ABSTRACT
Existing imaging genetics studies have been mostly limited in scope by using imaging-derived phenotypes defined by human experts. Here, leveraging new breakthroughs in self-supervised deep representation learning, we propose a new approach, image-based genome-wide association study (iGWAS), for identifying genetic factors associated with phenotypes discovered from medical images using contrastive learning. Using retinal fundus photos, our model extracts a 128-dimensional vector representing features of the retina as phenotypes. After training the model on 40,000 images from the EyePACS dataset, we generated phenotypes from 130,329 images of 65,629 British White participants in the UK Biobank. We conducted GWAS on these phenotypes and identified 14 loci with genome-wide significance (p<5×10-8 and intersection of hits from left and right eyes). We also did GWAS on the retina color, the average color of the center region of the retinal fundus photos. The GWAS of retina colors identified 34 loci, 7 are overlapping with GWAS of raw image phenotype. Our results establish the feasibility of this new framework of genomic study based on self-supervised phenotyping of medical images.
Subject(s)
Fundus Oculi , Genome-Wide Association Study , Phenotype , Retina , Humans , Genome-Wide Association Study/methods , Retina/diagnostic imaging , Male , Polymorphism, Single Nucleotide , Female , Image Processing, Computer-Assisted/methodsABSTRACT
Vancomycin is a commonly used antimicrobial in hospitals, and therapeutic drug monitoring (TDM) is required to optimize its efficacy and avoid toxicities. Bayesian models are currently recommended to predict the antibiotic levels. These models, however, although using carefully designed lab observations, were often developed in limited patient populations. The increasing availability of electronic health record (EHR) data offers an opportunity to develop TDM models for real-world patient populations. Here, we present a deep learning-based pharmacokinetic prediction model for vancomycin (PK-RNN-V E) using a large EHR dataset of 5,483 patients with 55,336 vancomycin administrations. PK-RNN-V E takes the patient's real-time sparse and irregular observations and offers dynamic predictions. Our results show that RNN-PK-V E offers a root mean squared error (RMSE) of 5.39 and outperforms the traditional Bayesian model (VTDM model) with an RMSE of 6.29. We believe that PK-RNN-V E can provide a pharmacokinetic model for vancomycin and other antimicrobials that require TDM.
Subject(s)
Deep Learning , Vancomycin , Bayes Theorem , Drug Monitoring/methods , Electronic Health Records , Humans , Vancomycin/therapeutic useABSTRACT
Synthesizing graphdiyne with a well-defined structure is a great challenge. We reported herein a rational approach to synthesize graphdiyne nanowalls using a modified Glaser-Hay coupling reaction. Hexaethynylbenzene and copper plate were selected as monomer and substrate, respectively. By adjusting the ratio of added organic alkali along with the amount of monomer, the proper amount of copper ions was dissolved into the solution, thus forming catalytic reaction sites. With a rapid reaction rate of Glaser-Hay coupling, graphdiyne grew vertically at these sites first, and then with more copper ions dissolved, uniform graphdiyne nanowalls formed on the surface of copper substrate. Raman spectra, UV-vis spectra, and HRTEM results confirmed the features of graphdiyne. These graphdiyne nanowalls also exhibited excellent and stable field-emission properties.
ABSTRACT
Methicillin-resistant Staphylococcus aureus (MRSA) poses significant morbidity and mortality in hospitals. Rapid, accurate risk stratification of MRSA is crucial for optimizing antibiotic therapy. Our study introduced a deep learning model, PyTorch_EHR, which leverages electronic health record (EHR) time-series data, including wide-variety patient specific data, to predict MRSA culture positivity within two weeks. 8,164 MRSA and 22,393 non-MRSA patient events from Memorial Hermann Hospital System, Houston, Texas are used for model development. PyTorch_EHR outperforms logistic regression (LR) and light gradient boost machine (LGBM) models in accuracy (AUROCPyTorch_EHR = 0.911, AUROCLR = 0.857, AUROCLGBM = 0.892). External validation with 393,713 patient events from the Medical Information Mart for Intensive Care (MIMIC)-IV dataset in Boston confirms its superior accuracy (AUROCPyTorch_EHR = 0.859, AUROCLR = 0.816, AUROCLGBM = 0.838). Our model effectively stratifies patients into high-, medium-, and low-risk categories, potentially optimizing antimicrobial therapy and reducing unnecessary MRSA-specific antimicrobials. This highlights the advantage of deep learning models in predicting MRSA positive cultures, surpassing traditional machine learning models and supporting clinicians' judgments.
