scholarly journals A multi prototype classification algorithm and its application to multi class diagnostics

2015 ◽  
Author(s):  
Mario Ziller
Keyword(s):  
Approximate Solution ◽  
Positive Predictive Value ◽  
Metric Space ◽  
Predictive Value ◽  
Roc Analysis ◽  
Geometric Model ◽  
Classification Procedure ◽  
Discrete Optimisation ◽  
Diagnostic Decision ◽  
Prototype Classification

This paper introduces a novel, universal distance-based classification procedure. It is based on a simple geometric model. Considering all objects as points in a metric space, a class is imagined as covered by potentially differentsized hyperspheres, the centres of which are referred to as prototypes. The radii of the hyperspheres are individually optimised by a generalised ROC-analysis. For the approximate solution of the entire discrete optimisation problem, a greedy algorithm was developed and implemented in R. It runs in O(k2∙n2∙log(n)) time where k is the number of prototypes to be selected and n the number of training objects. For application to multi class problems, one against all approach is performed. The diagnostic decision is finalised for that class of maximum positive predictive value when in doubt. Objects not recognised as a member of any of the classes are assigned to an additional residual class. The performance of the classification system presented is demonstrated on various data examples, and in comparison with other methods.

scholarly journals A multi prototype classification algorithm and its application to multi class diagnostics

2015 ◽  
Author(s):  
Mario Ziller
Keyword(s):  
Approximate Solution ◽  
Positive Predictive Value ◽  
Metric Space ◽  
Predictive Value ◽  
Roc Analysis ◽  
Geometric Model ◽  
Classification Procedure ◽  
Discrete Optimisation ◽  
Diagnostic Decision ◽  
Prototype Classification

This paper introduces a novel, universal distance-based classification procedure. It is based on a simple geometric model. Considering all objects as points in a metric space, a class is imagined as covered by potentially differentsized hyperspheres, the centres of which are referred to as prototypes. The radii of the hyperspheres are individually optimised by a generalised ROC-analysis. For the approximate solution of the entire discrete optimisation problem, a greedy algorithm was developed and implemented in R. It runs in O(k2∙n2∙log(n)) time where k is the number of prototypes to be selected and n the number of training objects. For application to multi class problems, one against all approach is performed. The diagnostic decision is finalised for that class of maximum positive predictive value when in doubt. Objects not recognised as a member of any of the classes are assigned to an additional residual class. The performance of the classification system presented is demonstrated on various data examples, and in comparison with other methods.

Predictive value of thyrotropin receptor antibodies using the second generation TRAb human assay after radioiodine treatment in Graves’ disease

2003 ◽  
Vol 42 (02) ◽  
pp. 63-70 ◽  
Author(s):  
G. Wunderlich ◽  
C. Kopprasch ◽  
R. Koch ◽  
W.-G. Franke ◽  
J. Kotzerke ◽  
...  
Keyword(s):  
Positive Predictive Value ◽  
Predictive Value ◽  
Roc Analysis ◽  
Second Generation ◽  
Graves Disease ◽  
Predictive Values ◽  
Before And After ◽  
Thyrotropin Receptor Antibodies ◽  
Increased Sensitivity ◽  
Receptor Antibodies

