We use machine learning methods and high‐dimensional detailed financial data to predict the direction of one‐year‐ahead earnings changes. Our models show significant out‐of‐sample predictive power: the area under the receiver operating characteristics curve ranges from 67.52% to 68.66%, significantly higher than the 50% of a random guess. The annual size‐adjusted returns to hedge portfolios formed based on the prediction of our models range from 5.02% to 9.74%. Our models outperform two conventional models that use logistic regressions and small sets of accounting variables, and professional analysts’ forecasts. Analyses suggest that the outperformance relative to the conventional models stems from both nonlinear predictor interactions missed by regressions and the use of more detailed financial data by machine learning.

Abstract. The expression of polycystin-1 in the vascular smooth muscle cells (VSMC) of elastic and large distributive arteries suggests that some vascular manifestations of autosomal-dominant polycystic kidney disease (ADPKD) result directly from the genetic defect. Intracranial aneurysms have been reported in PKD2, as well as in PKD1 families. To determine whether the vascular expression of polycystin-2 is similar to that of polycystin-1, the expression of PKD2 mRNA and protein in cultured pig aortic VSMC was studied and immunofluorescence and immunohistochemistry were used to study the localization of polycystin-2 in cultured pig aortic VSMC, pig ascending thoracic aorta, and normal elastic and intracranial arteries and intracranial aneurysms obtained at autopsy from patients without or with ADPKD. Tissues derived from Pkd2 wild-type and Pkd2 null mice were used to confirm the specificity of the immunostaining for polycystin-2. Northern blots of VSMC revealed the expected 5.3-kb band. Western blotting detected a 110-kb band in a 100,000 × g fraction of VSMC homogenates. Cultured VSMC as well as VSMC between the elastic lamellae of pig thoracic aorta were positive for polycystin-2 by immunofluorescence. The staining pattern was cytoplasmic. Treatment of the cells before fixation with Taxol, colchicine, or cytochalasin-D altered the pattern of staining in a way suggesting alignment with the cytoskeleton. The immunohistochemical staining for polycystin-2 was abolished by extraction with 0.5% Triton X-100, indicating that polycystin-2 is not associated with the cytoskeleton. Weak immunoreactivity for polycystin-2, which was markedly enhanced by protease digestion, was detected in formaldehydefixed normal human elastic and intracranial arteries. Immunostaining of variable intensity for polycystin-2, which was not consistently enhanced by protease digestion, was seen in the spindle-shaped cells of the wall of the intracranial aneurysms. The similar expression of polycystin-1 and polycystin-2 in the vascular smooth muscle is consistent with the proposed interaction of these proteins in a single pathway. These observations suggest a direct pathogenic role for PKD1 and PKD2 mutations in the vascular complications of ADPKD.

No abstract

We previously have shown that both acute and chronic SGLT-2 inhibition increases endogenous glucose production (EGP) . However, the organ - liver versus kidney - responsible for the increase in EGP has not been identified. We assessed the effect of a single dose of Dapagliflozin or Placebo on renal glucose production in 13 T2DM (age=57.5±1.8 yrs, BMI = 30±1.4 kg/m2) and 9 NGT (age 42±2 3 yrs, BMI = 30±1.1 kg/m2) subjects. Renal glucose production was measured using arteriovenous balance technique across the kidney combined with [3-3H] glucose infusion and PAH infusion (for determination of renal blood flow) before and 4 hours after administration of Dapagliflozin (10 mg) and Placebo; thus, each subject served as their own control. EGP increased following DAPA in both T2DM (2.00±0.11 to 2.43±0.15, P<0.05) and NGT (1.72±0.11 to 2.1±0.16, p<0.05) , while it decreased after placebo in T2DM (2.02±0.12 vs. 1.15±0.06) and NGT (2.10±0.2 vs. 2.05±0.1) (both p<0.01, DAPA vs. placebo) . The fractional renal extraction of glucose (0.02± 0.004 vs. 2.99 ± 1.0, p=0.001 in T2DM, and 0.02± 0.004 vs. 1.62± 1.4 in NGT, p=NS) and renal glucose uptake (0.067 ± 0.02 vs. 0.347 ± 0.06 in T2DM and 0.08 ± 0.02 vs. 0.27 ± 0.08 mg/kg.min in NGT) were higher following DAPA vs. placebo (p<0.05) and were entirely explained by the increase in glucosuria. There was a small, non-significant increase (0.065 & 0.032 mg/kg.min, respectively) in renal glucose production (RGP) following dapagliflozin in T2DM and NGT compared to the 0.45 mg/kg.min increase in total body EGP. Conclusion: A single dose of Dapagliflozin significantly increases EGP which primarily is explained by an increase in hepatic glucose production. Disclosure X. Chen: None. C. Solis-herrera: Speaker’s Bureau; Novo Nordisk. D. Tripathy: None. A. A. Hansis-diarte: None. R. Chilton: Advisory Panel; AstraZeneca, Boehringer Ingelheim International GmbH, Nova Biomedical. E. Cersosimo: Research Support; AstraZeneca. R. A. Defronzo: Advisory Panel; AstraZeneca, Boehringer Ingelheim International GmbH, Intarcia Therapeutics, Inc., Novo Nordisk, Research Support; AstraZeneca, Boehringer Ingelheim International GmbH, Merck & Co., Inc., Speaker’s Bureau; AstraZeneca. Funding Astra Zeneca

Lipoprotein lipase (LPL) is a key enzyme that hydrolyzes circulating triglycerides to release fatty acid (FA). In adipose tissue, LPL is required for lipid storage. However, it is currently unknown whether alteration of LPL in white adipose tissue (WAT) contributes to the development of hypertriglyceridemia. Our present study indicated that WAT isolated from human obese patients have increased expression of PAR2 which is negatively associated with LPL gene. The reduced LPL expression is also negatively correlated with increased plasma TG levels, suggesting that adipose PAR2 may modulate hyperlipidemia through downregulating LPL. In mice, aging and high palmitic oil diet significantly increased PAR2 expression in adipose tissue which was associated with high plasma MIF levels. PAR2 deficiency attenuates the rise of MIF, suggesting a key role of PAR2 in regulating adipose MIF release. MIF reduced LPL expression and activity in adipocytes. In a MIF overexpressed animal model (Mif lung Tg), high circulating MIF levels inhibited adipose LPL which was associated with increased plasma triglyceride but not fatty acid. Following high palmitic oil diet feeding, adipose LPL expression and activity were also reduced, and this reduction was reversed in PAR2 knockout mice. Interestingly, PAR2 mediated LPL in adipose tissue regulates hypertriglyceridemia through controlling adipocyte lipid storage. In Par2-/- mice, recombinant MIF perfusion recovered high plasma MIF levels, which decreased LPL and attenuated adipocyte lipid storage leading to hypertriglyceridemia. These data together suggest that the downregulation of adipose LPL by PAR2/MIF is an important mechanism for the development of hypertriglyceridemia. Disclosure Y.Huang: None. L.Li: None. L.Chen: None. X.Chen: None. P.Gao: None. Y.Qi: None. D.Qi: None. Funding Canadian Institutes of Health Research (PJT156116)