Subject(s)
Deep Learning , Methicillin-Resistant Staphylococcus aureus , Humans , Electronic Health Records , Methicillin-Resistant Staphylococcus aureus/genetics , Critical Care , HospitalsABSTRACT
Understanding the genetic architecture of brain structure is challenging, partly due to difficulties in designing robust, non-biased descriptors of brain morphology. Until recently, brain measures for genome-wide association studies (GWAS) consisted of traditionally expert-defined or software-derived image-derived phenotypes (IDPs) that are often based on theoretical preconceptions or computed from limited amounts of data. Here, we present an approach to derive brain imaging phenotypes using unsupervised deep representation learning. We train a 3-D convolutional autoencoder model with reconstruction loss on 6130 UK Biobank (UKBB) participants' T1 or T2-FLAIR (T2) brain MRIs to create a 128-dimensional representation known as Unsupervised Deep learning derived Imaging Phenotypes (UDIPs). GWAS of these UDIPs in held-out UKBB subjects (n = 22,880 discovery and n = 12,359/11,265 replication cohorts for T1/T2) identified 9457 significant SNPs organized into 97 independent genetic loci of which 60 loci were replicated. Twenty-six loci were not reported in earlier T1 and T2 IDP-based UK Biobank GWAS. We developed a perturbation-based decoder interpretation approach to show that these loci are associated with UDIPs mapped to multiple relevant brain regions. Our results established unsupervised deep learning can derive robust, unbiased, heritable, and interpretable brain imaging phenotypes.
Subject(s)
Genetic Loci , Genome-Wide Association Study , Humans , Genome-Wide Association Study/methods , Phenotype , Brain/diagnostic imaging , NeuroimagingABSTRACT
BACKGROUND: The rapid evolution of artificial intelligence (AI) in conjunction with recent updates in dual antiplatelet therapy (DAPT) management guidelines emphasizes the necessity for innovative models to predict ischemic or bleeding events after drug-eluting stent implantation. Leveraging AI for dynamic prediction has the potential to revolutionize risk stratification and provide personalized decision support for DAPT management. METHODS AND RESULTS: We developed and validated a new AI-based pipeline using retrospective data of drug-eluting stent-treated patients, sourced from the Cerner Health Facts data set (n=98 236) and Optum's de-identified Clinformatics Data Mart Database (n=9978). The 36 months following drug-eluting stent implantation were designated as our primary forecasting interval, further segmented into 6 sequential prediction windows. We evaluated 5 distinct AI algorithms for their precision in predicting ischemic and bleeding risks. Model discriminative accuracy was assessed using the area under the receiver operating characteristic curve, among other metrics. The weighted light gradient boosting machine stood out as the preeminent model, thus earning its place as our AI-DAPT model. The AI-DAPT demonstrated peak accuracy in the 30 to 36 months window, charting an area under the receiver operating characteristic curve of 90% [95% CI, 88%-92%] for ischemia and 84% [95% CI, 82%-87%] for bleeding predictions. CONCLUSIONS: Our AI-DAPT excels in formulating iterative, refined dynamic predictions by assimilating ongoing updates from patients' clinical profiles, holding value as a novel smart clinical tool to facilitate optimal DAPT duration management with high accuracy and adaptability.
Subject(s)
Coronary Artery Disease , Drug-Eluting Stents , Myocardial Infarction , Percutaneous Coronary Intervention , Humans , Platelet Aggregation Inhibitors/adverse effects , Myocardial Infarction/etiology , Coronary Artery Disease/diagnosis , Coronary Artery Disease/surgery , Drug-Eluting Stents/adverse effects , Artificial Intelligence , Retrospective Studies , Treatment Outcome , Risk Factors , Drug Therapy, Combination , Hemorrhage/chemically induced , Prognosis , Percutaneous Coronary Intervention/adverse effectsABSTRACT
Genome-wide association studies (GWAS) are used to identify relationships between genetic variations and specific traits. When applied to high-dimensional medical imaging data, a key step is to extract lower-dimensional, yet informative representations of the data as traits. Representation learning for imaging genetics is largely under-explored due to the unique challenges posed by GWAS in comparison to typical visual representation learning. In this study, we tackle this problem from the mutual information (MI) perspective by identifying key limitations of existing methods. We introduce a trans-modal learning framework Genetic InfoMax (GIM), including a regularized MI estimator and a novel genetics-informed transformer to address the specific challenges of GWAS. We evaluate GIM on human brain 3D MRI data and establish standardized evaluation protocols to compare it to existing approaches. Our results demonstrate the effectiveness of GIM and a significantly improved performance on GWAS.
