Data Mining Techniques Applied to Hydrogen Lactose Breath Test.
Ontology highlight
ABSTRACT: Objectives
Analyze a set of data of hydrogen breath tests by use of data mining tools. Identify new patterns of H2 production.Methods
Hydrogen breath tests data sets as well as k-means clustering as the data mining technique to a dataset of 2571 patients.Results
Six different patterns have been extracted upon analysis of the hydrogen breath test data. We have also shown the relevance of each of the samples taken throughout the test.Conclusions
Analysis of the hydrogen breath test data sets using data mining techniques has identified new patterns of hydrogen generation upon lactose absorption. We can see the potential of application of data mining techniques to clinical data sets. These results offer promising data for future research on the relations between gut microbiota produced hydrogen and its link to clinical symptoms.
SUBMITTER: Rubio-Escudero C
PROVIDER: S-EPMC5268498 | biostudies-literature | 2017
REPOSITORIES: biostudies-literature
Publications
Data Mining Techniques Applied to Hydrogen Lactose Breath Test.
Rubio-Escudero Cristina C Valverde-Fernández Justo J Nepomuceno-Chamorro Isabel I Pontes-Balanza Beatriz B Hernández-Mendoza Yoedusvany Y Rodríguez-Herrera Alfonso A
PloS one 20170126 1
<h4>Objectives</h4>Analyze a set of data of hydrogen breath tests by use of data mining tools. Identify new patterns of H2 production.<h4>Methods</h4>Hydrogen breath tests data sets as well as k-means clustering as the data mining technique to a dataset of 2571 patients.<h4>Results</h4>Six different patterns have been extracted upon analysis of the hydrogen breath test data. We have also shown the relevance of each of the samples taken throughout the test.<h4>Conclusions</h4>Analysis of the hydr ...[more]
Similar Datasets
Project description:BackgroundLactose malabsorption is a common condition that affects a broad segment of the population. Clinical diagnosis based on symptom recall can be unreliable and conventional testing can be inconvenient, requiring expensive laboratory-based equipment and conduction of the testing in a clinical setting.ObjectiveThe aim of this study is to assess the performance of a digital handheld hydrogen breath monitor (GIMate) in diagnosing lactose malabsorption compared to a US Food and Drug Administration (FDA)-cleared device (H2 Check) for the same indication.MethodsAn interventional crossover study was performed in adult participants with a prior confirmed diagnosis of lactose malabsorption or a suspected history of lactose intolerance.ResultsA total of 31 participants (mean age 33.9 years) were enrolled in the study. There was 100% positive percent agreement and 100% negative percent agreement between the GIMate monitor and the H2 Check. Correlation between gastrointestinal symptoms and hydrogen values was positive at 0.82 (P<.001).ConclusionsThe digital handheld GIMate breath monitor achieved equivalent diagnostic performance to that of an FDA-cleared device in the diagnosis of lactose malabsorption.Trial registrationClinicalTrials.gov NCT04754724; https://clinicaltrials.gov/ct2/show/NCT04754724.
| S-EPMC8561400 | biostudies-literature
Project description:Background and aimThe absence of lactase in the intestinal villi due to mucosal injury or genetic factors causes undigested lactose to reach the colon where it is fermented. Lactose intolerance is diagnosed based on clinical symptoms like bloating, abdominal pain and flatulence, lactose hydrogen breath test (HBT), and lactose tolerance test. No Indian studies are available on the use of lactase supplements. The aim was to study the effect of lactase chewable tablets on clinical symptoms and hydrogen breath excretion in patients with lactose intolerance.MethodsThis was a randomized, double-blind, crossover placebo-controlled trial to study the effect of lactase tablets on symptoms and hydrogen breath levels in adults with lactose intolerance, confirmed by Lactose HBT. Clinical symptom severity was recorded using a visual analog scale, and HBT was performed every 30 min for 180 min. As it was a crossover design, the same patients were tested with both lactase and placebo, acting as their own controls with a washout period of 1 week between visits.ResultsForty-seven patients (mean age 33.6 years; 30 males) with lactose intolerance formed the study group. Clinical symptoms, mean clinical score (P < 0.05), and mean hydrogen breath levels (P < 0.05) were improved when the patients were given lactase. Reduction in cumulative hydrogen breath level over 180 min was 55% when patients received lactase compared to placebo.ConclusionsOrally supplemented lactase enzyme significantly reduced the clinical symptoms and hydrogen breath excretion in patients with lactose intolerance.
