Search

Background Androgen deprivation therapy (ADT) with radiotherapy can benefit patients with localized prostate cancer. However, ADT can negatively impact quality of life and there remain no validated predictive models to guide its use. Methods Digital pathology image and clinical data from pre-treatment prostate tissue from 5,727 patients enrolled on five phase III randomized trials treated with radiotherapy +/- ADT were used to develop and validate an artificial intelligence (AI)-derived predictive model to assess ADT benefit with the primary endpoint of distant metastasis. After the model was locked, validation was performed on NRG/RTOG 9408 (n = 1,594) that randomized men to radiotherapy +/- 4 months of ADT. Fine-Gray regression and restricted mean survival times were used to assess the interaction between treatment and predictive model and within predictive model positive and negative subgroup treatment effects. Results In the NRG/RTOG 9408 validation cohort (14.9 years of median follow-up), ADT significantly improved time to distant metastasis (subdistribution hazard ratio [sHR] = 0.64, 95%CI [0.45–0.90], p = 0.01). The predictive model-treatment interaction was significant (p-interaction = 0.01). In predictive model positive patients (n = 543, 34%), ADT significantly reduced the risk of distant metastasis compared to radiotherapy alone (sHR = 0.34, 95%CI [0.19–0.63], p

Aromatic macromolecules tend to form a compact conformation after physically adsorbed on graphene and it brings about great entropy loss for physisorption, due to the strong interaction between aromatic macromolecules and graphene. However, previous researches have validated the availability of aromatic macromolecules to stabilize graphene based on physisorption. In order to clarify the underlying mechanism of this physisorption process on graphene, a series of aromatic polyamide copolymers are used as models in this research. Apart from their adsorbed conformations on graphene, the conformations of these copolymers as the free states in diluted solutions are taken into consideration. Although these copolymers present the fully extended conformation on graphene, their conformations in diluted solutions vary largely with the copolymer composition. It is verified that the copolymer with smaller conformational change could have the better stabilization effectiveness for graphene, rather than the one having stronger interaction with graphene. Therefore, the entropy-tailored behavior for the adsorption of aromatic macromolecules on graphene is put forward. Based on this mechanism, the chemical structure of aromatic polyamide is optimized and furthermore it is utilized to directly exfoliate natural graphite flakes. Eventually, high-quality graphene nanosheets with a large dimension and low defects are obtained. Moreover, its exfoliating effectiveness is superior to those of the commonly used exfoliating agents nowadays.

Background: Machine learning is a promising approach to personalize atrial fibrillation management strategies for patients after catheter ablation. Prior atrial fibrillation ablation outcome prediction studies applied classical machine learning methods to hand-crafted clinical scores, and none have leveraged intracardiac electrograms or 12-lead surface electrocardiograms for outcome prediction. We hypothesized that (1) machine learning models trained on electrograms or electrocardiogram (ECG) signals can perform better at predicting patient outcomes after atrial fibrillation ablation than existing clinical scores and (2) multimodal fusion of electrogram, ECG, and clinical features can further improve the prediction of patient outcomes. Methods: Consecutive patients who underwent catheter ablation between 2015 and 2017 with panoramic left atrial electrogram before ablation and clinical follow-up for at least 1 year following ablation were included. Convolutional neural network and a novel multimodal fusion framework were developed for predicting 1-year atrial fibrillation recurrence after catheter ablation from electrogram, ECG signals, and clinical features. The models were trained and validated using 10-fold cross-validation on patient-level splits. Results: One hundred fifty-six patients (64.5±10.5 years, 74% male, 42% paroxysmal) were analyzed. Using electrogram signals alone, the convolutional neural network achieved an area under the receiver operating characteristics curve (AUROC) of 0.731, outperforming the existing APPLE scores (AUROC=0.644) and CHA2DS2-VASc scores (AUROC=0.650). Similarly using 12-lead ECG alone, the convolutional neural network achieved an AUROC of 0.767. Combining electrogram, ECG, and clinical features, the fusion model achieved an AUROC of 0.859, outperforming single and dual modality models. Conclusions: Deep neural networks trained on electrogram or ECG signals improved the prediction of catheter ablation outcome compared with existing clinical scores, and fusion of electrogram, ECG, and clinical features further improved the prediction. This suggests the promise of using machine learning to help treatment planning for patients after catheter ablation.