SummaryThe detection of TSH-receptor antibodies (TRAb) in patients with Graves’ disease is routinely used in nuclear medicine laboratories. This determination has been possible for approximately 3 years with a second generation human TRAb assay. Studies showed that this TRAb determination is diagnostically more sensitive compared to established, porcine TRAb assays. Objective: The aim of our study was to investigate, based on a ROC analysis, whether TRAb determination with the new, second generation assay allows a dependable statement about probability of occurence of relapse after radioiodine therapy in patient suffering from Graves’ disease. Methods: 57 patients were examined with the DYNOtest® TRAKhuman (BRAHMS Diagnostica AG, Hennigsdorf) directly before and six months after therapy with radioiodine (dose: 150 Gy). A ROC-analysis was performed to determine positive/negative predictive values depending on different cut-off values. Results: Whereas 21/57 patients became eu- or hypothyroid after six months, 36/57 patients relapsed. Nonrelapsed patients showed a significant lower median TRAb titer (4.2 IU/l vs. 19.2 IU/l; p <0.05) compared to relapsed patients. But the positive predictive value conducted 63 and 66, 62 and 66 as well as 63 and 69% (before and after therapy) linked with the cut-offs 1.0, 1.5, and 2.0 IU/l. So it was in areas also achieved by the first generation porcine radioreceptorassay. Conclusion: An increased sensitivity is achieved undoubtedly with the new DYNOtest® TRAKhuman in the diagnostic of Graves’ disease. It is not held over the established radioreceptorassay concerning the positive predictive value for relapsing patients.

scholarly journals Discriminating Capacity of Indole Markers in the Diagnosis of Carcinoid Tumors

2000 ◽  
Vol 46 (10) ◽  
pp. 1588-1596 ◽  
Author(s):  
Wim G Meijer ◽  
Ido P Kema ◽  
Marcel Volmer ◽  
Pax H B Willemse ◽  
Elisabeth G E de Vries
Keyword(s):  
Positive Predictive Value ◽  
Carcinoid Tumor ◽  
Predictive Value ◽  
Roc Analysis ◽  
Reference Group ◽  
Curve Analysis ◽  
Carcinoid Tumors ◽  
Healthy Controls ◽  
Roc Curve Analysis ◽  
Platelet Serotonin

Abstract Background: We evaluated the discriminating capacity of the indole markers urinary 5-hydroxyindoleacetic acid (5-HIAA), urinary serotonin, and platelet serotonin in the diagnosis of carcinoid tumors. Methods: Indole markers were measured in 688 patients with suspected carcinoid disease. The initial values of indole markers from patients in whom a carcinoid tumor was confirmed during follow-up (n = 98) were used for ROC analysis. Two groups served as reference populations. The first consisted of 45 healthy individuals (“healthy controls”). The second was a random sample of 40 patients, drawn from the 590 (688 minus 98) patients with carcinoid-like symptoms but without a carcinoid tumor (“clinically suspected patients”). Results: ROC curve analysis showed platelet serotonin to have the highest discriminating capacity, especially in foregut carcinoids. Cutoff values for platelet serotonin obtained from ROC analysis with healthy controls as reference group (5.4 nmol/109 platelets) gave a sensitivity of 74%, specificity of 91%, positive predictive value of 63%, and negative predictive value of 95% when applied to the initial 688 patients. Using the cutoff value with the clinically suspected patients as the reference group (9.3 nmol/109 platelets) gave a sensitivity of 63%, specificity of 99%, positive predictive value of 89%, and negative predictive value of 93%. Indole markers were increased in 169 (25%) of 688 patients. In 76 (45%) of these 169 patients, a carcinoid tumor was present. Slight increases of markers were associated with non-carcinoid neuroendocrine tumors, non-neuroendocrine tumors, and disturbed bowel motility. Conclusions: ROC curve analysis shows that platelet serotonin is the most discriminating indole marker for the diagnosis of carcinoid tumors. Platelet serotonin especially improves the diagnosis of carcinoids producing small amounts of serotonin.

scholarly journals The comparison of predictive value of cervical length in singleton spontaneous preterm labor with in vitro fertilization pregnancies: A cohort study

2021 ◽  
Author(s):  
Razieh Mohammad ◽  
Mahvash Zargar ◽  
Mojgan Barati ◽  
Somayeh Ershadian
Keyword(s):  
Cohort Study ◽  
In Vitro Fertilization ◽  
Positive Predictive Value ◽  
Negative Predictive Value ◽  
Predictive Value ◽  
Preterm Labor ◽  
Roc Analysis ◽  
Cervical Length ◽  
Vitro Fertilization