| S-EPMC7812489 | biostudies-literature
Project description:Due to increasing use of technology-enhanced educational assessment, data mining methods have been explored to analyse process data in log files from such assessment. However, most studies were limited to one data mining technique under one specific scenario. The current study demonstrates the usage of four frequently used supervised techniques, including Classification and Regression Trees (CART), gradient boosting, random forest, support vector machine (SVM), and two unsupervised methods, Self-organizing Map (SOM) and k-means, fitted to one assessment data. The USA sample (N = 426) from the 2012 Program for International Student Assessment (PISA) responding to problem-solving items is extracted to demonstrate the methods. After concrete feature generation and feature selection, classifier development procedures are implemented using the illustrated techniques. Results show satisfactory classification accuracy for all the techniques. Suggestions for the selection of classifiers are presented based on the research questions, the interpretability and the simplicity of the classifiers. Interpretations for the results from both supervised and unsupervised learning methods are provided.
| S-EPMC6265513 | biostudies-literature
Project description:Data mining is the process of analyzing a massive amount of data to identify meaningful patterns and detect relations, which can lead to future trend prediction and appropriate decision making. Data mining applications are significant in marketing, banking, medicine, etc. In this paper, we present an overview of data mining applications in medicine to provide a clear view of the challenges and previous works in this area for researchers. Data mining techniques such as Decision Tree, Random Forest, K-means Clustering, Support Vector Machine, Logistic Regression, Neural Network, Naive Bayes, and association rule mining are used for diagnosing, prognosis, classifying, constructing predictive models, and analyzing risk factors of various diseases. The main objective of the paper is to analyze and compare different data mining techniques used in the medical applications. We present a summary of the results and provide comparison analysis of the data mining methods employed by the reviewed articles.Supplementary informationThe online version contains supplementary material available at 10.1007/s40200-021-00884-2.
| S-EPMC8630112 | biostudies-literature
Project description:BackgroundHyperbilirubinemia is emerging as an increasingly common problem in newborns due to a decreasing hospital length of stay after birth. Jaundice is the most common disease of the newborn and although being benign in most cases it can lead to severe neurological consequences if poorly evaluated. In different areas of medicine, data mining has contributed to improve the results obtained with other methodologies.Hence, the aim of this study was to improve the diagnosis of neonatal jaundice with the application of data mining techniques.MethodsThis study followed the different phases of the Cross Industry Standard Process for Data Mining model as its methodology.This observational study was performed at the Obstetrics Department of a central hospital (Centro Hospitalar Tâmega e Sousa--EPE), from February to March of 2011. A total of 227 healthy newborn infants with 35 or more weeks of gestation were enrolled in the study. Over 70 variables were collected and analyzed. Also, transcutaneous bilirubin levels were measured from birth to hospital discharge with maximum time intervals of 8 hours between measurements, using a noninvasive bilirubinometer.Different attribute subsets were used to train and test classification models using algorithms included in Weka data mining software, such as decision trees (J48) and neural networks (multilayer perceptron). The accuracy results were compared with the traditional methods for prediction of hyperbilirubinemia.ResultsThe application of different classification algorithms to the collected data allowed predicting subsequent hyperbilirubinemia with high accuracy. In particular, at 24 hours of life of newborns, the accuracy for the prediction of hyperbilirubinemia was 89%. The best results were obtained using the following algorithms: naive Bayes, multilayer perceptron and simple logistic.ConclusionsThe findings of our study sustain that, new approaches, such as data mining, may support medical decision, contributing to improve diagnosis in neonatal jaundice.
