regression Analysis ◽  
Operating Characteristics ◽  
Preoperative Prediction ◽  
Characteristics Analysis

Abstract BACKGROUND The preoperative prediction of transsphenoidal surgical (TSS) response is important for determining individual treatment strategies for acromegaly. Therefore, this study aimed to predict TSS response in a non-invasive way based on radiomic analysis. MATERIAL AND METHODS 273 patients with acromegaly were enrolled and divided into primary (n=180) and validation cohorts (n=93) according to time point. Radiomic features were extracted from the MR images and determined using the ‘Elastic Net’ feature selection algorithm. A radiomic signature was built using a support vector machine. Subsequently, multivariable logistic regression analysis was used to select the most informative clinical features, and a radiomic model, incorporating the radiomic signature and selected clinical features, was constructed and used as the final predictive model. The performance of this radiomic model was validated using receiver operating characteristics analysis, and its calibration, discriminating ability, and clinical usefulness were assessed. RESULTS The radiomic signature, which was constructed with six radiomic features selected using the primary cohort, showed a favorable discriminatory ability in the validation cohort. The radiomic model incorporating the radiomic signature and three selected clinical features showed good discrimination abilities and calibration, with an area under the curve (AUC) of 0.93 for the primary cohort and 0.89 for the validation cohort. The radiomic model better estimated the treatment responses of patients with acromegaly than did the clinical features. Decision curve analysis showed the radiomic model was clinically useful. CONCLUSION This radiomic model could aid neurosurgeons in the preoperative prediction of TSS response in patients with acromegaly, and could contribute to determining individual treatment strategies.

scholarly journals Correlation Between Chest CT Findings and Clinical Features of 211 COVID-19 Suspected Patients in Wuhan, China

2020 ◽  
Vol 7 (6) ◽  
Author(s):  
Songlin Song ◽  
Feihong Wu ◽  
Yiming Liu ◽  
Hongwei Jiang ◽  
Fu Xiong ◽  
...  
Keyword(s):  
Clinical Features ◽  
Area Under The Curve ◽  
High Sensitivity ◽  
Pulmonary Involvement ◽  
Chest Ct ◽  
Chain Reaction ◽  
Basic Model ◽  
Group 4 ◽  
Significant Difference ◽  
Polymerase Chain

Abstract Background Chest computed tomography (CT) has been widely used to assess pulmonary involvement in COVID-19. We aimed to investigate the correlation between chest CT and clinical features in COVID-19 suspected patients with or without fever. Methods We retrospectively enrolled 211 COVID-19 suspected patients who underwent both chest CT and reverse transcription polymerase chain reaction in Wuhan, China. The performance of CT in patients with relevant onset of symptoms, with fever (n = 141) and without fever (n = 70), was assessed respectively. Results The sensitivity of CT for COVID-19 was 97.3%, with area under the curve (AUC) of 0.71 (95% confidence interval [CI], 0.66–0.76). There were 141 suspected patients with fever and 70 without fever. In the fever group, 4 variables were screened to establish the basic model: age, monocyte, red blood cell, and hypertension. The AUC of the basic model was 0.72 (95% CI, 0.63–0.81), while the AUC of the CT-aided model was 0.77 (95% CI, 0.68–0.85), a significant difference (P < .05). In the nonfever group, only dry cough was screened out to establish the basic model. The AUC was 0.76 (95% CI, 0.64–0.88), which was not significantly different than the CT-aided model (P = .08). Conclusions Chest CT has a high sensitivity in patients with COVID-19, and it can improve diagnostic accuracy for COVID-19 suspected patients with fever during the initial screen, whereas its value for nonfever patients remains questionable.

scholarly journals Blood parameters measured on admission as predictors of outcome for COVID-19; a prospective UK cohort study

