Search

The traditional complications of diabetes are well known and continue to pose a considerable burden to millions of people with diabetes mellitus (DM). With the continuous accumulation of medical data and technological advances, artificial intelligence has shown great potential and advantages in the prediction, diagnosis, and treatment of DM. When DM is diagnosed, some subjective factors and diagnostic methods of doctors will have an impact on the diagnostic results, so the use of artificial intelligence for fast and effective early prediction of DM patients can provide decision-making support to doctors and give more accurate treatment services to patients in time, which is of great clinical medical significance and practical significance. In this paper, an adaptive Stacking ensemble model is proposed based on the theory of “error-ambiguity decomposition,” which can adaptively select the base classifiers from the pre-selected models. The adaptive Stacking ensemble model proposed in this paper is compared with KNN, SVM, RF, LR, DT, GBDT, XGBoost, LightGBM, CatBoost, MLP and traditional Stacking ensemble models. The results showed that the adaptive Stacking ensemble model achieved the best performance in five evaluation metrics: accuracy, precision, recall, F1 value and AUC value, which were 0.7559, 0.7286, 0.8132, 0.7686 and 0.8436. The model can effectively predict DM patients and provide a reference value for the screening and diagnosis of clinical DM.

Metagenomics, Metabolomics, and Metaproteomics have significantly advanced our knowledge of microbial communities by providing culture-independent insights into their composition and functional potential. However, a critical challenge in this field is the lack of standard and comprehensive metadata associated with raw data, hindering the ability to perform robust data stratifications and consider confounding factors. In this comprehensive review, we categorize publicly available microbiome data into five types: shotgun sequencing, amplicon sequencing, metatranscriptomic, metabolomic, and metaproteomic data. We explore the importance of metadata for data reuse and address the challenges in collecting standardized metadata. We also, assess the limitations in metadata collection of existing public repositories collecting metagenomic data. This review emphasizes the vital role of metadata in interpreting and comparing datasets and highlights the need for standardized metadata protocols to fully leveragemetagenomic data's potential. Furthermore, we explore future directions of implementation of Machine Learning (ML) in metadata retrieval, offering promising avenues for a deeper understanding of microbial communities and their ecological roles. Leveraging these tools will enhance our insights into microbial functional capabilities and ecological dynamics in diverse ecosystems. Finally, we emphasize the crucial metadata role in ML models development. [ABSTRACT FROM AUTHOR]

Introduction: Predictive models have been used to aid early diagnosis of PCOS, though existing models are based on small sample sizes and limited to fertility clinic populations. We built a predictive model using machine learning algorithms based on an outpatient population at risk for PCOS to predict risk and facilitate earlier diagnosis, particularly among those who meet diagnostic criteria but have not received a diagnosis. Methods: This is a retrospective cohort study from a SafetyNet hospital's electronic health records (EHR) from 2003-2016. The study population included 30,601 women aged 18-45 years without concurrent endocrinopathy who had any visit to Boston Medical Center for primary care, obstetrics and gynecology, endocrinology, family medicine, or general internal medicine. Four prediction outcomes were assessed for PCOS. The first outcome was PCOS ICD-9 diagnosis with additional model outcomes of algorithm-defined PCOS. The latter was based on Rotterdam criteria and merging laboratory values, radiographic imaging, and ICD data from the EHR to define irregular menstruation, hyperandrogenism, and polycystic ovarian morphology on ultrasound. Results: We developed predictive models using four machine learning methods: logistic regression, supported vector machine, gradient boosted trees, and random forests. Hormone values (follicle-stimulating hormone, luteinizing hormone, estradiol, and sex hormone binding globulin) were combined to create a multilayer perceptron score using a neural network classifier. Prediction of PCOS prior to clinical diagnosis in an out-of-sample test set of patients achieved an average AUC of 85%, 81%, 80%, and 82%, respectively in Models I, II, III and IV. Significant positive predictors of PCOS diagnosis across models included hormone levels and obesity; negative predictors included gravidity and positive bHCG. Conclusion: Machine learning algorithms were used to predict PCOS based on a large at-risk population. This approach may guide early detection of PCOS within EHR-interfaced populations to facilitate counseling and interventions that may reduce long-term health consequences. Our model illustrates the potential benefits of an artificial intelligence-enabled provider assistance tool that can be integrated into the EHR to reduce delays in diagnosis. However, model validation in other hospital-based populations is necessary. [ABSTRACT FROM AUTHOR]

