• Asian Pacific Journal of Cancer Prevention
• /
• 제17권11호
• /
• pp.4913-4916
• /
• 2016

Objective: As a source of information, medical data can feature hidden relationships. However, the high volume of datasets and complexity of decision-making in medicine introduce difficulties for analysis and interpretation and processing steps may be needed before the data can be used by clinicians in their work. This study focused on the use of Bayesian models with different numbers of nodes to aid clinicians in breast cancer risk estimation. Methods: Bayesian networks (BNs) with a retrospectively collected dataset including mammographic details, risk factor exposure, and clinical findings was assessed for prediction of the probability of breast cancer in individual patients. Area under the receiver-operating characteristic curve (AUC), accuracy, sensitivity, specificity, and positive and negative predictive values were used to evaluate discriminative performance. Result: A network incorporating selected features performed better (AUC = 0.94) than that incorporating all the features (AUC = 0.93). The results revealed no significant difference among 3 models regarding performance indices at the 5% significance level. Conclusion: BNs could effectively discriminate malignant from benign abnormalities and accurately predict the risk of breast cancer in individuals. Moreover, the overall performance of the 9-node BN was better, and due to the lower number of nodes it might be more readily be applied in clinical settings.

• 대한의용생체공학회:의공학회지
• /
• 제31권3호
• /
• pp.177-186
• /
• 2010

In 3D ultrasound color Doppler imaging (CDI), 8-16 pulse transmissions (ensembles) per each scanline are used for effective clutter rejection and flow estimation, but it yields a low volume acquisition rate. In this paper, we have evaluated three flow estimation methods: autoregression (AR), eigendecomposition (ED), and autocorrelation combined with adaptive clutter rejection (AC-ACR) for a small ensemble size (E=4). The performance of AR, ED and AC-ACR methods was compared using 2D and 3D in vivo data acquired under different clutter conditions (common carotid artery, kidney and liver). To evaluate the effectiveness of three methods, receiver operating characteristic (ROC) curves were generated. For 2D kidney in vivo data, the AC-ACR method outperforms the AR and ED methods in terms of the area under the ROC curve (AUC) (0.852 vs. 0.793 and 0.813, respectively). Similarly, the AC-ACR method shows higher AUC values for 2D liver in vivo data compared to the AR and ED methods (0.855 vs. 0.807 and 0.823, respectively). For the common carotid artery data, the AR provides higher AUC values, but it suffers from biased estimates. For 3D in vivo data acquired from a kidney transplant patient, the AC-ACR with E=4 provides an AUC value of 0.799. These in vivo experiment results indicate that the AC-ACR method can provide more robust flow estimates compared to the AR and ED methods with a small ensemble size.

• 말소리와 음성과학
• /
• 제7권4호
• /
• pp.111-121
• /
• 2015

The present study examines the auditory boundary between Korean /o/ and /u/ on a synthesized vowel continuum by Chinese learners of Korean language. Preceding researches reported that the Chinese learners have difficulty pronouncing Korean monophthongs /o/ and /u/. In this experiment, a nine-step continuum was resynthesized using Praat from a vowel token from a recording of a male announcer who produced it in isolated form. F1 and F2 were synchronously shifted in equal steps in qtone (quarter tone), while F3 and F4 values were held constant for the entire stimuli. A forced choice identification task was performed by the advanced learners who speak Mandarin Chinese as their native language. Their experiment data were compared to a Korean native group. ROC (Receiver Operating Characteristic) analysis and logistic regression were performed to estimate the perceptual boundary. The result indicated the learner group has a different auditory criterion on the continuum from the Korean native group. This suggests that more importance should be placed on hearing and listening training in order to acquire the phoneme categories of the two vowels.