2020 ◽  
Author(s):  
DT Arnold ◽  
M Attwood ◽  
S Barratt ◽  
K Elvers ◽  
A Morley ◽  
...  
Keyword(s):  
Clinical Features ◽  
Primary Outcome ◽  
Clinical Laboratory ◽  
Area Under The Curve ◽  
Blood Parameters ◽  
Prognostic Biomarkers ◽  
Predictors Of Outcome ◽  
Intensive Care Admission ◽  
Non Invasive ◽  
Non Invasive Ventilation

AbstractIntroductionCOVID-19 has an unpredictable clinical course so prognostic biomarkers would be invaluable when triaging patients on admission to hospital. Many biomarkers have been suggested using large observational datasets but sample timing is crucial to ensure prognostic relevance. The DISCOVER study prospectively recruited patients with COVID-19 admitted to a UK hospital and analysed a panel of putative prognostic biomarkers on the admission blood sample to identify markers of poor outcome.MethodsConsecutive patients admitted to hospital with proven or clinicoradiological suspected COVID-19 were recruited. Admission bloods were extracted from the clinical laboratory. A panel of biomarkers (IL-6, suPAR, KL-6, Troponin, Ferritin, LDH, BNP, Procalcitonin) were performed in addition to routinely performed markers (CRP, neutrophils, lymphocytes, neutrophil:lymphocyte ratio). Age, NEWS score and CURB-65 were included as comparators. All biomarkers were tested in logistic regression against a composite outcome of non-invasive ventilation, intensive care admission, or death, with Area Under the Curve (AUC) figures calculated.Results155 patients had 28-day outcomes at the time of analysis. CRP (AUC 0.51, CI:0.40-0.62), lymphocyte count (AUC 0.62, CI:0.51-0.72), and other routine markers did not predict the primary outcome. IL-6 (AUC: 0.78,0.65-0.89) and suPAR (AUC 0.77, CI: 0.66-0.85) showed some promise, but simple clinical features alone such as NEWS score (AUC: 0.74, 0.64-0.83) or age (AUC: 0.70, 0.61-0.78) performed nearly as well.DiscussionAdmission blood biomarkers have only moderate predictive value for predicting COVID-19 outcomes, while simple clinical features such as age and NEWS score outperform many biomarkers. IL-6 and suPAR had the best performance, and further studies should validate these biomarkers in a prospective fashion.

scholarly journals Urinary Cell-Free miR-99a-5p as a Potential Biomarker for Estrus Detection in Buffalo

2021 ◽  
Vol 8 ◽  
Author(s):  
Aparna Hebbar ◽  
Rajeev Chandel ◽  
Payal Rani ◽  
Suneel Kumar Onteru ◽  
Dheer Singh
Keyword(s):  
Characteristic Curve ◽  
Area Under The Curve ◽  
High Sensitivity ◽  
Detection Methods ◽  
Non Invasive ◽  
Discovery Sample ◽  
Potential Biomarker ◽  
Estrus Detection ◽  
Buffalo Urine

Accurate estrus detection method is the need of the hour to improve reproductive efficiency of buffaloes in dairy industry, as the currently available estrus detection methods/tools lack high sensitivity and specificity. Recently, circulating miRNAs have been shown as non-invasive biomarkers by various studies. Hence, in order to evaluate their potential as estrus biomarkers, the objective of this study was to identify and compare the levels of 10 hormone-responsive miRNAs in the urine collected at proestrus (PE), estrus (E), and diestrus (DE) phases of buffaloes (n = 3) pertaining to a discovery sample. Among 10 urinary miRNAs, the levels of bta-mir-99a-5p (E/PE 0.5-fold, P < 0.05; DE/PE 1.9-fold), bta-miR-125b (E/PE 0.5-fold; DE/PE 0.7-fold), bta-mir-145 (E/PE 1.5-fold; DE/PE 0.7-fold), bta-mir-210 (E/PE 1.2-fold, DE/PE 0.7-fold), mir-21 (E/PE 1.5-fold, DE/PE 2-fold), and bta-mir-191 (E/PE 1.3-fold; DE/PE 0.8-fold) were found to be altered during different phases of buffalo estrous cycle. In contrast, bta-mir-126-3p, bta-let-7f, bta-mir-16b, and bta-mir-378 were undetected in buffalo urine. Furthermore, a validation study in an independent group of 25 buffalo heifers showed the increased levels of urinary bta-mir-99a-5p during the DE (3.92-fold; P < 0.0001) phase as compared to the E phase. Receiver operating characteristic curve analyses also revealed the ability of urinary miR-99a-5p in distinguishing the E from the DE phase (area under the curve of 0.6464; P < 0.08). In silico analysis further showed an enrichment of miR-99a-5p putative targets in various ovarian signaling pathways, including androgen/estrogen/progesterone biosynthesis and apoptosis signaling, implicating the role of miR-99a-5p in ovarian physiology. In conclusion, significantly lower levels of bta-mir-99a-5p at the E phase than the DE phase in buffalo urine indicate its biomarker potential, which needs to be further explored in a large cohort in the future studies.

