Multi-Feature Map Integrated Attention Model for Early Prediction of Type 2 Diabetes Using Irregular Health Examination Records.

Type 2 diabetes (T2D) is a worldwide chronic disease that is difficult to cure and causes a heavy social burden. Early prediction of T2D can effectively identify high-risk populations and facilitate earlier implementation of appropriate preventive interventions. Various early prediction models for T2D have been proposed. However, these methods do not consider the following factors: 1) health examination records (HER) containing health information before diagnosis; 2) rating information containing clinical knowledge; and 3) local and global information of time-series features. These diagnostically relevant factors need to be considered. It is challenging due to irregular and multivariate time series. In this paper, we propose the multi-feature map integrated attention model (MFMAM) for early diabetes prediction using HER. Specifically, HER is converted into the multi-feature map to capture local and global volatility, as well as the sequence order of high-dimensional features. We concatenate rating indicators to introduce clinical knowledge. In addition, considering missing and temporal patterns, we utilize missing and time embedding to learn the complex transition of health status. We adopt attention mechanisms to capture essential features (channels) and time points (spatial). To evaluate the proposed model, we conducted experiments on real-world long-term HER. The results demonstrated that MFMAM outperformed baseline models on tasks of varying sequence lengths and prediction windows. Moreover, we applied our designs to baseline models, and their performance was considerably improved. The proposed model contributes to the short-term and long-term early prediction of T2D in individuals with varying information richness.

Predictive Synthesis of Copper Selenides Using a Multidimensional Phase Map Constructed with a Data-Driven Classifier.

Copper selenides are an important family of materials with applications in catalysis, plasmonics, photovoltaics, and thermoelectrics. Despite being a binary material system, the Cu-Se phase diagram is complex and contains multiple crystal structures in addition to several metastable structures that are not found on the thermodynamic phase diagram. Consequently, the ability to synthetically navigate this complex phase space poses a significant challenge. We demonstrate that data-driven learning can successfully map this phase space in a minimal number of experiments. We combine soft chemistry (chimie douce) synthetic methods with multivariate analyses via classification techniques to enable predictive phase determination. A surrogate model was constructed with experimental data derived from a design matrix of four experimental variables: C-Se bond strength of the selenium precursor, time, temperature, and solvent composition. The reactions in the surrogate model resulted in 11 distinct phase combinations of copper selenide. These data were used to train a classification model that predicts the phase with 95.7% accuracy. The resulting decision tree enabled conclusions to be drawn about how the experimental variables affect the phase and provided prescriptive synthetic conditions for specific phase isolation. This guided the accelerated phase targeting in a minimum number of experiments of klockmannite CuSe, which could not be isolated in any of the reactions used to construct the surrogate model. The reaction conditions that the model predicted to synthesize klockmannite CuSe were experimentally validated, highlighting the utility of this approach.

Assisting schizophrenia diagnosis using clinical electroencephalography and interpretable graph neural networks: a real-world and cross-site study.

Schizophrenia (SCZ) is a chronic and serious mental disorder with a high mortality rate. At present, there is a lack of objective, cost-effective and widely disseminated diagnosis tools to address this mental health crisis globally. Clinical electroencephalogram (EEG) is a noninvasive technique to measure brain activity with high temporal resolution, and accumulating evidence demonstrates that clinical EEG is capable of capturing abnormal SCZ neuropathology. Although EEG-based automated diagnostic tools have obtained impressive performance on individual datasets, the transportability of potential EEG biomarkers in cross-site real-world application is still an open question. To address the challenges of small sample sizes and population heterogeneity, we develop an advanced interpretable deep learning model using multimodal clinical EEG features and demographic information as inputs to graph neural networks, and further propose different transfer learning strategies to adapt to different clinical scenarios. Taking the disease discrimination of health control (HC) and SCZ with 1030 participants as a use case, our model is trained on a small clinical dataset (N = 188, Chinese) and enhanced using a large-scale public dataset (N = 508, American) of adult participants. Cross-site validation from an independent dataset of adult participants (N = 157, Chinese) produced stable performance, with AUCs of 0.793-0.852 and accuracies of 0.786-0.858 for different SCZ prevalence, respectively. In addition, cross-site validation from another dataset of adolescent boys (N = 84, Russian) yielded an AUC of 0.702 and an accuracy of 0.690. Moreover, feature visualization further revealed that the ranking of feature importance varied significantly among different datasets, and that EEG theta and alpha band power appeared to be the most significant and translational biomarkers of SCZ pathology. Overall, our promising results demonstrate the feasibility of SCZ discrimination using EEG biomarkers in multiple clinical settings.