Background: Preterm labor (PTL) is one of the most important factors in neonatal mortality. Some studies have revealed a reverse relationship between cervical length (CL) and PTL, however, further evidence is needed to confirm it. Objective: To investigate the predictive value of CL in spontaneous and in vitro fertilization (IVF) pregnancies. Materials and Methods: This prospective cohort study was performed on 154 pregnant women from 16-26 wk of gestation with a singleton fetus in spontaneous delivery (n = 77) and IVF pregnancies (n = 77) and followed up until delivery. Women with multiple pregnancy, placenta previa, cerclage, and congenital anomalies were excluded from the study. The cut-off determination was done according to the Roc analysis. Results: The mean CL in term delivery and PTL groups were 37 ± 7 mm and 31 ± 6 mm, respectively (p < 0.001). The frequency of PTL in spontaneous and IVF pregnancies were 7.8% and 23.27%, respectively (p = 0.007). According to the Roc analysis, the best cut-off for normal pregnancy was ≤ 36 mm with the negative predictive value of 97.9%, the positive predictive value of 11.4%, sensitivity 83.3%, and specificity of 46.5%. While for the IVF group, the cut off was ≤ 30 mm, with a negative predictive value of 88.4%, a positive predictive value of 57.8%, sensitivity of 63.2%, and a specificity of 86%. Conclusion: In this study, IVF had a significant direct correlation with PTL. CL also had a significant indirect relationship with PTL. Key words: Cervix, IVF, Preterm delivery, PTL.

Coated-platelets predict stroke at 30 days following TIA

Neurology ◽  
2017 ◽  
Vol 89 (2) ◽  
pp. 125-128 ◽  
Author(s):  
Angelia C. Kirkpatrick ◽  
Andrea S. Vincent ◽  
George L. Dale ◽  
Calin I. Prodan
Keyword(s):  
Confidence Interval ◽  
Positive Predictive Value ◽  
Predictive Value ◽  
Roc Analysis ◽  
Area Under The Curve ◽  
Predictive Ability ◽  
Receiver Operator Characteristic ◽  
Agonist Stimulation ◽  
Abcd2 Score ◽  
Dual Agonist

Objective:To examine the potential for coated-platelets, a subset of highly procoagulant platelets observed on dual agonist stimulation with collagen and thrombin, for predicting stroke at 30 days in patients with TIA.Methods:Consecutive patients with TIA were enrolled and followed up prospectively. ABCD2 scores were obtained for each patient. Coated-platelet levels, reported as percent of cells converted to coated-platelets, were determined at baseline. The primary endpoint was the occurrence of stroke at 30 days. Receiver operator characteristic (ROC) analysis was used to calculate area under the curve (AUC) values for a model including coated-platelets to predict incident stroke at 30 days.Results:A total of 171 patients with TIA were enrolled, and 10 strokes were observed at 30 days. A cutoff of 51.1% for coated-platelet levels yielded a sensitivity of 0.80 (95% confidence interval [CI] 0.55–1.0), specificity of 0.73 (95% CI 0.66–0.80), positive predictive value of 0.16 (95% CI 0.06–0.26), and negative predictive value of 0.98 (95% CI 0.96–1.0). The adjusted hazard ratio of incident stroke in patients with coated-platelet levels ≥51.1% was 10.72 compared to those with levels <51.1%. ROC analysis showed significant improvement in the predictive ability of the coated-platelet model compared to ABCD2 score (AUC 0.78 ± 0.07 vs 0.54 ± 0.07, p = 0.01).Conclusions:These findings suggest a role for coated-platelets in risk stratification for stroke at 30 days after TIA.

scholarly journals Lack of Specificity of Plasma Concentrations of Inhibin B and Follicle-Stimulating Hormone for Identification of Azoospermic Survivors of Childhood Cancer: A Report From the St Jude Lifetime Cohort Study

