- Browse by Subject
Browsing by Subject "Receiver operating characteristic (ROC) curve"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item AUCTSP: an improved biomarker gene pair class predictor(BMC, 2018-06-26) Kagaris, Dimitri; Khamesipour, Alireza; Yiannoutsos, Constantin T.; Biostatistics, School of Public HealthThe Top Scoring Pair (TSP) classifier, based on the concept of relative ranking reversals in the expressions of pairs of genes, has been proposed as a simple, accurate, and easily interpretable decision rule for classification and class prediction of gene expression profiles. The idea that differences in gene expression ranking are associated with presence or absence of disease is compelling and has strong biological plausibility. Nevertheless, the TSP formulation ignores significant available information which can improve classification accuracy and is vulnerable to selecting genes which do not have differential expression in the two conditions ("pivot" genes). RESULTS: We introduce the AUCTSP classifier as an alternative rank-based estimator of the magnitude of the ranking reversals involved in the original TSP. The proposed estimator is based on the Area Under the Receiver Operating Characteristic (ROC) Curve (AUC) and as such, takes into account the separation of the entire distribution of gene expression levels in gene pairs under the conditions considered, as opposed to comparing gene rankings within individual subjects as in the original TSP formulation. Through extensive simulations and case studies involving classification in ovarian, leukemia, colon, breast and prostate cancers and diffuse large b-cell lymphoma, we show the superiority of the proposed approach in terms of improving classification accuracy, avoiding overfitting and being less prone to selecting non-informative (pivot) genes. CONCLUSIONS: The proposed AUCTSP is a simple yet reliable and robust rank-based classifier for gene expression classification. While the AUCTSP works by the same principle as TSP, its ability to determine the top scoring gene pair based on the relative rankings of two marker genes across all subjects as opposed to each individual subject results in significant performance gains in classification accuracy. In addition, the proposed method tends to avoid selection of non-informative (pivot) genes as members of the top-scoring pair.Item Toward a Better Measure of Midlife Sexual Function: Pooled Analyses in Nearly 1000 Women Participating in MsFLASH Randomized Trials(Wolters Kluwer, 2022-01-31) Reed, Susan D.; Carpenter, Janet S.; Larson, Joseph; Mitchell, Caroline M.; Shifren, Jan; Heiman, Julia; Fugate Woods, Nancy; Tessler Lindau, Stacy; LaCroix, Andrea Z.; Guthrie, Katherine A.; School of NursingObjective: Evaluate appropriateness of the current Female Sexual Function Index (FSFI)-19 value of <26.6 to designate female sexual dysfunction (FSD) in postmenopausal women, using the Female Sexual Distress-Revised (FSDS-R) scale to measure distress. Methods: Participant-level data containing standardized measures from five completed Menopause Strategies: Finding Lasting Answers for Symptoms and Health trials was pooled. Baseline characteristics and FSFI-19 scores were compared across trials (F-test, homogeneity). FSFI-19 score associations with the FSDS-R were described. Receiver operating characteristic (ROC) curves were plotted to illustrate the choice of optimal FSFI-19 value to predict sexual distress. ROC curves were also estimated adjusting for trial number, clinical center, age, education, race, smoking, and BMI. Results: Nine hundred ninety eight women (79.2% postmenopausal), mean age 55.9 (SD 4.8) had complete FSFI-19, FSDS-R, and covariate data. Baseline mean FSFI-19 score among all participants and sexually active participants was 18.7 (SD 9.5) and 22.0 (SD 7.2), respectively. There was a consistent pattern across the trials of inverse association between poorer sexual function (FSFI-19) and greater sexual distress. Based on the ROC curve showing the likelihood of FSDS-R frequent or greater distress according to cut points of FSFI, the optimal cut point for FSD was FSFI-19 <21 for all participants. This cut point corresponded to sensitivity 87.2% (95% CI, 83.4-91.0), specificity 57.9% (95% CI, 54.3-61.6) and adjusted area under the ROC curve 78.8% (95% CI, 75.8-81.8). Conclusions: A new FSFI-19 cut point of ≥21 should be considered to describe normal sexual function in periand postmenopausal women as opposed to the standard cut point of >26.6. Video summary: http://links.lww.com/MENO/A915.