• Genomics & Informatics
• /
• 제11권1호
• /
• pp.46-51
• /
• 2013

Normal-karyotype acute myeloid leukemia (NK-AML) is a highly malignant and cytogenetically heterogeneous hematologic cancer. We searched for somatic mutations from 10 pairs of tumor and normal cells by using a highly efficient and reliable analysis workflow for whole-exome sequencing data and performed association tests between the NK-AML and somatic mutations. We identified 21 nonsynonymous single nucleotide variants (SNVs) located in a coding region of 18 genes. Among them, the SNVs of three leukemia-related genes (MUC4, CNTNAP2, and GNAS) reported in previous studies were replicated in this study. We conducted stepwise genetic risk score (GRS) models composed of the NK-AML susceptible variants and evaluated the prediction accuracy of each GRS model by computing the area under the receiver operating characteristic curve (AUC). The GRS model that was composed of five SNVs (rs75156964, rs56213454, rs6604516, rs10888338, and rs2443878) showed 100% prediction accuracy, and the combined effect of the three reported genes was validated in the current study (AUC, 0.98; 95% confidence interval, 0.92 to 1.00). Further study with large sample sizes is warranted to validate the combined effect of these somatic point mutations, and the discovery of novel markers may provide an opportunity to develop novel diagnostic and therapeutic targets for NK-AML.

• BMB Reports
• /
• 제46권1호
• /
• pp.41-46
• /
• 2013

Identifying genes indispensable for an organism's life and their characteristics is one of the central questions in current biological research, and hence it would be helpful to develop computational approaches towards the prediction of essential genes. The performance of a predictor is usually measured by the area under the receiver operating characteristic curve (AUC). We propose a novel method by implementing genetic algorithms to maximize the partial AUC that is restricted to a specific interval of lower false positive rate (FPR), the region relevant to follow-up experimental validation. Our predictor uses various features based on sequence information, protein-protein interaction network topology, and gene expression profiles. A feature selection wrapper was developed to alleviate the over-fitting problem and to weigh each feature's relevance to prediction. We evaluated our method using the proteome of budding yeast. Our implementation of genetic algorithms maximizing the partial AUC below 0.05 or 0.10 of FPR outperformed other popular classification methods.

• 중환자간호학회지
• /
• 제8권1호
• /
• pp.71-79
• /
• 2015

Purpose: The purpose of this study was to compare the applicability of the Charlson Comorbidity Index (CCI) and Acute Physiology, Age, Chronic Health Evaluation III (APACHE III) to the prediction of the healthcare outcomes of intensive care unit (ICU) patients. Methods: This research was performed with 136 adult patients (age>18 years) who were admitted to the ICU between May and June 2012. Data were measured using the CCI score with a comorbidity index of 19 and the APACHE III score on the standard of the worst result with vital signs and laboratory results. Discrimination was evaluated using receiver operating characteristic (ROC) curves and area under an ROC curve (AUC). Calibration was performed using logistic regression. Results: The overall mortality was 25.7%. The mean CCI and APACHE III scores for survivors were found to be significantly lower than those of non-survivors. The AUC was 0.835 for the APACHE III score and remained high, at 0.688, for the CCI score. The rate of concordance according to the CCI and the APACHE III score was 69.1%. Conclusion: The route of admission, days in ICU, CCI, and APACHE III score are associated with an increased mortality risk in ICU patients.

• Asian Pacific Journal of Cancer Prevention
• /
• 제14권5호
• /
• pp.3219-3221
• /
• 2013

Background: This study used receiver operating characteristic (ROC) curves to screen Surveillance, Epidemiology and End Results (SEER) skin melanoma data to identify and quantify the effects of socioeconomic factors on cause specific survival. Methods: 'SEER cause-specific death classification' used as the outcome variable. The area under the ROC curve was to select best pretreatment predictors for further multivariate analysis with socioeconomic factors. Race and other socioeconomic factors including rural-urban residence, county level % college graduate and county level family income were used as predictors. Univariate and multivariate analyses were performed to identify and quantify the independent socioeconomic predictors. Results: This study included 49,999 parients. The mean follow up time (SD) was 59.4 (17.1) months. SEER staging (ROC area of 0.08) was the most predictive foctor. Race, lower county family income, rural residence, and lower county education attainment were significant univariates, but rural residence was not significant under multivariate analysis. Living in poor neighborhoods was associated with a 2-4% disadvantage in actuarial cause specific survival. Conclusions: Racial and socioeconomic factors have a significant impact on the survival of melanoma patients. This generates the hypothesis that ensuring access to cancer care may eliminate these outcome disparities.

