The application of metagenomics, radiomics and machine learning for diagnosis of sepsis.

Introduction: Sepsis poses a serious threat to individual life and health. Early and accessible diagnosis and targeted treatment are crucial. This study aims to explore the relationship between microbes, metabolic pathways, and blood test indicators in sepsis patients and develop a machine learning model for clinical diagnosis. Methods: Blood samples from sepsis patients were sequenced. α-diversity and ß-diversity analyses were performed to compare the microbial diversity between the sepsis group and the normal group. Correlation analysis was conducted on microbes, metabolic pathways, and blood test indicators. In addition, a model was developed based on medical records and radiomic features using machine learning algorithms. Results: The results of α-diversity and ß-diversity analyses showed that the microbial diversity of sepsis group was significantly higher than that of normal group (p < 0.05). The top 10 microbial abundances in the sepsis and normal groups were Vitis vinifera, Mycobacterium canettii, Solanum pennellii, Ralstonia insidiosa, Ananas comosus, Moraxella osloensis, Escherichia coli, Staphylococcus hominis, Camelina sativa, and Cutibacterium acnes. The enriched metabolic pathways mainly included Protein families: genetic information processing, Translation, Protein families: signaling and cellular processes, and Unclassified: genetic information processing. The correlation analysis revealed a significant positive correlation (p < 0.05) between IL-6 and Membrane transport. Metabolism of other amino acids showed a significant positive correlation (p < 0.05) with Cutibacterium acnes, Ralstonia insidiosa, Moraxella osloensis, and Staphylococcus hominis. Ananas comosus showed a significant positive correlation (p < 0.05) with Poorly characterized and Unclassified: metabolism. Blood test-related indicators showed a significant negative correlation (p < 0.05) with microorganisms. Logistic regression (LR) was used as the optimal model in six machine learning models based on medical records and radiomic features. The nomogram, calibration curves, and AUC values demonstrated that LR performed best for prediction. Discussion: This study provides insights into the relationship between microbes, metabolic pathways, and blood test indicators in sepsis. The developed machine learning model shows potential for aiding in clinical diagnosis. However, further research is needed to validate and improve the model.

Osteocyte-derived exosomes regulate the DLX2/wnt pathway to alleviate osteoarthritis by mediating cartilage repair.

BACKGROUND: Chondrocyte viability, apoptosis, and migration are closely related to cartilage injury in osteoarthritis (OA) joints. Exosomes are identified as potential therapeutic agents for OA. OBJECTIVE: This study aimed to investigate the role of exosomes derived from osteocytes in OA, particularly focusing on their effects on cartilage repair and molecular mechanisms. METHODS: An injury cell model was established by treating chondrocytes with IL-1ß. Cartilage repair was evaluated using cell counting kit-8, flow cytometry, scratch test, and Western Blot. Molecular mechanisms were analyzed using quantitative real-time PCR, bioinformatic analysis, and Western Blot. An OA mouse model was established to explore the role of exosomal DLX2 in vivo. RESULTS: Osteocyte-released exosomes promoted cell viability and migration, and inhibited apoptosis and extracellular matrix (ECM) deposition. Moreover, exosomes upregulated DLX2 expression, and knockdown of DLX2 activated the Wnt pathway. Additionally, exosomes attenuated OA in mice by transmitting DLX2. CONCLUSION: Osteocyte-derived exosomal DLX2 alleviated IL-1ß-induced cartilage repair and inactivated the Wnt pathway, thereby alleviating OA progression. The findings suggested that osteocyte-derived exosomes may hold promise as a treatment for OA.

Development of rapid nucleic acid testing techniques for common respiratory infectious diseases in the Chinese population.

Background: Most respiratory viruses can cause serious lower respiratory diseases at any age. Therefore, timely and accurate identification of respiratory viruses has become even more important. This study focused on the development of rapid nucleic acid testing techniques for common respiratory infectious diseases in the Chinese population. Methods: Multiplex fluorescent quantitative polymerase chain reaction (PCR) assays were developed and validated for the detection of respiratory pathogens including the novel coronavirus (SARS-CoV-2), influenza A virus (FluA), parainfluenza virus (PIV), and respiratory syncytial virus (RSV). Results: The assays demonstrated high specificity and sensitivity, allowing for the simultaneous detection of multiple pathogens in a single reaction. These techniques offer a rapid and reliable method for screening, diagnosis, and monitoring of respiratory pathogens. Conclusion: The implementation of these techniques might contribute to effective control and prevention measures, leading to improved patient care and public health outcomes in China. Further research and validation are needed to optimize and expand the application of these techniques to a wider range of respiratory pathogens and to enhance their utility in clinical and public health settings.