Magnonics, an emerging research field that uses the quanta of spin waves as data carriers, has a potential to dominate the post-CMOS era owing to its intrinsic property of ultra-low power operation. Spin waves can be manipulated by a wide range of parameters; thus, they are suitable for sensing applications in a wide range of physical fields. In this study, we designed a highly sensitive, simple structure, and ultra-low power magnetic sensor using a simple CoFeB/Y

ABSTRCATPurposeThis study investigates whether graph-based fusion of imaging data with non-imaging EHR data can improve the prediction of disease trajectory for COVID-19 patients, beyond the prediction performance of only imaging or non-imaging EHR data.Materials and MethodsWe present a novel graph-based framework for fine-grained clinical outcome prediction (discharge, ICU admission, or death) that fuses imaging and non-imaging information using a similarity-based graph structure. Node features are represented by image embedding and edges are encoded with clinical or demographic similarity.ResultsOur experiments on data collected from Emory Healthcare network indicate that our fusion modeling scheme performs consistently better than predictive models using only imaging or non-imaging features, with f1-scores of 0.73, 0.77, and 0.66 for discharge from hospital, mortality, and ICU admission, respectively. External validation was performed on data collected from Mayo Clinic. Our scheme highlights known biases in the model prediction such as bias against patients with alcohol abuse history and bias based on insurance status.ConclusionThe study signifies the importance of fusion of multiple data modalities for accurate prediction of clinical trajectory. Proposed graph structure can model relationships between patients based on non-imaging EHR data and graph convolutional networks can fuse this relationship information with imaging data to effectively predict future disease trajectory more effectively than models employing only imaging or non-imaging data. Forecasting clinical events can enable intelligent resource allocation in hospitals. Our graph-based fusion modeling frameworks can be easily extended to other prediction tasks to efficiently combine imaging data with non-imaging clinical data.

Developing prediction models for emerging infectious diseases from relatively small numbers of cases is a critical need for improving pandemic preparedness. Using COVID-19 as an exemplar, we propose a transfer learning methodology for developing predictive models from multi-modal electronic healthcare records by leveraging information from more prevalent diseases with shared clinical characteristics. Our novel hierarchical, multi-modal model (TransMED) integrates baseline risk factors from the natural language processing of clinical notes at admission, time-series measurements of biomarkers obtained from laboratory tests, and discrete diagnostic, procedure and drug codes. We demonstrate the alignment of TransMED's predictions with well-established clinical knowledge about COVID-19 through univariate and multivariate risk factor driven sub-cohort analysis. TransMED's superior performance over state-of-the-art methods shows that leveraging patient data across modalities and transferring prior knowledge from similar disorders is critical for accurate prediction of patient outcomes, and this approach may serve as an important tool in the early response to future pandemics.

Weak transverse interaction of aramid fiber leads to low compressive strength, which is a prominent problem for its further application. In this study, a novel strategy by constructing dendritic structure in aramid fiber was conducted to solve the problem. Hyperbranched aromatic polyamide and linear aromatic polyamide are grafted on nano-SiO2 respectively, which will present absolutely different conformations. Structure of the SiO2 derivates was analyzed in detail by Fourier transform infrared spectroscopy (FTIR), dynamic laser scattering (DLS) and X-ray photoelectron spectroscopy (XPS). Compared with linear polyamide, hyperbranched polyamide tends to grow in multiple directions during polymerization due to significant steric effect, which can be confirmed by molecular simulation. When the SiO2 derivates were blended in aramid fiber, three-dimensional dendritic structure will be constructed by utilizing distinctive conformation of the hyperbranched polyamide. When loading content of nano-SiO2 derivate modified by hyperbranched polyamide in aramid fiber is 0.5 wt%, compressive strength of the fiber is improved by nearly 114%. Moreover, tensile strength and modulus are improved by nearly 13% and 9% respectively. Therefore, comprehensive performance of the aramid fiber can be remarkably improved by utilizing unique conformation of the hyperbranched polyamide, even if loading content of the SiO2 derivate is relatively low.

