scholarly journals A graph-embedded topic model enables characterization of diverse pain phenotypes among UK Biobank individuals

2022 ◽  
Author(s):  
Yuening Wang ◽  
Rodrigo Benavides ◽  
Luda Diatchenko ◽  
Audrey Grant ◽  
Yue Li
Keyword(s):  
Chronic Pain ◽  
Topic Model ◽  
Systematic Investigation ◽  
Superior Performance ◽  
Uk Biobank ◽  
Biomedical Knowledge ◽  
Learning Techniques ◽  
Phenotype Data ◽  
The Status ◽  
Clinical Conditions

Large biobank repositories of clinical conditions and medications data open opportunities to investigate the phenotypic disease network. To enable systematic investigation of entire structured phenomes, we present graph embedded topic model (GETM). We offer two main methodological contributions in GETM. First, to aid topic inference, we integrate existing biomedical knowledge graph information in the form of pre-trained graph embedding into the embedded topic model. Second, leveraging deep learning techniques, we developed a variational autoencoder framework to infer patient phenotypic mixture. For interpretability, we use a linear decoder to simultaneously infer the bi-modal distributions of the disease conditions and medications. We applied GETM to UK Biobank (UKB) self-reported clinical phenotype data, which contains conditions and medications for 457,461 individuals. Compared to existing methods, GETM demonstrates overall superior performance in imputing missing conditions and medications. Here, we focused on characterizing pain phenotypes recorded in the questionnaire of the UKB individuals. GETM accurately predicts the status of chronic musculoskeletal (CMK) pain, chronic pain by body-site, and non-specific chronic pain using past conditions and medications. Our analyses revealed not only the known pain-related topics but also the surprising predominance of medications and conditions in the cardiovascular category among the most predictive topics across chronic pain phenotypes.

scholarly journals Technology Hotspot Tracking: Topic Discovery and Evolution of China’s Blockchain Patents Based on a Dynamic LDA Model

Symmetry ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 415
Author(s):  
Jinli Wang ◽  
Yong Fan ◽  
Hui Zhang ◽  
Libo Feng
Keyword(s):  
Latent Dirichlet Allocation ◽  
Topic Model ◽  
Graph Model ◽  
Representation Learning ◽  
Research Direction ◽  
Calculation Model ◽  
Topic Evolution ◽  
Blockchain Technology ◽  
The Status ◽  
Research Hotspots

Tracking scientific and technological (S&T) research hotspots can help scholars to grasp the status of current research and develop regular patterns in the field over time. It contributes to the generation of new ideas and plays an important role in promoting the writing of scientific research projects and scientific papers. Patents are important S&T resources, which can reflect the development status of the field. In this paper, we use topic modeling, topic intensity, and evolutionary computing models to discover research hotspots and development trends in the field of blockchain patents. First, we propose a time-based dynamic latent Dirichlet allocation (TDLDA) modeling method based on a probabilistic graph model and knowledge representation learning for patent text mining. Second, we present a computational model, topic intensity (TI), that expresses the topic strength and evolution. Finally, the point-wise mutual information (PMI) value is used to evaluate topic quality. We obtain 20 hot topics through TDLDA experiments and rank them according to the strength calculation model. The topic evolution model is used to analyze the topic evolution trend from the perspectives of rising, falling, and stable. From the experiments we found that 8 topics showed an upward trend, 6 topics showed a downward trend, and 6 topics became stable or fluctuated. Compared with the baseline method, TDLDA can have the best effect when K is 40 or less. TDLDA is an effective topic model that can extract hot topics and evolution trends of blockchain patent texts, which helps researchers to more accurately grasp the research direction and improves the quality of project application and paper writing in the blockchain technology domain.

Brain Structural Differences in the Salience-Sensorimotor Networks of People Reporting Chronic Pain in the UK Biobank

2021 ◽  
Vol 89 (9) ◽  
pp. S86-S87
Author(s):  
Ravi R. Bhatt ◽  
Elizabeth Haddad ◽  
Alyssa Zhu ◽  
Paul M. Thompson ◽  
Neda Jahanshad
Keyword(s):  
Chronic Pain ◽  
Uk Biobank ◽  
Structural Differences ◽  
The Uk

scholarly journals Pills or Sleep Deprivation? Sleep-Deprivation as a Therapeutic Option Intervention in Psychiatry

2020 ◽  
pp. 16-32
Author(s):  
Andrey Viktorovich Antsyborov ◽  
Irina Vladimirovna Dubatova ◽  
Anna Valerievna Kalinchuk
Keyword(s):  
Sleep Deprivation ◽  
Therapeutic Option ◽  
Brain Regions ◽  
Clinical Effects ◽  
Data Set ◽  
Close Supervision ◽  
The Status ◽  
Clinical Conditions ◽  
Traditional Approaches