Association of fresh vegetable and salt-preserved vegetable consumptions with estimated glomerular filtration rate.

OBJECTIVE: This study aimed to investigate the relationship between the consumption of fresh and salt-preserved vegetables and the estimated glomerular filtration rate (eGFR), which requires further research. METHODS: For this purpose, the data of those subjects who participated in the 2011-2012 and 2014 surveys of the Chinese Longitudinal Healthy Longevity Survey (CLHLS) and had biomarker data were selected. Fresh and salt-preserved vegetable consumptions were assessed at each wave. eGFR was assessed using the Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) equation based on plasma creatinine. Furthermore, a linear mixed model was used to evaluate associations between fresh/salt-preserved vegetables and eGFR. RESULTS: The results indicated that the median baseline and follow-up eGFRs were 72.47 mL/min/1.73 m² and 70.26 mL/min/1.73 m², respectively. After applying adjusted linear mixed model analysis to the data, the results revealed that compared to almost daily intake, occasional consumption of fresh vegetables was associated with a lower eGFR (ß=-2.23, 95% CI: -4.23, -0.23). Moreover, rare or no consumption of salt-preserved vegetables was associated with a higher eGFR (ß = 1.87, 95% CI: 0.12, 3.63) compared to individuals who consumed salt-preserved vegetables daily. CONCLUSION: Fresh vegetable consumption was direct, whereas intake of salt-preserved vegetables was inversely associated with eGFR among the oldest subjects, supporting the potential benefits of diet-rich fresh vegetables for improving eGFR.

Deubiquitinase USP29 correlates RORγt expression and its association with thymoma myasthenia gravis.

OBJECTIVE: The objective of this study was to examine the expression of deubiquitylases USP29 in thymomas with myasthenia gravis (MG) and research associated immunological processes. METHODS: 69 MG patients with thymomas, 21 thymoma patients without MG, and 31 healthy controls were classified into three groups (categories): group with MG-associated thymoma (MG-T), group with non-MG-associated thymoma (NMG-T), and group with healthy controls (HC). In thymomas, the mRNA and protein levels of RORγt and USP29 were examined by real-time reverse transcription polymerase chain reaction (real-time RT-PCR) and western blotting. Th17 cell counts in MG patients with thymomas were investigated by flow cytometry. RESULTS: In MG-related thymomas, the mRNA and protein levels of deubiquitylases USP29 were substantially elevated. USP29 post-transcriptionally regulated RORγt. In MG patients with thymomas, the expression of USP29 was positively linked to the RORγt expression and Th17 cell frequency. CONCLUSION: This work exhibited that the elevated USP29 enhanced RORγt expression, which in turn affected the Th17 cell growth in thymomatous MG. Our data suggest that USP29 might take part in the regulation of RORγt expression and Th17 cell generation and constitute an innovative regulatory function for USP29 in autoimmune disease.

Explainable Dynamic Multimodal Variational Autoencoder for the Prediction of Patients With Suspected Central Precocious Puberty.

Central precocious puberty (CPP) is the most common type of precocious puberty and has a significant effect on children. A gonadotropin-releasing hormone (GnRH)-stimulation test is the gold standard for confirming CPP. This test, however, is costly and unpleasant for patients. Therefore, it is critical to developing alternative methods for CPP diagnosis in order to alleviate patient suffering. This study aims to develop an artificial intelligence (AI) diagnostic system for predicting response to the GnRH-stimulation test using data from laboratory tests, electronic health records (EHRs), and pelvic ultrasonography and left-hand radiography reports. The challenges are in integrating these multimodal features into a comprehensive deep learning model in order to achieve an accurate diagnosis while also accounting for the missing or incomplete modalities. To begin, we developed a dynamic multimodal variational autoencoder (DMVAE) that can exploit intrinsic correlations between different modalities to impute features for missing modalities. Next, we combined features from all modalities to predict the outcome of a CPP diagnosis. The experimental results (AUROC 0.9086) demonstrate that our DMVAE model is superior to standard methods. Additionally, we showed that by setting appropriate operating thresholds, clinicians could diagnose about two-thirds of patients with confidence (1.0 specificity). Only about one-third of patients require confirmation of their diagnoses using GnRH (or GnRH analog)-stimulation tests. To interpret the results, we implemented an explainer Shapley additive explanation (SHAP) to analyze the local and global feature attributions.

A model for predicting 7-day pressure injury outcomes in paediatric patients: A machine learning approach.

