scholarly journals A Preoperative MRI-Based Radiomics-Clinicopathological Classifier to Predict the Recurrence of Pituitary Macroadenoma Within 5 Years

2022 ◽  
Vol 12 ◽  
Author(s):  
Yu Zhang ◽  
Yuqi Luo ◽  
Xin Kong ◽  
Tao Wan ◽  
Yunling Long ◽  
...  
Keyword(s):  
Risk Factors ◽  
Multivariate Analyses ◽  
Area Under The Curve ◽  
Predictive Performance ◽  
Pituitary Macroadenoma ◽  
Roc Curve Analysis ◽  
3D Slicer ◽  
Contrast Enhanced ◽  
Selection Operator

Objective: To investigate the ability of a MRI-based radiomics-clinicopathological model to predict pituitary macroadenoma (PMA) recurrence within 5 years.Materials and Methods: We recruited 74 recurrent and 94 non-recurrent subjects, following first surgery with 5-year follow-up data. Univariate and multivariate analyses were conducted to identify independent clinicopathological risk factors. Two independent and blinded neuroradiologists used 3D-Slicer software to manually delineate whole tumors using preoperative axial contrast-enhanced T1WI (CE-T1WI) images. 3D-Slicer was then used to extract radiomics features from segmented tumors. Dimensionality reduction was carried out by the least absolute shrinkage and selection operator (LASSO). Two multilayer perceptron (MLP) models were established, including independent clinicopathological risk factors (Model 1) and a combination of screened radiomics features and independent clinicopathological markers (Model 2). The predictive performance of these models was evaluated by receiver operator characteristic (ROC) curve analysis.Results: In total, 1,130 features were identified, and 4 of these were selected by LASSO. In the test set, the area under the curve (AUC) of Model 2 was superior to Model 1 {0.783, [95% confidence interval (CI): 0.718—.860] vs. 0.739, (95% CI: 0.665–0.818)}. Model 2 also yielded the higher accuracy (0.808 vs. 0.692), sensitivity (0.826 vs. 0.652), and specificity (0.793 vs. 0.724) than Model 1.Conclusions: The integrated classifier was superior to a clinical classifier and may facilitate the prediction of individualized prognosis and therapy.

scholarly journals The Clinical Utility of Serial Procalcitonin and Procalcitonin Clearance in Predicting the Outcome of COVID-19 Patients

2021 ◽  
Author(s):  
Sara I. Taha ◽  
Aalaa K. Shata ◽  
Shereen A. Baioumy ◽  
Shaimaa H. Fouad ◽  
Mariam K. Youssef
Keyword(s):  
Hospital Mortality ◽  
Prospective Observational Study ◽  
Operating Characteristic ◽  
Area Under The Curve ◽  
Predictive Performance ◽  
Roc Curve Analysis ◽  
Laboratory Tool ◽  
Serial Measurements ◽  
Better Than

Background: The pandemic of coronavirus disease 2019 (COVID‐19) represents a great threat to global health. Sensitive tests that effectively predict the disease outcome are essentially required to guide proper intervention. Objectives: To evaluate the prognostic ability of serial procalcitonin (PCT) measurement to predict the outcome of COVID-19 patients, using PCT clearance (PCT-c) as a tool to reflect its dynamic changes. Methods: A prospective observational study of inpatients diagnosed with COVID-19 at the Quarantine Hospitals of Ain-Shams University, Cairo, Egypt. During the first five days of hospitalization, serial PCT and PCT-c values were obtained and compared between survivors and non-survivors. Patients were followed up to hospital discharge or in-hospital mortality. Results: Compared to survivors, serial PCT levels of non-survivors were significantly higher (p<0.001) and progressively increased during follow-up, in contrast, PCT-c values were significantly lower (p<0.01) and progressively decreased. Receiver operating characteristic (ROC) curve analysis showed that by using the initial PCT value alone, at a cut off value of 0.80 ng/ml, the area under the curve for predicting in-hospital mortality was 0.81 with 61.1% sensitivity and 87.3% accuracy. Serial measurements showed better predictive performance and the combined prediction value was better than the single prediction by the initial PCT. Conclusions: Serial PCT measurement could be a useful laboratory tool to predict the prognosis and outcome of COVID-19 patients. Moreover, PCT-c could be a reliable tool to assess PCT progressive kinetics.