ABSTRACT
BACKGROUND: Automatic skin lesion recognition has shown to be effective in increasing access to reliable dermatology evaluation; however, most existing algorithms rely solely on images. Many diagnostic rules, including the 3-point checklist, are not considered by artificial intelligence algorithms, which comprise human knowledge and reflect the diagnosis process of human experts. OBJECTIVE: In this paper, we aimed to develop a semisupervised model that can not only integrate the dermoscopic features and scoring rule from the 3-point checklist but also automate the feature-annotation process. METHODS: We first trained the semisupervised model on a small, annotated data set with disease and dermoscopic feature labels and tried to improve the classification accuracy by integrating the 3-point checklist using ranking loss function. We then used a large, unlabeled data set with only disease label to learn from the trained algorithm to automatically classify skin lesions and features. RESULTS: After adding the 3-point checklist to our model, its performance for melanoma classification improved from a mean of 0.8867 (SD 0.0191) to 0.8943 (SD 0.0115) under 5-fold cross-validation. The trained semisupervised model can automatically detect 3 dermoscopic features from the 3-point checklist, with best performances of 0.80 (area under the curve [AUC] 0.8380), 0.89 (AUC 0.9036), and 0.76 (AUC 0.8444), in some cases outperforming human annotators. CONCLUSIONS: Our proposed semisupervised learning framework can help with the automatic diagnosis of skin disease based on its ability to detect dermoscopic features and automate the label-annotation process. The framework can also help combine semantic knowledge with a computer algorithm to arrive at a more accurate and more interpretable diagnostic result, which can be applied to broader use cases.
ABSTRACT
BACKGROUND: Predicting outcomes of patients with COVID-19 at an early stage is crucial for optimised clinical care and resource management, especially during a pandemic. Although multiple machine learning models have been proposed to address this issue, because of their requirements for extensive data preprocessing and feature engineering, they have not been validated or implemented outside of their original study site. Therefore, we aimed to develop accurate and transferrable predictive models of outcomes on hospital admission for patients with COVID-19. METHODS: In this study, we developed recurrent neural network-based models (CovRNN) to predict the outcomes of patients with COVID-19 by use of available electronic health record data on admission to hospital, without the need for specific feature selection or missing data imputation. CovRNN was designed to predict three outcomes: in-hospital mortality, need for mechanical ventilation, and prolonged hospital stay (>7 days). For in-hospital mortality and mechanical ventilation, CovRNN produced time-to-event risk scores (survival prediction; evaluated by the concordance index) and all-time risk scores (binary prediction; area under the receiver operating characteristic curve [AUROC] was the main metric); we only trained a binary classification model for prolonged hospital stay. For binary classification tasks, we compared CovRNN against traditional machine learning algorithms: logistic regression and light gradient boost machine. Our models were trained and validated on the heterogeneous, deidentified data of 247â960 patients with COVID-19 from 87 US health-care systems derived from the Cerner Real-World COVID-19 Q3 Dataset up to September 2020. We held out the data of 4175 patients from two hospitals for external validation. The remaining 243â785 patients from the 85 health systems were grouped into training (n=170â626), validation (n=24â378), and multi-hospital test (n=48â781) sets. Model performance was evaluated in the multi-hospital test set. The transferability of CovRNN was externally validated by use of deidentified data from 36â140 patients derived from the US-based Optum deidentified COVID-19 electronic health record dataset (version 1015; from January, 2007, to Oct 15, 2020). Exact dates of data extraction were masked by the databases to ensure patient data safety. FINDINGS: CovRNN binary models achieved AUROCs of 93·0% (95% CI 92·6-93·4) for the prediction of in-hospital mortality, 92·9% (92·6-93·2) for the prediction of mechanical ventilation, and 86·5% (86·2-86·9) for the prediction of a prolonged hospital stay, outperforming light gradient boost machine and logistic regression algorithms. External validation confirmed AUROCs in similar ranges (91·3-97·0% for in-hospital mortality prediction, 91·5-96·0% for the prediction of mechanical ventilation, and 81·0-88·3% for the prediction of prolonged hospital stay). For survival prediction, CovRNN achieved a concordance index of 86·0% (95% CI 85·1-86·9) for in-hospital mortality and 92·6% (92·2-93·0) for mechanical ventilation. INTERPRETATION: Trained on a large, heterogeneous, real-world dataset, our CovRNN models showed high prediction accuracy and transferability through consistently good performances on multiple external datasets. Our results show the feasibility of a COVID-19 predictive model that delivers high accuracy without the need for complex feature engineering. FUNDING: Cancer Prevention and Research Institute of Texas.