The study was to explore the effect of the extracts of Angelica sinensis (EAs) on lipid oxidation in fish feeds compared with ethoxyquin (EQ) and the effect of dietary EAs on growth performance of carp (Cyprinus carpio var. Jian). Firstly, fish feeds were respectively added with EQ, and ethyl ether extract, ethyl acetate extract (EAE), acetone extract, ethanol extract (EE) and aqueous extract (AQE) of Angelica sinensis, except for the control. The results showed that EAs and EQ inhibited lipid oxidation in fish feeds (P < 0.05). Of all of the examined EAs, EAE showed the strongest protective effects against lipid oxidation (P < 0.05). Moreover, EAE at high concentrations showed a stronger effect on lipid oxidation compared with EQ (P < 0.05). Then, 7 experimental diets respectively supplemented with 0.0, 1.0, 2.0, 3.0, 4.0, 5.0 and 6.0 g/kg of EAE were fed to the respective treatment groups for 30 d. Four replicates were performed for each treatment group; 20 carp (mean weight: 12.10 ± 0.13 g) were in each replicate. The results indicated that dietary EAE improved the growth performance in carp (P < 0.05). The appropriate concentration of EAE for carp growth was estimated to be 3.643 g/kg diet. Thus, EAE could be used as a natural antioxidant in feeds for Jian carp. Keywords: Angelica sinensis, Extracts, Ethoxyquin, Lipid oxidation, Growth performance

Labeled data is a critical resource for training and evaluating machine learning models. However, many real-life datasets are only partially labeled. We propose a semi-supervised machine learning training strategy to improve event detection performance on sequential data, such as video recordings, when only sparse labels are available, such as event start times without their corresponding end times. Our method uses noisy guesses of the events' end times to train event detection models. Depending on how conservative these guesses are, mislabeled samples may be introduced into the training set. We further propose a mathematical model for explaining and estimating the evolution of the classification performance for increasingly noisier end time estimates. We show that neural networks can improve their detection performance by leveraging more training data with less conservative approximations despite the higher proportion of incorrect labels. We adapt sequential versions of CIFAR-10 and MNIST, and use the Berkeley MHAD and HMBD51 video datasets to empirically evaluate our method, and find that our risk-tolerant strategy outperforms conservative estimates by 3.5 points of mean average precision for CIFAR, 30 points for MNIST, 3 points for MHAD, and 14 points for HMBD51. Then, we leverage the proposed training strategy to tackle a real-life application: processing continuous video recordings of epilepsy patients, and show that our method outperforms baseline labeling methods by 17 points of average precision, and reaches a classification performance similar to that of fully supervised models. We share part of the code for this article.

The reliability of machine learning models can be compromised when trained on low quality data. Many large-scale medical imaging datasets contain low quality labels extracted from sources such as medical reports. Moreover, images within a dataset may have heterogeneous quality due to artifacts and biases arising from equipment or measurement errors. Therefore, algorithms that can automatically identify low quality data are highly desired. In this study, we used data Shapley, a data valuation metric, to quantify the value of training data to the performance of a pneumonia detection algorithm in a large chest X-ray dataset. We characterized the effectiveness of data Shapley in identifying low quality versus valuable data for pneumonia detection. We found that removing training data with high Shapley values decreased the pneumonia detection performance, whereas removing data with low Shapley values improved the model performance. Furthermore, there were more mislabeled examples in low Shapley value data and more true pneumonia cases in high Shapley value data. Our results suggest that low Shapley value indicates mislabeled or poor quality images, whereas high Shapley value indicates data that are valuable for pneumonia detection. Our method can serve as a framework for using data Shapley to denoise large-scale medical imaging datasets.