Stochastic processes drive the soil fungal communities in a developing mid-channel bar.

Intricate associations between rhizosphere microbial communities and plants play a critical role in developing and maintaining of soil ecological functioning. Therefore, understanding the assembly patterns of rhizosphere microbes in different plants and their responses to environmental changes is of great ecological implications for dynamic habitats. In this study, a developing mid-channel bar was employed in the Yangtze River to explore the assembly processes of rhizosphere fungal communities among various plant species using high-throughput sequencing-based null model analysis. The results showed a rare significant variation in the composition and alpha diversity of the rhizosphere fungal community among various plant species. Additionally, the soil properties were found to be the primary drivers instead of plant species types. The null model analysis revealed that the rhizosphere fungal communities were primarily driven by stochastic processes (i.e., undominated processes of ecological drift), and the predominance varied with various plant species. Moreover, the assembly processes of rhizosphere fungal communities were significantly related to the changes in soil properties (i.e., soil total carbon, total nitrogen, organic matter, and pH). The co-occurrence network analysis revealed that many keystone species belonged to unclassified fungi. Notably, five network hubs were almost unaffected by the measured soil properties and aboveground plant traits, indicating the effect of stochastic processes on the rhizosphere fungal community assembly. Overall, these results will provide insights into the underlying mechanisms of fungal community assembly in the rhizosphere soils, which are significant for maintaining the functional stability of a developing ecosystem.

Discrepant Effects of Flooding on Assembly Processes of Abundant and Rare Communities in Riparian Soils.

Numerous rare species coexist with a few abundant species in microbial communities and together play an essential role in riparian ecosystems. Relatively little is understood, however, about the nature of assembly processes of these communities and how they respond to a fluctuating environment. In this study, drivers controlling the assembly of abundant and rare subcommunities for bacteria and archaea in a riparian zone were determined, and their resulting patterns on these processes were analyzed. Abundant and rare bacteria and archaea showed a consistent variation in the community structure along the riparian elevation gradient, which was closely associated with flooding frequency. The community assembly of abundant bacteria was not affected by any measured environmental variables, while soil moisture and ratio of submerged time to exposed time were the two most decisive factors determining rare bacterial community. Assembly of abundant archaeal community was also determined by these two factors, whereas rare archaea was significantly associated with soil carbon-nitrogen ratio and total carbon content. The assembly process of abundant and rare bacterial subcommunities was driven respectively by dispersal limitation and variable selection. Undominated processes and dispersal limitation dominated the assembly of abundant archaea, whereas homogeneous selection primarily driven rare archaea. Flooding may therefore play a crucial role in determining the community assembly processes by imposing disturbances and shaping soil niches. Overall, this study reveals the assembly patterns of abundant and rare communities in the riparian zone and provides further insight into the importance of their respective roles in maintaining a stable ecosystem during times of environmental perturbations.

Adversarial reinforcement learning for dynamic treatment regimes.