2013 ◽  
Vol 31 (10) ◽  
pp. 1324-1328 ◽  
Author(s):  
Daniel M. Green ◽  
Liang Zhu ◽  
Nan Zhang ◽  
Charles A. Sklar ◽  
Raymond W. Ke ◽  
...  
Keyword(s):  
Positive Predictive Value ◽  
Childhood Cancer ◽  
Predictive Value ◽  
Roc Analysis ◽  
Follicle Stimulating Hormone ◽  
Sperm Concentration ◽  
Inhibin B ◽  
Male Survivors ◽  
Survivors Of Childhood Cancer ◽  
Stimulating Hormone

Purpose Many male survivors of childhood cancer are at risk for azoospermia. Although both the levels of follicle-stimulating hormone (FSH) and inhibin B are correlated with sperm concentration, their ability to predict azoospermia in survivors of childhood cancer remains uncertain. Patients and Methods Semen analysis was performed and serum levels of FSH and inhibin B were measured in 275 adult male survivors of childhood cancer who had received gonadotoxic therapy. Receiver operating characteristic (ROC) analysis was performed to determine the optimal inhibin B and FSH values for identifying patients with azoospermia. The patient sample was divided into a learning set and a validation set. Sensitivity, specificity, and positive and negative predictive value were calculated. Results Inhibin B was dichotomized as ≤ 31 ng/L or more than 31 ng/L and FSH was dichotomized as ≤ 11.5 mIU/mL or more than 11.5 mIU/mL based on results of the ROC analysis. Using these values, the specificity of the serum level of inhibin B for identifying azoospermic survivors was 45.0%, and the positive predictive value was 52.1%. The specificity for FSH was 74.1%, and the positive predictive value was 65.1%. Conclusion Neither serum inhibin B nor FSH is a suitable surrogate for determination of sperm concentration in a semen sample. Young men and their physicians should be aware of the limitations of these measures for assessment of fertility potential.

Diagnosis of cerebral hemorrhage before the era of computed tomography

2013 ◽  
Vol 154 (44) ◽  
pp. 1743-1746
Author(s):  
Gergely Hofgárt ◽  
Rita Szepesi ◽  
Bertalan Vámosi ◽  
László Csiba
Keyword(s):  
Computed Tomography ◽  
Cerebrospinal Fluid ◽  
Positive Predictive Value ◽  
Predictive Value ◽  
Hemorrhagic Stroke ◽  
Cranial Computed Tomography ◽  
Cerebral Stroke ◽  
Daily Routine ◽  
Stroke Patients ◽  
The Difference

Introduction: During the past decades there has been a great progress in neuroimaging methods. Cranial computed tomography is part of the daily routine now and its use allows a fast diagnosis of parenchymal hemorrhage. However, before the availability of computed tomography the differentiation between ischemic and hemorrhagic stroke was based on patient history, physical examination, percutan angiography and cerebrospinal fluid sampling, and the clinical utility could be evaluated by autopsy of deceased patients. Aim: The authors explored the diagnostic performance of cerebrospinal fluid examination for the diagnosis of ischemic and hemorrhagic stroke. Method: Data of 200 deceased stroke patients were retrospectively evaluated. All patients had liquor sampling at admission and all of them had brain autopsy. Results: Bloody or yellowish cerebrospinal fluid at admission had a positive predictive value of 87.5% for hemorrhagic stroke confirmed by autopsy, while clear cerebrospinal fluid had positive predictive value of 90.7% for ischemic stroke. Patients who had clear liquor, but autopsy revealed hemorrhagic stroke had higher protein level in the cerebrospinal fluid, but the difference was not statistically significant (p = 0.09). Conclusions: The results confirm the importance of pathological evaluation of the brain in cases deceased from cerebral stroke. With this article the authors wanted to salute for those who contributed to the development of the Hungarian neuropathology. In this year we remember the 110th anniversary of the birth, and the 60th anniversary of the death of professor Kálmán Sántha. Professor László Molnár would be 90 years old in 2013. Orv. Hetil., 154 (44), 1743–1746.