IntroductionOsteoporosis, characterized by low bone mineral density (BMD), is an increasingly serious public health issue. So far, several traditional regression models and machine learning (ML) algorithms have been proposed for predicting osteoporosis risk. However, these models have shown relatively low accuracy in clinical implementation. Recently proposed deep learning (DL) approaches, such as deep neural network (DNN), which can discover knowledge from complex hidden interactions, offer a new opportunity to improve predictive performance. In this study, we aimed to assess whether DNN can achieve a better performance in osteoporosis risk prediction.MethodsBy utilizing hip BMD and extensive demographic and routine clinical data of 8,134 subjects with age more than 40 from the Louisiana Osteoporosis Study (LOS), we developed and constructed a novel DNN framework for predicting osteoporosis risk and compared its performance in osteoporosis risk prediction with four conventional ML models, namely random forest (RF), artificial neural network (ANN), k-nearest neighbor (KNN), and support vector machine (SVM), as well as a traditional regression model termed osteoporosis self-assessment tool (OST). Model performance was assessed by area under ‘receiver operating curve’ (AUC) and accuracy.ResultsBy using 16 discriminative variables, we observed that the DNN approach achieved the best predictive performance (AUC = 0.848) in classifying osteoporosis (hip BMD T-score ≤ −1.0) and non-osteoporosis risk (hip BMD T-score > −1.0) subjects, compared to the other approaches. Feature importance analysis showed that the top 10 most important variables identified by the DNN model were weight, age, gender, grip strength, height, beer drinking, diastolic pressure, alcohol drinking, smoke years, and economic level. Furthermore, we performed subsampling analysis to assess the effects of varying number of sample size and variables on the predictive performance of these tested models. Notably, we observed that the DNN model performed equally well (AUC = 0.846) even by utilizing only the top 10 most important variables for osteoporosis risk prediction. Meanwhile, the DNN model can still achieve a high predictive performance (AUC = 0.826) when sample size was reduced to 50% of the original dataset.ConclusionIn conclusion, we developed a novel DNN model which was considered to be an effective algorithm for early diagnosis and intervention of osteoporosis in the aging population.

Metagenomics, Metabolomics, and Metaproteomics have significantly advanced our knowledge of microbial communities by providing culture-independent insights into their composition and functional potential. However, a critical challenge in this field is the lack of standard and comprehensive metadata associated with raw data, hindering the ability to perform robust data stratifications and consider confounding factors. In this comprehensive review, we categorize publicly available microbiome data into five types: shotgun sequencing, amplicon sequencing, metatranscriptomic, metabolomic, and metaproteomic data. We explore the importance of metadata for data reuse and address the challenges in collecting standardized metadata. We also, assess the limitations in metadata collection of existing public repositories collecting metagenomic data. This review emphasizes the vital role of metadata in interpreting and comparing datasets and highlights the need for standardized metadata protocols to fully leverage metagenomic data's potential. Furthermore, we explore future directions of implementation of Machine Learning (ML) in metadata retrieval, offering promising avenues for a deeper understanding of microbial communities and their ecological roles. Leveraging these tools will enhance our insights into microbial functional capabilities and ecological dynamics in diverse ecosystems. Finally, we emphasize the crucial metadata role in ML models development.

IntroductionPredictive models have been used to aid early diagnosis of PCOS, though existing models are based on small sample sizes and limited to fertility clinic populations. We built a predictive model using machine learning algorithms based on an outpatient population at risk for PCOS to predict risk and facilitate earlier diagnosis, particularly among those who meet diagnostic criteria but have not received a diagnosis.MethodsThis is a retrospective cohort study from a SafetyNet hospital’s electronic health records (EHR) from 2003-2016. The study population included 30,601 women aged 18-45 years without concurrent endocrinopathy who had any visit to Boston Medical Center for primary care, obstetrics and gynecology, endocrinology, family medicine, or general internal medicine. Four prediction outcomes were assessed for PCOS. The first outcome was PCOS ICD-9 diagnosis with additional model outcomes of algorithm-defined PCOS. The latter was based on Rotterdam criteria and merging laboratory values, radiographic imaging, and ICD data from the EHR to define irregular menstruation, hyperandrogenism, and polycystic ovarian morphology on ultrasound.ResultsWe developed predictive models using four machine learning methods: logistic regression, supported vector machine, gradient boosted trees, and random forests. Hormone values (follicle-stimulating hormone, luteinizing hormone, estradiol, and sex hormone binding globulin) were combined to create a multilayer perceptron score using a neural network classifier. Prediction of PCOS prior to clinical diagnosis in an out-of-sample test set of patients achieved an average AUC of 85%, 81%, 80%, and 82%, respectively in Models I, II, III and IV. Significant positive predictors of PCOS diagnosis across models included hormone levels and obesity; negative predictors included gravidity and positive bHCG.ConclusionMachine learning algorithms were used to predict PCOS based on a large at-risk population. This approach may guide early detection of PCOS within EHR-interfaced populations to facilitate counseling and interventions that may reduce long-term health consequences. Our model illustrates the potential benefits of an artificial intelligence-enabled provider assistance tool that can be integrated into the EHR to reduce delays in diagnosis. However, model validation in other hospital-based populations is necessary.

