A prediction and interpretation framework of acute kidney injury in critical care.

Acute kidney injury (AKI) is a common clinical condition with high mortality and resource consumption. Early identification of high-risk patients to achieve an appropriate allocation of limited clinical resources and timely interventions is of significant importance, which has attracted substantial research to develop prediction models for AKI risk stratification. However, most available AKI prediction models have moderate performance and lack of interpretability, which limits their applicability in supporting care intervention. In this paper, a machine learning-based framework for AKI prediction and interpretation in critical care is presented. First, an ensemble model is developed to predict a patient's risk of AKI within 72 h of admission to the intensive care units. Next, the model is interpreted both globally and locally. For the global interpretation, the important predictors are pinpointed and the detailed relationships between AKI risk and these predictors are illustrated. For the local interpretation, patient-specific analysis is presented to provide a visualized explanation for each individual prediction. Experimental results show that such a prediction and interpretation framework can lead to good prediction and interpretation performance, which has the potential to provide effective clinical decision support.

High-density QTL mapping of leaf-related traits and chlorophyll content in three soybean RIL populations.

BACKGROUND: Leaf size and shape, which affect light capture, and chlorophyll content are important factors affecting photosynthetic efficiency. Genetic variation of these components significantly affects yield potential and seed quality. Identification of the genetic basis for these traits and the relationship between them is of great practical significance for achieving ideal plant architecture and high photosynthetic efficiency for improved yield. RESULTS: Here, we undertook a large-scale linkage mapping study using three mapping populations to determine the genetic interplay between soybean leaf-related traits and chlorophyll content across two environments. Correlation analysis revealed a significant negative correlation between leaf size and shape, while both traits were positively correlated with chlorophyll content. This phenotypic relationship was verified across the three mapping populations as determined by principal component analysis, suggesting that these traits are under the control of complex and interrelated genetic components. The QTLs for leaf-related traits and chlorophyll are partly shared, which further supports the close genetic relationship between the two traits. The largest-effect major loci, q20, was stably identified across all population and environments and harbored the narrow leaflet gene Gm-JAG1 (Ln/ln), which is a key regulator of leaflet shape in soybean. CONCLUSION: Our results uncover several major QTLs (q4-1, q4-2, q11, q13, q18 and q20) and its candidate genes specific or common to leaf-related traits and chlorophyll, and also show a complex epistatic interaction between the two traits. The SNP markers closely linked to these valuable QTLs could be used for molecular design breeding with improved plant architecture, photosynthetic capacity and even yield.

Genome-Wide Analysis Reveals Dynamic Epigenomic Differences in Soybean Response to Low-Phosphorus Stress.

Low-phosphorus (low-P) stress has a significant limiting effect on crop yield and quality. Although the molecular mechanisms of the transcriptional level responsible for the low-P stress response have been studied in detail, the underlying epigenetic mechanisms in gene regulation remain largely unknown. In this study, we evaluated the changes in DNA methylation, gene expression and small interfering RNAs (siRNAs) abundance genome-wide in response to low-P stress in two representative soybean genotypes with different P-efficiencies. The DNA methylation levels were slightly higher under low-P stress in both genotypes. Integrative methylation and transcription analysis suggested a complex regulatory relationship between DNA methylation and gene expression that may be associated with the type, region, and extent of methylation. Association analysis of low-P-induced differential methylation and gene expression showed that transcriptional alterations of a small part of genes were associated with methylation changes. Dynamic methylation alterations in transposable element (TE) regions in the CHH methylation context correspond with changes in the amount of siRNA under low-P conditions, indicating an important role of siRNAs in modulating TE activity by guiding CHH methylation in TE regions. Together, these results could help to elucidate the epigenetic regulation mechanisms governing the responses of plants to abiotic stresses.

Transcriptome-wide identification of novel circular RNAs in soybean in response to low-phosphorus stress.

