Dataset Information

Data Mining Techniques Applied to Hydrogen Lactose Breath Test.

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

ACCESS DATA

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]

PMID: 28125620

Similar Datasets

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.

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 ?-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 ?-casein) and A1 ?-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.

Dataset Information

Data Mining Techniques Applied to Hydrogen Lactose Breath Test.

Objectives

Methods

Results

Conclusions

Publications

Data Mining Techniques Applied to Hydrogen Lactose Breath Test.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets