Gut microbiome-based supervised machine learning for clinical diagnosis of inflammatory bowel diseases

The interaction between gut microbiome and bone health

PURPOSE OF REVIEW

This review critically examines interconnected health domains like gut microbiome, bone health, interleukins, chronic periodontitis, and coronavirus disease 2019 (COVID-19), offering insights into fundamental mechanisms and clinical implications, contributing significantly to healthcare and biomedical research.

RECENT FINDINGS

This review explores the relationship between gut microbiome and bone health, a growing area of study. It provides insights into skeletal integrity and potential therapeutic avenues. The review also examines interleukins, chronic periodontitis, and COVID-19, highlighting the complexity of viral susceptibility and immune responses. It highlights the importance of understanding genetic predispositions and immune dynamics in the context of disease outcomes. The review emphasizes experimental evidence and therapeutic strategies, aligning with evidence-based medicine and personalized interventions. This approach offers actionable insights for healthcare practitioners and researchers, paving the way for targeted therapeutic approaches and improved patient outcomes.

SUMMARY

The implications of these findings for clinical practice and research underscore the importance of a multidisciplinary approach to healthcare that considers the complex interactions between genetics, immune responses, oral health, and systemic diseases. By leveraging advances in biomedical research, clinicians can optimize patient care and improve health outcomes across diverse patient populations.

Exploring the Gut Microbiome's Role in Inflammatory Bowel Disease: Insights and Interventions

Inflammatory Bowel Disease (IBD), encompassing Crohn's disease (CD) and ulcerative colitis (UC), is a chronic and relapsing inflammatory condition of the intestine that significantly impairs quality of life and imposes a heavy burden on healthcare systems globally. While the exact etiology of IBD is unclear, it is influenced by genetic, environmental, immunological, and microbial factors. Recent advances highlight the gut microbiome's pivotal role in IBD pathogenesis. The microbial dysbiosis characteristic of IBD, marked by a decline in beneficial bacteria and an increase in pathogenic microbes, suggests a profound connection between microbial imbalance and disease mechanisms. This review explores diagnostic approaches to IBD that integrate clinical assessment with advanced microbiological analyses, highlighting the potential of microbiome profiling as a non-invasive diagnostic tool. In addition, it evaluates conventional and emerging treatments and discusses microbiome-targeted intervention prospects, such as probiotics, symbiotics, and faecal microbiota transplantation. The necessity for future research to establish their efficacy and safety is emphasised.

Exploring the Predictive Value of Gut Microbiome Signatures for Therapy Intensification in Patients With Inflammatory Bowel Disease: A 10-Year Follow-up Study

BACKGROUND

Inflammatory bowel diseases (IBDs) pose a significant challenge due to their diverse, often debilitating, and unpredictable clinical manifestations. The absence of prognostic tools to anticipate the future complications that require therapy intensification presents a substantial burden to patient private life and health. We aimed to explore whether the gut microbiome is a potential biomarker for future therapy intensification in a cohort of 90 IBD patients.

METHODS

We conducted whole-genome metagenomics sequencing on fecal samples from these patients, allowing us to profile the taxonomic and functional composition of their gut microbiomes. Additionally, we conducted a retrospective analysis of patients' electronic records over a period of 10 years following the sample collection and classified patients into (1) those requiring and (2) not requiring therapy intensification. Therapy intensification included medication escalation, intestinal resections, or a loss of response to a biological treatment. We applied gut microbiome diversity analysis, dissimilarity assessment, differential abundance analysis, and random forest modeling to establish associations between baseline microbiome profiles and future therapy intensification.

RESULTS

We identified 12 microbial species (eg, Roseburia hominis and Dialister invisus) and 16 functional pathways (eg, biosynthesis of L-citrulline and L-threonine) with significant correlations to future therapy intensifications. Random forest models using microbial species and pathways achieved areas under the curve of 0.75 and 0.72 for predicting therapy intensification.

CONCLUSIONS

The gut microbiome is a potential biomarker for therapy intensification in IBD patients and personalized management strategies. Further research should validate our findings in other cohorts to enhance the generalizability of these results.

Predicting short-term major postoperative complications in intestinal resection for Crohn's disease: A machine learning-based study

BACKGROUND

Due to the complexity and numerous comorbidities associated with Crohn's disease (CD), the incidence of postoperative complications is high, significantly impacting the recovery and prognosis of patients. Consequently, additional studies are required to precisely predict short-term major complications following intestinal resection (IR), aiding surgical decision-making and optimizing patient care.

AIM

To construct novel models based on machine learning (ML) to predict short-term major postoperative complications in patients with CD following IR.

METHODS

A retrospective analysis was performed on clinical data derived from a patient cohort that underwent IR for CD from January 2017 to December 2022. The study participants were randomly allocated to either a training cohort or a validation cohort. The logistic regression and random forest (RF) were applied to construct models in the training cohort, with model discrimination evaluated using the area under the curves (AUC). The validation cohort assessed the performance of the constructed models.

RESULTS

Out of the 259 patients encompassed in the study, 5.0% encountered major postoperative complications (Clavien-Dindo ≥ III) within 30 d following IR for CD. The AUC for the logistic model was 0.916, significantly lower than the AUC of 0.965 for the RF model. The logistic model incorporated a preoperative CD activity index (CDAI) of ≥ 220, a diminished preoperative serum albumin level, conversion to laparotomy surgery, and an extended operation time. A nomogram for the logistic model was plotted. Except for the surgical approach, the other three variables ranked among the top four important variables in the novel ML model.

CONCLUSION

Both the nomogram and RF exhibited good performance in predicting short-term major postoperative complications in patients with CD, with the RF model showing more superiority. A preoperative CDAI of ≥ 220, a diminished preoperative serum albumin level, and an extended operation time might be the most crucial variables. The findings of this study can assist clinicians in identifying patients at a higher risk for complications and offering personalized perioperative management to enhance patient outcomes.

Gut microbiota predicts the diagnosis of ulcerative colitis in Saudi children

BACKGROUND

Ulcerative colitis (UC) is an immune-mediated chronic inflammatory condition with a worldwide distribution. Although the etiology of this disease is still unknown, the understanding of the role of the microbiota is becoming increasingly strong.