The fields of medicine and neuroscience often face challenges in obtaining a sufficient amount of diverse data for training machine learning models. Data augmentation can alleviate this issue by artificially synthesizing new data from existing data. Generative adversarial networks (GANs) provide a promising approach for data augmentation in the context of images and biomarkers. GANs can synthesize high-quality, diverse, and realistic data that can supplement real data in the training process. This study provides an overview of the use of GANs for data augmentation in medicine and neuroscience. The strengths and weaknesses of various GAN models, including deep convolutional GANs (DCGANs) and Wasserstein GANs (WGANs), are discussed. This study also explores the challenges and ways to address them when using GANs for data augmentation in the field of medicine and neuroscience. Future works on this topic are also discussed.

Background: Acute respiratory distress syndrome (ARDS) is the most common cause of organ failure in acute pancreatitis (AP) patients, which associated with high mortality. Specific changes in the gut microbiota have been shown to influence progression of acute pancreatitis. We aimed to determine whether early alterations in the gut microbiota is related to and could predict ARDS occurrence in AP patients. Methods: In this study, we performed 16S rRNA sequencing analysis in 65 AP patients and 20 healthy volunteers. The AP patients were further divided into two groups: 26 AP-ARDS patients and 39 AP-nonARDS patients based on ARDS occurrence during hospitalization. Results: Our results showed that the AP-ARDS patients exhibited specific changes in gut microbiota composition and function as compared to subjects of AP-nonARDS group. Higher abundances of Proteobacteria phylum, Enterobacteriaceae family, Escherichia-Shigella genus, and Klebsiella pneumoniae, but lower abundances of Bifidobacterium genus were found in AP-ARDS group compared with AP-nonARDS groups. Random forest modelling analysis revealed that the Escherichia-shigella genus was effective to distinguish AP-ARDS from AP-nonARDS, which could predict ARDS occurrence in AP patients. Conclusions: Our study revealed that alterations of gut microbiota in AP patients on admission were associated with ARDS occurrence after hospitalization, indicating a potential predictive and pathogenic role of gut microbiota in the development of ARDS in AP patients. [ABSTRACT FROM AUTHOR]

Deep Learning (DL) has been broadly applied to solve big data problems in biomedical fields, which is most successful in image processing. Recently, many DL methods have been applied to analyze genomic studies. However, genomic data usually has too small a sample size to fit a complex network. They do not have common structural patterns like images to utilize pre-trained networks or take advantage of convolution layers. The concern of overusing DL methods motivates us to evaluate DL methods' performance versus popular non-deep Machine Learning (ML) methods for analyzing genomic data with a wide range of sample sizes. In this paper, we conduct a benchmark study using the UK Biobank data and its many random subsets with different sample sizes. The original UK Biobank data has about 500k participants. Each patient has comprehensive patient characteristics, disease histories, and genomic information, i.e., the genotypes of millions of Single-Nucleotide Polymorphism (SNPs). We are interested in predicting the risk of three lung diseases: asthma, COPD, and lung cancer. There are 205,238 participants have recorded disease outcomes for these three diseases. Five prediction models are investigated in this benchmark study, including three non-deep machine learning methods (Elastic Net, XGBoost, and SVM) and two deep learning methods (DNN and LSTM). Besides the most popular performance metrics, such as the F1-score, we promote the hit curve, a visual tool to describe the performance of predicting rare events. We discovered that DL methods frequently fail to outperform non-deep ML in analyzing genomic data, even in large datasets with over 200k samples. The experiment results suggest not overusing DL methods in genomic studies, even with biobank-level sample sizes. The performance differences between DL and non-deep ML decrease as the sample size of data increases. This suggests when the sample size of data is significant, further increasing sample sizes leads to more performance gain in DL methods. Hence, DL methods could be better if we analyze genomic data bigger than this study. [ABSTRACT FROM AUTHOR]