| S-EPMC3557145 | biostudies-literature
Project description:Floods are among the devastating types of disasters in terms of human life, social and financial losses. Authoritative data from flood gauges are scarce in arid regions because of the specific type of dry climate that dysfunctions these measuring devices. Hence, social media data could be a useful tool in this case, where a wealth of information is available online. This study investigates the reliability of flood related data quality collected from social media, particularly for an arid region where the usage of flow gauges is limited. The data (text, images and videos) of social media, related to a flood event, was analyzed using the Machine Learning approach. For this reason, digital data (758 images and 1413 video frames) was converted into numeric values through ResNet50 model using the VGG-16 architecture. Numeric data of images, videos and text was further classified using different Machine Learning algorithms. Receiver operating characteristics (ROC) curve and area under curve (AUC) methods were used to evaluate and compare the performance of the developed machine learning algorithms. This novel approach of studying the quality of social media data could be a reliable alternative in the absence of real-time flow gauges data. A flash flood that occurred in the United Arab Emirates (UAE) from March 7-11, 2016 was selected as the focus of this study. Random forest showed the highest accuracy of 80.18% among the five other classifiers for images and videos. Precipitation/rainfall data were used to validate social media data, which showed a significant relationship between rainfall and the number of posts. The validity of the machine learning models was assessed using the area under the curve, precision-recall curve, root mean square error, and kappa statistics to confirm the validity and accuracy of the model. The data quality of YouTube videos was found to have the highest accuracy followed by Facebook, Flickr, Twitter, and Instagram. These results showed that social media data could be used when gauge data is unavailable.
| S-EPMC9037947 | biostudies-literature
Project description:ObjectiveThe most common form of measurement of breath alcohol content (BrAC) is through the use of a diode catheter. This study aims to test the accuracy of breath alcohol analysis through different manipulations.MethodsBrAC was measured after individuals consumed each standardized beer until they reached a 0.1 BrAC. Then, the individuals were breath analyzed while not providing full effort, using the side of their mouths, immediately after hyperventilating, 5 and 10 min after hyperventilation, immediately after a sip of water, and 5 min after that water.ResultsThere were 54 individuals. Two baselines were used as the controls. The first baseline was a mean BrAC of. 104 with standard deviation of +0.008 for poor effort, side of mouth, and hyperventilating. The second baseline used for drinking water manipulations was a BrAC of 0.099 + 0.11. Poor effort (mean + standard deviation: 0.099 ± 0.10, P < 0.0001), immediately after hyperventilating (0.086 ± 0.011, P < 0.0001), 5 min after hyperventilating (0.099 ± 0.009, P < 0.0001), and 10 min after hyperventilating (0.099 ± 0.011, P < 0.0001) were all found to be statistically significant in their ability to lower BrAC. Both immediately after water (0.084 ± 0.011, P < 0001) and 5 min after drinking water (0.096 ± 0.13, P < 0.0001) were found to have significantly altered the BrAC.ConclusionOur research shows that manipulations can alter BrAC readings significantly. Breath analyzer operators should be cognizant of these methods that may lead to falsely lower BrAC readings.
