The convergence of artificial intelligence (AI) and precision medicine promises to revolutionize health care. Precision medicine methods identify phenotypes of patients with less‐common responses to ...treatment or unique healthcare needs. AI leverages sophisticated computation and inference to generate insights, enables the system to reason and learn, and empowers clinician decision making through augmented intelligence. Recent literature suggests that translational research exploring this convergence will help solve the most difficult challenges facing precision medicine, especially those in which nongenomic and genomic determinants, combined with information from patient symptoms, clinical history, and lifestyles, will facilitate personalized diagnosis and prognostication.
Current approaches to predicting a cardiovascular disease (CVD) event rely on conventional risk factors and cross-sectional data. In this study, we applied machine learning and deep learning models ...to 10-year CVD event prediction by using longitudinal electronic health record (EHR) and genetic data. Our study cohort included 109, 490 individuals. In the first experiment, we extracted aggregated and longitudinal features from EHR. We applied logistic regression, random forests, gradient boosting trees, convolutional neural networks (CNN) and recurrent neural networks with long short-term memory (LSTM) units. In the second experiment, we applied a late-fusion approach to incorporate genetic features. We compared the performance with approaches currently utilized in routine clinical practice - American College of Cardiology and the American Heart Association (ACC/AHA) Pooled Cohort Risk Equation. Our results indicated that incorporating longitudinal feature lead to better event prediction. Combining genetic features through a late-fusion approach can further improve CVD prediction, underscoring the importance of integrating relevant genetic data whenever available.
To compare three groupings of Electronic Health Record (EHR) billing codes for their ability to represent clinically meaningful phenotypes and to replicate known genetic associations. The three ...tested coding systems were the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes, the Agency for Healthcare Research and Quality Clinical Classification Software for ICD-9-CM (CCS), and manually curated "phecodes" designed to facilitate phenome-wide association studies (PheWAS) in EHRs.
We selected 100 disease phenotypes and compared the ability of each coding system to accurately represent them without performing additional groupings. The 100 phenotypes included 25 randomly-chosen clinical phenotypes pursued in prior genome-wide association studies (GWAS) and another 75 common disease phenotypes mentioned across free-text problem lists from 189,289 individuals. We then evaluated the performance of each coding system to replicate known associations for 440 SNP-phenotype pairs.
Out of the 100 tested clinical phenotypes, phecodes exactly matched 83, compared to 53 for ICD-9-CM and 32 for CCS. ICD-9-CM codes were typically too detailed (requiring custom groupings) while CCS codes were often not granular enough. Among 440 tested known SNP-phenotype associations, use of phecodes replicated 153 SNP-phenotype pairs compared to 143 for ICD-9-CM and 139 for CCS. Phecodes also generally produced stronger odds ratios and lower p-values for known associations than ICD-9-CM and CCS. Finally, evaluation of several SNPs via PheWAS identified novel potential signals, some seen in only using the phecode approach. Among them, rs7318369 in PEPD was associated with gastrointestinal hemorrhage.
Our results suggest that the phecode groupings better align with clinical diseases mentioned in clinical practice or for genomic studies. ICD-9-CM, CCS, and phecode groupings all worked for PheWAS-type studies, though the phecode groupings produced superior results.
The role of urate in cardiovascular diseases (CVDs) has been extensively investigated in observational studies; however, the extent of any causal effect remains unclear, making it difficult to ...evaluate its clinical relevance.
A phenome-wide association study (PheWAS) together with a Bayesian analysis of tree-structured phenotypic model (TreeWAS) was performed to examine disease outcomes related to genetically determined serum urate levels in 339,256 unrelated White British individuals (54% female) in the UK Biobank who were aged 40-69 years (mean age, 56.87; SD, 7.99) when recruited from 2006 to 2010. Mendelian randomization (MR) analyses were performed to replicate significant findings using various genome-wide association study (GWAS) consortia data. Sensitivity analyses were conducted to examine possible pleiotropic effects on metabolic traits of the genetic variants used as instruments for urate. PheWAS analysis, examining the association with 1,431 disease outcomes, identified 13 distinct phecodes representing 4 disease groups (inflammatory polyarthropathies, hypertensive disease, circulatory disease, and metabolic disorders) and 9 disease outcomes (gout, gouty arthropathy, pyogenic arthritis, essential hypertension, coronary atherosclerosis, ischemic heart disease, chronic ischemic heart disease, myocardial infarction, and hypercholesterolemia) that were associated with genetically determined serum urate levels after multiple testing correction (p < 3.35 × 10-4). TreeWAS analysis, examining 10,750 ICD-10 diagnostic terms, identified more sub-phenotypes of cardiovascular and cerebrovascular diseases (e.g., angina pectoris, heart failure, cerebral infarction). MR analysis successfully replicated the association with gout, hypertension, heart diseases, and blood lipid levels but indicated the existence of genetic pleiotropy. Sensitivity analyses support an inference that pleiotropic effects of genetic variants on urate and metabolic traits contribute to the observational associations with CVDs. The main limitations of this study relate to possible bias from pleiotropic effects of the considered genetic variants and possible misclassification of cases for mild disease that did not require hospitalization.