AIM

To investigate the predictive power of the gut microbiota for the diagnosis of UC in a cohort of newly diagnosed treatment-naïve Saudi children with UC.

METHODS

The study population included 20 children with a confirmed diagnosis of UC and 20 healthy controls. Microbial DNA was extracted and sequenced, and shotgun metagenomic analysis was performed for bacteria and bacteriophages. Biostatistics and bioinformatics demonstrated significant dysbiosis in the form of reduced alpha diversity, beta diversity, and significant difference of abundance of taxa between children with UC and control groups. The receiver operating characteristic curve, a probability curve, was used to determine the difference between the UC and control groups. The area under the curve (AUC) represents the degree of separability between the UC group and the control group. The AUC was calculated for all identified bacterial species and for bacterial species identified by the random forest classification algorithm as important potential biomarkers of UC. A similar method of AUC calculation for all bacteriophages and important species was used.

RESULTS

The median age and range were 14 (0.5-21) and 12.9 (6.8-16.3) years for children with UC and controls, respectively, and 40% and 35% were male for children with UC and controls, respectively. The AUC for all identified bacterial species was 89.5%. However, when using the bacterial species identified as important by random forest classification algorithm analysis, the accuracy increased to 97.6%. Similarly, the AUC for all the identified bacteriophages was 87.4%, but this value increased to 94.5% when the important bacteriophage biomarkers were used.

CONCLUSION

The very high to excellent AUCs of fecal bacterial and viral species suggest the potential use of noninvasive microbiota-based tests for the diagnosis of unusual cases of UC in children. In addition, the identification of important bacteria and bacteriophages whose abundance is reduced in children with UC suggests the potential of preventive and adjuvant microbial therapy for UC.

Machine learning application in autoimmune diseases: State of art and future prospectives

Autoimmune diseases are a group of disorders resulting from an alteration of immune tolerance, characterized by the formation of autoantibodies and the consequent development of heterogeneous clinical manifestations. Diagnosing autoimmune diseases is often complicated, and the available prognostic tools are limited. Machine learning allows us to analyze large amounts of data and carry out complex calculations quickly and with minimal effort. In this work, we examine the literature focusing on the use of machine learning in the field of the main systemic (systemic lupus erythematosus and rheumatoid arthritis) and organ-specific autoimmune diseases (type 1 diabetes mellitus, autoimmune thyroid, gastrointestinal, and skin diseases). From our analysis, interesting applications of machine learning emerged for developing algorithms useful in the early diagnosis of disease or prognostic models (risk of complications, therapeutic response). Subsequent studies and the creation of increasingly rich databases to be supplied to the algorithms will eventually guide the clinician in the diagnosis, allowing intervention when the pathology is still in an early stage and immediately directing towards a correct therapeutic approach.

Methodology for biomarker discovery with reproducibility in microbiome data using machine learning

BACKGROUND

In recent years, human microbiome studies have received increasing attention as this field is considered a potential source for clinical applications. With the advancements in omics technologies and AI, research focused on the discovery for potential biomarkers in the human microbiome using machine learning tools has produced positive outcomes. Despite the promising results, several issues can still be found in these studies such as datasets with small number of samples, inconsistent results, lack of uniform processing and methodologies, and other additional factors lead to lack of reproducibility in biomedical research. In this work, we propose a methodology that combines the DADA2 pipeline for 16s rRNA sequences processing and the Recursive Ensemble Feature Selection (REFS) in multiple datasets to increase reproducibility and obtain robust and reliable results in biomedical research.

RESULTS

Three experiments were performed analyzing microbiome data from patients/cases in Inflammatory Bowel Disease (IBD), Autism Spectrum Disorder (ASD), and Type 2 Diabetes (T2D). In each experiment, we found a biomarker signature in one dataset and applied to 2 other as further validation. The effectiveness of the proposed methodology was compared with other feature selection methods such as K-Best with F-score and random selection as a base line. The Area Under the Curve (AUC) was employed as a measure of diagnostic accuracy and used as a metric for comparing the results of the proposed methodology with other feature selection methods. Additionally, we use the Matthews Correlation Coefficient (MCC) as a metric to evaluate the performance of the methodology as well as for comparison with other feature selection methods.

CONCLUSIONS

We developed a methodology for reproducible biomarker discovery for 16s rRNA microbiome sequence analysis, addressing the issues related with data dimensionality, inconsistent results and validation across independent datasets. The findings from the three experiments, across 9 different datasets, show that the proposed methodology achieved higher accuracy compared to other feature selection methods. This methodology is a first approach to increase reproducibility, to provide robust and reliable results.

Challenges involved in the application of artificial intelligence in gastroenterology: The race is on!

Gastroenterology is a particularly data-rich field, generating vast repositories of data that are a fruitful ground for artificial intelligence (AI) and machine learning (ML) applications. In this opinion review, we initially elaborate on the current status of the application of AI/ML-based software in gastroenterology. Currently, AI/ML-based models have been developed in the following applications: Models integrated into the clinical setting following real-time patient data flagging patients at high risk for developing a gastrointestinal disease, models employing non-invasive parameters that provide accurate diagnoses aiming to either replace, minimize, or refine the indications of endoscopy, models utilizing genomic data to diagnose various gastrointestinal diseases, computer-aided diagnosis systems facilitating the interpretation of endoscopy images, models to facilitate treatment allocation and predict the response to treatment, and finally, models in prognosis predicting complications, recurrence following treatment, and overall survival. Then, we elaborate on several challenges and how they may negatively impact the widespread application of AI in healthcare and gastroenterology. Specifically, we elaborate on concerns regarding accuracy, cost-effectiveness, cybersecurity, interpretability, oversight, and liability. While AI is unlikely to replace physicians, it will transform the skillset demanded by future physicians to practice. Thus, physicians are expected to engage with AI to avoid becoming obsolete.

