DigEST: Digital plug‐n‐probe disease Endotyping Sensor Technology. Issue 2 (5th November 2022)

• Record Type: Journal Article
• Authors: Ganguly, Antra; Ebrahimzadeh, Tahmineh; Komarovsky, Jessica; Zimmern, Philippe E.; De Nisco, Nicole J.; Prasad, Shalini
• Is Part Of: Bioengineering & translational medicine. Volume 8:Issue 2(2023)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-11-05
• Subjects: Boolean logic -- digital biosensor -- disease endotyping -- electrochemical impedance spectroscopy -- random‐forest; Bioengineering -- Periodicals; Drug development -- Periodicals; Drugs -- Testing -- Periodicals; 660.6
• DOI: 10.1002/btm2.10437
• Languages: English
• ISSNs: 2380-6761

Abstract

Abstract: In this work, we propose a novel diagnostic workflow—DigEST—that will enable stratification of disease states based on severity using multiplexed point of care (POC) biosensors. This work can boost the performance of current POC tests by enabling clear, digestible, and actionable diagnoses to the end user. The scheme can be applied to any disease model, which requires time‐critical disease stratification for personalized treatment. Here, urinary tract infection is explored as the proof‐of‐concept disease model and a four‐class classification of disease severity is discussed. Our method is superior to traditional enzyme‐linked immunosorbent assay (ELISA) as it is faster and can work with multiple disease biomarkers and categorize diseases by endotypes (or disease subtype) and severity. To map the nonlinear nature of biochemical pathways of complex diseases, the method utilizes an established supervised machine learning model for digital classification. This scheme can potentially boost the diagnostic power of current electrochemical biosensors for better precision therapy and improved patient outcomes.