Subject(s)
COVID-19 , COVID-19/epidemiology , COVID-19/therapy , Electronic Health Records , Hospitals , Humans , Neural Networks, Computer , Retrospective StudiesABSTRACT
Deep learning (DL)-based predictive models from electronic health records (EHRs) deliver impressive performance in many clinical tasks. Large training cohorts, however, are often required by these models to achieve high accuracy, hindering the adoption of DL-based models in scenarios with limited training data. Recently, bidirectional encoder representations from transformers (BERT) and related models have achieved tremendous successes in the natural language processing domain. The pretraining of BERT on a very large training corpus generates contextualized embeddings that can boost the performance of models trained on smaller datasets. Inspired by BERT, we propose Med-BERT, which adapts the BERT framework originally developed for the text domain to the structured EHR domain. Med-BERT is a contextualized embedding model pretrained on a structured EHR dataset of 28,490,650 patients. Fine-tuning experiments showed that Med-BERT substantially improves the prediction accuracy, boosting the area under the receiver operating characteristics curve (AUC) by 1.21-6.14% in two disease prediction tasks from two clinical databases. In particular, pretrained Med-BERT obtains promising performances on tasks with small fine-tuning training sets and can boost the AUC by more than 20% or obtain an AUC as high as a model trained on a training set ten times larger, compared with deep learning models without Med-BERT. We believe that Med-BERT will benefit disease prediction studies with small local training datasets, reduce data collection expenses, and accelerate the pace of artificial intelligence aided healthcare.
ABSTRACT
ß-Graphdiyne (ß-GDY) is a two-dimensional carbon material with zero band gap and highly intrinsic carrier mobility and a promising material with potential applications in electronic devices. However, the synthesis of continuous single or ultrathin ß-GDY has not been realized yet. Here, we proposed an approach for ultrathin ß-GDY-like film synthesis using graphene as a template because of the strong π-π interaction between ß-GDY and graphene. The as-synthesized film presents smooth and continuous morphology and has good crystallinity. Electrical measurement reveals that the film presented a conductivity of 1.30 × 10-2 S·m-1 by fabricating electronic devices on ß-GDY grown on a dielectric hexagonal boron nitride template.
ABSTRACT
Graphdiyne is predicted to have a natural band gap and simultaneously possesses superior carrier mobility, which makes it potential for electronic devices. Synthesis of ultrathin graphdiyne film is highly demanded. In this work, we proposed an approach for synthesis of ultrathin graphdiyne film using graphene as a surface template, which can induce confined reaction on substrate. With all-carbon, conjugated, atomically flat structure, graphene has a strong interaction with the graphdiyne system, resulting the formation of continuous flat ultrathin graphdiyne film with thickness less than 3 nm. Raman spectra, grazing incidence X-ray diffraction, and transmission electron microscopy characterization all confirmed the features of graphdiyne. Furthermore, this strategy was also extended to the hexagonal boron nitride (hBN) surface with resembling structure, serving as a perfect dielectric layer. Field-effect transistor devices based on graphdiyne film grown on hBN were fabricated directly, and electrical transport measurements demonstrate the good conductivity with p-type characteristics of the as-obtained graphdiyne film.