A Machine Learning-Based Diagnostic Model for Crohn's Disease and Ulcerative Colitis Utilizing Fecal Microbiome Analysis

Recent research has demonstrated the potential of fecal microbiome analysis using machine learning (ML) in the diagnosis of inflammatory bowel disease (IBD), mainly Crohn's disease (CD) and ulcerative colitis (UC). This study employed the sparse partial least squares discriminant analysis (sPLS-DA) ML technique to develop a robust prediction model for distinguishing among CD, UC, and healthy controls (HCs) based on fecal microbiome data. Using data from multicenter cohorts, we conducted 16S rRNA gene sequencing of fecal samples from patients with CD (n = 671) and UC (n = 114) while forming an HC cohort of 1462 individuals from the Kangbuk Samsung Hospital Healthcare Screening Center. A streamlined pipeline based on HmmUFOTU was used. After a series of filtering steps, 1517 phylotypes and 1846 samples were retained for subsequent analysis. After 100 rounds of downsampling with age, sex, and sample size matching, and division into training and test sets, we constructed two binary prediction models to distinguish between IBD and HC and CD and UC using the training set. The binary prediction models exhibited high accuracy and area under the curve (for differentiating IBD from HC (mean accuracy, 0.950; AUC, 0.992) and CD from UC (mean accuracy, 0.945; AUC, 0.988)), respectively, in the test set. This study underscores the diagnostic potential of an ML model based on sPLS-DA, utilizing fecal microbiome analysis, highlighting its ability to differentiate between IBD and HC and distinguish CD from UC.

Next-Generation Sequencing for the Detection of Microbial Agents in Avian Clinical Samples

Direct-targeted next-generation sequencing (tNGS), with its undoubtedly superior diagnostic capacity over real-time PCR (RT-PCR), and direct-non-targeted NGS (ntNGS), with its higher capacity to identify and characterize multiple agents, are both likely to become diagnostic methods of choice in the future. tNGS is a rapid and sensitive method for precise characterization of suspected agents. ntNGS, also known as agnostic diagnosis, does not require a hypothesis and has been used to identify unsuspected infections in clinical samples. Implemented in the form of multiplexed total DNA metagenomics or as total RNA sequencing, the approach produces comprehensive and actionable reports that allow semi-quantitative identification of most of the agents present in respiratory, cloacal, and tissue samples. The diagnostic benefits of the use of direct tNGS and ntNGS are high specificity, compatibility with different types of clinical samples (fresh, frozen, FTA cards, and paraffin-embedded), production of nearly complete infection profiles (viruses, bacteria, fungus, and parasites), production of "semi-quantitative" information, direct agent genotyping, and infectious agent mutational information. The achievements of NGS in terms of diagnosing poultry problems are described here, along with future applications. Multiplexing, development of standard operating procedures, robotics, sequencing kits, automated bioinformatics, cloud computing, and artificial intelligence (AI) are disciplines converging toward the use of this technology for active surveillance in poultry farms. Other advances in human and veterinary NGS sequencing are likely to be adaptable to avian species in the future.

Profiling the inflammatory bowel diseases using genetics, serum biomarkers, and smoking information

Crohn's disease (CD) and ulcerative colitis (UC) are two etiologically related yet distinctive subtypes of the inflammatory bowel diseases (IBD). Differentiating CD from UC can be challenging using conventional clinical approaches in a subset of patients. We designed and evaluated a novel molecular-based prediction model aggregating genetics, serum biomarkers, and tobacco smoking information to assist the diagnosis of CD and UC in over 30,000 samples. A joint model combining genetics, serum biomarkers and smoking explains 46% (42-50%, 95% CI) of phenotypic variation. Despite modest overlaps with serum biomarkers, genetics makes unique contributions to distinguishing IBD subtypes. Smoking status only explains 1% (0-6%, 95% CI) of the phenotypic variance suggesting it may not be an effective biomarker. This study reveals that molecular-based models combining genetics, serum biomarkers, and smoking information could complement current diagnostic strategies and help classify patients based on biologic state rather than imperfect clinical parameters.

Fecal Microbial Composition and Predicted Functional Profile in Irritable Bowel Syndrome Differ between Subtypes and Geographical Locations

Increasing evidence suggests a microbial pathogenesis in irritable bowel syndrome (IBS) but the relationship remains elusive. Fecal DNA samples from 120 patients with IBS, 82 Mexican (IBS-C: n = 33, IBS-D: n = 24, IBS-M: n = 25) and 38 British (IBS-C: n = 6, IBS-D: n = 27, IBS-M: n = 5), were available for analysis using 16S rRNA gene sequencing. Firmicutes (mean: 82.1%), Actinobacteria (10.2%), and Bacteroidetes (4.4%) were the most abundant taxa. The analysis of all samples (n = 120), and females (n = 94) only, showed no significant differences in bacterial microbiota, but the analysis of Mexican patients (n = 82) showed several differences in key taxa (e.g., Faecalibacterium) among the different IBS subtypes. In IBS-D there were significantly higher Bacteroidetes in British patients (n = 27) than in Mexican patients (n = 24), suggesting unique fecal microbiota signatures within the same IBS subtype. These differences in IBS-D were also observed at lower phylogenetic levels (e.g., higher Enterobacteriaceae and Streptococcus in Mexican patients) and were accompanied by differences in several alpha diversity metrics. Beta diversity was not different among IBS subtypes when using all samples, but the analysis of IBS-D patients revealed consistent differences between Mexican and British patients. This study suggests that fecal microbiota is different between IBS subtypes and also within each subtype depending on geographical location.

Crohn's Disease Prediction Using Sequence Based Machine Learning Analysis of Human Microbiome

Human microbiota refers to the trillions of microorganisms that inhabit our bodies and have been discovered to have a substantial impact on human health and disease. By sampling the microbiota, it is possible to generate massive quantities of data for analysis using Machine Learning algorithms. In this study, we employed several modern Machine Learning techniques to predict Inflammatory Bowel Disease using raw sequence data. The dataset was obtained from NCBI preprocessed graph representations and converted into a structured form. Seven well-known Machine Learning frameworks, including Random Forest, Support Vector Machines, Extreme Gradient Boosting, Light Gradient Boosting Machine, Gaussian Naïve Bayes, Logistic Regression, and k-Nearest Neighbor, were used. Grid Search was employed for hyperparameter optimization. The performance of the Machine Learning models was evaluated using various metrics such as accuracy, precision, fscore, kappa, and area under the receiver operating characteristic curve. Additionally, Mc Nemar's test was conducted to assess the statistical significance of the experiment. The data was constructed using k-mer lengths of 3, 4 and 5. The Light Gradient Boosting Machine model overperformed over other models with 67.24%, 74.63% and 76.47% accuracy for k-mer lengths of 3, 4 and 5, respectively. The LightGBM model also demonstrated the best performance in each metric. The study showed promising results predicting disease from raw sequence data. Finally, Mc Nemar's test results found statistically significant differences between different Machine Learning approaches.

