Application of the skew exponential power distribution to ROC curves.

The bi-Normal ROC model and corresponding metrics are commonly used in medical studies to evaluate the discriminatory ability of a biomarker. However, in practice, many clinical biomarkers tend to have skewed or other non-Normal distributions. And while the bi-Normal ROC model's AUC tends to be unbiased in this setting, providing a reasonable measure of global performance, the corresponding decision thresholds tend to be biased. To correct this bias, we propose using an ROC model based on the skew exponential power (SEP) distribution, whose additional parameters can accommodate skewed, heavy tailed, or other non-Normal distributions. Additionally, the SEP distribution can be used to evaluate whether the bi-Normal model would be appropriate. The performance of these ROC models and the non-parametric approach are evaluated via a simulation study and applied to a real data set involving infections from Klebsiella pneumoniae. The SEP based ROC-model provides some efficiency gains with respect to estimation of the AUC and provides cut-points with improved classification rates. As such, in the presence non-Normal data, we suggest using the proposed SEP ROC model.

Stability of renal parenchymal volume and function during active surveillance of renal oncocytoma patients.

INTRODUCTION AND OBJECTIVE: To evaluate whether significant loss in ipsilateral renal parenchymal volume (IRPV) and renal function occurs during active surveillance (AS) of renal oncocytoma (RO) patients. METHODS: Renal function (estimated glomerular filtration rate, eGFR) dynamics were retrospectively analyzed in 32 consecutive biopsy-diagnosed RO patients managed with AS at a National Comprehensive Cancer Network institute. Three-dimensional kidney and tumor reconstructions were generated and IRPV was calculated using volumetry software (Myrian®) for all patients with manually estimated RO growth >+10 cm3. GFR and IRPV were compared at AS initiation vs. the last follow-up using 2-sided paired t-tests. The correlation between change in IRPV and change in RO size or GFR was tested using a Spearman coefficient. RESULTS: With median follow-up of 37 months, there was no significant change between initial vs. last eGFR (median 71.0 vs. 70.5 ml/min/1.73 m2, P = 0.50; median change -3.0 ml/min/1.73 m2). Among patients (n = 17) with RO growth >+10 cm3 during AS (median growth +28.6 cm3, IQR +16.9- + 46.5 cm3), IRPV generally remained stable (median change +0.5%, IQR -1.2%- + 1.2%), with only 2 cases surpassing 5% loss. No IRPV loss was detected among any patient within the top tertile of RO growth magnitude. RO growth magnitude did not correlate with loss of either IRPV (ρ = -0.30, P = 0.24) or eGFR (ρ = -0.16, P = 0.40), including among patient subsets with lower initial eGFR. Study limitations include a lack of long-term follow-up. CONCLUSIONS: Volumetry is a promising novel tool to measure kidney and tumor tissue changes during AS. Our study using volumetry indicates that clinically significant loss of IRPV or eGFR is uncommon and unrelated to tumor growth among untreated RO patients with intermediate follow-up. These findings support that AS is in general functionally safe for RO patients, however longer study is needed to determine safety durability, particularly among uncommon ≥cT2 RO variants.

Integrative nearest neighbor classifier for block-missing multi-modality data.

In modern biomedical classification applications, data are often collected from multiple modalities, ranging from various omics technologies to brain scans. As different modalities provide complementary information, classifiers using multi-modality data usually have good classification performance. However, in many studies, due to the high cost of measures, in a lot of samples, some modalities are missing and therefore all data from those modalities are missing completely. In this case, the training data set is a block-missing multi-modality data set. In this paper, considering such classification problems, we develop a new weighted nearest neighbors classifier, called the integrative nearest neighbor (INN) classifier. INN harnesses all available information in the training data set and the feature vector of the test data point effectively to predict the class label of the test data point without deleting or imputing any missing data. Given a test data point, INN determines the weights on the training samples adaptively by minimizing the worst-case upper bound on the estimation error of the regression function over a convex class of functions. Our simulation study shows that INN outperforms common weighted nearest neighbors classifiers that only use complete training samples or modalities that are available in each sample. It performs better than methods that impute the missing data as well, even for the case where some modalities are missing not at random. The effectiveness of INN has been also demonstrated by our theoretical studies and a real application from the Alzheimer's disease neuroimaging initiative.