Treatment recommendation, as a critical task of delivering effective interventions according to patient state and expected outcome, plays a vital role in precision medicine and healthcare management. As a well-suited tactic to learn optimal policies of recommender systems, reinforcement learning is promising to address the challenge of treatment recommendation. However, existing solutions mostly require frequent interactions between treatment recommender systems and clinical environment, which are expensive, time-consuming, and even infeasible in clinical practice. In this study, we present a novel model-based offline reinforcement learning approach to optimize a treatment policy by utilizing patient treatment trajectories in Electronic Health Records (EHRs). Specifically, a patient treatment trajectory simulator is firstly constructed based on the ground-truth trajectories in EHRs. Thereafter, the constructed simulator is utilized to model the online interactions between the treatment recommender system and clinical environment. In this way, the counterfactual trajectories can be generated. To alleviate the bias deriving from the ground-truth and the counterfactual trajectories, an adversarial network is incorporated into the proposed model, such that a large space of treatment actions can be explored with the scaled rewards. The proposed model is evaluated on a simulated dataset and a real-world dataset. The experimental results demonstrate that the proposed model is superior to other methods, giving rise to a new solution for dynamic treatment regimes and beyond.

Identification of a pyrone-type species as the active site for the oxygen reduction reaction.

A bicyclic pyrone-type species on oxygen-doped carbon catalysts was identified as the active site for the oxygen reduction reaction in acidic solution. It has much higher activity than that of typical nitrogen-doped carbon catalysts (0.219 e s-1 site-1vs. 0.021-0.088 e s-1 site-1 at 0.6 VRHE). The ortho-carbon atom in the carbonyl ring of the pyrone-type species was revealed as the reactive site by theoretical calculations.

Deep Dynamic Patient Similarity Analysis: Model Development and Validation in ICU.

BACKGROUND: Personalized medicine requires the patient similarity analysis for providing specific treatments tailed for each patient. However, the patient similarity analysis in personalized clinical scenarios encounters challenges, which are twofold. First, heterogeneous and multi-type data are usually recorded to Electronic Health Records (EHRs) during the course of admissions, which makes it difficult to measure the patient similarity. Second, disease progression manifests diverse disease states at different times, which brings sequential complexity to dynamically retrieve similar patients' sequences. MATERIALS AND METHODS: To overcome the above-mentioned challenges, we propose a novel dynamic patient similarity analysis model based on deep learning. Specifically, the proposed model embeds the multi-type and heterogeneous data into hidden representations with a specially designed embedding and attention module. Thereafter, the proposed model retrieves similar patients' sequences based on these hidden representations in a dynamic manner. More importantly, we adopt two clinical tasks, i.e., diagnosis prediction and medication recommendation, to validate the effectiveness of the proposed model. It is worth noticing that the proposed model integrates a drug-drug interaction (DDI) knowledge graph in the medication recommendation task to reduce adverse reactions caused by combinational treatments, such that a more rational strategy can be realized. We evaluate our proposed model using the critical care database MIMIC-III, which includes 5,430 patients covering 14,096 clinical visits. RESULTS: The proposed model outperforms several state-of-the-art methods. For diagnosis prediction, the average PR-AUC score of the proposed model reaches 0.6200, which is significantly higher than that of the baseline models (0.2497∼0.5407). Meanwhile, for medication recommendation, the average PR-AUC of the proposed model is 0.6682 (Jaccard: 0.4070; F1: 0.5672; Recall: 0.7832) whereas the K-nearest model can only reach 0.3805 (Jaccard: 0.3911; F1: 0.5465; Recall: 0.5705). In addition, our proposed model achieves a lower DDI rate. CONCLUSION: We propose a novel dynamic patient similarity analysis model, which can be implemented into a decision support system for clinical tasks including diagnosis prediction, surgical procedure selection, medication recommendation, etc. Also, the proposed model serves as an explainable protocol in clinical practice thanks to its analogy to real clinical reasoning where a doctor diagnoses diseases and prescribes medications according to the previous cured patients empirically.

Towards Predictive Analysis on Disease Progression: A Variational Hawkes Process Model.