Performance of Machine Learning Algorithms for Predicting Disease Activity in Inflammatory Bowel Disease

This study aimed to explore the effectiveness of predicting disease activity in patients with inflammatory bowel disease (IBD), using machine learning (ML) models. A retrospective research was undertaken on IBD patients who were admitted into the First Affiliated Hospital of Wenzhou Medical University between September 2011 and September 2019. At first, data were randomly split into a 3:1 ratio of training to test set. The least absolute shrinkage and selection operator (LASSO) algorithm was applied to reduce the dimension of variables. These variables were used to generate seven ML algorithms, namely random forests (RFs), adaptive boosting (AdaBoost), K-nearest neighbors (KNNs), support vector machines (SVMs), naïve Bayes (NB), ridge regression, and eXtreme gradient boosting (XGBoost) to train to predict disease activity in IBD patients. SHapley Additive exPlanation (SHAP) analysis was performed to rank variable importance. A total of 876 participants with IBD, consisting of 275 ulcerative colitis (UC) and 601 Crohn's disease (CD), were retrospectively enrolled in the study. Thirty-three variables were obtained from the clinical characteristics and laboratory tests of the participants. Finally, after LASSO analysis, 11 and 5 variables were screened out to construct ML models for CD and UC, respectively. All seven ML models performed well in predicting disease activity in the CD and UC test sets. Among these ML models, SVM was more effective in predicting disease activity in the CD group, whose AUC reached 0.975, sensitivity 0.947, specificity 0.920, and accuracy 0.933. AdaBoost performed best for the UC group, with an AUC of 0.911, sensitivity 0.844, specificity 0.875, and accuracy 0.855. ML algorithms were available and capable of predicting disease activity in IBD patients. Based on clinical and laboratory variables, ML algorithms demonstrate great promise in guiding physicians' decision-making.

Error Consistency for Machine Learning Evaluation and Validation with Application to Biomedical Diagnostics

Supervised machine learning classification is the most common example of artificial intelligence (AI) in industry and in academic research. These technologies predict whether a series of measurements belong to one of multiple groups of examples on which the machine was previously trained. Prior to real-world deployment, all implementations need to be carefully evaluated with hold-out validation, where the algorithm is tested on different samples than it was provided for training, in order to ensure the generalizability and reliability of AI models. However, established methods for performing hold-out validation do not assess the consistency of the mistakes that the AI model makes during hold-out validation. Here, we show that in addition to standard methods, an enhanced technique for performing hold-out validation—that also assesses the consistency of the sample-wise mistakes made by the learning algorithm—can assist in the evaluation and design of reliable and predictable AI models. The technique can be applied to the validation of any supervised learning classification application, and we demonstrate the use of the technique on a variety of example biomedical diagnostic applications, which help illustrate the importance of producing reliable AI models. The validation software created is made publicly available, assisting anyone developing AI models for any supervised classification application in the creation of more reliable and predictable technologies.

Machine learning based gut microbiota pattern and response to fiber as a diagnostic tool for chronic inflammatory diseases

Gut microbiota has been implicated in the pathogenesis of multiple gastrointestinal (GI) and systemic metabolic and inflammatory disorders where disrupted gut microbiota composition and function (dysbiosis) has been found in multiple studies. Thus, human microbiome data has a potential to be a great source of information for the diagnosis and disease characteristics (phenotypes, disease course, therapeutic response) of diseases with dysbiotic microbiota community. However, multiple attempts to leverage gut microbiota taxonomic data for diagnostic and disease characterization have failed due to significant inter-individual variability of microbiota community and overlap of disrupted microbiota communities among multiple diseases. One potential approach is to look at the microbiota community pattern and response to microbiota modifiers like dietary fiber in different disease states. This approach is now feasible by availability of machine learning that is able to identify hidden patterns in the human microbiome and predict diseases. Accordingly, the aim of our study was to test the hypothesis that application of machine learning algorithms can distinguish stool microbiota pattern and microbiota response to fiber between diseases where overlapping dysbiotic microbiota have been previously reported. Here, we have applied machine learning algorithms to distinguish between Parkinson's disease, Crohn's disease (CD), ulcerative colitis (UC), human immune deficiency virus (HIV), and healthy control (HC) subjects in the presence and absence of fiber treatments. We have shown that machine learning algorithms can classify diseases with accuracy as high as 95%. Furthermore, machine learning methods applied to the microbiome data to predict UC vs CD led to prediction accuracy as high as 90%.

Determining the most accurate 16S rRNA hypervariable region for taxonomic identification from respiratory samples

16S rRNA gene profiling, which contains nine hypervariable regions (V1-V9), is the gold standard for identifying taxonomic units by high-throughput sequencing. Microbiome studies combine two or more region sequences (usually V3-V4) to increase the resolving power for identifying bacterial taxa. We compare the resolving powers of V1-V2, V3-V4, V5-V7, and V7-V9 to improve microbiome analyses in sputum samples from patients with chronic respiratory diseases. DNA were isolated from 33 human sputum samples, and libraries were created using a QIASeq screening panel intended for Illumina platforms (16S/ITS; Qiagen Hilden, Germany). The analysis included a mock community as a microbial standard control (ZymoBIOMICS). We used the Deblur algorithm to identify bacterial amplicon sequence variants (ASVs) at the genus level. Alpha diversity was significantly higher for V1-V2, V3-V4, and V5-V7 compared with V7-V9, and significant compositional dissimilarities in the V1-V2 and V7-V9 analyses versus the V3-V4 and V5-V7 analyses. A cladogram confirmed these compositional differences, with the latter two being very similar in composition. The combined hypervariable regions showed significant differences when discriminating between the relative abundances of bacterial genera. The area under the curve revealed that V1-V2 had the highest resolving power for accurately identifying respiratory bacterial taxa from sputum samples. Our study confirms that 16S rRNA hypervariable regions provide significant differences for taxonomic identification in sputum. Comparing the taxa of microbial community standard control with the taxa samples, V1-V2 combination exhibits the most sensitivity and specificity. Thus, while third generation full-length 16S rRNA sequencing platforms become more available, the V1-V2 hypervariable regions can be used for taxonomic identification in sputum.