| S-EPMC7204959 | biostudies-literature
Project description:BackgroundGlucose hydrogen breath testing is a noninvasive test for small intestine bacterial overgrowth (SIBO). A positive glucose hydrogen breath test is common in children from low-income countries and has been found to be associated with malnutrition as measured by stunted growth. The microbiome associated with positive breath testing is relatively unstudied.MethodsWe performed 16 S V4 rDNA microbiome analysis on the stool of 90 Bangladeshi children aged 2 years from an impoverished neighborhood who were tested at the same time for SIBO by glucose hydrogen breath testing. Data were analyzed by linear discriminant analysis effect size with SIBO as the outcome. Any selected genera were tested individually by Wilcoxon's rank-sum test to ensure that linear discriminant analysis effect size results were not outlier-skewed.ResultsLinear discriminant analysis effect size analysis identified Lactobacillus (linear discriminate analysis score, 4.59; P = .03) as over-represented in 15 out of the 90 children who were SIBO positive.ConclusionsThese results suggest that glucose hydrogen breath test positivity in children from low-income settings may be due to an upper intestinal Lactobacillus bloom, potentially explaining the association of SIBO with the gut damage and inflammation that leads to malnutrition.
| S-EPMC6602902 | biostudies-literature
Project description:BackgroundAdult lactase non-persistence (LNP) is due to low lactase expression, resulting in lactose malabsorption (LM). LNP is a genetic trait, but is typically determined by LM markers including breath H2, blood glucose, and urinary galactose after a lactose tolerance test. Known validity of these markers using milk is limited, despite being common practice. Compositional variation, such as β-casein variants, in milk may impact diagnostic efficacy. This study aimed to evaluate the diagnostic accuracy to detect LNP using these commonly measured LM markers after both lactose and milk challenges.MethodsFourty healthy young women were challenged with 50 g lactose then randomized for separate cross-over visits to ingest 750 mL milk (37.5 g lactose) as conventional (both A1 and A2 β-casein) and A1 β-casein-free (a2 Milk™) milk. Blood, breath and urine were collected prior to and up to 3 h following each challenge. The presence of C/T13910 and G/A22018 polymorphisms, determined by restriction fragment length polymorphism, was used as the diagnostic reference for LNP.ResultsGenetic testing identified 14 out of 40 subjects as having LNP (C/C13910 and G/G22018). All three LM markers (breath H2, plasma glucose and urinary galactose/creatinine) discriminated between lactase persistence (LP) and LNP following lactose challenge with an area under the receiver operating characteristic (ROC) curve (AUC) of 1.00, 0.75 and 0.73, respectively. Plasma glucose and urinary galactose/creatinine were unreliable (AUC < 0.70) after milk ingestion. The specificity of breath H2 remained high (100%) when milk was used, but sensitivity was reduced with conventional (92.9%) and a2 Milk™ (78.6%) compared to lactose (sensitivities adjusted for lactose content). The breath H2 optimal cut-off value was lower with a2 Milk™ (13 ppm) than conventional milk (21 ppm). Using existing literature cut-off values the sensitivity and specificity of breath H2 was greater than plasma glucose to detect LNP following lactose challenge whereas values obtained for urinary galactose/creatinine were lower than the existing literature cut-offs.ConclusionThis study showed accurate diagnosis of LNP by breath H2 irrespective of the substrate used, although the diagnostic threshold may vary depending on the lactose substrate or the composition of the milk.Trial registrationACTRN12616001694404 . Registered prospectively on December 9, 2016.
| S-EPMC7325051 | biostudies-literature
Project description:The thermo-mechanical properties of streptavidin-conjugated gold nanospheres, adhered to a surface via complex molecular chains, are investigated by two-color infrared asynchronous optical sampling pump-probe spectroscopy. Nanospheres with different surface densities have been deposited and exposed to a plasma treatment to modify their polymer binding chains. The aim is to monitor their optical response in complex chemical environments that may be experienced in, e.g., photothermal therapy or drug delivery applications. By applying unsupervised learning techniques to the spectroscopic traces, we identify their thermo-mechanical response variation. This variation discriminates nanospheres in different chemical environments or different surface densities. Such discrimination is not evident based on a standard analysis of the spectroscopic traces. This kind of analysis is important, given the widespread application of conjugated gold nanospheres in medicine and biology.
| S-EPMC7530730 | biostudies-literature