Prediction of the number of metastatic axillary lymph nodes in breast cancer by radiomic signature based on dynamic contrast-enhanced MRI

2021 ◽  
pp. 028418512110258
Author(s):  
Lan Li ◽  
Tao Yu ◽  
Jianqing Sun ◽  
Shixi Jiang ◽  
Daihong Liu ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Lymph Nodes ◽  
Area Under The Curve ◽  
Test Group ◽  
Predictive Performance ◽  
Axillary Lymph Nodes ◽  
Axillary Lymph ◽  
Dynamic Contrast Enhanced ◽  
Contrast Enhanced ◽  
Delayed Phase

Background The number of metastatic axillary lymph nodes (ALNs) play a crucial role in the staging, prognosis and therapy of patients with breast cancer. Purpose To predict the number of metastatic ALNs in breast cancer via radiomics. Material and Methods We enrolled 197 patients with breast cancer who underwent dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). A total of 3386 radiomic features were extracted from the early- and delayed-phase subtraction images. To classify the number of metastatic ALNs, logistic regression was used to develop a radiomic signature and nomogram. Results The radiomic signature were constructed to distinguish the N0 group from the N+ (metastatic ALNs ≥ 1) group, which yielded area under the curve (AUC) values of 0.82 and 0.81 in the training and test group, respectively. Based on the radiomic signature and BI-RADS category, a nomogram was further developed and showed excellent predictive performance with AUC values of 0.85 and 0.89 in the training and test groups, respectively. Another radiomic signature was constructed to distinguish the N1 (1–3 ALNs) group from the N2–3 (≥4 metastatic ALNs) group and showed encouraging performance with AUC values of 0.94 and 0.84 in training and test group, respectively. Conclusions We developed a nomogram and a radiomic signature that can be used to predict ALN metastasis and distinguish the N1 from the N2-3 group. Both nomogram and radiomic signature may be potential tools to assist clinicians in assessing ALN metastasis in patients with breast cancer.

A proof-of-concept study applying machine learning methods to putative risk factors for eating disorders: results from the multi-centre European project on healthy eating

2021 ◽  
pp. 1-10
Author(s):  
I. Krug ◽  
J. Linardon ◽  
C. Greenwood ◽  
G. Youssef ◽  
J. Treasure ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Logistic Regression ◽  
Predictive Accuracy ◽  
Area Under The Curve ◽  
Prediction Rule ◽  
Predictive Performance ◽  
Individual Risk ◽  
European Project ◽  
Wide Range

Abstract Background Despite a wide range of proposed risk factors and theoretical models, prediction of eating disorder (ED) onset remains poor. This study undertook the first comparison of two machine learning (ML) approaches [penalised logistic regression (LASSO), and prediction rule ensembles (PREs)] to conventional logistic regression (LR) models to enhance prediction of ED onset and differential ED diagnoses from a range of putative risk factors. Method Data were part of a European Project and comprised 1402 participants, 642 ED patients [52% with anorexia nervosa (AN) and 40% with bulimia nervosa (BN)] and 760 controls. The Cross-Cultural Risk Factor Questionnaire, which assesses retrospectively a range of sociocultural and psychological ED risk factors occurring before the age of 12 years (46 predictors in total), was used. Results All three statistical approaches had satisfactory model accuracy, with an average area under the curve (AUC) of 86% for predicting ED onset and 70% for predicting AN v. BN. Predictive performance was greatest for the two regression methods (LR and LASSO), although the PRE technique relied on fewer predictors with comparable accuracy. The individual risk factors differed depending on the outcome classification (EDs v. non-EDs and AN v. BN). Conclusions Even though the conventional LR performed comparably to the ML approaches in terms of predictive accuracy, the ML methods produced more parsimonious predictive models. ML approaches offer a viable way to modify screening practices for ED risk that balance accuracy against participant burden.