• Asian Pacific Journal of Cancer Prevention
• /
• 제14권9호
• /
• pp.5043-5047
• /
• 2013

Background: This is a part of a larger effort to characterize the effects on socio-economic factors (SEFs) on cancer outcome. Surveillance, Epidemiology and End Result (SEER) bone and joint sarcoma (BJS) data were used to identify potential disparities in cause specific survival (CSS). Materials and Methods: This study analyzed SEFs in conjunction with biologic and treatment factors. Absolute BJS specific risks were calculated and the areas under the receiver operating characteristic (ROC) curve were computed for predictors. Actuarial survival analysis was performed with Kaplan-Meier method. Kolmogorov-Smirnov's 2-sample test was used to for comparing two survival curves. Cox proportional hazard model was used for multivariate analysis. Results: There were 13501 patients diagnosed BJS from 1973 to 2009. The mean follow up time (SD) was 75.6 (90.1) months. Staging was the highest predictive factor of outcome (ROC area of 0.68). SEER stage, histology, primary site and sex were highly significant pre-treatment predictors of CSS. Under multivariate analysis, patients living in low income neighborhoods and rural areas had a 2% and 5% disadvantage in cause specific survival respectively. Conclusions: This study has found 2-5% decrement of CSS of BJS due to SEFs. These data may be used to generate testable hypothesis for future clinical trials to eliminate BJS outcome disparities.

• Bulletin of the Korean Chemical Society
• /
• 제35권4호
• /
• pp.1133-1138
• /
• 2014

Ultrahigh performance liquid chromatography-electrospray ionization-tandem mass spectrometry (UPLC-ESI- MS/MS) provides a high-speed method to screen a large number of samples for small molecules with specific properties. In this study, UPLC-ESI-MS/MS with multiple reaction monitoring (MRM) was employed to screen urinary phospholipid (PL) content for biomarkers of prostate cancer. From lists of urinary PLs structurally identified using nanoflow LC-ESI-MS/MS, 52 PL species were selected for quantitative analysis in urine samples between 22 cancer-free urologic patients as controls and 45 prostate cancer patients. Statistical treatment of data by receiver operating characteristic (ROC) analysis yielded 14 PL species that differed significantly in relative concentrations (area under curve (AUC) > 0.8) between the two groups. Among PLs present at higher levels in prostate cancer urine, phosphatidylcholines (PCs) and phosphatidylinositols (PIs) constituted the major head group PLs (3 PCs and 7 PIs). For technical reasons, PL species of low abundance may be underrepresented in data from UPLC-ESI-MS/MS performed in MRM mode. However, the proposed method enables the rapid screening of large numbers of plasma or urine samples in the search for biomarkers of human disease.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• 제29권4호
• /
• pp.172-177
• /
• 2018

Objectives: We examined the agreement between the Autism Diagnostic Observation Schedule (ADOS) and the Childhood Autism Rating Scale (CARS) in the diagnosis of autism spectrum disorder. Methods: The ADOS and CARS scores of 78 children were retrospectively collected from a chart review. A correlation analysis was performed to examine the concurrent validity between the two measures. Using the receiver operating characteristic (ROC) curve, we determined the optimal cut-off score of the CARS for identifying autism spectrum disorder. Results: The CARS score was significantly correlated with the ADOS score (r=0.808, p<0.001). Taking ADOS as the ideal standard, the optimal cut-off scores of CARS for identifying autism and autism spectrum were 30 and 24.5, respectively. Conclusion: We determined the optimal cut-off scores of CARS for screening and diagnosing autism spectrum disorder.