Objective: To analyze the differential expression of related serum proteins was detected in patients with AR who were sensitized to dust mites pre- and 6-day post-RIT. Methods: Serum samples were collected from 15 AR, 15 6-day post-RIT and 10 healthy control patients. This analysis was performed using iTRAQ technique and was coupled with 2-dimensional gel electrophoresis and mass spectrometry. To determine the intimacy of the screened related differential proteins, a hierarchical analysis was performed with Cluster 3.0 software, and the results were visualized using Java TreeView software. Last, an ELISA was employed to validate the selected CRP, CTHRC1 and WDR89 protein expression data. Results: Compared with the healthy control group, the most upregulated protein in the AR group and the most downregulated proteins in the 6-day post-RIT group were CTHRC1 and WDR89. Compared with the healthy control group, the most downregulated protein in the AR group and the most upregulated protein of the 6-day post-RIT group was CRP. The serum protein levels of CRP, CTHRC1 and WDR89 proteins were determined by ELISA. It was found that the differential expression of CTHRC1 and WDR89 in the AR and 6-day post-RIT groups were statistically significant (P 0.05) was found in the differential expression of serum CRP in the AR and 6-day post-RIT groups. Conclusions: We found that CTHRC1 and WDR89 might be associated with the pathogenesis of AR, and they may play a regulatory role in the RIT.

In this study, a series of acid-base bi-functional catalysts were prepared by mixing different amounts of basic amino acids (AAs) and phosphotungstic acid (PTA), which exhibited the excellent performance in catalyzing conversion of oleic acid (OA) for the biodiesel production. The physicochemical properties of the catalysts were characterized and analyzed using modern testing techniques and characterization methods such as XRD, FT-IR, XPS, SEM, TEM, and Hammett titration. The various influence parameters were optimized using the central composite design based the response surface methodology, where the maximum biodiesel yield of 97.0% was achieved at the MeOH/OA molar ratio of 5.9, the catalyst loading of 8%, reaction time of 6 h, and reaction temperature of 65℃. Furthermore, the stability and reusability of the prepared catalyst were also demonstrated. At last, the possible catalytic mechanism of the prepared catalyst was comprehensively described.

Superparamagnetic tunnel junctions (SMTJs) are spintronic nanodevices that can oscillate spontaneously under the influence of thermal noise. Studies have proposed that SMTJs can be modeled as magnetic neurons by subjecting them to electrical Gaussian white noise and can be subsequently synchronized under subthreshold driving. Considering the non-Gaussian background noise in industrial applications, this study investigated the influence of levy noise on SMTJ subthreshold synchronization. The results revealed that levy noise with weak pulse characteristics can be used to promote the subthreshold synchronization of the SMTJs, whereas levy noise with enhanced pulse characteristics cannot be used. Under the same conditions, enhanced levy noise asymmetry is advantageous for achieving SMTJ synchronization under subthreshold driving.

BackgroundHeterogeneity in autism spectrum disorder (ASD) has hindered the development of biomarkers, thus motivating subtyping efforts. Most subtyping studies divide ASD individuals into non-overlapping (categorical) subgroups. However, continuous inter-individual variation in ASD suggests the need for a dimensional approach.MethodsA Bayesian model was employed to decompose resting-state functional connectivity (RSFC) of ASD individuals into multiple abnormal RSFC patterns, i.e., categorical subtypes henceforth referred to as “factors”. Importantly, the model allowed each individual to express one or more factors to varying degrees (dimensional subtyping). The model was applied to 306 ASD individuals (age 5.2-57 years) from two multisite repositories. Posthoc analyses associated factors with symptoms and demographics.ResultsAnalyses yielded three factors with dissociable whole-brain hypo/hyper RSFC patterns. Most participants expressed multiple (categorical) factors, suggestive of a mosaic of subtypes within individuals. All factors shared abnormal RSFC involving the default network, but the directionality (hypo/hyper RSFC) differed across factors. Factor 1 was associated with core ASD symptoms, while factor 2 was associated with comorbid symptoms. Older males preferentially expressed factor 3. Factors were robust across multiple control analyses and not associated with IQ, nor head motion.ConclusionsThere exist at least three ASD factors with dissociable patterns of whole-brain RSFC, behaviors and demographics. Heterogeneous default network hypo/hyper RSFC across the factors might explain previously reported inconsistencies. The factors differentiated between core ASD and comorbid symptoms - a less appreciated domain of heterogeneity in ASD. These factors are co-expressed in ASD individuals with different degrees, thus reconciling categorical and dimensional perspectives of ASD heterogeneity.