Serum procalcitonin levels predict disseminated intravascular coagulation in patients with sepsis shock: A retrospective cohort study

2020 ◽  
Author(s):  
Guang Fu ◽  
Xi-si He ◽  
Hao-li Li ◽  
Hai-chao Zhan ◽  
Jun-fu Lu ◽  
...  
Keyword(s):  
Risk Factors ◽  
Septic Shock ◽  
Cohort Study ◽  
Disseminated Intravascular Coagulation ◽  
Area Under The Curve ◽  
Multivariable Logistic Regression Model ◽  
Intravascular Coagulation ◽  
The Relationship ◽  
Conventional Risk Factors

Abstract Background Complication of disseminated intravascular coagulation (DIC) is a determinant of the prognosis in patients with sepsis shock. Procalcitonin (PCT) has been advocated as a marker of bacterial sepsis. The purpose of this study was to evaluate the relationship between serum PCT levels and DIC with sepsis shock Methods A cohort study was designed which included patients that admitted in intensive care unit (ICU) between January 1, 2015 and December 31, 2018 and the follow-up to discharge. 164 septic shock patients were divided into DIC and non-DIC groups according to international society of thrombosis and homeostasis (ISTH). PCT was measured at the admission to ICU, and all the participants received routine biochemical coagulation test subsequently. Results PCT levels were considerably higher in septic shock patients who developed DIC than those who did not (54.6[13.6–200]vs12.6[2.4–53.3]ng/ml), respectively, P < 0.001). Multivariable logistic regression model revealed that PCT level was significantly associated with risk of DIC independent of conventional risk factors. In addition, curve fitting showed a linear relationship between PCT and DIC score. The Receiver Operating characteristic(ROC) curve suggested that the optimal cut-off point for PCT to predicting DIC induced by septic shock was 42.0 ng/ml, and the area under the curve (AUC) was 0.701(95% CI [0.619–0.784], P < 0.001). More importantly, incorporating PCT with other risk factors into the prediction model significantly increased the AUC for prediction of DIC induced by sepsis shock (0.801vs 0.706; P = 0.012). Conclusions Our study suggests that PCT levels on admission is significantly and independently associated with DIC development subsequently with septic shock, combining PCT levels with other risk factors could significantly improve the prediction of DIC induced by sepsis shock.

scholarly journals Factors Affecting Volume Reduction Velocity for Arteriovenous Malformations After Treatment With Dose-Stage Stereotactic Radiosurgery

2021 ◽  
Vol 11 ◽  
Author(s):  
Xiangyu Meng ◽  
Dezhi Gao ◽  
Hengwei Jin ◽  
Kuanyu Wang ◽  
Enmeng Bao ◽  
...  
Keyword(s):  
Stereotactic Radiosurgery ◽  
Multivariate Analyses ◽  
Area Under The Curve ◽  
Target Volume ◽  
Volume Reduction ◽  
Time Interval ◽  
Lesion Volume ◽  
3D Slicer ◽  
Factors Affecting ◽  
The Mean

Background and PurposeThe purpose of this study was to identify morphologic and dosimetric features associated with volume reduction velocity for arteriovenous malformation (AVM) after dose-stage stereotactic radiosurgery (DS-SRS).MethodsThirty patients with intracranial AVM were treated with DS fractionated SRS at Beijing Tiantan Hospital from 2011 to 2019. The AVM nidus was automatically segmented from DICOMRT files using the 3D Slicer software. The change in lesion volume was obtained from the decrease in the planning target volume (PTV) between the two treatment sessions. The volume reduction velocity was measured by the change in volume divided by the time interval between treatments. Fourteen morphologic features of AVM prior to treatment were extracted from the PTV using ‘Pyradiomics’ implemented in Python. Along with other dosimetric features, univariate and multivariate analyses were performed to explore predictors of the volume reduction velocity.ResultsAmong the 15 male (50.0%) and 15 female (50.0%) patients enrolled in this study, 17 patients (56.7%) initially presented with hemorrhage. The mean treatment interval between the initial and second SRS was 35.73 months. In multivariate analysis, the SurfaceVolumeRatio was the only independent factor associated with the volume reduction velocity (p=0.010, odds ratio=0.720, 95% confidence interval: 0.560–0.925). The area under the curve of this feature for predicting the volume reduction velocity after the initial treatment of DS-SRS was 0.83. (p=0.0018).ConclusionsThe morphologic features correlated well with the volume reduction velocity in patients with intracranial AVM who underwent DS-SRS treatment. The SurfaceVolumeRatio could predict the rate of volume reduction of AVMs after DS-SRS.