Low-phosphorus (LP) stress is a major factor limiting the growth and yield of soybean. Circular RNAs (circRNAs) are novel noncoding RNAs that play a crucial role in plant responses to abiotic stress. However, how LP stress mediates the biogenesis of circRNAs in soybean remains unclear. Here, to explore the response mechanisms of circRNAs to LP stress, the roots of two representative soybean genotypes with different P-use efficiency, Bogao (a LP-sensitive genotype) and Nannong 94156 (a LP-tolerant genotype), were used for the construction of RNA sequencing (RNA-seq) libraries and circRNA identification. In total, 371 novel circRNA candidates, including 120 significantly differentially expressed (DE) circRNAs, were identified across different P levels and genotypes. More DE circRNAs were significantly regulated by LP stress in Bogao than in NN94156, suggesting that the tolerant genotype was less affected by LP stress than the sensitive genotype was; in other words, NN94156 may have a better ability to maintain P homeostasis under LP stress. Moreover, a positive correlation was observed between the expression patterns of P stress-induced circRNAs and their circRNA-host genes. Gene Ontology (GO) enrichment analysis of these circRNA-host genes and microRNA (miRNA)-targeted genes indicated that these DE circRNAs were involved mainly in defense responses, ADP binding, nucleoside binding, organic substance catabolic processes, oxidoreductase activity, and signal transduction. Together, our results revealed that LP stress can significantly alter the genome-wide profiles of circRNAs and indicated that the regulation of circRNAs was both genotype and environment specific in response to LP stress. LP-induced circRNAs might provide a rich resource for LP-responsive circRNA candidates for future studies.

Predicting Hospital Readmission: A Joint Ensemble-Learning Model.

Hospital readmission is among the most critical issues in the healthcare system due to its high prevalence and cost. The improvement effort necessitates reliable prediction models which can identify high-risk patients effectively and enable healthcare practitioners to take a strategic approach. Using predictive analytics based on electronic health record (EHR) for hospital readmission is faced with multiple challenges such as high dimensionality and event sparsity of medical codes and the class imbalance. To response to these challenges, an analytical framework is proposed by data-driven approaches using hospital inpatient administrative data from a nationwide healthcare dataset. A joint ensemble-learning model, which combines the modified weight boosting algorithm with stacking algorithm, is developed and validated. Our study first explores the effects of different feature engineering methods, which effectively handles the challenge of medical vector representation and medical vector sparsity. Secondly, ensemble learning with the proposed modified weight boosting algorithm is used to tackle the class imbalance problem and improve predictability. Finally, we provide various misclassification costs by setting different weights for each class during model training. Using the framework with the proposed modified weight boosting algorithm improves overall model performance by 22.7% and recall from 0.726 to the highest of 0.891 comparing to the benchmark models. Hospital practitioners can also utilize the prediction results of different cost weight to select the most suitable readmission intervention for patients according to the penalty policy of Centers for Medicare and Medicaid Services (CMS) and the cost trade-off of their hospitals.

Artificial selection on GmOLEO1 contributes to the increase in seed oil during soybean domestication.

Increasing seed oil content is one of the most important breeding goals for soybean due to a high global demand for edible vegetable oil. However, genetic improvement of seed oil content has been difficult in soybean because of the complexity of oil metabolism. Determining the major variants and molecular mechanisms conferring oil accumulation is critical for substantial oil enhancement in soybean and other oilseed crops. In this study, we evaluated the seed oil contents of 219 diverse soybean accessions across six different environments and dissected the underlying mechanism using a high-resolution genome-wide association study (GWAS). An environmentally stable quantitative trait locus (QTL), GqOil20, significantly associated with oil content was identified, accounting for 23.70% of the total phenotypic variance of seed oil across multiple environments. Haplotype and expression analyses indicate that an oleosin protein-encoding gene (GmOLEO1), colocated with a leading single nucleotide polymorphism (SNP) from the GWAS, was significantly correlated with seed oil content. GmOLEO1 is predominantly expressed during seed maturation, and GmOLEO1 is localized to accumulated oil bodies (OBs) in maturing seeds. Overexpression of GmOLEO1 significantly enriched smaller OBs and increased seed oil content by 10.6% compared with those of control seeds. A time-course transcriptomics analysis between transgenic and control soybeans indicated that GmOLEO1 positively enhanced oil accumulation by affecting triacylglycerol metabolism. Our results also showed that strong artificial selection had occurred in the promoter region of GmOLEO1, which resulted in its high expression in cultivated soybean relative to wild soybean, leading to increased seed oil accumulation. The GmOLEO1 locus may serve as a direct target for both genetic engineering and selection for soybean oil improvement.

Genome-Wide Association Studies of Photosynthetic Traits Related to Phosphorus Efficiency in Soybean.

