Receiver operator curve

Figure 18.2 Representative receiver operator curves to demonstrate the leave n out validation of K-PLS classification models (metabolite formed or not formed) derived with approximately 300 molecules and over 60 descriptors. The diagonal line represents random. The horizontal axis represents the percentage of false positives and the vertical axis the percentage of false negatives in each case. a. Al-dealkylation. b. O-dealkylation. c. Aromatic hydroxylation. d. Aliphatic hydroxylation. e. O-glucuronidation. f. O-sulfation. Data generated in collaboration with Dr. Mark Embrechts (Rensselaer Polytechnic Institute).

Diagnostic specificity and sensitivity are analyzed by receiver-operator curves (ROC) using data obtained from defined healthy populations, patients with diseases other than the investigated ones, and patients with chnical relevance to the respective disease. 

Receiver operator curves (ROC) have demonstrated the superiority of urinary Bik vs CRP in predicting vascular inflammation, viral and bacterial infection. Bik determination by immunoassay is better able to separate patients with inflammation, that is fewer false positives and higher correlation to CRP and WBC, vs enzyme inhibition methods. Urinary IL-8 activity is also increased in acute and active inflammatory conditions and correlates positively with inflammatory markers. 

Sun [54] reported a naive Bayes classifier built around a training set of 1979 compounds with measured hERG activity from the Roche corporate collection. For the training set, 218 in-house atom-type descriptors were used to develop the model, and pICso = 4.52 was set as a threshold between hERG actives and inactives. Receiver operator curve (ROC) accuracy of 0.87 was achieved. The model was validated on an external set of 66 drugs, of which 58 were classified correctly (88% accuracy). 

N = 1979 compounds with measured hERG activity from the Roche corporate collection. Receiver operator curve (ROC) accuracy of 0.87 was achieved for the training set. 

Fig. 22.3. Comparison of imaging data across patients, (a) Pseudo-gel view of selected mass spectra from different images/samples. The mass spectra are representative for tumor or tumor-free mucosa. Spectra in between dashed lines are from the same patient, each of these lanes represents one patient. Characteristic biomarkers can now be found by visual inspection or by statistical tools such as receiver-operating curves or p-values. (b) PCA applied to the data set. Each element represents one patient squares indicate tumor and circle tumor-free mucosa. In this score plot of the first three principal components a separation between tumor and tumor-free mucosa is seen. This indicates that classification based on the MALDI imaging result is possible, (c) Hierarchical clustering can be performed, e.g., on tumor spectra from all patients. This allows correlation of patient clusters with clinical meta-information. The data shown here are described in (7).

Figure 1 Receiver operating curve obtained with quantitative cultures of endotracheal aspirates (EA) for the diagnosis of pneumonia in 57 ventilator-dependent patients in whom pulmonary infection is clinically thought to have developed. (From Ref. 51, with permission.)...

Fig. 2 A receiver operator characteristic curve reproduced from PubMedCentral http //www. pubmedcentral.nih.gov/articlerender.fcgi artid=1065080 and [16]...

The Role of Receiver Operating Characteristic (ROC) Curves in the Evaluation... 

A new tumor marker is evaluated using the same criteria used for many diagnostic tests (i.e., sensitivity, specificity, and accuracy). The diagnostic sensitivity and specificity are best represented by a receiver operating characteristic (ROC) curve. The ROC curve is constructed with the true-positive rate versus false-positive rate at various decision levels. As a test improves in its diagnostic performance, it shifts upward and to the left as the true-positive rate increases and the false-positive rate decreases. 

Fig. 11.8. A binormal receiver operating characteristic (ROC) curve (solid line) plotting the sensitivity versus 1-specificity using the 850 nm OCT attenuation coefficient to distinguish between eariy caries and heaithy enamel. The dashed line represents the ROC curve for a nondiscriminatory test. The markers on the curve represent setting an OCT attenuation coefficient threshold between caries and healthy enamel at 0.9 rnrri 1 (diamond) and at 1.08 rrirri 1 (star)...

Enrichment based methods. These focus on recovering active molecules from a test database in which a small number of known actives have been hidden in a large database of randomly selected compounds. Database mining and the utilization of receiver operating characteristic (ROC) curves [43] can be included in this category. 

This maximizes Se (Se l). However, specificity will be minimized as most of the inactive molecules will be in the selection. The situation is reversed in the case where n is very small (n 0). Consequently, one cannot optimize both Se and Sp at the same time and a trade-off is to be determined. If one can choose to rely on one of the above metrics to find an optimum, we have recently advocated the use of a simpler graphical technique which has been adopted as a gold standard in many other research areas the receiver operating characteristic (ROC) curve method [53]. 

Constructing a receiver operating characteristic (ROC) curve, which is a quantitative analysis, it showed that a rapamycin blood concentration of >8 ng/mL was the proper cutoff to define high blood concentration of the drug, and that it was in agreement with the mean rapamycin blood concentration in patients having no restenosis (7.9 ng/mL). 

Fig. 6 Test set receiver operator characteristic curves for M. tuberculosis Bayesian models, (a) Southern Research Institute data for >100,000 molecules (1,702 actives), (b) Novartis data for 248 molecules (34 actives), (c) FDA-approved drugs, 2,108 molecules (21 actives) (17,29)...

The selectivity of the sensor is determined by the efficiency of the coating material. Developing selective coatings is an ongoing research area. Figure 3 shows a useful metric for sensor performance called the receiver operating characteristic (ROC) curve [16]. 

LLD, lower limit of detection 99th, 99th percentile reference limit ROC, receiver operator characteristic curve optimized cutoff 10% Cy lowest concentration to provide a total imprecision of 10%. 

---