scholarly journals Cystatin C and α-1-Microglobulin Predict Severe Acute Kidney Injury in Patients with Hemorrhagic Fever with Renal Syndrome

Pathogens ◽  
2020 ◽  
Vol 9 (8) ◽  
pp. 666 ◽  
Author(s):  
Magnus Hansson ◽  
Rasmus Gustafsson ◽  
Chloé Jacquet ◽  
Nedia Chebaane ◽  
Simon Satchell ◽  
...  
Keyword(s):  
Acute Kidney Injury ◽  
Cystatin C ◽  
Area Under The Curve ◽  
Kidney Injury ◽  
Hemorrhagic Fever ◽  
Roc Curve Analysis ◽  
Abrupt Decrease ◽  
Neutrophil Gelatinase Associated Lipocalin ◽  
Neutrophil Gelatinase

Puumala orthohantavirus causes hemorrhagic fever with renal syndrome (HFRS) characterized by acute kidney injury (AKI), an abrupt decrease in renal function. Creatinine is routinely used to detect and quantify AKI; however, early AKI may not be reflected in increased creatinine levels. Therefore, kidney injury markers that can predict AKI are needed. The potential of the kidney injury markers urea, cystatin C, α1-microglobulin (A1M) and neutrophil gelatinase-associated lipocalin (NGAL) to detect early AKI during HFRS was studied by quantifying the levels of these markers in consecutively obtained plasma (P) and urine samples (U) for 44 HFRS patients. P-cystatin C and U-A1M levels were significantly increased during early HFRS compared to follow-up. In a receiver operating characteristic (ROC) curve analysis, P-cystatin C, U-A1M and P-urea predicted severe AKI with area under the curve 0.72, 0.73 and 0.71, respectively, whereas the traditional kidney injury biomarkers creatinine and U-albumin did not predict AKI. Nearly half of the HFRS patients (41%) fulfilled the criteria for shrunken pore syndrome, which was associated with the level of inflammation as measured by P-CRP. P-cystatin C and U-A1M are more sensitive and earlier markers compared to creatinine in predicting kidney injury during HFRS.

Growth-Related Major Recanalization of Coiled Aneurysms: Incidence and Risk Factors

Neurosurgery ◽  
2017 ◽  
Vol 82 (2) ◽  
pp. 185-191 ◽  
Author(s):  
Young Dae Cho ◽  
Jin Pyeong Jeon ◽  
Dong Hyun Yoo ◽  
Won-Sang Cho ◽  
Hyun-Seung Kang ◽  
...  
Keyword(s):  
Risk Factors ◽  
Medical Records ◽  
Coil Embolization ◽  
Multivariate Analyses ◽  
Multiple Logistic Regression Analysis ◽  
Multiple Logistic Regression ◽  
Endovascular Techniques ◽  
Radiological Data ◽  
Aneurysm Volume

