Attention-Based Models for Multivariate Time Series Forecasting: Multi-step Solar Irradiation Prediction.

Bangladesh's subtropical climate with an abundance of sunlight throughout the greater portion of the year results in increased effectiveness of solar panels. Solar irradiance forecasting is an essential aspect of grid-connected photovoltaic systems to efficiently manage solar power's variation and uncertainty and to assist in balancing power supply and demand. This is why it is essential to forecast solar irradiation accurately. Many meteorological factors influence solar irradiation, which has a high degree of fluctuation and uncertainty. Predicting solar irradiance multiple steps ahead makes it difficult for forecasting models to capture long-term sequential relationships. Attention-based models are widely used in the field of Natural Language Processing for their ability to learn long-term dependencies within sequential data. In this paper, our aim is to present an attention-based model framework for multivariate time series forecasting. Using data from two different locations in Bangladesh with a resolution of 30 min, the Attention-based encoder-decoder, Transformer, and Temporal Fusion Transformer (TFT) models are trained and tested to predict over 24 steps ahead and compared with other forecasting models. According to our findings, adding the attention mechanism significantly increased prediction accuracy and TFT has shown to be more precise than the rest of the algorithms in terms of accuracy and robustness. The obtained mean square error (MSE), the mean absolute error (MAE), and the coefficient of determination (R2) values for TFT are 0.151, 0.212, and 0.815, respectively. In comparison to the benchmark and sequential models (including the Naive, MLP, and Encoder-Decoder models), TFT has a reduction in the MSE and MAE of 8.4-47.9% and 6.1-22.3%, respectively, while R2 is raised by 2.13-26.16%. The ability to incorporate long-distance dependency increases the predictive power of attention models.

Efficacy and safety of memantine in children with autism spectrum disorder: Results from three phase 2 multicenter studies.

Three phase 2 trials were conducted to assess the efficacy and long-term safety of weight-based memantine extended release (ER) treatment in children with autism spectrum disorder. MEM-MD-91, a 50-week open-label trial, identified memantine extended-release treatment responders for enrollment into MEM-MD-68, a 12-week randomized, double-blind, placebo-controlled withdrawal trial. MEM-MD-69 was an open-label extension trial in which participants from MEM-MD-68, MEM-MD-91, and open-label trial MEM-MD-67 were treated ⩽48 weeks with memantine extended release. In MEM-MD-91, 517 (59.6%) participants were confirmed Social Responsiveness Scale responders at week 12; mean Social Responsiveness Scale total raw scores improved two to three times a minimal clinically important difference of 10 points. In MEM-MD-68, there was no difference between memantine and placebo on the primary efficacy parameter, the proportion of patients with a loss of therapeutic response (defined as ⩾10-point increase from baseline in Social Responsiveness Scale total raw score). MEM-MD-69 exploratory analyses revealed mean standard deviation improvement in Social Responsiveness Scale total raw score of 32.4 (26.4) from baseline of the first lead-in study. No new safety concerns were evident. While the a priori-defined efficacy results of the double-blind trial were not achieved, the considerable improvements in mean Social Responsiveness Scale scores from baseline in the open-label trials were presumed to be clinically important.

Prevalence, treatment patterns, and stay characteristics associated with hospitalizations for major depressive disorder.

BACKGROUND: Hospitalizations for major depressive disorder (MDD) are a significant burden on patients, their families, and to healthcare systems. This study characterized the prevalence of MDD hospitalizations in the US and described clinical characteristics, treatment patterns, length of stay, costs, and MDD-related hospitalization readmissions. METHODS: A retrospective analysis of the Premier Perspective® Hospital Database was conducted using records of hospital admissions for MDD from January 1, 2014 to December 31, 2015. To supplement this analysis, healthcare claims data from Truven MarketScan® Research Database were also evaluated between January 1, 2013 and December 31, 2014. RESULTS: Among adult hospital stays in the Premier network, 1.3% included a primary diagnosis of MDD. The mean length of MDD-related stays was 6 days, with a mean total hospital charge per stay of $6713. Of those with hospital stays, 5.2% of patients had at least 1 readmission for MDD within 30 days of discharge. In the MarketScan database, 4% of adults with MDD had a MDD-related hospital stay, with a mean length of stay of 6 days and total reimbursed amount per stay of $8441. Of those with hospital stays, 5.4% had at least 1 readmission for MDD within 30 days. LIMITATIONS: Results may not be generalizable to hospitals outside of those represented by these databases. CONCLUSIONS: Adult MDD hospitalizations are costly and associated with high rates of readmission. There is a need for new treatments that may help reduce hospitalizations and costs related to hospitalizations in patients with MDD.

Risk of Hospitalization for Cardiovascular Events with ß-Blockers in Hypertensive Patients: A Retrospective Cohort Study.