Human gut microbiome is subject to high inter-individual and temporal variability, which complicates building microbiome-based applications, including applications that can be used to improve public health. Categorizing the microbiome profiles into a small number of distinct clusters, such as enterotyping, has been proposed as a solution that can ameliorate these shortcomings. However, the clinical relevance of the enterotypes is poorly characterized despite a few studies marking the potential for using the enterotypes for disease diagnostics and personalized nutrition. To gain a further understanding of the clinical relevance of the enterotypes, we used the Estonian microbiome cohort dataset (n = 2,506) supplemented with diagnoses and drug usage information from electronic health records to assess the possibility of using enterotypes for disease diagnostics, detecting disease subtypes, and evaluating the susceptibility for developing a condition. In addition to the previously established 3-cluster enterotype model, we propose a 5-cluster community type model based on our data, which further separates the samples with extremely high Bacteroides and Prevotella abundances. Collectively, our systematic analysis including 231 phenotypic factors, 62 prevalent diseases, and 33 incident diseases greatly expands the knowledge about the enterotype-specific characteristics; however, the evidence suggesting the practical use of enterotypes in clinical practice remains scarce. [ABSTRACT FROM AUTHOR]

Human gut microbiome is subject to high inter-individual and temporal variability, which complicates building microbiome-based applications, including applications that can be used to improve public health. Categorizing the microbiome profiles into a small number of distinct clusters, such as enterotyping, has been proposed as a solution that can ameliorate these shortcomings. However, the clinical relevance of the enterotypes is poorly characterized despite a few studies marking the potential for using the enterotypes for disease diagnostics and personalized nutrition. To gain a further understanding of the clinical relevance of the enterotypes, we used the Estonian microbiome cohort dataset (n = 2,506) supplemented with diagnoses and drug usage information from electronic health records to assess the possibility of using enterotypes for disease diagnostics, detecting disease subtypes, and evaluating the susceptibility for developing a condition. In addition to the previously established 3-cluster enterotype model, we propose a 5-cluster community type model based on our data, which further separates the samples with extremely high Bacteroides and Prevotella abundances. Collectively, our systematic analysis including 231 phenotypic factors, 62 prevalent diseases, and 33 incident diseases greatly expands the knowledge about the enterotype-specific characteristics; however, the evidence suggesting the practical use of enterotypes in clinical practice remains scarce.

BackgroundArtificial intelligence-based disease prediction models have a greater potential to screen COVID-19 patients than conventional methods. However, their application has been restricted because of their underlying black-box nature.ObjectiveTo addressed this issue, an explainable artificial intelligence (XAI) approach was developed to screen patients for COVID-19.MethodsA retrospective study consisting of 1,737 participants (759 COVID-19 patients and 978 controls) admitted to San Raphael Hospital (OSR) from February to May 2020 was used to construct a diagnosis model. Finally, 32 key blood test indices from 1,374 participants were used for screening patients for COVID-19. Four ensemble learning algorithms were used: random forest (RF), adaptive boosting (AdaBoost), gradient boosting decision tree (GBDT), and extreme gradient boosting (XGBoost). Feature importance from the perspective of the clinical domain and visualized interpretations were illustrated by using local interpretable model-agnostic explanations (LIME) plots.ResultsThe GBDT model [area under the curve (AUC): 86.4%; 95% confidence interval (CI) 0.821–0.907] outperformed the RF model (AUC: 85.7%; 95% CI 0.813–0.902), AdaBoost model (AUC: 85.4%; 95% CI 0.810–0.899), and XGBoost model (AUC: 84.9%; 95% CI 0.803–0.894) in distinguishing patients with COVID-19 from those without. The cumulative feature importance of lactate dehydrogenase, white blood cells, and eosinophil counts was 0.145, 0.130, and 0.128, respectively.ConclusionsEnsemble machining learning (ML) approaches, mainly GBDT and LIME plots, are efficient for screening patients with COVID-19 and might serve as a potential tool in the auxiliary diagnosis of COVID-19. Patients with higher WBC count, higher LDH level, or higher EOT count, were more likely to have COVID-19.