Background Heterogeneity in autism spectrum disorder (ASD) has hindered the development of biomarkers, thus motivating subtyping efforts. Most subtyping studies divide individuals with ASD into nonoverlapping (categorical) subgroups. However, continuous interindividual variation in ASD suggests that there is a need for a dimensional approach. Methods A Bayesian model was employed to decompose resting-state functional connectivity (RSFC) of individuals with ASD into multiple abnormal RSFC patterns, i.e., categorical subtypes, henceforth referred to as “factors.” Importantly, the model allowed each individual to express one or more factors to varying degrees (dimensional subtyping). The model was applied to 306 individuals with ASD (5.2–57 years of age) from two multisite repositories. Post hoc analyses associated factors with symptoms and demographics. Results Analyses yielded three factors with dissociable whole-brain hypo- and hyper–RSFC patterns. Most participants expressed multiple (categorical) factors, suggestive of a mosaic of subtypes within individuals. All factors shared abnormal RSFC involving the default mode network, but the directionality (hypo- or hyper–RSFC) differed across factors. Factor 1 was associated with core ASD symptoms. Factors 1 and 2 were associated with distinct comorbid symptoms. Older male participants preferentially expressed factor 3. Factors were robust across control analyses and were not associated with IQ or head motion. Conclusions There exist at least three ASD factors with dissociable whole-brain RSFC patterns, behaviors, and demographics. Heterogeneous default mode network hypo- and hyper–RSFC across the factors might explain previously reported inconsistencies. The factors differentiated between core ASD and comorbid symptoms—a less appreciated domain of heterogeneity in ASD. These factors are coexpressed in individuals with ASD with different degrees, thus reconciling categorical and dimensional perspectives of ASD heterogeneity.

Rigid-chain polymeric gels with excellent performance and multi-functions are rarely reported due to the difficulty in balancing solubility and precipitation caused by π-π stacking. Herein, a rigid aromatic polyamide organogel containing benzimidazole moiety was prepared successfully by utilizing protonation effect of protic acid HCl. Due to protonation, coplanarity of stacking structures was destroyed and the dissolution interaction of benzimidazole moiety and solvent was weakened. With increasing temperature, the further decreased solvation capacity led to the formation of interchain hydrogen bonds with a self-assembly process that induced gelation. What’ s more, due to weakened conjugation of protonated PABI, aggregation-induced quenching (ACQ) was suppressed, and this LCST-type organogel showed aggregation-induced emission (AIE) phenomenon with enhanced blue-light emission. This paper provides an ingenious approach via regulating conjugation and solvation for constructing functional rigid-chain polymer gels.

PURPOSE: To compare machine learning methods for classifying mass lesions on mammography images that use predefined image features computed over lesion segmentations to those that leverage segmentation-free representation learning on a standard, public evaluation dataset. METHODS: We apply several classification algorithms to the public Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM), in which each image contains a mass lesion. Segmentation-free representation learning techniques for classifying lesions as benign or malignant include both a Bag-of-Visual-Words (BoVW) method and a Convolutional Neural Network (CNN). We compare classification performance of these techniques to that obtained using two different segmentation-dependent approaches from the literature that rely on specific combinations of end classifiers (e.g. linear discriminant analysis, neural networks) and predefined features computed over the lesion segmentation (e.g. spiculation measure, morphological characteristics, intensity metrics). RESULTS: We report area under the receiver operating characteristic curve (A(Z)) values for malignancy classification on CBIS-DDSM for each technique. We find average A(Z) values of 0.73 for a segmentation-free BoVW method, 0.86 for a segmentation-free CNN method, 0.75 for a segmentation-dependent linear discriminant analysis of Rubber-Band Straightening Transform features, and 0.58 for a hybrid rule-based neural network classification using a small number of hand-designed features. CONCLUSIONS: We find that malignancy classification performance on the CBIS-DDSM dataset using segmentation-free BoVW features is comparable to that of the best segmentation-dependent methods we study, but also observe that a common segmentation-free CNN model substantially and significantly outperforms each of these (p

