Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning. Specifically, designing models with tractable learning, sampling, inference and evaluation is crucial in solving this task. We extend the space of such models using real-valued non-volume preserving (real NVP) transformations, a set of powerful, stably invertible, and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact and efficient sampling, exact and efficient inference of latent variables, and an interpretable latent space. We demonstrate its ability to model natural images on four datasets through sampling, log-likelihood evaluation, and latent variable manipulations.

Accurate measurement of GFR is critical for the evaluation of new therapies and the care of renal transplant recipients. Although not accurate in renal transplantation, GFR is often estimated using creatinine-based equations. Cystatin C is a marker of GFR that seems to be more accurate than creatinine. Equations to predict GFR based on the serum cystatin C concentration have been developed, but their accuracy in transplantation is unknown. GFR was estimated using four equations (Filler, Le Bricon, Larsson, and Hoek) that are based on serum cystatin C and seven equations that are based on serum creatinine in 117 adult renal transplant recipients. GFR was measured using radiolabeled diethylenetriaminepentaacetic acid ( 99m Tc-DTPA), and the bias, precision, and accuracy of each equation were determined. The mean 99m Tc-DTPA GFR was 58 ؎ 23 ml/min per 1.73 m 2 . The cystatin C-based equations of Filler and Le Bricon had the lowest bias (؊1.7 and ؊3.8 ml/min per 1.73 m 2 ), greatest precision (11.4 and 11.8 ml/min per 1.73 m 2 ), and highest accuracy (87 and 89% within 30% of measured GFR, respectively). The cystatin C equations remained accurate even when the measured GFR was >60 ml/min per 1.73 m 2 . The creatinine-based equations were not as accurate, with only 53 to 80% of estimates within 30% of measured GFR. Cystatin C-based equations are more accurate at predicting GFR in renal transplant recipients than traditional creatininebased equations. Further prospective studies with repetitive measurement of cystatin C are needed to determine whether cystatin C-based estimates of GFR will be sufficiently accurate to monitor long-term allograft function.

Background: Beta-trace protein (BTP) is a low molecular weight glycoprotein that is a more sensitive marker of glomerular filtration rate (GFR) than serum creatinine. The utility of BTP has been limited by the lack of an equation to translate BTP into an estimate of GFR. The objectives of this study were to develop a BTP-based GFR estimation equation. Methods: We measured BTP and GFR by 99mtechnetium-diethylenetriaminepentaacetic acid in 163 stable adult renal transplant recipients. Stepwise multiple regression models were created to predict GFR corrected for body surface area. The following variables were considered for entry into the model: BTP, urea, sex, albumin, creatinine, age, and race. Results: BTP alone accounted for 75.6% of variability in GFR. The model that included all the predictor variables had the largest coefficient of determination (R2) at 0.821. The model with only BTP, urea, and sex had only a slightly lower R2 of 0.81 and yielded the following equation: GFR mL · min−1 · (1.73 m2)−1 = 112.1 × BTP−0.662 × Urea−0.280 × (0.88 if female). A 2nd equation (R2 = 0.79) using creatinine instead of urea was also developed: GFR mL · min−1 · (1.73 m2)−1 = 1.678 × BTP−0.758 × creatinine−0.204 × (0.871 if female). Conclusions: We have shown that BTP can be used in a simple equation to estimate GFR. Further study is needed in other populations to determine accuracy and clinical utility of this equation.

No abstract

The ability to predict drug deposition of inhaled drugs used in cystic fibrosis (CF) is important if there is a need to target specific doses of drug to the lungs of individual patients. The gold standard of measuring pulmonary deposition is the quantification of an aerosolized radiolabel either mixed with the drug solution or tagged directly to the compound of interest. Accuracy of the quantification could be assured if there is agreement between the amount of radioactivity before and after administration. Before administration, the radiolabel is concentrated in the well of the nebulizer, whereas after administration, it is distributed throughout the nebulizer, the expiratory filter and connectors, and the upper airway, stomach, trachea, and lung. Not only is the geometry of the distribution that is presented to the gamma camera different, but there are different attenuation factors for the various body tissues. The primary aim of this study was to evaluate the accuracy of the quantification of deposition. Secondary goals were to compare in vitro nebulizer performance with that measured in vivo during the deposition study. Eighty milligrams of tobramycin and technetium bound to human serum albumin was administered to 10 normal adults using a Pari LC Jet Plus (Pari Respiratory Equipment, Inc., Richmond, VA) breath-enhanced nebulizer. Techniques were developed that allowed for the accounting of 99 +/- 2% of the initial radioactivity. The fraction of the rate of lung deposition to total body deposition was the in vivo respirable fraction (0.62 +/- 0.07), which closely agreed with in vitro measurements of respirable fraction (0.62 +/- 0.04). Drug output measured from the change in weight and concentration in the nebulizer systematically overestimated drug output measured by the deposition study. The results indicate that 11.8 of the initial 80 mg would be deposited in the lungs. This technique could be adapted to accurately quantify the amount of deposition on any inhaled therapeutic agent, but caution must be used when extrapolating performance of a nebulizer on the bench to expected deposition in patients.