Artificial intelligence and inflammatory bowel disease: Where are we going?

Inflammatory bowel diseases, namely ulcerative colitis and Crohn’s disease, are chronic and relapsing conditions that pose a growing burden on healthcare systems worldwide. Because of their complex and partly unknown etiology and pathogenesis, the management of ulcerative colitis and Crohn’s disease can prove challenging not only from a clinical point of view but also for resource optimization. Artificial intelligence, an umbrella term that encompasses any cognitive function developed by machines for learning or problem solving, and its subsets machine learning and deep learning are becoming ever more essential tools with a plethora of applications in most medical specialties. In this regard gastroenterology is no exception, and due to the importance of endoscopy and imaging numerous clinical studies have been gradually highlighting the relevant role that artificial intelligence has in inflammatory bowel diseases as well. The aim of this review was to summarize the most recent evidence on the use of artificial intelligence in inflammatory bowel diseases in various contexts such as diagnosis, follow-up, treatment, prognosis, cancer surveillance, data collection, and analysis. Moreover, insights into the potential further developments in this field and their effects on future clinical practice were discussed.

Artificial Intelligence in Medicine: Microbiome-Based Machine Learning for Phenotypic Classification

Advanced computational approaches in artificial intelligence, such as machine learning, have been increasingly applied in life sciences and healthcare to analyze large-scale complex biological data, such as microbiome data. In this chapter, we describe the experimental procedures for using microbiome-based machine learning models for phenotypic classification.

Machine learning-based feature selection to search stable microbial biomarkers: application to inflammatory bowel disease

BACKGROUND

Biomarker discovery exploiting feature importance of machine learning has risen recently in the microbiome landscape with its high predictive performance in several disease states. To have a concrete selection among a high number of features, recursive feature elimination (RFE) has been widely used in the bioinformatics field. However, machine learning-based RFE has factors that decrease the stability of feature selection. In this article, we suggested methods to improve stability while sustaining performance.

RESULTS

We exploited the abundance matrices of the gut microbiome (283 taxa at species level and 220 at genus level) to classify between patients with inflammatory bowel disease (IBD) and healthy control (1,569 samples). We found that applying an already published data transformation before RFE improves feature stability significantly. Moreover, we performed an in-depth evaluation of different variants of the data transformation and identify those that demonstrate better improvement in stability while not sacrificing classification performance. To ensure a robust comparison, we evaluated stability using various similarity metrics, distances, the common number of features, and the ability to filter out noise features. We were able to confirm that the mapping by the Bray-Curtis similarity matrix before RFE consistently improves the stability while maintaining good performance. Multilayer perceptron algorithm exhibited the highest performance among 8 different machine learning algorithms when a large number of features (a few hundred) were considered based on the best performance across 100 bootstrapped internal test sets. Conversely, when utilizing only a limited number of biomarkers as a trade-off between optimal performance and method generalizability, the random forest algorithm demonstrated the best performance. Using the optimal pipeline we developed, we identified 14 biomarkers for IBD at the species level and analyzed their roles using Shapley additive explanations.

CONCLUSION

Taken together, our work not only showed how to improve biomarker discovery in the metataxonomic field without sacrificing classification performance but also provided useful insights for future comparative studies.

Repurposing a Drug Targeting Inflammatory Bowel Disease for Lowering Hypertension

Background The gut and gut microbiota, which were previously neglected in blood pressure regulation, are becoming increasingly recognized as factors contributing to hypertension. Diseases affecting the gut such as inflammatory bowel disease (IBD) present with aberrant energy metabolism of colonic epithelium and gut dysbiosis, both of which are also mechanisms contributing to hypertension. We reasoned that current measures to remedy deficits in colonic energy metabolism and dysbiosis in IBD could also ameliorate hypertension. Among them, 5-aminosalicylic acid (5-ASA; mesalamine) is a PPARγ (peroxisome proliferator-activated receptor gamma) agonist. It attenuates IBD by a dual mechanism of selectively enhancing colonic epithelial cell energy metabolism and ameliorating gut dysbiosis. Methods and Results A total of 2 groups of 11- to 12-week-old male, hypertensive, Dahl salt-sensitive (S) rats were gavaged with (n=10) or without (n=10) 5-aminosalicylic acid (150 mg/kg) for 4 weeks. Rats receiving 5-aminosalicylic acid treatment had a lower mean blood pressure than controls (145±3 mm Hg versus 153±4 mm Hg; P<0.0001). This reduction in blood pressure was accompanied by increased activity of PPARγ, increased expression of energy metabolism-related genes, and lowering of the Firmicutes/Bacteroidetes ratio in the colon, the reduction of which is a marker for the correction of gut dysbiosis. Furthermore, these data were consistent with the American Gut Project wherein the Firmicutes/Bacteroidetes ratio of non-IBD (n=611) patients was significantly lower than patients with IBD (n=631). Conclusions 5-Aminosalicylic acid could be repurposed for hypertension by specifically enhancing the gut energy metabolism and correction of microbiota dysbiosis.

The role of gut microbiome in inflammatory bowel disease diagnosis and prognosis

Inflammatory bowel disease (IBD) is a chronic immune-mediated intestinal disease consisting of ulcerative colitis and Crohn's disease. Inflammatory bowel disease is believed to be developed as a result of interactions between environmental, immune-mediated and microbial factors in a genetically susceptible host. Recent advances in high-throughput sequencing technologies have aided the identification of consistent alterations of the gut microbiome in patients with IBD. Preclinical and murine models have also shed light on the role of beneficial and pathogenic bacteria in IBD. These findings have stimulated interest in development of non-invasive microbial and metabolite biomarkers for predicting disease risk, disease progression, recurrence after surgery and responses to therapeutics. This review briefly summarizes the current evidence on the role of gut microbiome in IBD pathogenesis and mainly discusses the latest literature on the utilization of potential microbial biomarkers in disease diagnosis and prognosis.