Abstract BACKGROUND Though endovascular techniques and procedural devices continue to advance, recurrence of embolized aneurysms is still problematic. Enlarging size during follow-up is the presumed basis of recanalization in some lesions, but such growth has not been adequately investigated. OBJECTIVE To generate estimates of growth in coiled aneurysms with major recanalization, focusing on incidence and risk factors involved. METHODS A cohort of 134 patients harboring 139 aneurysms were retrospectively reviewed, each subjected to re-embolization for major recanalization after initial coil embolization. Cumulative medical records and radiological data were assessed. The aneurysms were grouped by nature of recanalization, either related or unrelated to growth. Growth was defined as &gt;50% increase in aneurysm volume (including coil mass) at the time of re-embolization, compared initial status. Aneurysm volumes were determined by volume of coil mass within full confines of the aneurysm. Univariate and multivariate analyses were performed to identify risk factors predisposing to growth. RESULTS Major recanalization was growth related in 74 coiled aneurysms (53.2%) and unrelated to growth (by coil compaction) in 65 (46.8%). Multiple logistic regression analysis indicated that growth of coiled aneurysm was linked to aneurysms initially ruptured at presentation (P = .002) and aneurysm size &lt;7 mm (P &lt; .001). Cumulative growth rates were as follows: 14 (18.9%), 6 mo; 18 (24.3%), 12 mo; 13 (17.6%), 24 mo; 10 (13.5%), 36 mo; and 19 (25.7%), &gt;36 mo. CONCLUSION Our data suggest that aneurysms presenting with hemorrhage and small-sized aneurysms (&lt;7 mm) are predisposed major recanalization by growth after coil embolization, as opposed to coil compaction.

Thirty years of experience with epicardial pacing in children

2004 ◽  
Vol 14 (5) ◽  
pp. 512-519 ◽  
Author(s):  
Nicolas Noiseux ◽  
Paul Khairy ◽  
Anne Fournier ◽  
Suzanne J. Vobecky
Keyword(s):  
Risk Factors ◽  
Relative Risk ◽  
Multivariate Analyses ◽  
Median Sternotomy ◽  
Small Children ◽  
Permanent Pacing ◽  
Epicardial Pacing ◽  
Univariate Analyses

Due to underlying cardiovascular anatomy and size, epicardial pacing may be the preferred method of pacing in small children. To assess long-term safety, we reviewed all epicardial pacemakers implanted in children between 1971 and 2001. We found that 122 patients, with a median age of 5.4 years, had a total of 181 pacemakers and 260 electrodes implanted over a total follow-up of 789 patient-years. Of the total, 12 patients died after the first implantation, with one death attributable to dysfunction of the pacemaker. Reintervention was required in 75 patients after 5.0 ± 3.2 years, due to depletion of the battery in 45 patients (60%), fracture or dysfunction of electrodes in 27 patients (36%), and infection in 3 patients (4%). In univariate analyses, risk factors for reintervention were an approach via a median sternotomy, with a relative risk of 2.3 (p = 0.0087), and an indication for pacing other than atrioventricular block, with a relative risk of 1.7 (p = 0.0314). In multivariate analyses, the approach via the median sternotomy independently predicted the need for reintervention, with a relative risk of 2.1, and 95% confidence intervals from 1.1 to 4.1 (p = 0.0256). The longevity of the second pacemaker and/or its electrode, assessed in 26 patients, was 3.7 ± 2.6 years, not shorter than the first implantation (p = 0.4037). We conclude that epicardial pacing is a reliable means of achieving permanent pacing in children, with low morbidity and mortality. A substantial proportion, nonetheless, requires reintervention within five years, warranting meticulous follow-up.

scholarly journals The association the patient-reported outcomes after periacetabular osteotomy with radiographic features: a short-term retrospective study

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Yinuo Fan ◽  
Weifeng Li ◽  
Yunlong Wu ◽  
Ruoyu Li ◽  
Guoju Hong ◽  
...  
Keyword(s):  
Risk Factors ◽  
Roc Curve ◽  
Patient Reported Outcomes ◽  
Periacetabular Osteotomy ◽  
Multivariate Logistic Regression Analysis ◽  
Curve Analysis ◽  
Roc Curve Analysis ◽  
Joint Congruency ◽  
Patient Reported

