IMS2 – An integrated medical software system for early lung cancer detection using ion mobility spectrometry data of human breath

Baumbach, Jan; Bunkowski, Alexander; Lange, Sita J.; Oberwahrenbrock, Timm; Kleinbölting, Nils; Rahmann, Sven

doi:10.1515/jib-2007-75

Cited by 26 publications

(30 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…from breath analysis) [3,4,13,14] and process control [15][16][17][18][19][20][21][22]. For such applications, IMS measurements faces challenges such as humid and rather complex samples, requirement of a specific sampling procedure adapted to the application, fast pre-separation techniques like multi-capillary columns and most importantly, suitable data processing techniques which include databases of relevant analytes for automatic characterisation of the signals detected in an IMS chromatogram [23][24][25][26][27][28], and different data pre-processing steps [29][30][31][32].…”

Section: Introductionmentioning

confidence: 99%

Empirical prediction of reduced ion mobilities of secondary alcohols

Hariharan

Baumbach

Vautz

2009

Int. J. Ion Mobil. Spec.

View full text Add to dashboard Cite

Ion Mobility Spectrometry is a powerful method for the rapid identification of gas-phase analytes and finds its usage in various fields including the sensitive analysis of extremely complex and humid mixtures such as human breath when additional pre-separation techniques are applied. The output data from an ion mobility spectrometer (IMS), equipped with a Multi-Capillary Column (MCC) for pre-separation, is a chromatogram of the signal intensity versus a particular retention time and a specific reduced ion mobility which are the characteristics of the detected analyte. Hence, it is important to have a database of analytes with both the values for comparison and identification of peaks in any IMS chromatogram. Commonly, such databases are collected by measurements of reference analytes. It is obvious that a prognosis of the values, without the time consuming and costly reference measurements, would be a considerable facilitation for a preliminary identification of unknowns and development of databases. In this study, a correlation between the reduced ion mobilities and the number of carbon atoms was found for secondary alcohols. The correlation was then used to predict the reduced ion mobilities of other analytes in the same homologous series. To verify the accuracy of the prognosis, the analytes were measured individually using a 63 Ni-MCC-IMS and compared to the predicted values. The results of the prognosis show an accuracy higher than 99.5%.

show abstract

Section: Introductionmentioning

confidence: 99%

Empirical prediction of reduced ion mobilities of secondary alcohols

Hariharan

Baumbach

Vautz

2009

Int. J. Ion Mobil. Spec.

View full text Add to dashboard Cite

show abstract

“…One study applied naive Bayes, multi layer perceptron, and SVM to a set of MCC/IMS chromatograms and achieved an outstanding performance (accuracy and AUC both 99%) (Baumbach et al, 2007). Despite the good results, one has to consider that 1) the prediction was done on a comparatively large feature set, where each chromatogram was separated by a grid, while each feature was calculated as the average intensity of the corresponding grid element, and 2) the accuracy and AUC were evaluated on the training set, without cross validation, as in the study of Westhoff et al (2011).…”

Section: Copd+bc Classificationmentioning

confidence: 99%

Integrated statistical learning of metabolic ion mobility spectrometry profiles for pulmonary disease identification

Hauschild¹,

Baumbach²

2012

Genet. Mol. Res.

View full text Add to dashboard Cite

ABSTRACT. Exhaled air carries information on human health status. Ion mobility spectrometers combined with a multi-capillary column (MCC/IMS) is a well-known technology for detecting volatile organic compounds (VOCs) within human breath. This technique is relatively inexpensive, robust and easy to use in every day practice. However, the potential of this methodology depends on successful application of computational approaches for finding relevant VOCs and classification of patients into disease-specific profile groups based on the detected VOCs. We developed an integrated state-of-the-art system using sophisticated statistical learning techniques for VOC-based feature selection and supervised classification into patient groups. We analyzed breath data from 84 volunteers, each of them either suffering from chronic obstructive pulmonary disease (COPD), or both COPD and bronchial carcinoma (COPD + BC), as well as from 35 healthy volunteers, comprising a control group (CG). We standardized and ©FUNPEC-RP www.funpecrp.com.br Genetics and Molecular Research 11 (3): 2733-2744 (2012) A.-C. Hauschild et al. 2734 integrated several statistical learning methods to provide a broad overview of their potential for distinguishing the patient groups. We found that there is strong potential for separating MCC/IMS chromatograms of healthy controls and COPD patients (best accuracy COPD vs CG: 94%). However, further examination of the impact of bronchial carcinoma on COPD/no-COPD classification performance is necessary (best accuracy CG vs COPD vs COPD + BC: 79%). We also extracted 20 high-scoring VOCs that allowed differentiating COPD patients from healthy controls. We conclude that these statistical learning methods have a generally high accuracy when applied to wellstructured, medical MCC/IMS data.

show abstract

“…1.500.000 data points and more from each analyses). As a consequence, data processing must be efficient and has to guarantee reproducible results with respect to the location (ion mobility and retention time) of the numerous detected signals and of signal height for quantification-such procedures are currently under development [29][30][31][32].…”

Section: Introductionmentioning

confidence: 99%

An implementable approach to obtain reproducible reduced ion mobility

Vautz

Bödeker

Baumbach

et al. 2009

Int. J. Ion Mobil. Spec.

Self Cite

View full text Add to dashboard Cite

Ion mobility spectrometry is increasingly in demand for medical applications and its potential for implementation in food quality and safety or process control suggest rising use of instruments in this field as well. All those samples are commonly extremely complex and mostly humid mixtures. Therefore, pre-separation techniques have to be applied. As ion mobility spectrometers with gas-chromatographic pre-separation acquire a huge amount of data, effective data processing and automated evaluation by comparison of detected peak pattern with data bases have to be utilised. This requires accurate on-line calibration of the instruments to guarantee reproducible results, in particular with respect to identification of an analyte by determination of its ion mobility and retention time. To reduce environmental and instrumental influence, the reduced ion mobility is used. It is derived from the drift time normalised to electric field, length of the drift region and to temperature and pressure of the drift gas (traditional method). All data required for this normalisation are afflicted with a particular error and thus leading to a deviation of the calculated ion mobility value. Furthermore, this traditional method enables a calculation of the reduced ion mobility only after the measurement. To avoid those errors and to enable on-line calibration of ion mobility, an instrument specific factor is implemented generally representing all relevant variables. This factor can be determined from an initial measurement of few spectra and can thereafter be applied on the following measurement. The application of this approach obtained reproducible reduced ion mobility values for positive and negative ions over a broad drift time range and for common variation of ambient conditions as well for varying instrument conditions such as electric fields respectively drift times and in different drift gases. Moreover, the reduced ion mobility is available already during the measurements with a significantly higher reliability and accuracy which was increased to a factor of 5 compared to the traditional ion mobility determination and enables an on-line identification of analytes for the first time.

show abstract

IMS2 – An integrated medical software system for early lung cancer detection using ion mobility spectrometry data of human breath

Cited by 26 publications

References 8 publications

Empirical prediction of reduced ion mobilities of secondary alcohols

Empirical prediction of reduced ion mobilities of secondary alcohols

Integrated statistical learning of metabolic ion mobility spectrometry profiles for pulmonary disease identification

An implementable approach to obtain reproducible reduced ion mobility

Contact Info

Product

Resources

About