In recent decades, sleep deprivation has evolved from a single experimental data set to the status of an effective and affordable therapeutic intervention used in daily clinical practice. The mechanism of action of this method is aimed at the same neurotransmitter systems and brain regions as antidepressants. As in the case of pharmacotherapy for sleep deprivation, it should be used under close supervision of a physician. Clinical effects with sleep deprivation are achieved much faster than with psychopharmacotherapy, but they are not long-term in nature. It is possible to improve the results using a combination of pharmacotherapy and sleep deprivation. The use of sleep deprivation in clinical conditions is aimed primarily at preventing depression and its recurrence, as well as in cases resistant to pharmacotherapy. In modern conditions, the method of sleep deprivation is a significant alternative to traditional approaches to therapy of depression.

scholarly journals Sex-stratified genome-wide association study of multisite chronic pain in UK Biobank

PLoS Genetics ◽  
2021 ◽  
Vol 17 (4) ◽  
pp. e1009428
Author(s):  
Keira J. A. Johnston ◽  
Joey Ward ◽  
Pradipta R. Ray ◽  
Mark J. Adams ◽  
Andrew M. McIntosh ◽  
...  
Keyword(s):  
Chronic Pain ◽  
Sex Differences ◽  
Association Study ◽  
Genome Wide Association Study ◽  
Chronic Widespread Pain ◽  
Genome Wide Association ◽  
System Component ◽  
Widespread Pain ◽  
Uk Biobank ◽  
Genome Wide

Chronic pain is highly prevalent worldwide and imparts a significant socioeconomic and public health burden. Factors influencing susceptibility to, and mechanisms of, chronic pain development, are not fully understood, but sex is thought to play a significant role, and chronic pain is more prevalent in women than in men. To investigate sex differences in chronic pain, we carried out a sex-stratified genome-wide association study of Multisite Chronic Pain (MCP), a derived chronic pain phenotype, in UK Biobank on 178,556 men and 209,093 women, as well as investigating sex-specific genetic correlations with a range of psychiatric, autoimmune and anthropometric phenotypes and the relationship between sex-specific polygenic risk scores for MCP and chronic widespread pain. We also assessed whether MCP-associated genes showed expression pattern enrichment across tissues. A total of 123 SNPs at five independent loci were significantly associated with MCP in men. In women, a total of 286 genome-wide significant SNPs at ten independent loci were discovered. Meta-analysis of sex-stratified GWAS outputs revealed a further 87 independent associated SNPs. Gene-level analyses revealed sex-specific MCP associations, with 31 genes significantly associated in females, 37 genes associated in males, and a single gene, DCC, associated in both sexes. We found evidence for sex-specific pleiotropy and risk for MCP was found to be associated with chronic widespread pain in a sex-differential manner. Male and female MCP were highly genetically correlated, but at an rg of significantly less than 1 (0.92). All 37 male MCP-associated genes and all but one of 31 female MCP-associated genes were found to be expressed in the dorsal root ganglion, and there was a degree of enrichment for expression in sex-specific tissues. Overall, the findings indicate that sex differences in chronic pain exist at the SNP, gene and transcript abundance level, and highlight possible sex-specific pleiotropy for MCP. Results support the proposition of a strong central nervous-system component to chronic pain in both sexes, additionally highlighting a potential role for the DRG and nociception.

scholarly journals 0259 Shiftworkers are at Increased Risk of Developing Chronic Pain and Opioid Use Disorders: A Study of 116,000 UK Biobank Participants Over a Decade

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A98-A99
Author(s):  
L Gao ◽  
P Li ◽  
L Cui ◽  
Y Luo ◽  
C Vetter ◽  
...  
Keyword(s):  
Chronic Pain ◽  
Bone Fractures ◽  
Inflammatory Diseases ◽  
Opioid Use Disorder ◽  
Uk Biobank ◽  
Opioid Use ◽  
Logistic Regression Models ◽  
Diagnostic Coding ◽  
Increased Risk ◽  
Opioid Use Disorders