AIMS: We sought to explore factors associated with early pressure injury progression and build a model for predicting these outcomes using a machine learning approach. DESIGN: A retrospective cohort study. METHODS: In this study, we recruited paediatric patients, with hospital-acquired stage I pressure injury or suspected deep tissue injury, who met the inclusion criteria between 1 January 2015-31 October 2018. We divided patients into two groups, namely healing or delayed healing, then followed them up for 7 days. We analysed patient pressure injury characteristics, demographics, treatment, clinical situation, vital signs, and blood test results, then build prediction models using the Random Forest and eXtreme Gradient Boosting approaches. RESULTS: The best prediction model, trained and tested using Random Forest with 10 variables, achieved an accuracy, sensitivity, specificity, and area under the curve of 0.82 (SD 0.06), 0.80 (SD 0.08), 0.84 (SD 0.08), and 0.89 (SD 0.06), respectively. The most contributing variables, in order of importance, included serum creatinine, red blood cell, and haematocrit. CONCLUSION: An awareness of specific conditions and areas that could lead to delayed healing pressure injury in paediatric patients is needed. IMPACT: This evidence-based prediction model, coupled with the aforementioned clinical indicators, is expected to enhance early prediction of outcomes in paediatric patients thereby improve the quality of care and the outcome of children with PIs.

Machine learning identifies girls with central precocious puberty based on multisource data.

OBJECTIVE: The study aimed to develop simplified diagnostic models for identifying girls with central precocious puberty (CPP), without the expensive and cumbersome gonadotropin-releasing hormone (GnRH) stimulation test, which is the gold standard for CPP diagnosis. MATERIALS AND METHODS: Female patients who had secondary sexual characteristics before 8 years old and had taken a GnRH analog (GnRHa) stimulation test at a medical center in Guangzhou, China were enrolled. Data from clinical visiting, laboratory tests, and medical image examinations were collected. We first extracted features from unstructured data such as clinical reports and medical images. Then, models based on each single-source data or multisource data were developed with Extreme Gradient Boosting (XGBoost) classifier to classify patients as CPP or non-CPP. RESULTS: The best performance achieved an area under the curve (AUC) of 0.88 and Youden index of 0.64 in the model based on multisource data. The performance of single-source models based on data from basal laboratory tests and the feature importance of each variable showed that the basal hormone test had the highest diagnostic value for a CPP diagnosis. CONCLUSION: We developed three simplified models that use easily accessed clinical data before the GnRH stimulation test to identify girls who are at high risk of CPP. These models are tailored to the needs of patients in different clinical settings. Machine learning technologies and multisource data fusion can help to make a better diagnosis than traditional methods.

Early and Accurate Prediction of Clinical Response to Methotrexate Treatment in Juvenile Idiopathic Arthritis Using Machine Learning.

Background and Aims: Accurately predicting the response to methotrexate (MTX) in juvenile idiopathic arthritis (JIA) patients before administration is the key point to improve the treatment outcome. However, no simple and reliable prediction model has been identified. Here, we aimed to develop and validate predictive models for the MTX response to JIA using machine learning based on electronic medical record (EMR) before and after administering MTX. Materials and Methods: Data of 362 JIA patients with MTX mono-therapy were retrospectively collected from EMR between January 2008 and October 2018. DAS44/ESR-3 simplified standard was used to evaluate the MTX response. Extreme gradient boosting (XGBoost), support vector machine (SVM), random forest (RF), and logistic regression (LR) algorithms were applied to develop and validate models with 5-fold cross-validation on the randomly split training and test set. Data of 13 patients additionally collected were used for external validation. Results: The XGBoost screened out the optimal 10 pre-administration features and 6 mix-variables. The XGBoost established the best model based on the 10 pre-administration variables. The performances were accuracy 91.78%, sensitivity 90.70%, specificity 93.33%, AUC 97.00%, respectively. Similarly, the XGBoost developed a better model based on the 6 mix-variables, whose performances were accuracy 94.52%, sensitivity 95.35%, specificity 93.33%, AUC 99.00%, respectively. Conclusion: Based on common EMR data, we developed two MTX response predictive models with excellent performance in JIA using machine learning. These models can predict the MTX efficacy early and accurately, which provides powerful decision support for doctors to make or adjust therapeutic scheme before or after treatment.

Development of Prediction Models Using Machine Learning Algorithms for Girls with Suspected Central Precocious Puberty: Retrospective Study.