Association of Sleep Apnea with Mortality in Patients with Advanced Kidney Disease.

BACKGROUND AND OBJECTIVES: In the general population, sleep disorders are associated with mortality. However, such evidence in patients with CKD and ESKD is limited and shows conflicting results. Our aim was to examine the association of sleep apnea with mortality among patients with CKD and ESKD. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: In this prospective cohort study, 180 patients (88 with CKD stage 4 or 5, 92 with ESKD) underwent in-home polysomnography, and sleep apnea measures such as apnea hypopnea index (AHI) and nocturnal hypoxemia were obtained. Mortality data were obtained from the National Death Index. Cox proportional hazard models were used for survival analysis. RESULTS: Among the 180 patients (mean age 54 years, 37% women, 39% with diabetes, 49% CKD with mean eGFR 18±7 ml/min per 1.73 m2), 71% had sleep apnea (AHI>5) and 23% had severe sleep apnea (AHI>30). Median AHI was 13 (range, 4-29) and was not significantly different in patients with advanced CKD or ESKD. Over a median follow-up of 9 years, there were 84 (47%) deaths. AHI was not significantly associated with mortality after adjusting for age, sex, race, diabetes, body mass index, CKD/ESKD status, and kidney transplant status (AHI>30: hazard ratio [HR], 1.5; 95% confidence interval [95% CI], 0.6 to 4.0; AHI >15 to 30: HR, 2.3; 95% CI, 0.9 to 5.9; AHI >5 to 15: HR, 2.1; 95% CI, 0.8 to 5.4, compared with AHI≤5). Higher proportion of sleep time with oxygen saturation <90% and lower mean oxygen saturation were significantly associated with higher mortality in adjusted analysis (HR, 1.4; 95% CI, 1.1 to 1.7; P=0.007 for every 15% higher proportion, and HR, 1.6; 95% CI, 1.2 to 2.1; P=0.003 for every 2% lower saturation, respectively). Sleep duration, sleep efficiency, or periodic limb movement index were not associated with mortality. CONCLUSIONS: Hypoxemia-based measures of sleep apnea are significantly associated with increased risk of death among advanced CKD and ESKD.

Does Kidney Transplantation Affect Sleep and Fatigue in Patients With Kidney Disease?

BACKGROUND: Sleep disorders and fatigue are highly prevalent in chronic kidney disease (CKD) and end-stage kidney disease (ESKD) patients but there is limited evidence on the effect of kidney transplant (KTx) on these. METHODS: In a prospective cohort study of patients with advanced CKD (estimated glomerular filtration rate<30 mL/min/1.73 m2) or ESKD, polysomnography and patient-reported symptom assessments were conducted. Pre- and post-KTx changes in sleep apnea (SA) severity (measured by apnea hypopnea index [AHI]) were analyzed and compared with patients who did not receive KTx. Regression models were used to examine predictors of SA severity. RESULTS: Among 77 patients (mean age 51 y, BMI 29 kg/m2, 66% males, 23% ESKD), 61% had SA at baseline. Among 39 KTx recipients, 56% had SA, with 39% having moderate-severe SA after 10 ± 5.6 months post-KTx. There was no difference in AHI in either the KTx (median 6 versus 8; P = 0.37) or no-KTx (median 15 versus 16; P = 0.61) groups after an average of 19.9 ± 8.9 months. KTx led to significant clinically meaningful improvements in fatigue and health-related quality of life (adjusted effect size 0.3-0.6). In multivariable regression, baseline AHI was the only significant predictor of SA severity (adjusted ß = 3.6/5 units, 95% confidence interval 2.1, 5.2) after adjusting for KTx status, age, sex, and body mass index. CONCLUSIONS: More than half of the KTx recipients had SA. There was no significant change in SA severity with KTx. Clinically meaningful moderate size improvements in patient-reported fatigue and health-related quality of life may be seen with KTx.