ABSTRACT
OBJECTIVE: Conventional decoding pipeline for brain-machine interfaces (BMIs) consists of chained different stages of feature extraction, time-frequency analysis and statistical learning models. Each of these stages uses a different algorithm trained in a sequential manner, which makes it difficult to make the whole system adaptive. The goal was to create an adaptive online system with a single objective function and a single learning algorithm so that the whole system can be trained in parallel to increase the decoding performance. Here, we used deep neural networks consisting of convolutional neural networks (CNN) and a special kind of recurrent neural network (RNN) called long short term memory (LSTM) to address these needs. APPROACH: We used electrocorticography (ECoG) data collected by Kubanek et al. The task consisted of individual finger flexions upon a visual cue. Our model combined a hierarchical feature extractor CNN and a RNN that was able to process sequential data and recognize temporal dynamics in the neural data. CNN was used as the feature extractor and LSTM was used as the regression algorithm to capture the temporal dynamics of the signal. MAIN RESULTS: We predicted the finger trajectory using ECoG signals and compared results for the least angle regression (LARS), CNN-LSTM, random forest, LSTM model (LSTM_HC, for using hard-coded features) and a decoding pipeline consisting of band-pass filtering, energy extraction, feature selection and linear regression. The results showed that the deep learning models performed better than the commonly used linear model. The deep learning models not only gave smoother and more realistic trajectories but also learned the transition between movement and rest state. SIGNIFICANCE: This study demonstrated a decoding network for BMI that involved a convolutional and recurrent neural network model. It integrated the feature extraction pipeline into the convolution and pooling layer and used LSTM layer to capture the state transitions. The discussed network eliminated the need to separately train the model at each step in the decoding pipeline. The whole system can be jointly optimized using stochastic gradient descent and is capable of online learning.
Subject(s)
Brain-Computer Interfaces , Deep Learning , Electrocorticography/methods , Fingers/physiology , Movement/physiology , Sensorimotor Cortex/physiology , Humans , Photic Stimulation/methodsABSTRACT
Graphdiyne (GDY), a new kind of two-dimensional (2D) carbon allotropes, has extraordinary electrical, mechanical, and optical properties, leading to advanced applications in the fields of energy storage, photocatalysis, electrochemical catalysis, and sensors. However, almost all reported methods require metallic copper as a substrate, which severely limits their large-scale application because of the high cost and low specific surface area (SSA) of copper substrate. Here, freestanding three-dimensional GDY (3DGDY) is successfully prepared using naturally abundant and inexpensive diatomite as template. In addition to the intrinsic properties of GDY, the fabricated 3DGDY exhibits a porous structure and high SSA that enable it to be directly used as a lithium-ion battery anode material and a 3D scaffold to create Rh@3DGDY composites, which would hold great potential applications in energy storage and catalysts, respectively.
ABSTRACT
Graphdiyne analogs, linked carbon monolayers with acetylenic scaffoldings, are fabricated by adopting low-temperature chemical vapor deposition which provides a route for the synthesis of two-dimensional carbon materials via molecular building blocks. The electrical conductivity of the as-grown films can reach up to 6.72 S cm-1 . Moreover, the films show potential as promising substrates for fluorescence suppressing and Raman advancement.
ABSTRACT
ß-Graphdiyne (ß-GDY) is a member of 2D graphyne family with zero band gap, and is a promising material with potential applications in energy storage, organic electronics, etc. However, the synthesis of ß-GDY has not been realized yet, and the measurement of its intrinsic properties remains elusive. In this work, ß-GDY-containing thin film is successfully synthesized on copper foil using modified Glaser-Hay coupling reaction with tetraethynylethene as precursor. The as-grown carbon film has a smooth surface and is continuous and uniform. Electrical measurements reveal the conductivity of 3.47 × 10-6 S m-1 and the work function of 5.22 eV. TiO2 @ß-GDY nanocomposite is then prepared and presented with an enhancement of photocatalytic ability compared to pure TiO2 .
ABSTRACT
A general and simple route to fabricate graphdiyne nanowalls on arbitrary substrates is developed by using a copper envelope catalysis strategy. The GDY/BiVO4 system is but one example of combing the unique properites of GDY with those target substrates where GDY improves the photoelectrochemical performance dramatically.
ABSTRACT
Robust superhydrophobic foam is fabricated by combining an ordered graphdiyne-based hierarchical structure with a low-surface-energy coating. This foam shows not only superhydrophobicity both in air (≈160.1°) and in oil (≈171.0°), but also high resistance toward abrasion cycles. Owing to its 3D porous structures and numerous superhydrophobic surfaces, it can easily separate oil from water with high efficiency and good recyclability.