scholarly journals “Stifflammation” in hypertension is a predictor of future cardiovascular hospitalizations

2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
D Terentes-Printzios ◽  
G Christopoulou ◽  
L Korogiannis ◽  
N Ioakeimidis ◽  
K Aznaouridis ◽  
...  
Keyword(s):  
Arterial Stiffness ◽  
Confidence Intervals ◽  
Venous Blood ◽  
Area Under The Curve ◽  
High Sensitivity ◽  
Roc Curves ◽  
Left Ventricular ◽  
Multivariable Logistic Regression Analysis

Abstract Background/Introduction Hypertension is associated with increased cardiovascular risk, inflammation and arterial stiffness. Purpose We sought to investigate the role of inflammation and arterial stiffness in the prognosis of cardiovascular hospitalizations in hypertensive patients over an extended follow-up. Methods One hundred and seventy-three patients (mean age 52.5±13.2 years, 57% males) untreated hypertensives at baseline without cardiovascular disease, were included in the study. Arterial stiffness was assessed with carotid-femoral pulse wave velocity (PWV). High-sensitivity C-reactive protein (hsCRP) was measured in venous blood samples. Other markers of subclinical organ damage [left ventricular mass index (LVMI) by echocardiography and estimated glomerular filtration rate (eGFR)] were also evaluated in all patients. Results During 13.6±0.4 years of follow-up, forty-four patients (25.4%) patients were admitted in hospital due to cardiovascular causes. In multivariable logistic regression analysis, only higher hsCRP (Odds Ratio [OR] = 3.34, 95% Confidence intervals [CI]: 1.22–9.51, P=0.02) and increased PWV (OR = 1.48, 95% Confidence intervals [CI]: 1.03–2.12, P=0.036) were associated with higher risk of cardiovascular hospitalizations, which was independent of age, gender, systolic blood pressure, LVMI and presence of diabetes. In further analysis, receiver operating characteristic (ROC) curves were generated to evaluate the ability of hsCRP and PWV to discriminate subjects with cardiovascular hospitalization. The area under the curve (AUC) and 95% CIs of the ROC curves were AUC=0.69 (95% CI: 0.59–0.78, p<0.001) for hsCRP and AUC=0.74 (95% CI: 0.65–0.83, P<0.001) for PWV (Figure). Conclusions Our study shows the independent complimentary prognostic role of inflammation and arterial stiffness in the prognosis of hypertensives even in studies with extended follow-up. FUNDunding Acknowledgement Type of funding sources: None. ROC curves for the prediction of outcome

scholarly journals Non-invasive Prostate Cancer Detection by Measuring Expression Level of miR-21 and miR-214 in Urine

2021 ◽  
Vol In Press (In Press) ◽  
Author(s):  
Alireza Emamvirdizadeh ◽  
Faranak Jamshidian ◽  
Maliheh Entezari ◽  
Saghi Nooraei ◽  
Mehrdad Hashemi
Keyword(s):  
Prostate Cancer ◽  
Sensitivity And Specificity ◽  
Healthy Subjects ◽  
Specific Antigen ◽  
Area Under The Curve ◽  
High Sensitivity ◽  
Expression Level ◽  
Control Group ◽  
Non Invasive ◽  
Invasive Method

