Search

Methotrexate is the most frequently administered first-line treatment for rheumatoid arthritis (RA). The disease-modifying effects of methotrexate are mainly associated with enhanced release of free adenosine. The downstream anti-inflammatory effects of adenosine are mediated via its binding to adenosine receptor 2A (ADORA2A) and 3 (ADORA3). Many clinically important single nucleotide polymorphisms (SNPs) were reported in ADORA2A and ADORA3 genes.To investigate whether tagging ADORA2A and ADORA3 polymorphisms influences methotrexate treatment in RA.In total, 212 RA patients treated with methotrexate were genotyped for tagging ADORA2A (rs2298383, rs8141793, rs2236624, rs5751876, rs35320474, and rs17004921) and ADORA3 SNPs (rs2298191, rs1544223, rs78594984, rs35511654, rs2229155, rs3393, and rs3394).RA patients who carried ADORA3 rs35511654 G allele showed a tendency toward better response to methotrexate treatment (P = 0.054). Carriers of ADORA2A polymorphic allele rs2298383 (P = 0.011), rs2236624 (P = 0.027), rs5751876 (P = 0.018), and rs35320474 (P = 0.026) were less likely to experience methotrexate induced adverse events. All associations remained significant after adjustment for clinical factors. The effects of these polymorphisms were also significant in haplotype analyses.Polymorphisms in the ADORA2A gene may influence methotrexate treatment response and may be considered as a potential biomarker for methotrexate treatment in rheumatoid arthritis.

Objective: Evaluate a method for the estimation of the nocturnal systolic blood pressure dip from 24-hour blood pressure trends using a wrist-worn Photoplethysmography (PPG) sensor and a deep neural network in free-living individuals, comparing the deep neural network to traditional machine learning and non-machine learning baselines. Approach: A wrist-worn PPG sensor was worn by 106 healthy individuals for 226 days during which 5111 reference values for blood pressure were obtained with a 24-hour ambulatory blood pressure monitor as ground truth and matched with the PPG sensor data. Features based on heart rate variability and pulse morphology were extracted from the PPG waveforms. Machine learning models (linear regression, random forests, dense neural networks and long- and short-term memory neural networks) were then trained and evaluated in their capability of tracking trends in systolic and diastolic blood pressure, as well as the estimation of the nocturnal systolic blood pressure dip. Main results Best performance was obtained with a deep long- and shortterm memory neural network with a Root Mean Squared Error (RMSE) of 3.12±2.20 ∆mmHg and a correlation of 0.69 (p = 3 ∗ 10−5) with the ground truth Systolic Blood Pressure (SBP) dip. This dip was derived from trend estimates of blood pressure which had an RMSE of 8.22±1.49 mmHg for systolic and 6.55±1.39 mmHg for diastolic blood pressure. The random forest model showed slightly lower average error magnitude for SBP trends (7.86±1.57 mmHg), however Bland-Altmann analysis revealed systematic problems in its predictions that were less present in the long- and short-term memory model. Significance The work provides first evidence for the unobtrusive estimation of the nocturnal blood pressure dip, a highly prognostic clinical parameter. It is also the first to evaluate unobtrusive blood pressure measurement in a large data set of unconstrained 24-hour measurements in free-living individuals and provides evidence for the utility of long- and short-term models in this domain.