The diagnostic potential and barriers of microbiome based therapeutics

High throughput technological innovations in the past decade have accelerated research into the trillions of commensal microbes in the gut. The 'omics' technologies used for microbiome analysis are constantly evolving, and large-scale datasets are being produced. Despite of the fact that much of the research is still in its early stages, specific microbial signatures have been associated with the promotion of cancer, as well as other diseases such as inflammatory bowel disease, neurogenerative diareses etc. It has been also reported that the diversity of the gut microbiome influences the safety and efficacy of medicines. The availability and declining sequencing costs has rendered the employment of RNA-based diagnostics more common in the microbiome field necessitating improved data-analytical techniques so as to fully exploit all the resulting rich biological datasets, while accounting for their unique characteristics, such as their compositional nature as well their heterogeneity and sparsity. As a result, the gut microbiome is increasingly being demonstrating as an important component of personalised medicine since it not only plays a role in inter-individual variability in health and disease, but it also represents a potentially modifiable entity or feature that may be addressed by treatments in a personalised way. In this context, machine learning and artificial intelligence-based methods may be able to unveil new insights into biomedical analyses through the generation of models that may be used to predict category labels, and continuous values. Furthermore, diagnostic aspects will add value in the identification of the non invasive markers in the critical diseases like cancer.

Perceptions of US Medical Students on Artificial Intelligence in Medicine: Mixed Methods Survey Study

BACKGROUND

Given the rapidity with which artificial intelligence is gaining momentum in clinical medicine, current physician leaders have called for more incorporation of artificial intelligence topics into undergraduate medical education. This is to prepare future physicians to better work together with artificial intelligence technology. However, the first step in curriculum development is to survey the needs of end users. There has not been a study to determine which media and which topics are most preferred by US medical students to learn about the topic of artificial intelligence in medicine.

OBJECTIVE

We aimed to survey US medical students on the need to incorporate artificial intelligence in undergraduate medical education and their preferred means to do so to assist with future education initiatives.

METHODS

A mixed methods survey comprising both specific questions and a write-in response section was sent through Qualtrics to US medical students in May 2021. Likert scale questions were used to first assess various perceptions of artificial intelligence in medicine. Specific questions were posed regarding learning format and topics in artificial intelligence.

RESULTS

We surveyed 390 US medical students with an average age of 26 (SD 3) years from 17 different medical programs (the estimated response rate was 3.5%). A majority (355/388, 91.5%) of respondents agreed that training in artificial intelligence concepts during medical school would be useful for their future. While 79.4% (308/388) were excited to use artificial intelligence technologies, 91.2% (353/387) either reported that their medical schools did not offer resources or were unsure if they did so. Short lectures (264/378, 69.8%), formal electives (180/378, 47.6%), and Q and A panels (167/378, 44.2%) were identified as preferred formats, while fundamental concepts of artificial intelligence (247/379, 65.2%), when to use artificial intelligence in medicine (227/379, 59.9%), and pros and cons of using artificial intelligence (224/379, 59.1%) were the most preferred topics for enhancing their training.

CONCLUSIONS

The results of this study indicate that current US medical students recognize the importance of artificial intelligence in medicine and acknowledge that current formal education and resources to study artificial intelligence-related topics are limited in most US medical schools. Respondents also indicated that a hybrid formal/flexible format would be most appropriate for incorporating artificial intelligence as a topic in US medical schools. Based on these data, we conclude that there is a definitive knowledge gap in artificial intelligence education within current medical education in the US. Further, the results suggest there is a disparity in opinions on the specific format and topics to be introduced.

A Systematic Review of Artificial Intelligence and Machine Learning Applications to Inflammatory Bowel Disease, with Practical Guidelines for Interpretation

BACKGROUND

Inflammatory bowel disease (IBD) is a gastrointestinal chronic disease with an unpredictable disease course. Computational methods such as machine learning (ML) have the potential to stratify IBD patients for the provision of individualized care. The use of ML methods for IBD was surveyed, with an additional focus on how the field has changed over time.

METHODS

On May 6, 2021, a systematic review was conducted through a search of MEDLINE and Embase databases, with the search structure ("machine learning" OR "artificial intelligence") AND ("Crohn* Disease" OR "Ulcerative Colitis" OR "Inflammatory Bowel Disease"). Exclusion criteria included studies not written in English, no human patient data, publication before 2001, studies that were not peer reviewed, nonautoimmune disease comorbidity research, and record types that were not primary research.

RESULTS

Seventy-eight (of 409) records met the inclusion criteria. Random forest methods were most prevalent, and there was an increase in neural networks, mainly applied to imaging data sets. The main applications of ML to clinical tasks were diagnosis (18 of 78), disease course (22 of 78), and disease severity (16 of 78). The median sample size was 263. Clinical and microbiome-related data sets were most popular. Five percent of studies used an external data set after training and testing for additional model validation.

DISCUSSION

Availability of longitudinal and deep phenotyping data could lead to better modeling. Machine learning pipelines that consider imbalanced data and that feature selection only on training data will generate more generalizable models. Machine learning models are increasingly being applied to more complex clinical tasks for specific phenotypes, indicating progress towards personalized medicine for IBD.

GMEmbeddings: An R Package to Apply Embedding Techniques to Microbiome Data

Large-scale microbiome studies investigating disease-inducing microbial roles base their findings on differences between microbial count data in contrasting environments (e.g., stool samples between cases and controls). These microbiome survey studies are often impeded by small sample sizes and database bias. Combining data from multiple survey studies often results in obvious batch effects, even when DNA preparation and sequencing methods are identical. Relatedly, predictive models trained on one microbial DNA dataset often do not generalize to outside datasets. In this study, we address these limitations by applying word embedding algorithms (GloVe) and PCA transformation to ASV data from the American Gut Project and generating translation matrices that can be applied to any 16S rRNA V4 region gut microbiome sequencing study. Because these approaches contextualize microbial occurrences in a larger dataset while reducing dimensionality of the feature space, they can improve generalization of predictive models that predict host phenotype from stool associated gut microbiota. The GMEmbeddings R package contains GloVe and PCA embedding transformation matrices at 50, 100 and 250 dimensions, each learned using ∼15,000 samples from the American Gut Project. It currently supports the alignment, matching, and matrix multiplication to allow users to transform their V4 16S rRNA data into these embedding spaces. We show how to correlate the properties in the new embedding space to KEGG functional pathways for biological interpretation of results. Lastly, we provide benchmarking on six gut microbiome datasets describing three phenotypes to demonstrate the ability of embedding-based microbiome classifiers to generalize to independent datasets. Future iterations of GMEmbeddings will include embedding transformation matrices for other biological systems. Available at: https://github.com/MaudeDavidLab/GMEmbeddings.