Background: Prostate cancer is the most prevalent cancer among men worldwide. Diagnosis in this cancer is primarily done, using aggressive methods such as biopsy. Laboratory methods, such as the measurement of prostate-specific antigen (PSA) in the blood, do not have high sensitivity and specificity. MicroRNAs (miRNAs), a group of diagnostic biomarkers, can diagnose diseases such as cancer. MicroRNA (miRNA) is a small, non-coding, single-stranded RNA with a length of 21 to 23 nucleotides. Objectives: This study was designed to investigate the changes in the expression level of miR-21 and miR-214 in the urine of patients with prostate cancer compared with healthy controls. Methods: A total of 70 urine samples from prostate cancer patients (32 metastatic and 38 non-metastatic) and 30 from healthy subjects with negative biopsy reports were collected. The expression level of miR-21 and miR-214 in the urine were detected by quantitative reverse transcription-polymerase chain reaction (qRT-PCR). Results: miR-21 showed a significant increase in expression (P = 0.003) and miR-214 showed a significant decrease in expression (P = 0.000) compared with the control group. The specificity, sensitivity, and area under the curve (AUC) were 100, 72.14, and 0.721% for combined panels of miR-21 and miR-214 and 63.33, 61.43, and 0.620%, respectively, for PSA. Conclusions: miR-21 and miR-214 showed significant change in expression in patients with prostate cancer compared with healthy subjects. It is hoped that, with further research, a combined panel of miR-21 and miR-214 can be used as a non-invasive method for detecting prostate cancer with higher sensitivity and specificity than the PSA test.

scholarly journals NIMG-22. DEVELOPMENT AND VALIDATION OF A RADIOMIC MODEL FOR RWDD3 EXPRESSION PREDICTION IN PATIENTS WITH ACROMEGALY

2019 ◽  
Vol 21 (Supplement_6) ◽  
pp. vi166-vi166
Author(s):  
Yanghua Fan ◽  
Renzhi Wang ◽  
Ming Feng
Keyword(s):  
Clinical Features ◽  
Validation Cohort ◽  
Area Under The Curve ◽  
Support Vector ◽  
Multivariable Logistic Regression Analysis ◽  
Operating Characteristics ◽  
Discriminatory Ability ◽  
Characteristics Analysis ◽  
Treatment Responses ◽  
Development And Validation

Abstract BACKGROUND The expression of RWDD3 is closely related to the prognosis of acromegaly. Therefore, this study aimed to investigate a radiomics method based on MRI to noninvasively evaluate RWDD3 expression in acromegaly. MATERIAL AND METHODS 132 patients with acromegaly were enrolled and divided into primary (n=88) and validation cohorts (n=44) according. The expression of RWDD3 was determined by immunohistochemistry. Radiomic features were extracted from the MR images and determined using the ‘Elastic Net’ feature selection algorithm. A radiomic signature was built using a support vector machine. Subsequently, multivariable logistic regression analysis was used to select the most informative clinical features, and a radiomic model, incorporating the radiomic signature and selected clinical features, was constructed and used as the final predictive model. The performance of this radiomic model was validated using receiver operating characteristics analysis, and its calibration, discriminating ability, and clinical usefulness were assessed. RESULTS The radiomic signature, which was constructed with radiomic features selected using the primary cohort, showed a favorable discriminatory ability in the validation cohort. The radiomic model incorporating the radiomic signature and three selected clinical features showed good discrimination abilities and calibration, with an area under the curve (AUC) of 0.89 for the primary cohort and 0.84 for the validation cohort. The radiomic model better estimated the treatment responses of patients with acromegaly than did the clinical features. Decision curve analysis showed the radiomic model was clinically useful. CONCLUSION This radiomic model could aid neurosurgeons in the prediction of RWDD3 expression in patients with acromegaly, and could contribute to predicting of patient prognoses.

Sign in / Sign up

Export Citation Format

Share Document