Gestational diabetes mellitus (GDM) is a type of diabetes that usually resolves at the end of the pregnancy but exposes to a higher risk of developing type 2 diabetes mellitus (T2DM). This study aimed to unravel the factors, among those that quantify specific metabolic processes, which determine progression to T2DM by using machine-learning techniques. Classification of women who did progress to T2DM (labeled as PROG, n = 19) vs. those who did not (labeled as NON-PROG, n = 59) progress to T2DM has been performed by using Orange software through a data analysis procedure on a generated data set including anthropometric data and a total of 34 features, extracted through mathematical modeling/methods procedures. Feature selection has been performed through decision tree algorithm and then Naïve Bayes and penalized (L2) logistic regression were used to evaluate the ability of the selected features to solve the classification problem. Performance has been evaluated in terms of area under the operating receiver characteristics (AUC), classification accuracy (CA), precision, sensitivity, specificity, and F1. Feature selection provided six features, and based on them, classification was performed as follows: AUC of 0.795, 0.831, and 0.884; CA of 0.827, 0.813, and 0.840; precision of 0.830, 0.854, and 0.834; sensitivity of 0.827, 0.813, and 0.840; specificity of 0.700, 0.821, and 0.662; and F1 of 0.828, 0.824, and 0.836 for tree algorithm, Naïve Bayes, and penalized logistic regression, respectively. Fasting glucose, age, and body mass index together with features describing insulin action and secretion may predict the development of T2DM in women with a history of GDM. [ABSTRACT FROM AUTHOR]

Gestational diabetes mellitus (GDM) is a type of diabetes that usually resolves at the end of the pregnancy but exposes to a higher risk of developing type 2 diabetes mellitus (T2DM). This study aimed to unravel the factors, among those that quantify specific metabolic processes, which determine progression to T2DM by using machine-learning techniques. Classification of women who did progress to T2DM (labeled as PROG, n = 19) vs. those who did not (labeled as NON-PROG, n = 59) progress to T2DM has been performed by using Orange software through a data analysis procedure on a generated data set including anthropometric data and a total of 34 features, extracted through mathematical modeling/methods procedures. Feature selection has been performed through decision tree algorithm and then Naïve Bayes and penalized (L2) logistic regression were used to evaluate the ability of the selected features to solve the classification problem. Performance has been evaluated in terms of area under the operating receiver characteristics (AUC), classification accuracy (CA), precision, sensitivity, specificity, and F1. Feature selection provided six features, and based on them, classification was performed as follows: AUC of 0.795, 0.831, and 0.884; CA of 0.827, 0.813, and 0.840; precision of 0.830, 0.854, and 0.834; sensitivity of 0.827, 0.813, and 0.840; specificity of 0.700, 0.821, and 0.662; and F1 of 0.828, 0.824, and 0.836 for tree algorithm, Naïve Bayes, and penalized logistic regression, respectively. Fasting glucose, age, and body mass index together with features describing insulin action and secretion may predict the development of T2DM in women with a history of GDM.

In order to realize the early prediction of refractory epilepsy in children, data preprocessing technology was used to improve the data quality, and the detection model of refractory epilepsy in children based on convolutional neural network (CNN) was established. Then, the data in the epilepsy electroencephalography (EEG) signal public data set was used for model training and the diagnosis of refractory epilepsy in children. Moreover, back propagation neural network (BPNN), support vector machine (SVM), XGBoost, gradient boosting decision tree (GBDT), AdaBoost algorithm were introduced for comparison. The results showed that the early prediction accuracy of BP, SVM, XGBoost, GBDT, AdaBoost, and the algorithm in this study for refractory epilepsy in children were 0.745, 0.778, 0.885, 0.846, 0.874, and 0.941, respectively. The sensitivities were 0.81, 0.826, 0.822, 0.84, 0.859, and 0.918, respectively. The specificities were 0.683, 0.696, 0.743, 0.792, 0.84, and 0.905, respectively. The accuracy was 0.707, 0.732, 0.765, 0.802, 0.839, and 0.881, respectively. The recall rates were 0.69, 0.716, 0.753, 0.784, 0.813, and 0.877, respectively. F1 scores were 0.698, 0.724, 0.759, 0.793, 0.826, and 0.879, respectively. Through the comparisons of the above six indicators, the algorithm proposed in this study was significantly higher than other algorithms, suggesting that the proposed algorithm was more accurate in early prediction of refractory epilepsy in children. Analysis of the EEG characteristics and magnetic resonance imaging (MRI) images of refractory epilepsy in children suggested that the MRI images of patients' brains under this algorithm had obvious characteristics. The reason for the prediction error of the algorithm was that the duration of epilepsy was too short or the EEG of the patient didn't change notably during the epileptic seizure. In summary, the prediction method of refractory epilepsy in children based on CNN was accurate, which had broad adoption prospects in assisting clinicians in the examination and diagnosis of refractory epilepsy in children.

