A psychological symptom based machine learning model for clinical evaluation of irritable bowel syndrome.

Background: Irritable bowel syndrome (IBS) is a chronic functional gastrointestinal disorder characterized by recurrent abdominal pain associated with alterations  in stool form and/or stool frequency. Co-morbidities such as anxiety, depression, fatigue, and insomnia are frequently reported by patients suffering from IBS. Identification of these symptoms should thus be an integral part of an IBS assessment.      However, an optimal tool to screen for core psychological symptoms in IBS is still  missing. Here, we aim to develop a psychological symptom based machine learning model to efficiently help clinicians to identify patients suffering from IBS. Methods: We developed a machine learning workflow to select the most significant psychological features associated with IBS in a dataset including 49 patients with IBS and 35 healthy controls. These features were used to train three different types of machine learning models: logistic regression, decision trees and support vector machine classifiers; which were validated on a holdout validation dataset and an unseen test set. The performance of these models was compared in terms of balanced accuracy scores. Results: A logistic regression model including a combination of symptom features associated with anxiety and fatigue resulted in a balanced accuracy score of 0.93 (0.81-1.0) on unseen test data and outperformed the other comparable models. The same model correctly identified all patients with IBS in a test set (recall score 1) and misclassified one non-IBS subject (precision score 0.91). A complementary post-hoc leave-one-out cross validation analysis including the same symptom features showed similar, but slightly inferior results (balanced accuracy 0.84, recall 0.88, precision 0.86). Conclusions: Inclusion of machine learning based psychological evaluation can complement and improve existing clinical procedure for diagnosis of IBS.

Study protocol of the Bergen brain-gut-microbiota-axis study: A prospective case-report characterization and dietary intervention study to evaluate the effects of microbiota alterations on cognition and anatomical and functional brain connectivity in patients with irritable bowel syndrome.

INTRODUCTION: Irritable bowel syndrome (IBS) is a common clinical label for medically unexplained gastrointestinal (GI) symptoms, recently described as a disturbance of the brain-gut-microbiota (BGM) axis. To gain a better understanding of the mechanisms underlying the poorly understood etiology of IBS, we have designed a multifaceted study that aim to stratify the complex interaction and dysfunction between the brain, the gut, and the microbiota in patients with IBS. METHODS: Deep phenotyping data from patients with IBS (n = 100) and healthy age- (between 18 and 65) and gender-matched controls (n = 40) will be collected between May 2019 and December 2021. Psychometric tests, questionnaires, human biological tissue/samples (blood, faeces, saliva, and GI biopsies from antrum, duodenum, and sigmoid colon), assessment of gastric accommodation and emptying using transabdominal ultrasound, vagal activity, and functional and structural magnetic resonance imaging (MRI) of the brain, are included in the investigation of each participant. A subgroup of 60 patients with IBS-D will be further included in a 12-week low FODMAP dietary intervention-study to determine short and long-term effects of diet on GI symptoms, microbiota composition and functions, molecular GI signatures, cognitive, emotional and social functions, and structural and functional brain signatures. Deep machine learning, prediction tools, and big data analyses will be used for multivariate analyses allowing disease stratification and diagnostic biomarker detection. DISCUSSION: To our knowledge, this is the first study to employ unsupervised machine learning techniques and incorporate systems-based interactions between the central and the peripheral components of the brain-gut-microbiota axis at the levels of the multiomics, microbiota profiles, and brain connectome of a cohort of 100 patients with IBS and matched controls; study long-term safety and efficacy of the low-FODMAP diet on changes in nutritional status, gut microbiota composition, and metabolites; and to investigate changes in the brain and gut connectome after 12 weeks strict low-FODMAP-diet in patients with IBS. However, there are also limitations to the study. As a restrictive diet, the low-FODMAP diet carries risks of nutritional inadequacy and may foster disordered eating patterns. Strict FODMAP restriction induces a potentially unfavourable gut microbiota, although the health effects are unknown. TRIAL REGISTRATION NUMBER: NCT04296552 (ClinicalTrials.gov).

Tensor-Based Method for Residual Water Suppression in 1H Magnetic Resonance Spectroscopic Imaging.

OBJECTIVE: Magnetic resonance spectroscopic imaging (MRSI) signals are often corrupted by residual water and artifacts. Residual water suppression plays an important role in accurate and efficient quantification of metabolites from MRSI. A tensor-based method for suppressing residual water is proposed. METHODS: A third-order tensor is constructed by stacking the Löwner matrices corresponding to each MRSI voxel spectrum along the third mode. A canonical polyadic decomposition is applied on the tensor to extract the water component and to, subsequently, remove it from the original MRSI signals. RESULTS: The proposed method applied on both simulated and in-vivo MRSI signals showed good water suppression performance. CONCLUSION: The tensor-based Löwner method has better performance in suppressing residual water in MRSI signals as compared to the widely used subspace-based Hankel singular value decomposition method. SIGNIFICANCE: A tensor method suppresses residual water simultaneously from all the voxels in the MRSI grid and helps in preventing the failure of the water suppression in single voxels.