In this study, high serum urate levels were found to be associated with increased risk of different types of cardiac events. The finding of genetic pleiotropy indicates the existence of common upstream pathological elements influencing both urate and metabolic traits, and this may suggest new opportunities and challenges for developing drugs targeting a common mediator that would be beneficial for both the treatment of gout and the prevention of cardiovascular comorbidities.
The South China Craton consists of the Yangtze and Cathaysia blocks that were welded together along the Jiangnan Fold Belt in the Neoproterozoic. The Neoproterozoic magmatism in the western and ...northern margins of the Yangtze Block is characterized by voluminous volcano-sedimentary strata, numerous felsic intrusions and many mafic-ultramafic plutons which provide a good opportunity to examine the geodynamics and tectonic evolution of the South China Craton during the assembly and breakup of Rodinia. Based on the geochronological and geochemical data, our study shows that the Neoproterozoic igneous rocks in the western and northern margins of the Yangtze Block were formed in subduction- and rift-related tectonic settings, respectively.
In the western margin of the Yangtze Block, the Neoproterozoic mafic and ultramafic rocks show arc-affinity trace elemental compositions that are indicative of mantle sources enriched by slab fluids. High-δ18O mafic rocks (850–780 Ma) were derived from mantle wedges that were modified by sediment melts, whereas low-δ18O mafic rocks (750–740 Ma) were formed by partial melting of mantle sources further enriched by altered oceanic crust melts. The widespread calc-alkaline I-type granitoids in this region, generated between 870 and 750 Ma, show negative to positive whole rock εNd (−4.9 to +4.8) and variable zircon εHf values (−1.9 to +10.6), similar to those of the contemporary mafic-ultramafic rocks, suggesting that they were produced by melting of the juvenile crust. The 780–750 Ma adakitic granitoids are characterized by high Sr/Y (19–318) and low Y (1.78–17.9 ppm) and have relatively constant εNd (−2.1 to +2.9) and εHf (+4.3 to +7.1) and mantle-like δ18O values (3.40‰ to 6.86‰), suggesting that they were partial melts of a subducted oceanic slab. These three types of igneous rocks demonstrate that the Neoproterozoic magmatism in the western margin of the Yangtze Block was controlled by a continuous subduction system.
However, Neoproterozoic magmatism in the South Qinling Belt at the northern margin of the Yangtze Block generated both arc- and rift-related igneous rocks. The arc-like mafic-ultramafic rocks are thought to have been derived from a subduction-modified lithospheric mantle source, whereas the MORB-affinity mafic rocks were probably sourced from an asthenosphere mantle. Associated Neoproterozoic granitoids were produced by melting of the juvenile mafic crust, except minor felsic rocks derived from the ancient basement. Widespread 800–700 Ma volcano-sedimentary sequences and 650 Ma mafic dike swarms suggest an extensional environment. Neoproterozoic magmatic zircons from felsic volcanic rocks and HP/UHP metamorphic rocks preserve low-δ18O values that were inherited from their protolith which underwent high temperature hydrothermal interaction in a rift setting. On the basis of these observations, the Neoproterozoic magmatism in the South Qinling Belt is proposed to have been controlled by a subduction-transform edge propagator (STEP) in relation to the continuous subduction system at the western margin of the Yangtze Block.
In genome-wide association studies (GWAS) for thousands of phenotypes in large biobanks, most binary traits have substantially fewer cases than controls. Both of the widely used approaches, the ...linear mixed model and the recently proposed logistic mixed model, perform poorly; they produce large type I error rates when used to analyze unbalanced case-control phenotypes. Here we propose a scalable and accurate generalized mixed model association test that uses the saddlepoint approximation to calibrate the distribution of score test statistics. This method, SAIGE (Scalable and Accurate Implementation of GEneralized mixed model), provides accurate P values even when case-control ratios are extremely unbalanced. SAIGE uses state-of-art optimization strategies to reduce computational costs; hence, it is applicable to GWAS for thousands of phenotypes by large biobanks. Through the analysis of UK Biobank data of 408,961 samples from white British participants with European ancestry for > 1,400 binary phenotypes, we show that SAIGE can efficiently analyze large sample data, controlling for unbalanced case-control ratios and sample relatedness.
Microlenses are desired by a wide range of industrial applications while it is always challenging to make them with diffraction‐limited quality. Here, it is shown that high‐quality microlenses based ...on Pancharatnam–Berry (PB) phases can be made with liquid crystal polymers by using a plasmonic photopatterning technique. Based on the generalized Snell's law for the PB phases, PB microlenses with a range of focal lengths and f‐numbers are designed and fabricated and their point‐spread functions and ability to image micrometer‐sized particles are carefully characterized. The results show that these PB microlenses with f‐number down to 2 are all diffraction‐limited. The capability of arraying these PB microlenses with 100% filling factor with a step‐and‐flash approach is further demonstrated.