In order to realize the early prediction of refractory epilepsy in children, data preprocessing technology was used to improve the data quality, and the detection model of refractory epilepsy in children based on convolutional neural network (CNN) was established. Then, the data in the epilepsy electroencephalography (EEG) signal public data set was used for model training and the diagnosis of refractory epilepsy in children. Moreover, back propagation neural network (BPNN), support vector machine (SVM), XGBoost, gradient boosting decision tree (GBDT), AdaBoost algorithm were introduced for comparison. The results showed that the early prediction accuracy of BP, SVM, XGBoost, GBDT, AdaBoost, and the algorithm in this study for refractory epilepsy in children were 0.745, 0.778, 0.885, 0.846, 0.874, and 0.941, respectively. The sensitivities were 0.81, 0.826, 0.822, 0.84, 0.859, and 0.918, respectively. The specificities were 0.683, 0.696, 0.743, 0.792, 0.84, and 0.905, respectively. The accuracy was 0.707, 0.732, 0.765, 0.802, 0.839, and 0.881, respectively. The recall rates were 0.69, 0.716, 0.753, 0.784, 0.813, and 0.877, respectively. F1 scores were 0.698, 0.724, 0.759, 0.793, 0.826, and 0.879, respectively. Through the comparisons of the above six indicators, the algorithm proposed in this study was significantly higher than other algorithms, suggesting that the proposed algorithm was more accurate in early prediction of refractory epilepsy in children. Analysis of the EEG characteristics and magnetic resonance imaging (MRI) images of refractory epilepsy in children suggested that the MRI images of patients' brains under this algorithm had obvious characteristics. The reason for the prediction error of the algorithm was that the duration of epilepsy was too short or the EEG of the patient didn't change notably during the epileptic seizure. In summary, the prediction method of refractory epilepsy in children based on CNN was accurate, which had broad adoption prospects in assisting clinicians in the examination and diagnosis of refractory epilepsy in children. [ABSTRACT FROM AUTHOR]

A mechanistic model was developed to predict secondary infections of Plasmopara viticola and their severity as influenced by environmental conditions; the model incorporates the processes of sporangia production and survival on downy mildew (DM) lesions, dispersal and deposition, and infection. The model was evaluated against observed data (collected in a 3-year vineyard) for its accuracy to predict periods with no sporangia (i.e., for negative prognosis) or with peaks of sporangia, so that growers can identify periods with no/low risk or high risk. The model increased the probability to correctly predict no sporangia [P(P−O−) = 0.67] by two times compared to the prior probability, with fewer than 3% of the total sporangia found in the vineyard being sampled when not predicted by the model. The model also correctly predicted peaks of sporangia, with only 1 of 40 peaks unpredicted. When evaluated for the negative prognosis of infection periods, the model showed a posterior probability for infection not to occur when not predicted P(P−O−) = 0.87 with only 9 of 108 real infections not predicted; these unpredicted infections were mild, accounting for only 4.4% of the total DM lesions observed in the vineyard. In conclusion, the model was able to identify periods in which the DM risk was nil or very low. It may, therefore, help growers avoid fungicide sprays when not needed and lengthen the interval between two sprays, i.e., it will help growers move from calendar-based to risk-based fungicide schedules for the control of P. viticola in vineyards.

The number of microbiome-related studies has notably increased the availability of data on human microbiome composition and function. These studies provide the essential material to deeply explore host-microbiome associations and their relation to the development and progression of various complex diseases. Improved data-analytical tools are needed to exploit all information from these biological datasets, taking into account the peculiarities of microbiome data, i.e., compositional, heterogeneous and sparse nature of these datasets. The possibility of predicting host-phenotypes based on taxonomy-informed feature selection to establish an association between microbiome and predict disease states is beneficial for personalized medicine. In this regard, machine learning (ML) provides new insights into the development of models that can be used to predict outputs, such as classification and prediction in microbiology, infer host phenotypes to predict diseases and use microbial communities to stratify patients by their characterization of state-specific microbial signatures. Here we review the state-of-the-art ML methods and respective software applied in human microbiome studies, performed as part of the COST Action ML4Microbiome activities. This scoping review focuses on the application of ML in microbiome studies related to association and clinical use for diagnostics, prognostics, and therapeutics. Although the data presented here is more related to the bacterial community, many algorithms could be applied in general, regardless of the feature type. This literature and software review covering this broad topic is aligned with the scoping review methodology. The manual identification of data sources has been complemented with: (1) automated publication search through digital libraries of the three major publishers using natural language processing (NLP) Toolkit, and (2) an automated identification of relevant software repositories on GitHub and ranking of the related research papers relying on learning to rank approach.