VALUE OF COMBINATION OF HAP SCORE AND BISAP SCORE IN PREDICTING SEVERITY IN PATIENTS OF ACUTE PANCREATITIS

2019 ◽  
pp. 96-100
Author(s):  
Thi Ngoc Suong Le ◽  
Pham Chi Tran ◽  
Van Huy Tran
Keyword(s):  
Acute Pancreatitis ◽  
Positive Predictive Value ◽  
Roc Curve ◽  
Predictive Value ◽  
Prognostic Value ◽  
Acute Inflammation ◽  
Clinical Symptoms ◽  
Mortality Rates ◽  
Multiple Organ ◽  
Central Hospital

Acute pancreatitis (AP) is an acute inflammation of the pancreas, usually occurs suddenly with a variety of clinical symptoms, complications of multiple organ failure and high mortality rates. Objectives: To determine the value of combination of HAP score and BISAP score in predicting the severity of acute pancreatitis of the Atlanta 2012 Classification. Patients and Methods: 75 patients of acute pancreatitis hospitalized at Hue Central Hospital between March 2017 and July 2018; HAP and BISHAP score is calculated within the first 24 hours. The severity of AP was classified by the revised Atlanta criteria 2012. Results: When combining the HAP and BISAP scores in predicting the severity of acute pancreatitis, the area under the ROC curve was 0,923 with sensitivity value was 66.7%, specificity value was 97.1%; positive predictive value was 66.7%, negative predictive value was 97.1%. Conclusion: The combination of HAP and BISAP scores increased the sensitivity, predictive value, and prognostic value in predicting the severity of acute pancreatitis of the revised Atlanta 2012 classification in compare to each single scores. Key words: HAPscore, BiSAP score, acute pancreatitis, predicting severity

scholarly journals Accuracy of MSCT Coronary Angiography with 64 Row CT Scanner—Facing the Facts

2010 ◽  
Vol 4 ◽  
pp. CMC.S3864 ◽  
Author(s):  
M. Wehrschuetz ◽  
E. Wehrschuetz ◽  
H. Schuchlenz ◽  
G. Schaffler
Keyword(s):  
Coronary Artery Disease ◽  
Coronary Artery ◽  
Coronary Angiography ◽  
Positive Predictive Value ◽  
Diagnostic Accuracy ◽  
Predictive Value ◽  
Diagnostic Potential ◽  
Coronary Artery Stenoses ◽  
Artery Disease ◽  
Msct Angiography

Improvements in multislice computed tomography (MSCT) angiography of the coronary vessels have enabled the minimally invasive detection of coronary artery stenoses, while quantitative coronary angiography (QCA) is the accepted reference standard for evaluation thereof. Sixteen-slice MSCT showed promising diagnostic accuracy in detecting coronary artery stenoses haemodynamically and the subsequent introduction of 64-slice scanners promised excellent and fast results for coronary artery studies. This prompted us to evaluate the diagnostic accuracy, sensitivity, specificity, and the negative und positive predictive value of 64-slice MSCT in the detection of haemodynamically significant coronary artery stenoses. Thirty-seven consecutive subjects with suspected coronary artery disease were evaluated with MSCT angiography and the results compared with QCA. All vessels were considered for the assessment of significant coronary artery stenosis (diameter reduction ≥ 50%). Thirteen patients (35%) were identified as having significant coronary artery stenoses on QCA with 6.3% (35/555) affected segments. None of the coronary segments were excluded from analysis. Overall sensitivity for classifying stenoses of 64-slice MSCT was 69%, specificity was 92%, positive predictive value was 38% and negative predictive value was 98%. The interobserver variability for detection of significant lesions had a κ-value of 0.43. Sixty-four-slice MSCT offers the diagnostic potential to detect coronary artery disease, to quantify haemodynamically significant coronary artery stenoses and to avoid unnecessary invasive coronary artery examinations.

Sign in / Sign up

Export Citation Format

Share Document