Photosynthesis is the basis of plant growth and development, and is seriously affected by low phosphorus (P) stress. However, few studies have reported for the genetic foundation of photosynthetic response to low P stress in soybean. To address this issue, 219 soybean accessions were genotyped by 292,035 high-quality single nucleotide polymorphisms (SNPs) and phenotyped under normal and low P conditions in 2015 and 2016. These datasets were used to identify quantitative trait nucleotides (QTNs) for photosynthesis-related traits using mrMLM, ISIS EM-BLASSO, pLARmEB, FASTmrMLM, FASTmrEMMA, and pKWmEB methods. As a result, 159 QTNs within 31 genomic regions were found to be associated with four photosynthesis-related traits under different P stress conditions. Among the 31 associated regions, five (q7-2, q8-1, q9, q13-1, and q20-2) were detected commonly under both normal and low P conditions, indicating the insensitivity of these candidate genes to low P stress; five were detected only under normal P condition, indicating the sensitivity of these candidate genes to low P stress; six were detected only under low P condition, indicating the tolerantness of these candidate genes to low P stress; 20 were reported in previous studies. Around the 159 QTNs, 52 candidate genes were mined. These results provide the important information for marker-assisted breeding in soybean and further reveal the basis for the application of P tolerance to photosynthetic capacity.

Physiological and Proteomics Analyses Reveal Low-Phosphorus Stress Affected the Regulation of Photosynthesis in Soybean.

Previous studies have revealed a significant genetic relationship between phosphorus (P)-efficiency and photosynthesis-related traits in soybean. In this study, we used proteome profiling in combination with expression analysis, biochemical investigations, and leaf ultrastructural analysis to identify the underlying physiological and molecular responses. The expression analysis and ultrastructural analysis showed that the photosynthesis key genes were decreased at transcript levels and the leaf mesophyll and chloroplast were severely damaged after low-P stress. Approximately 55 protein spots showed changes under low-P condition by mass spectrometry, of which 17 were involved in various photosynthetic processes. Further analysis revealed the depression of photosynthesis caused by low-P stress mainly involves the regulation of leaf structure, adenosine triphosphate (ATP) synthesis, absorption and transportation of CO2, photosynthetic electron transport, production of assimilatory power, and levels of enzymes related to the Calvin cycle. In summary, our findings indicated that the existence of a stringent relationship between P supply and the genomic control of photosynthesis in soybean. As an important strategy to protect soybean photosynthesis, P could maintain the stability of cell structure, up-regulate the enzymes' activities, recover the process of photosystem II (PSII), and induce the expression of low-P responsive genes and proteins.

Contributing factors of elective surgical case cancellation: a retrospective cross-sectional study at a single-site hospital.

BACKGROUND: Case cancellation (CC) has significant impact on the efficiency of operating room (OR) management, which can be mitigated by taking preventive measures. In this study, using the data of the West China Hospital (WCH), we identified the effect of contributing factors and recommended hospital interventions to facilitate CC prevention. METHOD: We conducted a retrospective review of 11,331 elective surgical cases from January 1 to December 31, 2014. CC reasons were grouped into six categories. The methods of descriptive statistics and hypothesis test were used to identify the effect of factors. RESULTS: CC reasons (746) were divided into six broad categories: workup related (preoperative diagnostic assessment issues or sudden medical condition changes) (25.8%), non-specified reasons (25.8%), coordination issues (15.1%), patient related (13.0%), support system issues (11.8%), and doctor related (8.5%). The types of the most frequently performed operations are identified, as well as their CRs. The cancellation rate (CR) of males was lower than that of females (16.7% to 18.3%). A large difference in the CRs existed among doctors. The CR on Monday was significantly higher than the other four weekdays. CONCLUSIONS: Workup related issues, the types of procedures, the menstrual cycle of females, highly imbalanced CRs among doctors, and tendency of cancellation on Monday are the major identified factors, which account for a significant amount of preventable cancellations. It is suggested that corresponding hospital interventions can reduce CR and improve OR efficiency, including maintaining effective coordination, good communication and well-designed preoperative assessment processes, focusing on the type of procedures which are more time-consuming and complex, paying special attention to the physiology of females during surgery planning, taking measures to reduce CR of top eight doctors, and improving surgery scheduling on Monday.