Massively available longitudinal data about long-term disease trajectories of patients provides a golden mine for the understanding of disease progression and efficient health service delivery. It calls for quantitative modeling of disease progression, which is a tricky problem due to the complexity of the disease progression process as well as the irregularity of time documented in trajectories. In this study, we tackle the problem with the goal of predictively analyzing disease progression. Specifically, we propose a novel Variational Hawkes Process (VHP) model to generalize disease progression and predict future patient states based on the clinical observational data of past disease trajectories. First, Hawkes Process captures the intensity of irregular visits in a trajectory documented to medical facilities and controls the aforementioned information flowing into future visits. Thereafter, the captured intensity is incorporated into a Variational Auto-Encoder to generate the representation of the future partial disease trajectory for a target patient in a predictive manner. To further improve the prediction performance, we equip the proposed model with a disease trajectory discriminator to distinguish the generated trajectories from real ones. We evaluate the proposed model on two public datasets from the MIMIC-III database pertaining to heart failure and sepsis patients, respectively, and one real-world dataset from a Chinese hospital pertaining to heart failure patients with multiple admissions. Experimental results demonstrate that the proposed model significantly outperforms state-of-the-art baselines, and may derive a set of practical implications that can benefit a wide spectrum of management and applications on disease progression.

Identification of the molecular origin and development of a panzootic caused by Beauveria bassiana in praying mantis populations in eastern China.

A panzootic in praying mantid species Tenodera sinensis and Statilia maculate, caused by Beauveria bassiana, occurred in north, southwest and southeast regions of Anhui Province, eastern China in Autumn, 2009. A 3-d principal component analysis (PCA) of 123 isolates from three sites revealed that the B. bassiana populations were heterogeneous with obvious dominance. Furthermore, the causal source of the panzootic in Anhui was shown to be polyphyletic. The populations were homogenized into homogenous subunits for investigation of genetic structure by inter-simple sequence repeat (ISSR) markers. Variance was greater than 70%, largely due to genetic differences within populations and subpopulations. Genetic distances and genetic differentiation were negatively associated with geographic distances and it was speculated that this was due to the effects of monsoons and topography. Mantid isolates were divided into five pathotypes based on a two-way cluster analysis of genetic distance. Pathotype I consisted of the predominant subpopulations of Huangcangyu and Chashui populations, with a genetic distance of 0.120 and gene flow up to 1.833. This pathotype caused a widespread epizootic in north and southwest Anhui, and Pathotype III caused enzootic at Site A in September and then epizootic in October, while the other three pathotypes caused enzootics at all three investigation sites. The widespread epizootics and isolated enzootics composed the polyphyletic panzootic in Anhui. A strong gene flow between isolates from the two mantid species was identified, resulting in negligible gene differentiation. This indicated a lack of host specificity in mantid isolates of B. bassiana.

[Genetic differentiation of Isaria farinosa populations in Anhui Province of East China].

Isaria farinosa is an important entomopathogenic fungus. By using ISSR, this paper studied the genetic heterogeneity of six I. farinosa populations at different localities of Anhui Province, East China. A total of 98.5% polymorphic loci were amplified with ten polymorphic primers, but the polymorphism at population level varied greatly, within the range of 59.6%-93.2%. The genetic differentiation index (G(st)) between the populations based on Nei's genetic heterogenesis analysis was 0.3365, and the gene flow (N(m)) was 0.4931. The genetic differentiation between the populations was lower than that within the populations, suggesting that the genetic variation of I. farinosa mainly come from the interior of the populations. The UPGMA clustering based on the genetic similarities between the isolates revealed that the Xishan population was monophylectic, while the other five populations were polyphylectic, with the Yaoluoping population being the most heterogenic and the Langyashan population being the least heterogenic. No correlations were observed between the geographic distance and the genetic distance of the populations. According to the UPGMA clustering based on the genetic distance between the populations, the six populations were classified into three groups, and this classification was accorded with the clustering based on geographic environment, suggesting the effects of environmental heterogeneity on the population heterogeneity.