INTRODUCTION: ß-Blockers are a heterogenous class of drugs that are no longer recommended for initial antihypertension monotherapy due to unfavorable long-term cardiovascular events observed with non-vasodilatory ß-blockers. However, the comparative cardiovascular event risk between the vasodilatory ß1-selective antagonist/ß3 agonist nebivolol and non-vasodilatory ß1-blockers, atenolol and metoprolol, is unknown. METHODS: Incident nebivolol, atenolol, or metoprolol monotherapy users with hypertension were identified using US claims data (2007-2014). The first ß-blocker claim on/after 1/1/2008 defined the index drug/date. Hypertensive patients without pre-index cardiovascular history were followed until index drug discontinuation (> 90 day supply gap), use of other ß-blockers, or end of continuous plan enrollment. Patients were pair-wise propensity score-matched using logistic regression, adjusted for baseline demographics, Charlson Comorbidity Index score, comorbid chronic pulmonary disease, rheumatic disease, renal disease, and diabetes, and use of other antihypertensive drugs during baseline. Time to first hospital claim for a cardiovascular event was assessed via Cox proportional hazards regression, adjusted for the variables above. RESULTS: Inclusion criteria were met by 81,402 patients (n = 27,134 in each matched treatment cohort), with no between-cohort differences in baseline characteristics, comorbid conditions, or average follow-up duration. Atenolol and metoprolol cohorts had greater risk of hospitalization for a composite event (myocardial infarction, angina, congestive heart failure, stroke) than nebivolol users (adjusted hazard ratios [95% confidence interval] atenolol: 1.68 [1.29, 2.17]; metoprolol: 2.05 [1.59, 2.63]; P < 0.001, both). Risks of most individual cardiovascular events were also lower with nebivolol, including myocardial infarction and angina versus atenolol, and myocardial infarction, congestive heart failure, and angina versus metoprolol (P < 0.05, all). CONCLUSIONS: Nebivolol was associated with significantly lower risk of hospitalization due to composite cardiovascular events than atenolol or metoprolol in this large retrospective cohort study of monotherapy with three different ß1-selective blockers in hypertensive patients. FUNDING: Allergan plc, Madison, NJ, USA.

Additivity of nebivolol/valsartan single-pill combinations versus other single-pill combinations for hypertension.

The single-pill combination (SPC) comprising nebivolol (5 mg), a vasodilatory ß1 -selective antagonist/ß3 -agonist, and valsartan (80 mg), a renin-angiotensin-aldosterone system inhibitor, is the only Food and Drug Administration-approved ß-blocker/renin-angiotensin-aldosterone system inhibitor SPC for hypertension. Additive effects of four nebivolol/valsartan SPC doses (5 mg/80 mg, 5/160 mg, 10/160 mg, 10/320 mg nebivolol/valsartan) were compared with five Food and Drug Administration-approved non-ß-blocker/renin-angiotensin-aldosterone system inhibitor SPCs (aliskiren/hydrochlorothiazide, aliskiren/amlodipine, valsartan/amlodipine, aliskiren/valsartan, and telmisartan/amlodipine). Additivity is the ratio of placebo-adjusted SPC blood pressure (BP) reduction to the placebo-adjusted monotherapy component BP reduction sums. A weighted average of comparator scores was calculated and compared vs nebivolol/valsartan. Additivity ratio scores for nebivolol/valsartan SPCs (diastolic BP range: 0.735-0.866; systolic BP range: 0.717-0.822) were similar to the comparator weighted average (diastolic BP: 0.837; systolic BP: 0.825). Among the nebivolol/valsartan SPCs, 5/80 mg had the greatest additivity (diastolic BP: 0.866; systolic BP: 0.822). BP reduction contributions with monotherapy were similar for nebivolol/valsartan 5/80 mg SPC. Additivity scores for nebivolol/valsartan and select non-ß-blocker/renin-angiotensin-aldosterone system inhibitor SPCs were comparable.

Mature myelin basic protein-expressing oligodendrocytes are insensitive to kainate toxicity.

We examined the vulnerability to excitotoxicity of rat oligodendrocytes in dissociated cell culture at different developmental stages. Mature oligodendrocytes that express myelin basic protein were resistant to excitotoxic injury produced by kainate, whereas earlier stages in the oligodendrocyte lineage were vulnerable to this insult. To test the hypothesis that the sensitivity of immature oligodendrocytes and the resistance of mature oligodendrocytes to kainate toxicity were due to differences in membrane responsiveness to kainate, we used whole-cell patch-clamp recording. Oligodendrocyte precursors in cultures vulnerable to kainate toxicity responded to 500 microM kainate with large inward currents, whereas mature myelin basic protein-expressing oligodendrocytes in cultures resistant to kainate toxicity showed no clear response to application of this agonist. We assayed expression of glutamate receptor subunits (GluR) -2, -4, -6, -7, and KA2 using immunoblot analysis and found that expression of all of these glutamate receptors was significantly down-regulated in mature oligodendrocytes. These results suggest a striking developmental regulation of glutamate receptors in oligodendrocytes and suggest that the vulnerability of oligodendrocytes to non- N-methyl-D-aspartate receptor-mediated excitotoxicity might be much greater in developing oligodendrocytes than after the completion of myelination.