Gut Microbiota of Wild Fish as Reporters of Compromised Aquatic Environments Sleuthed through Machine Learning

Human-generated negative impacts on aquatic environments are rising. Despite wild fish playing a key role in aquatic ecologies and comprising a major global food source, physiological consequences of these impacts to them are poorly understood. Here we address the issue through the lens of interrelationship between wild fish and their gut microbiota, hypothesizing that fish microbiota are reporters of the aquatic environs. Two geographically separate teleost wild-fish species were studied (Lake Erie, Ohio and Caribbean Sea, US Virgin Islands). At each geo-location, fresh fecal samples were collected from fish in areas of presence or absence of known aquatic compromise. Gut microbiota was assessed via microbial 16S-rRNA gene sequencing and represents the first complete report for both fish species. Despite marked differences in geography, climate, water type, fish species, habitat, diet and gut microbial compositions, the pattern of shifts in microbiota shared by both fish species was nearly identical due to aquatic compromise. Next, these data were subjected to Machine Learning (ML) to examine reliability for using the fish-gut microbiota as an eco-marker for anthropogenic aquatic impacts. Independent of geo-location, ML predicted aquatic compromise with remarkable accuracy (>90%). Overall, this study represents the first multi-species stress-related comparison of its kind and demonstrates the potential of artificial intelligence via ML as a tool for bio-monitoring and detecting compromised aquatic conditions.

ECCO Topical Review on Clinicopathological Spectrum and Differential Diagnosis of Inflammatory Bowel Disease

INTRODUCTION

Many diseases can imitate inflammatory bowel disease [IBD] clinically and pathologically. This review outlines the differential diagnosis of IBD and discusses morphological pointers and ancillary techniques that assist with the distinction between IBD and its mimics.

METHODS

European Crohn's and Colitis Organisation [ECCO] Topical Reviews are the result of an expert consensus. For this review, ECCO announced an open call to its members and formed three working groups [WGs] to study clinical aspects, pathological considerations, and the value of ancillary techniques. All WGs performed a systematic literature search.

RESULTS

Each WG produced a draft text and drew up provisional Current Practice Position [CPP] statements that highlighted the most important conclusions. Discussions and a preliminary voting round took place, with subsequent revision of CPP statements and text and a further meeting to agree on final statements.

CONCLUSIONS

Clinicians and pathologists encounter a wide variety of mimics of IBD, including infection, drug-induced disease, vascular disorders, diverticular disease, diversion proctocolitis, radiation damage, and immune disorders. Reliable distinction requires a multidisciplinary approach.

Functional profile of host microbiome indicates Clostridioides difficile infection

Clostridioides difficile infection (CDI) is a gastro-intestinal (GI) infection that illustrates how perturbations in symbiotic host-microbiome interactions render the GI tract vulnerable to the opportunistic pathogens. CDI also serves as an example of how such perturbations could be reversed via gut microbiota modulation mechanisms, especially fecal microbiota transplantation (FMT). However, microbiome-mediated diagnosis of CDI remains understudied. Here, we evaluated the diagnostic capabilities of the fecal microbiome on the prediction of CDI. We used the metagenomic sequencing data from ten previous studies, encompassing those acquired from CDI patients treated by FMT, CDI-negative patients presenting other intestinal health conditions, and healthy volunteers taking antibiotics. We designed a hybrid species/function profiling approach that determines the abundances of microbial species in the community contributing to its functional profile. These functionally informed taxonomic profiles were then used for classification of the microbial samples. We used logistic regression (LR) models using these features, which showed high prediction accuracy (with an average A U C ≥ 0.91 ), substantiating that the species/function composition of the gut microbiome has a robust diagnostic prediction of CDI. We further assessed the confounding impact of antibiotic therapy on CDI prediction and found that it is distinguishable from the CDI impact. Finally, we devised a log-odds score computed from the output of the LR models to quantify the likelihood of CDI in a gut microbiome sample and applied it to evaluating the effectiveness of FMT based on post-FMT microbiome samples. The results showed that the gut microbiome of patients exhibited a gradual but steady improvement after receiving successful FMT, indicating the restoration of the normal microbiome functions.

Characteristics of Fecal Microbiota and Machine Learning Strategy for Fecal Invasive Biomarkers in Pediatric Inflammatory Bowel Disease

Background

Early diagnosis and treatment of pediatric Inflammatory bowel disease (PIBD) is challenging due to the complexity of the disease and lack of disease specific biomarkers. The novel machine learning (ML) technique may be a useful tool to provide a new route for the identification of early biomarkers for the diagnosis of PIBD.

Methods

In total, 66 treatment naive PIBD patients and 27 healthy controls were enrolled as an exploration cohort. Fecal microbiome profiling using 16S rRNA gene sequencing was performed. The correlation between microbiota and inflammatory and nutritional markers was evaluated using Spearman's correlation. A random forest model was used to set up an ML approach for the diagnosis of PIBD using 1902 markers. A validation cohort including 14 PIBD and 48 irritable bowel syndrome (IBS) was enrolled to further evaluate the sensitivity and accuracy of the model.

Result

Compared with healthy subjects, PIBD patients showed a significantly lower diversity of the gut microbiome. The increased Escherichia-Shigella and Enterococcus were positively correlated with inflammatory markers and negatively correlated with nutrition markers, which indicated a more severe disease. A diagnostic ML model was successfully set up for differential diagnosis of PIBD integrating the top 11 OTUs. This diagnostic model showed outstanding performance at differentiating IBD from IBS in an independent validation cohort.