Abstract Background Bernese periacetabular osteotomy (PAO) is an effective treatment for patients with developmental dysplasia of the hip (DDH). PAO has been widely used in China, but few follow-up outcomes have been reported in the international community. Moreover, the risk factors affecting patient-reported outcomes have not been discussed in recent studies. In this study, patient-reported outcomes after PAO were reported, and risk factors affecting patient-reported outcomes were analyzed. Methods Patients who underwent PAO for DDH from January 2014 to January 2020 were selected as the study subjects, and 66 hips were included in the analysis after screening (59 patients, with an average follow-up time of 3.01 years). The Harris Hip Score (HHS) and International Hip Outcome Instrument-12 (iHOT-12) were used to assess hip function and patient quality of life. The changes of preoperative and latest follow-up HHSs less than 9 were defined as symptomatic hips, that is, an adverse outcome; otherwise, the score indicates preserved hips. Also, the changes of preoperative and latest follow-up iHOT-12 were defined as symptomatic hips and preserved hips. Multivariate logistic regression analysis was used to predict the risk factors influencing the patient-reported outcomes, and receiver operating characteristic (ROC) curve analysis was performed on the risk factors to determine their sensitivity, specificity and cutoff value. Results Clinical outcome analysis demonstrates marked improvements in patient-reported outcomes. The multivariate logistic regression analysis showed that when the postoperative LCEA was > 38°, adverse outcomes were much more likely. However, a Tönnis angle of − 10° to 0° was a protective factor. In addition, hips with fair or poor joint congruency were more likely to develop negative outcomes. The ROC curve analysis showed that the optimal thresholds for the LCEA and Tönnis angles used to predict outcomes after PAO were 38.2° and − 9°, respectively. Based on the results of the ROC curve analysis, among hips with poor or fair joint congruency preoperatively treated by surgeons who obtained the improper postoperative LCEAs and Tönnis angles, bad patient-reported outcomes will most likely be obtained. Conclusions Our results demonstrate marked improvements in patient-reported outcomes. Among hips with preoperative excellent or good joint congruency treated by experienced surgeons who obtain the proper postoperative LCEA and Tönnis angles, good patient-reported outcomes can be expected.

scholarly journals Risk Factors to Predict Ocular Metastasis in Older Adult Patients With Gastric Cancer:LDL, ApoA1, and CA724

2022 ◽  
Vol 21 ◽  
pp. 153303382110658
Author(s):  
Wen-Qing Shi ◽  
Shi-Nan Wu ◽  
Tie Sun ◽  
Hui-Ye Shu ◽  
Qi-Chen Yang ◽  
...  
Keyword(s):  
Risk Factors ◽  
Roc Curve ◽  
Area Under The Curve ◽  
Density Lipoprotein ◽  
Demographic Characteristics ◽  
Curve Analysis ◽  
Apolipoprotein A1 ◽  
Roc Curve Analysis ◽  
Significant Difference ◽  
Ocular Metastasis

Objective: The purpose of this study was to explore the risk factors for Ocular metastasis (OM) of Gastric cancer (GC). Methods: This is a retrospective cohort study. A total of 1165 patients with GC were enrolled in this study and divided into OM and non-ocular metastasis (NOM) groups. Chi-square and independent samples t tests were used to determine whether differences in demographic characteristics and serological indicators (SI) between the two groups were significant. In addition, binary logistic regression was used to analyze the value of various SI as risk factors for OM in patients with GC. The statistical threshold was set as P < .05. Finally, receiver operating characteristic (ROC) curve analysis was used to assess the diagnostic value of various SI in differentiating the occurrence of OM in patients with GC. Results: The incidence of OM in older adults with GC was 1.1%. Adenocarcinoma was the most common type of GC in both groups, and there was no significant difference in demographic characteristics between the groups. Low-density lipoprotein (LDL), carbohydrate antigen-724 (CA724), and carcinoembryonic antigen levels were significantly higher in the OM group than the NOM group, while those of apolipoprotein A1 (ApoA1) were significantly lower in the OM than the NOM group. Binary logistic analysis showed that LDL, ApoA1, and CA724 were independent risk factors for OM in patients with GC ( P < .001, P = .033, and P = .008, respectively). ROC curve analysis generated area under the curve (AUC) values of 0.881, 0.576, and 0.906 for LDL, ApoA1, and CA724, respectively. In addition, combined analysis of LDL, ApoA1, and CA724 generated the highest AUC value of 0.924 ( P < .001). Conclusion: Among SI, LDL, ApoA1, and CA724 have predictive value for the occurrence of OM in GC, with the three factors combined having the highest value.

Sign in / Sign up

Export Citation Format

Share Document