A mechanistic model was developed to predict secondary infections of Plasmopara viticola and their severity as influenced by environmental conditions; the model incorporates the processes of sporangia production and survival on downy mildew (DM) lesions, dispersal and deposition, and infection. The model was evaluated against observed data (collected in a 3-year vineyard) for its accuracy to predict periods with no sporangia (i.e., for negative prognosis) or with peaks of sporangia, so that growers can identify periods with no/low risk or high risk. The model increased the probability to correctly predict no sporangia [P(P−O−) = 0.67] by two times compared to the prior probability, with fewer than 3% of the total sporangia found in the vineyard being sampled when not predicted by the model. The model also correctly predicted peaks of sporangia, with only 1 of 40 peaks unpredicted. When evaluated for the negative prognosis of infection periods, the model showed a posterior probability for infection not to occur when not predicted P(P−O−) = 0.87 with only 9 of 108 real infections not predicted; these unpredicted infections were mild, accounting for only 4.4% of the total DM lesions observed in the vineyard. In conclusion, the model was able to identify periods in which the DM risk was nil or very low. It may, therefore, help growers avoid fungicide sprays when not needed and lengthen the interval between two sprays, i.e., it will help growers move from calendar-based to risk-based fungicide schedules for the control of P. viticola in vineyards. [ABSTRACT FROM AUTHOR]

The number of microbiome-related studies has notably increased the availability of data on human microbiome composition and function. These studies provide the essential material to deeply explore host-microbiome associations and their relation to the development and progression of various complex diseases. Improved data-analytical tools are needed to exploit all information from these biological datasets, taking into account the peculiarities of microbiome data, i.e., compositional, heterogeneous and sparse nature of these datasets. The possibility of predicting host-phenotypes based on taxonomy-informed feature selection to establish an association between microbiome and predict disease states is beneficial for personalized medicine. In this regard, machine learning (ML) provides new insights into the development of models that can be used to predict outputs, such as classification and prediction in microbiology, infer host phenotypes to predict diseases and use microbial communities to stratify patients by their characterization of state-specific microbial signatures. Here we review the state-of-the-art ML methods and respective software applied in human microbiome studies, performed as part of the COST Action ML4Microbiome activities. This scoping review focuses on the application of ML in microbiome studies related to association and clinical use for diagnostics, prognostics, and therapeutics. Although the data presented here is more related to the bacterial community, many algorithms could be applied in general, regardless of the feature type. This literature and software review covering this broad topic is aligned with the scoping review methodology. The manual identification of data sources has been complemented with: (1) automated publication search through digital libraries of the three major publishers using natural language processing (NLP) Toolkit, and (2) an automated identification of relevant software repositories on GitHub and ranking of the related research papers relying on learning to rank approach. [ABSTRACT FROM AUTHOR]

The 2019 coronavirus disease (COVID-19) pandemic began in the city of Wuhan, China, at the end of 2019 and quickly spread worldwide. The disease is caused by contact with the SARS-CoV-2 virus, which probably jumped from an animal host to humans. SARS-CoV-2 infects various tissues in the body, notably the lungs, and patients usually die from respiratory complications. Mathematical models of the disease have been instrumental to guide the implementation of mitigation strategies aimed at slowing the spread of the disease. One of the key parameters of mathematical models is the basic reproduction ratio R0, which measures the degree of infectivity of affected individuals. The goal of mitigation is to reduce R0 as close or below 1 as possible, as it means that new infections are in decline. In this work, we use the recursive least-squares algorithm to establish the stochastic variability of a time-varying R0(t) from eight different countries: Argentina, Belgium, Brazil, Germany, Italy, New Zealand, Spain, and the United States. The proposed system can be implemented as an online tracking application providing information about the dynamics of the pandemic to health officials and the public at large.