Conclusion

The diagnosis penal based on the ML of the gut microbiome may be a favorable tool for the precise diagnosis and treatment of PIBD. A study of the relationship between disease status and the microbiome was an effective way to clarify the pathogenesis of PIBD.

Can the Salivary Microbiome Predict Cardiovascular Diseases? Lessons Learned From the Qatari Population

Background: Many studies have linked dysbiosis of the gut microbiome to the development of cardiovascular diseases (CVD). However, studies assessing the association between the salivary microbiome and CVD risk on a large cohort remain sparse. This study aims to identify whether a predictive salivary microbiome signature is associated with a high risk of developing CVD in the Qatari population. Methods: Saliva samples from 2,974 Qatar Genome Project (QGP) participants were collected from Qatar Biobank (QBB). Based on the CVD score, subjects were classified into low-risk (LR < 10) (n = 2491), moderate-risk (MR = 10-20) (n = 320) and high-risk (HR > 30) (n = 163). To assess the salivary microbiome (SM) composition, 16S-rDNA libraries were sequenced and analyzed using QIIME-pipeline. Machine Learning (ML) strategies were used to identify SM-based predictors of CVD risk. Results: Firmicutes and Bacteroidetes were the predominant phyla among all the subjects included. Linear Discriminant Analysis Effect Size (LEfSe) analysis revealed that Clostridiaceae and Capnocytophaga were the most significantly abundant genera in the LR group, while Lactobacillus and Rothia were significantly abundant in the HR group. ML based prediction models revealed that Desulfobulbus, Prevotella, and Tissierellaceae were the common predictors of increased risk to CVD. Conclusion: This study identified significant differences in the SM composition in HR and LR CVD subjects. This is the first study to apply ML-based prediction modeling using the SM to predict CVD in an Arab population. More studies are required to better understand the mechanisms of how those microbes contribute to CVD.

Machine Learning Prediction Model for Inflammatory Bowel Disease Based on Laboratory Markers. Working Model in a Discovery Cohort Study

Inflammatory bowel disease (IBD) is a chronic, incurable disease involving the gastrointestinal tract. It is characterized by complex, unclear pathogenesis, increased prevalence worldwide, and a wide spectrum of extraintestinal manifestations and comorbidities. Recognition of IBD remains challenging and delays in disease diagnosis still poses a significant clinical problem as it negatively impacts disease outcome. The main diagnostic tool in IBD continues to be invasive endoscopy. We aimed to create an IBD machine learning prediction model based on routinely performed blood, urine, and fecal tests. Based on historical patients’ data (702 medical records: 319 records from 180 patients with ulcerative colitis (UC) and 383 records from 192 patients with Crohn’s disease (CD)), and using a few simple machine learning classificators, we optimized necessary hyperparameters in order to get reliable few-features prediction models separately for CD and UC. Most robust classificators belonging to the random forest family obtained 97% and 91% mean average precision for CD and UC, respectively. For comparison, the commonly used one-parameter approach based on the C-reactive protein (CRP) level demonstrated only 81% and 61% average precision for CD and UC, respectively. Results of our study suggest that machine learning prediction models based on basic blood, urine, and fecal markers may with high accuracy support the diagnosis of IBD. However, the test requires validation in a prospective cohort.

Challenges and opportunities in the application of artificial intelligence in gastroenterology and hepatology

Artificial intelligence (AI) is an umbrella term used to describe a cluster of interrelated fields. Machine learning (ML) refers to a model that learns from past data to predict future data. Medicine and particularly gastroenterology and hepatology, are data-rich fields with extensive data repositories, and therefore fruitful ground for AI/ML-based software applications. In this study, we comprehensively review the current applications of AI/ML-based models in these fields and the opportunities that arise from their application. Specifically, we refer to the applications of AI/ML-based models in prevention, diagnosis, management, and prognosis of gastrointestinal bleeding, inflammatory bowel diseases, gastrointestinal premalignant and malignant lesions, other nonmalignant gastrointestinal lesions and diseases, hepatitis B and C infection, chronic liver diseases, hepatocellular carcinoma, cholangiocarcinoma, and primary sclerosing cholangitis. At the same time, we identify the major challenges that restrain the widespread use of these models in healthcare in an effort to explore ways to overcome them. Notably, we elaborate on the concerns regarding intrinsic biases, data protection, cybersecurity, intellectual property, liability, ethical challenges, and transparency. Even at a slower pace than anticipated, AI is infiltrating the healthcare industry. AI in healthcare will become a reality, and every physician will have to engage with it by necessity.

Immuno-Hormonal, Genetic and Metabolic Profiling of Newborns as a Basis for the Life-Long OneHealth Medical Record: A Scoping Review

Holistic and life-long medical surveillance is the core of personalised medicine and supports an optimal implementation of both preventive and curative healthcare. Personal medical records are only partially unified by hospital or general practitioner informatics systems, but only for citizens with long-term permanent residence. Otherwise, insight into the medical history of patients greatly depends on their medical archive and memory. Additionally, occupational exposure records are not combined with clinical or general practitioner records. Environmental exposure starts preconceptionally and continues during pregnancy by transplacental exposure. Antenatal exposure is partially dependent on parental lifestyle, residence and occupation. Newborn screening (NBS) is currently being performed in developed countries and includes testing for rare genetic, hormone-related, and metabolic conditions. Transplacental exposure to substances such as endocrine disruptors, air pollutants and drugs may have life-long health consequences. However, despite the recognised impact of transplacental exposure on the increased risk of metabolic syndrome, neurobehavioral disorders as well as immunodisturbances including allergy and infertility, not a single test within NBS is geared toward detecting biomarkers of exposure (xenobiotics or their metabolites, nutrients) or effect such as oestradiol, testosterone and cytokines, known for being associated with various health risks and disturbed by transplacental xenobiotic exposures. The outcomes of ongoing exposome projects might be exploited to this purpose. Developing and using a OneHealth Medical Record (OneHealthMR) may allow the incorporated chip to harvest information from different sources, with high integration added value for health prevention and care: environmental exposures, occupational health records as well as diagnostics of chronic diseases, allergies and medication usages, from birth and throughout life. Such a concept may present legal and ethical issues pertaining to personal data protection, requiring no significant investments and exploits available technologies and algorithms, putting emphasis on the prevention and integration of environmental exposure and health data.