BackgroundThere is considerable interest in a dimensional transdiagnostic approach to psychiatry. Most transdiagnostic studies have derived factors based only on clinical symptoms, which might miss possible links between psychopathology, cognitive processes and personality traits. Furthermore, many psychiatric studies focus on higher-order association brain networks, thus neglecting the potential influence of huge swaths of the brain.MethodsA multivariate data-driven approach (partial least squares; PLS) was utilized to identify latent components linking a large set of clinical, cognitive and personality measures to whole-brain resting-state functional connectivity (RSFC) patterns across 224 participants. The participants were either healthy (N=110) or diagnosed with bipolar disorder (N=40), attention-deficit/hyperactivity disorder (N=37), schizophrenia (N=29) or schizoaffective disorder (N=8). In contrast to traditional case-control analyses, the diagnostic categories were not utilized in the PLS analysis, but were helpful for interpreting the components.ResultsOur analyses revealed three latent components corresponding to general psychopathology, cognitive dysfunction and impulsivity. Each component was associated with a unique whole-brain RSFC signature and shared across all participants. The components were robust across multiple control analyses and replicated using independent task functional magnetic resonance imaging data from the same participants. Strikingly, all three components featured connectivity alterations within the somatosensory-motor network, and its connectivity with subcortical structures and cortical executive networks.ConclusionsWe identified three distinct dimensions with dissociable (but overlapping) whole-brain RSFC signatures across healthy individuals and individuals with psychiatric illness, providing potential intermediate phenotypes that span across diagnostic categories. Our results suggest expanding the focus of psychiatric neuroscience beyond higher-order brain networks.

The study was to explore the effect of the extracts of Angelica sinensis (EAs) on lipid oxidation in fish feeds compared with ethoxyquin (EQ) and the effect of dietary EAs on growth performance of carp (Cyprinus carpio var. Jian). Firstly, fish feeds were respectively added with EQ, and ethyl ether extract, ethyl acetate extract (EAE), acetone extract, ethanol extract (EE) and aqueous extract (AQE) of Angelica sinensis, except for the control. The results showed that EAs and EQ inhibited lipid oxidation in fish feeds (P < 0.05). Of all of the examined EAs, EAE showed the strongest protective effects against lipid oxidation (P < 0.05). Moreover, EAE at high concentrations showed a stronger effect on lipid oxidation compared with EQ (P < 0.05). Then, 7 experimental diets respectively supplemented with 0.0, 1.0, 2.0, 3.0, 4.0, 5.0 and 6.0 g/kg of EAE were fed to the respective treatment groups for 30 d. Four replicates were performed for each treatment group; 20 carp (mean weight: 12.10 ± 0.13 g) were in each replicate. The results indicated that dietary EAE improved the growth performance in carp (P < 0.05). The appropriate concentration of EAE for carp growth was estimated to be 3.643 g/kg diet. Thus, EAE could be used as a natural antioxidant in feeds for Jian carp.

Neuromorphic image sensors produce activity-driven spiking output at every pixel. These low-power consuming imagers which encode visual change information in the form of spikes help reduce computational overhead and realize complex real-time systems; object recognition and pose-estimation to name a few. However, there exists a lack of algorithms in event-based vision aimed towards capturing invariance to transformations. In this work, we propose a methodology for recognizing objects invariant to their pose with the Dynamic Vision Sensor (DVS). A novel slow-ELM architecture is proposed which combines the effectiveness of Extreme Learning Machines and Slow Feature Analysis. The system, tested on an Intel Core i5-4590 CPU, can perform 10,000 classifications per second and achieves 1% classification error for 8 objects with views accumulated over 90 degrees of 2D pose.