BACKGROUND: Central precocious puberty (CPP) in girls seriously affects their physical and mental development in childhood. The method of diagnosis-gonadotropin-releasing hormone (GnRH)-stimulation test or GnRH analogue (GnRHa)-stimulation test-is expensive and makes patients uncomfortable due to the need for repeated blood sampling. OBJECTIVE: We aimed to combine multiple CPP-related features and construct machine learning models to predict response to the GnRHa-stimulation test. METHODS: In this retrospective study, we analyzed clinical and laboratory data of 1757 girls who underwent a GnRHa test in order to develop XGBoost and random forest classifiers for prediction of response to the GnRHa test. The local interpretable model-agnostic explanations (LIME) algorithm was used with the black-box classifiers to increase their interpretability. We measured sensitivity, specificity, and area under receiver operating characteristic (AUC) of the models. RESULTS: Both the XGBoost and random forest models achieved good performance in distinguishing between positive and negative responses, with the AUC ranging from 0.88 to 0.90, sensitivity ranging from 77.91% to 77.94%, and specificity ranging from 84.32% to 87.66%. Basal serum luteinizing hormone, follicle-stimulating hormone, and insulin-like growth factor-I levels were found to be the three most important factors. In the interpretable models of LIME, the abovementioned variables made high contributions to the prediction probability. CONCLUSIONS: The prediction models we developed can help diagnose CPP and may be used as a prescreening tool before the GnRHa-stimulation test.

Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence.

Artificial intelligence (AI)-based methods have emerged as powerful tools to transform medical care. Although machine learning classifiers (MLCs) have already demonstrated strong performance in image-based diagnoses, analysis of diverse and massive electronic health record (EHR) data remains challenging. Here, we show that MLCs can query EHRs in a manner similar to the hypothetico-deductive reasoning used by physicians and unearth associations that previous statistical methods have not found. Our model applies an automated natural language processing system using deep learning techniques to extract clinically relevant information from EHRs. In total, 101.6 million data points from 1,362,559 pediatric patient visits presenting to a major referral center were analyzed to train and validate the framework. Our model demonstrates high diagnostic accuracy across multiple organ systems and is comparable to experienced pediatricians in diagnosing common childhood diseases. Our study provides a proof of concept for implementing an AI-based system as a means to aid physicians in tackling large amounts of data, augmenting diagnostic evaluations, and to provide clinical decision support in cases of diagnostic uncertainty or complexity. Although this impact may be most evident in areas where healthcare providers are in relative shortage, the benefits of such an AI system are likely to be universal.

Comprehensive Analysis of Differentially Expressed Unigenes under NaCl Stress in Flax (Linum usitatissimum L.) Using RNA-Seq.

Flax (Linum usitatissimum L.) is an important industrial crop that is often cultivated on marginal lands, where salt stress negatively affects yield and quality. High-throughput RNA sequencing (RNA-seq) using the powerful Illumina platform was employed for transcript analysis and gene discovery to reveal flax response mechanisms to salt stress. After cDNA libraries were constructed from flax exposed to water (negative control) or salt (100 mM NaCl) for 12 h, 24 h or 48 h, transcription expression profiles and cDNA sequences representing expressed mRNA were obtained. A total of 431,808,502 clean reads were assembled to form 75,961 unigenes. After ruling out short-length and low-quality sequences, 33,774 differentially expressed unigenes (DEUs) were identified between salt-stressed and unstressed control (C) flax. Of these DEUs, 3669, 8882 and 21,223 unigenes were obtained from flax exposed to salt for 12 h (N1), 24 h (N2) and 48 h (N4), respectively. Gene function classification and pathway assignments of 2842 DEUs were obtained by comparing unigene sequences to information within public data repositories. qRT-PCR of selected DEUs was used to validate flax cDNA libraries generated for various durations of salt exposure. Based on transcriptome sequences, 1777 EST-SSRs were identified of which trinucleotide and dinucleotide repeat microsatellite motifs were most abundant. The flax DEUs and EST-SSRs identified here will serve as a powerful resource to better understand flax response mechanisms to salt exposure for development of more salt-tolerant varieties of flax.

QTL Mapping of Fiber-Related Traits Based on a High-Density Genetic Map in Flax (Linum usitatissimum L.).

