Electronic Nose Sensor Drift Affects Diagnostic Reliability and Accuracy of Disease-Specific Algorithms

Abstract

Sensor drift is a well-known disadvantage of electronic nose (eNose) technology and may affect the accuracy of diagnostic algorithms. Correction for this phenomenon is not routinely performed. The aim of this study was to investigate the influence of eNose sensor drift on the development of a disease-specific algorithm in a real-life cohort of inflammatory bowel disease patients (IBD). In this multi-center cohort, patients undergoing colonoscopy collected a fecal sample prior to bowel lavage. Mucosal disease activity was assessed based on endoscopy. Controls underwent colonoscopy for various reasons and had no endoscopic abnormalities. Fecal eNose profiles were measured using Cyranose 320®. Fecal samples of 63 IBD patients and 63 controls were measured on four subsequent days. Sensor data displayed associations with date of measurement, which was reproducible across all samples irrespective of disease state, disease activity state, disease localization and diet of participants. Based on logistic regression, corrections for sensor drift improved accuracy to differentiate between IBD patients and controls based on the significant differences of six sensors (p = 0.004; p < 0.001; p = 0.001; p = 0.028; p < 0.001 and p = 0.005) with an accuracy of 0.68. In this clinical study, short-term sensor drift affected fecal eNose profiles more profoundly than clinical features. These outcomes emphasize the importance of sensor drift correction to improve reliability and repeatability, both within and across eNose studies.

Early Detection of Prostate Cancer: The Role of Scent

“…This tool should be simple to manufacture, easily accessible, and practical for use in clinical settings. Among the available options, the eNose has garnered increasing attention in recent years for the non-invasive diagnosis of various cancers [10,11,49,[83][84][85][86][87][88][89][90][91][92][93][94]. This technique holds great promise for clinical practice as a real-time non-invasive diagnostic tool and for monitoring disease progression and immunotherapy treatment effects [95].…”

“…Although sensor drift [44], the lack of mathematical models [96], and environmental variables (e.g., temperature and humidity) [45] still represent drawbacks of eNose technology, its high diagnostic accuracy demonstrated in all studies, coupled with its relatively low cost and rapid measurements, make it a compelling choice for routine testing in clinical settings [86] and with the possibility of reducing the number of invasive procedures such as prostate biopsies in clinical practice [64].…”

Potential for Early Noninvasive COVID-19 Detection Using Electronic-Nose Technologies and Disease-Specific VOC Metabolic Biomarkers

“…Sensor drift has been dealt with using various strategies. Bosch et al [ 176 ] determined that sensor drift of the C-320 e-nose could be effectively controlled by using regression models to improve accuracy in differentiating between IBD patients and controls based on corrections of six sensors in the 32-sensor array. The residuals of the regression models were applied to original patient data to produce date-corrected measurements used for subsequent data analyses.…”

Developments of Recent Applications for Early Diagnosis of Diseases Using Electronic-Nose and Other VOC-Detection Devices

“…A correction for this problem is not always routinely performed in clinical practice. In a related IBD study, Bosch et al [ 6 ] investigated the influence of e-nose sensor drift on the development and accuracy of an IBD disease-specific algorithm in a real-life multi-center cohort of IBD patients. In this cohort, patients undergoing colonoscopy collected a fecal sample themselves prior to bowel lavage.…”

“…Corrections for e-nose sensor drift significantly improved the accuracy in differentiating between IBD patients and controls based on output differences of six of the 32 sensors (contributing most to discriminations) with an accuracy of 0.68 based on logistic regression [ 6 ]. Short-term sensor drift affected fecal e-nose profiles more profoundly than clinical features.…”