Abstract Introduction In the current epidemic of opioid-related deaths, and widespread use of opioids to treat chronic pain, there is a pressing need to understand the underlying risk factors that contribute to such devastating conditions. Shiftwork has been associated with adverse health outcomes. We tested whether shiftwork during middle age is linked to the development of chronic pain and opioid misuse. Methods We studied 116,474 participants in active employment between 2006–2010 (mean age 57±8; range 37–71) from the UK Biobank, who have been followed for up to 10 years until 2017. We included participants who were free from all forms of self-reported pain, and were not taking opioid medications at baseline. Chronic pain and opioid use disorder diagnoses were determined using hospitalization records and diagnostic coding from ICD-10. Multivariate logistic regression models were performed to examine the associations of shiftwork status (yes/no) and nightshift frequency (none/occasional/permanent) and with incident chronic pain and/or opioid use disorder during follow-up. Models were adjusted for demographics, education, Townsend deprivation index, major confounders (BMI, diabetes, bone fractures/injuries, operations, peripheral vascular disease, joint/inflammatory diseases, cancer, standing/manual labor at work) and covariates (smoking, alcohol, high cholesterol, depression/anxiety, and cardiovascular diseases). Results In total, 190 (1.6/1,000) developed chronic pain or opioid use disorders. Shiftworkers (n=17,673) saw a 1.5-fold increased risk (OR 1.56, 95% CI: 1.08–2.24, p=0.01) relative to day workers. Within shiftworkers, those who reported occasional nightshift work (n=3,966) were most vulnerable (OR 1.57, 95% CI: 1.06–2.34, p=0.02). Results remained similar after adjusting for baseline sleep duration, chronotype and insomnia. Conclusion Shiftwork, and in particular rotating nightshift work is associated with increased risk for developing chronic pain and opioid use disorders. Replication is required to confirm the findings and to examine underlying mechanisms. Support This work was supported by NIH grants T32GM007592, RF1AG064312, and RF1AG059867.

scholarly journals Towards Better Interpretability in Deep Q-Networks

2019 ◽  
Vol 33 ◽  
pp. 4561-4569 ◽  
Author(s):  
Raghuram Mandyam Annasamy ◽  
Katia Sycara
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Empirical Studies ◽  
Superior Performance ◽  
Training Algorithms ◽  
Neural Network Architecture ◽  
Q Learning ◽  
The Neural Network ◽  
Learning Techniques ◽  
Out Of Sample

Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these networks seem to learn, are far behind. In this paper we propose an interpretable neural network architecture for Q-learning which provides a global explanation of the model’s behavior using key-value memories, attention and reconstructible embeddings. With a directed exploration strategy, our model can reach training rewards comparable to the state-of-the-art deep Q-learning models. However, results suggest that the features extracted by the neural network are extremely shallow and subsequent testing using out-of-sample examples shows that the agent can easily overfit to trajectories seen during training.

scholarly journals Automatic and Reliable Leaf Disease Detection Using Deep Learning Techniques

2021 ◽  
Vol 3 (2) ◽  
pp. 294-312
Author(s):  
Muhammad E. H. Chowdhury ◽  
Tawsifur Rahman ◽  
Amith Khandakar ◽  
Mohamed Arselene Ayari ◽  
Aftab Ullah Khan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Binary Classification ◽  
Experimental Studies ◽  
Plant Diseases ◽  
Superior Performance ◽  
World Population ◽  
Comparative Performance ◽  
Learning Techniques ◽  
Segmented Images ◽  
Segmentation Models

Plants are a major source of food for the world population. Plant diseases contribute to production loss, which can be tackled with continuous monitoring. Manual plant disease monitoring is both laborious and error-prone. Early detection of plant diseases using computer vision and artificial intelligence (AI) can help to reduce the adverse effects of diseases and also overcome the shortcomings of continuous human monitoring. In this work, we propose the use of a deep learning architecture based on a recent convolutional neural network called EfficientNet on 18,161 plain and segmented tomato leaf images to classify tomato diseases. The performance of two segmentation models i.e., U-net and Modified U-net, for the segmentation of leaves is reported. The comparative performance of the models for binary classification (healthy and unhealthy leaves), six-class classification (healthy and various groups of diseased leaves), and ten-class classification (healthy and various types of unhealthy leaves) are also reported. The modified U-net segmentation model showed accuracy, IoU, and Dice score of 98.66%, 98.5%, and 98.73%, respectively, for the segmentation of leaf images. EfficientNet-B7 showed superior performance for the binary classification and six-class classification using segmented images with an accuracy of 99.95% and 99.12%, respectively. Finally, EfficientNet-B4 achieved an accuracy of 99.89% for ten-class classification using segmented images. It can be concluded that all the architectures performed better in classifying the diseases when trained with deeper networks on segmented images. The performance of each of the experimental studies reported in this work outperforms the existing literature.

