The Mahalanobis distance

Maesschalck, Roy De; Jouan-Rimbaud, Delphine; Massart, D.L.

doi:10.1016/s0169-7439(99)00047-7

Cited by 1,829 publications

(895 citation statements)

References 43 publications

Supporting

Mentioning

821

Contrasting

Unclassified

Order By: Relevance

“…Statistical analysis using standard measures, such as p values, is not applicable to this multivariate data analysis. Rather, results from principal components analysis were used in canonic discriminant analysis to create a model that maximizes the distance among the two sample classes (i.e., cancer versus noncancer) (23).…”

Section: Data Processing and Analysis For Discovery And Training Phasementioning

confidence: 99%

“…Quantification of the discrimination between two sample classes was performed using the Mahalanobis distance, a measure of class separation between different data clusters (23). A Mahalanobis distance of 3 or greater indicates that the classes are discrete from each other, and that the sensor array may be able to classify unknown samples belonging to different groups.…”

Section: Data Processing and Analysis For Discovery And Training Phasementioning

confidence: 99%

See 1 more Smart Citation

Detection of Lung Cancer by Sensor Array Analyses of Exhaled Breath

Machado

Laskowski²,

Deffenderfer³

et al. 2005

Am J Respir Crit Care Med

533

429

View full text Add to dashboard Cite

Rationale: Electronic noses are successfully used in commercial applications, including detection and analysis of volatile organic compounds in the food industry. Objectives: We hypothesized that the electronic nose could identify and discriminate between lung diseases, especially bronchogenic carcinoma. Methods: In a discovery and training phase, exhaled breath of 14 individuals with bronchogenic carcinoma and 45 healthy control subjects or control subjects without cancer was analyzed. Principal components and canonic discriminant analysis of the sensor data was used to determine whether exhaled gases could discriminate between cancer and noncancer. Discrimination between classes was performed using Mahalanobis distance. Support vector machine analysis was used to create and apply a cancer prediction model prospectively in a separate group of 76 individuals, 14 with and 62 without cancer. Main Results: Principal components and canonic discriminant analysis demonstrated discrimination between samples from patients with lung cancer and those from other groups. In the validation study, the electronic nose had 71.4% sensitivity and 91.9% specificity for detecting lung cancer; positive and negative predictive values were 66.6 and 93.4%, respectively. In this population with a lung cancer prevalence of 18%, positive and negative predictive values were 66.6 and 94.5%, respectively. Conclusion: The exhaled breath of patients with lung cancer has distinct characteristics that can be identified with an electronic nose. The results provide feasibility to the concept of using the electronic nose for managing and detecting lung cancer.

show abstract

Section: Data Processing and Analysis For Discovery And Training Phasementioning

confidence: 99%

Section: Data Processing and Analysis For Discovery And Training Phasementioning

confidence: 99%

Detection of Lung Cancer by Sensor Array Analyses of Exhaled Breath

Machado

Laskowski²,

Deffenderfer³

et al. 2005

Am J Respir Crit Care Med

533

429

View full text Add to dashboard Cite

show abstract

“…Then, the T 2 values and the upper control limit were computed for each digester with Statistica 10 Ò (Statsoft, France) using the means and variance-covariance matrix of the training data set cleared from outliers. Information relative to the Hotelling's T 2 test for process monitoring can be found in [30].…”

Section: Statistical Analysesmentioning

confidence: 99%

“…However, the training data set to calculate the distance from the steady-state process must be carefully managed [11,30]. True performance of a gas sensor array for biogas process monitoring could only be estimated by extending the present work to conditions prevailing in real agricultural situations while comparing results with VFA monitoring in the liquid phase, the latter being a well accepted method for identifying organic overload state the anaerobic process [8,[37][38][39][40].…”

Section: Future Workmentioning

confidence: 99%

Evaluation of an electronic nose for the early detection of organic overload of anaerobic digesters

Adam

Lemaigre²,

Romain

et al. 2012

Bioprocess Biosyst Eng

View full text Add to dashboard Cite

This study aimed at analysing the utilization of an electronic nose (e-nose) to serve as a specific monitoring tool for anaerobic digestion process, especially for detecting organic overload. An array of non specific metal oxide semiconductor gas sensors were used to detect process faults due to organic overload events in twelve 1.8-L anaerobic semi-continuous reactors. Three different load strategies were followed: (1) a cautious organic load (1.3 gVS L -1 day -1 ); (2) an increasing load strategy (1.3-5.3 gVS L -1 day -1 ) and (3) a cautious organic load with load pulses of up to 12 gVS L -1 day -1 . A first monitoring campaign was conducted with three different substrates: sucrose, maize oil and a mix of sucrose/oil during 60 days. The second campaign was run with dry sugar beet pulp for 45 days. Hotelling's T 2 value and upper control limit to a reference set of digesters fed with a cautious OLR (1.3 gVS L -1 day -1 ) was used as indirect state variable of the reactors. Overload situations were identified by the e-nose apparatus with Hotelling's T 2 values at least four times higher in magnitude than the upper control limit of 23.7. These results confirmed that the e-nose technology appeared promising for online detection of process imbalances in the domain of anaerobic digestion.

show abstract

“…Figure 7a schematically illustrates the concept for a three-component mixture in a three-dimensional space. Other measures of distance between the reference point and subsequently measured test points, such as the Mahalanobis distance, which takes into account correlations in the data and is independent of the scale, can also be used [51].…”

Section: Thermometer Ion-based Strategy For Instrument Tuningmentioning

confidence: 99%

A method for monitoring and controlling reproducibility of intensity data in complex electrospray mass spectra: A thermometer ion-based strategy

Lecchi¹,

Zhao²,

Wiggins³

et al. 2009

J. Am. Soc. Mass Spectrom.

View full text Add to dashboard Cite

Reproducibility in mass spectral data is important in both biomarker discovery and spectral database searching. We report a strategy, employing a series of substituted benzylpyridinium thermometer ions that can be used to monitor changes in performance of multiple aspects of an electrospray ionization source that impact the intensity axis of a spectrum. Performance attributes, which could confound even isotope-based quantification strategies, are readily assessed using a mixture of thermometer ions. Based on the observed behavior of the ions, a procedure is proposed for monitoring instrument performance and compensating for factors that affect reproducibility across both time and instruments. (J Am Soc Mass Spectrom 2009, 20, 398 -410)

show abstract

The Mahalanobis distance

Cited by 1,829 publications

References 43 publications

Detection of Lung Cancer by Sensor Array Analyses of Exhaled Breath

Detection of Lung Cancer by Sensor Array Analyses of Exhaled Breath

Evaluation of an electronic nose for the early detection of organic overload of anaerobic digesters

A method for monitoring and controlling reproducibility of intensity data in complex electrospray mass spectra: A thermometer ion-based strategy

Contact Info

Product

Resources

About