A genetic map is an important and valuable tool for quantitative trait locus (QTL) mapping, marker-assisted selection (MAS)-based breeding, and reference-assisted chromosome assembly. In this study, 112 F2 plants from a cross between Linum usitatissimum L. "DIANE" and "NY17" and parent plants were subjected to high-throughput sequencing and specific-locus amplified fragment (SLAF) library construction. After preprocessing, 61.64 Gb of raw data containing 253.71 Mb paired-end reads, each 101 bp in length, were obtained. A total of 192,797 SLAFs were identified, of which 23,115 were polymorphic, with a polymorphism rate of 11.99%. Finally, 2,339 SLAFs were organized into a linkage map consisting of 15 linkage groups (LGs). The total length of the genetic map was 1483.25 centimorgans (cM) and the average distance between adjacent markers was 0.63 cM. Combined with flax chromosome-scale pseudomolecules, 12 QTLs associating with 6 flax fiber-related traits were mapped on the chromosomal scaffolds. This high-density genetic map of flax should serve as a foundation for flax fine QTL mapping, draft genome assembly, and MAS-guided breeding. Ultimately, the genomic regions identified in this research could potentially be valuable for improving flax fiber cultivars, as well as for identification of candidate genes involved in flax fiber formation processes. SIGNIFICANCE STATEMENT: A high-density genetic map of flax was constructed, and QTLs were identified on the sequence scaffolds to be interrelated with fiber-related traits. The results of this study will not only provide a platform for gene/QTL fine mapping, map-based gene isolation, and molecular breeding for flax, but also provide a reference to help position sequence scaffolds on the physical map and assist in the process of assembling the flax genome sequence.

Developing a Machine Learning System for Identification of Severe Hand, Foot, and Mouth Disease from Electronic Medical Record Data.

Children of severe hand, foot, and mouth disease (HFMD) often present with same clinical features as those of mild HFMD during the early stage, yet later deteriorate rapidly with a fulminant disease course. Our goal was to: (1) develop a machine learning system to automatically identify cases with high risk of severe HFMD at the time of admission; (2) compare the effectiveness of the new system with the existing risk scoring system. Data on 2,532 HFMD children admitted between March 2012 and July 2015, were collected retrospectively from a medical center in China. By applying a holdout strategy and a 10-fold cross validation method, we developed four models with the random forest algorithm using different variable sets. The prediction system HFMD-RF based on the model of 16 variables from both the structured and unstructured data, achieved 0.824 sensitivity, 0.931 specificity, 0.916 accuracy, and 0.916 area under the curve in the independent test set. Most remarkably, HFMD-RF offers significant gains with respect to the commonly used pediatric critical illness score in clinical practice. As all the selected risk factors can be easily obtained, HFMD-RF might prove to be useful for reductions in mortality and complications of severe HFMD.

Interrelationship of rotavirus infection and Creatine Kinase-MB isoenzyme levels in children hospitalized with acute gastroenteritis in Guangzhou, China, 2012-2015.

Elevated levels of Creatine Kinase-MB (CK-MB) Isoenzyme are a common phenomenon among rotavirus (RV) diarrhea. However, few studies have addressed this issue using large sample size. In current study, 1,118 children (age <5 years) hospitalized with diarrhea in Guangzhou Women and Children's Medical Center from 2012 to 2015 were finally included. Changing pattern of CK-MB and its relationship with RV-infection were analyzed and characterized. Multivariate linear regression models showed that RV-positive cases had a 28% rise in CK-MB compared to RV-negative cases (OR = 1.28, 95% CI: 1.15 to 1.41, P < 0.01) after controlling for age, gender, season of admission, and weight. The pattern of change showed that CK-MB level of RV-positive group started to rise immediately at the 1st day of diarrhea, reached the peak on days 2 to 4, declined during 4-9 days, and then reached a relatively stable level when compared to the RV-negative group. Mediation analyses showed that indirect effect of RV infection on the increase of CK-MB via Vesikari score was significant (ß = 8.01, P < 0.01), but direct effect was not (ß = 9.96, P = 0.12). Thus, elevated CK-MB value is a common finding in RV-infection and completely mediated by the severity of diarrhea. CK-MB monitoring may help to identify children with more severe viral infection.

Machine learning applications for prediction of relapse in childhood acute lymphoblastic leukemia.

The prediction of relapse in childhood acute lymphoblastic leukemia (ALL) is a critical factor for successful treatment and follow-up planning. Our goal was to construct an ALL relapse prediction model based on machine learning algorithms. Monte Carlo cross-validation nested by 10-fold cross-validation was used to rank clinical variables on the randomly split training sets of 336 newly diagnosed ALL children, and a forward feature selection algorithm was employed to find the shortest list of most discriminatory variables. To enable an unbiased estimation of the prediction model to new patients, besides the split test sets of 150 patients, we introduced another independent data set of 84 patients to evaluate the model. The Random Forest model with 14 features achieved a cross-validation accuracy of 0.827 ± 0.031 on one set and an accuracy of 0.798 on the other, with the area under the curve of 0.902 ± 0.027 and 0.904, respectively. The model performed well across different risk-level groups, with the best accuracy of 0.829 in the standard-risk group. To our knowledge, this is the first study to use machine learning models to predict childhood ALL relapse based on medical data from Electronic Medical Record, which will further facilitate stratification treatments.