Sero-prevalence and Risk Factor Analysis of BoHV-1 in Bovines in Haryana State of India

2020 ◽  
Author(s):  
Aman Kumar ◽  
Suman Chaudhary ◽  
C. S. Patil ◽  
Yogesh Banger ◽  
Vipin Khasa ◽  
...  
Keyword(s):  
Risk Factor ◽  
The State ◽  
Serum Samples ◽  
Cross Sectional ◽  
Bovine Herpesvirus 1 ◽  
Apparent Prevalence ◽  
Eastern Zone ◽  
The Status ◽  
Herpesvirus 1 ◽  
Clinical Conditions

Background: Bovine herpesvirus-1 (BoHV-1) is an important pathogen of cattle and buffaloes associated with various clinical conditions including infectious bovine rhinotracheitis (IBR) and abortion. To know the status of BoHV-1, a cross-sectional serological study was conducted with the objectives of estimating the apparent prevalence of BoHV-1 and potential risk factor among unorganized cattle and buffalo herds. Method: A total of 490 serum samples were collected from cattle and buffaloes from all twenty two (22) districts of Haryana from unorganised herd randomly and tested for antibodies against BoHV-1 using ELISA. Result: The overall percent sero-prevalence of BoHV-1 was observed as 48.78% however the species wise sero-prevalence was 37.77% in cattle and 62.27% in buffaloes. The overall sero-prevalence was significantly (p less than 0.05) associated with species, zone and age of animals. The likelihood of BoHV-1 was significantly higher (2.72 times) in buffaloes (Odds ratio (OR) =2.72, 95% Confidence Interval (CI):1.86; 3.98) than in cattle (OR=1). Eastern zone of the state showed higher (1.52 times, 95% CI: 1.03, 2.26) likelihood of BoHV-1 as compared to western zone (OR=1.00).The aged animals with age³6.5 years (2.96 times), followed by 2.5-4.5 years (2.44 times) and 4.5-6.5 years (1.68 times) showed higher likelihood than younger animals (Age less than 2.5 years). Further, it can be concluded that BoHV1 is circulating among livestock population in the state.

scholarly journals Using Abductive Machine Learning for Online Vibration Monitoring of Turbo Molecular Pumps

1999 ◽  
Vol 6 (5-6) ◽  
pp. 253-265 ◽  
Author(s):  
R.E. Abdel-Aal ◽  
M. Raashid
Keyword(s):  
Machine Learning ◽  
Online Monitoring ◽  
Model Development ◽  
Low Frequency ◽  
Vibration Monitoring ◽  
Machine Learning Techniques ◽  
Vibration Signals ◽  
Output Performance ◽  
Learning Techniques ◽  
The Status

Turbo molecular vacuum pumps constitute a critical component in many accelerator installations, where failures can be costly in terms of both money and lost beam time. Catastrophic failures can be averted if prior warning is given through a continuous online monitoring scheme. This paper describes the use of modern machine learning techniques for online monitoring of the pump condition through the measurement and analysis of pump vibrations. Abductive machine learning is used for modeling the pump status as ‘good’ or ‘bad’ using both radial and axial vibration signals measured close to the pump bearing. Compared to other statistical methods and neural network techniques, this approach offers faster and highly automated model synthesis, requiring little or no user intervention. Normalized 50-channel spectra derived from the low frequency region (0–10 kHz) of the pump vibration spectra provided data inputs for model development. Models derived by training on only 10 observations predict the correct value of the logical pump status output with 100% accuracy for an evaluation population as large as 500 cases. Radial vibration signals lead to simpler models and smaller errors in the computed value of the status output. Performance is comparable with literature data on a similar diagnosis scheme for compressor valves using neural networks.

scholarly journals A machine-learning heuristic to improve gene score prediction of polygenic traits

2017 ◽  
Author(s):  
Guillaume Paré ◽  
Shihong Mao ◽  
Wei Q. Deng
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
Risk Scores ◽  
Uk Biobank ◽  
Polygenic Risk ◽  
Learning Techniques ◽  
Diabetes Status ◽  
Polygenic Traits ◽  
The Uk ◽  
Prediction Problems

AbstractMachine-learning techniques have helped solve a broad range of prediction problems, yet are not widely used to build polygenic risk scores for the prediction of complex traits. We propose a novel heuristic based on machine-learning techniques (GraBLD) to boost the predictive performance of polygenic risk scores. Gradient boosted regression trees were first used to optimize the weights of SNPs included in the score, followed by a novel regional adjustment for linkage disequilibrium. A calibration set with sample size of ~200 individuals was sufficient for optimal performance. GraBLD yielded prediction R2 of 0.239 and 0.082 using GIANT summary association statistics for height and BMI in the UK Biobank study (N=130K; 1.98M SNPs), explaining 46.9% and 32.7% of the overall polygenic variance, respectively. For diabetes status, the area under the receiver operating characteristic curve was 0.602 in the UK Biobank study using summary-level association statistics from the DIAGRAM consortium. GraBLD outperformed other polygenic score heuristics for the prediction of height (p<2.2x10−16) and BMI (p<1.57x10−4), and was equivalent to LDpred for diabetes. Results were independently validated in the Health and Retirement Study (N=8,292; 688,398 SNPs). Our report demonstrates the use of machine-learning techniques, coupled with summary-level data from large genome-wide meta-analyses to improve the prediction of polygenic traits.

Sign in / Sign up

Export Citation Format

Share Document