Multi-omics analyses, disease prediction, machine learning, complex diseases, data integration analysis Keywords: multi-omics analyses; disease prediction; machine learning; complex diseases; data integration analysis EN multi-omics analyses disease prediction machine learning complex diseases data integration analysis 1 3 3 08/23/21 20210818 NES 210818 Physiological data are the reflections of the physiological status of living systems (Terranova et al., [5]). [Extracted from the article]

Comparing metagenomic samples is crucial for understanding microbial communities. For different groups of microbial communities, such as human gut metagenomic samples from patients with a certain disease and healthy controls, identifying group-specific sequences offers essential information for potential biomarker discovery. A sequence that is present, or rich, in one group, but absent, or scarce, in another group is considered “group-specific” in our study. Our main purpose is to discover group-specific sequence regions between control and case groups as disease-associated markers. We developed a long k-mer (k ≥ 30 bps)-based computational pipeline to detect group-specific sequences at strain resolution free from reference sequences, sequence alignments, and metagenome-wide de novo assembly. We called our method MetaGO: Group-specific oligonucleotide analysis for metagenomic samples. An open-source pipeline on Apache Spark was developed with parallel computing. We applied MetaGO to one simulated and three real metagenomic datasets to evaluate the discriminative capability of identified group-specific markers. In the simulated dataset, 99.11% of group-specific logical 40-mers covered 98.89% disease-specific regions from the disease-associated strain. In addition, 97.90% of group-specific numerical 40-mers covered 99.61 and 96.39% of differentially abundant genome and regions between two groups, respectively. For a large-scale metagenomic liver cirrhosis (LC)-associated dataset, we identified 37,647 group-specific 40-mer features. Any one of the features can predict disease status of the training samples with the average of sensitivity and specificity higher than 0.8. The random forests classification using the top 10 group-specific features yielded a higher AUC (from ∼0.8 to ∼0.9) than that of previous studies. All group-specific 40-mers were present in LC patients, but not healthy controls. All the assembled 11 LC-specific sequences can be mapped to two strains of Veillonella parvula: UTDB1-3 and DSM2008. The experiments on the other two real datasets related to Inflammatory Bowel Disease and Type 2 Diabetes in Women consistently demonstrated that MetaGO achieved better prediction accuracy with fewer features compared to previous studies. The experiments showed that MetaGO is a powerful tool for identifying group-specific k-mers, which would be clinically applicable for disease prediction. MetaGO is available at https://github.com/VVsmileyx/MetaGO.

Comparing metagenomic samples is crucial for understanding microbial communities. For different groups of microbial communities, such as human gut metagenomic samples from patients with a certain disease and healthy controls, identifying groupspecific sequences offers essential information for potential biomarker discovery. A sequence that is present, or rich, in one group, but absent, or scarce, in another group is considered "group-specific" in our study. Our main purpose is to discover groupspecific sequence regions between control and case groups as disease-associated markers. We developed a long k-mer (k ≥ 30 bps)-based computational pipeline to detect group-specific sequences at strain resolution free from reference sequences, sequence alignments, and metagenome-wide de novo assembly. We called our method MetaGO: Group-specific oligonucleotide analysis for metagenomic samples. An opensource pipeline on Apache Spark was developed with parallel computing. We applied MetaGO to one simulated and three real metagenomic datasets to evaluate the discriminative capability of identified group-specific markers. In the simulated dataset, 99.11% of group-specific logical 40-mers covered 98.89% disease-specific regions from the disease-associated strain. In addition, 97.90% of group-specific numerical 40-mers covered 99.61 and 96.39% of differentially abundant genome and regions between two groups, respectively. For a large-scale metagenomic liver cirrhosis (LC)-associated dataset, we identified 37,647 group-specific 40-mer features. Any one of the features can predict disease status of the training samples with the average of sensitivity and specificity higher than 0.8. The random forests classification using the top 10 group-specific features yielded a higher AUC (from ~0.8 to ~0.9) than that of previous studies. All group-specific 40-mers were present in LC patients, but not healthy controls. All the assembled 11 LC-specific sequences can be mapped to two strains of Veillonella parvula: UTDB1-3 and DSM2008. The experiments on the other two real datasets related to Inflammatory Bowel Disease and Type 2 Diabetes in Women consistently demonstrated that MetaGO achieved better prediction accuracy with fewer features compared to previous studies. The experiments showed that MetaGO is a powerful tool for identifying group-specific k-mers, which would be clinically applicable for disease prediction. [ABSTRACT FROM AUTHOR]