Microlenses are indispensable optical components in numerous applications. It is shown that high‐quality microlenses and microlens arrays can be designed based on Pancharatnam–Berry phases and fabricated with liquid crystal polymers by using a plasmonic photopatterning technique. These microlenses are diffraction‐limited and are expected to find various unique applications such as microscopic imaging.
Although flexible and multifunctional textiles are promising for wearable electronics and portable device applications, the main issue is to endow textiles with multifunctionalities while maintaining ...their innate flexible and porous features. Herein, a vacuum‐assisted layer‐by‐layer assembly technique is demonstrated to conformally deposit electrically conductive substances on textiles for developing multifunctional and flexible textiles with superb electromagnetic interference (EMI) shielding performances, superhydrophobicity, and highly sensitive humidity response. The formed leaf‐like nanostructure is composed of silver nanowires (AgNWs) as the highly conductive skeleton (vein) and transition metal carbide/carbonitride (MXene) nanosheets as the lamina. The presence of MXene protects AgNWs from oxidation and enhances the combination of AgNWs with the fabric substrate, and the transformation of its functional groups leads to self‐derived hydrophobicity. The flexible and multifunctional textile exhibits a low sheet resistance of 0.8 Ω sq−1, outstanding EMI shielding efficiency of 54 dB in the X‐band at a small thickness of 120 µm, and highly sensitive humidity responses, while retaining its satisfactory porosity and permeability. The self‐derived hydrophobicity with a large contact angle of >140° is achieved by aging the hydrophilic MXene coated silk. The wearable multifunctional textiles are highly promising for applications in intelligent garments, humidity sensors, actuators, and EMI shielding.
A biomimetic leaf‐like nanostructure composed of a 1D AgNWs skeleton (vein) and 2D MXene as the lamina is fabricated via vacuum‐assisted layer‐by‐layer assembly for electromagnetic interference (EMI) shielding, humidity monitoring, and self‐derived hydrophobicity. The (MA1)10 silk presents an exceptional EMI shielding effectiveness of ≈90 dB at 12.4 GHz at a thickness of 480 µm, and the MXene‐coated textile induces a hydrophilic‐to‐hydrophobic transition, generating a large contact angle of >140°.
The convergence of two rapidly developing technologies - high-throughput genotyping and electronic health records (EHRs) - gives scientists an unprecedented opportunity to utilize routine healthcare ...data to accelerate genomic discovery. Institutions and healthcare systems have been building EHR-linked DNA biobanks to enable such a vision. However, the precise extraction of detailed disease and drug-response phenotype information hidden in EHRs is not an easy task. EHR-based studies have successfully replicated known associations, made new discoveries for diseases and drug response traits, rapidly contributed cases and controls to large meta-analyses, and demonstrated the potential of EHRs for broad-based phenome-wide association studies. In this review, we summarize the advantages and challenges of repurposing EHR data for genetic research. We also highlight recent notable studies and novel approaches to provide an overview of advanced EHR-based phenotyping.
Muscle health is essential for children's physical development and future health. PPARGC1A gene encode the peroxisome proliferator-activated receptor coactivator 1α which coactivates transcription ...factors that control mediating skeletal muscle fiber type conversion and skeletal muscle fiber formation. The PPARGC1A rs8192678 Gly/Ser (Gly482Ser) polymorphism was associated with the regulation of skeletal muscle fibre type. This paper aims to explore the association between the PPARGC1A rs8192678 (Gly482Ser) polymorphism and muscle fitness in Chinese schoolchildren.
We detected the distribution of the PPARGC1A rs8192678 (Gly482Ser) polymorphism by DNA typing of saliva samples from untrained Southern Chinese Han children aged 7-12 years. Considering that muscle studies in children cannot use invasive sampling, we analyzed the association between alleles and genotypes with high validity tests of muscle fitness assesment in children(handgrip strength, standing long jump, sit-ups and push-ups).
The results showed no significant differences in height, weight or body mass index between the sexes. The grip strength indicators were correlated with age in boys and height and weight in girls. Sit-ups were significantly higher in girls with the PPARGC1A Gly/Gly genotype than in boys, and handgrip strength and standing long jump were significantly lower in girls with the PPARGC1A rs8192678 (Gly482Ser) genotype than in boys. Genetic model analysis showed that the Gly482 allele had a dominant genetic effect on the Gly482 allele is hypothesized to influence the expression of type I fibers in skeletal muscle in girls, while the Ser482 allele affects on type II fibers in girls. The two alleles had little genetic effect on boys.
The results suggested the possible association of the PPARGC1A rs8192678 (Gly482Ser) polymorphism on myofibril type-related phenotypes in Han Chinese children in southern China, with a particular impact on girls.