Inflammatory Stimuli Responsive Non-Faradaic, Ultrasensitive Combinatorial Electrochemical Urine Biosensor

Area of Science:

• Biomedical Engineering
• Biosensor Technology
• Machine Learning in Diagnostics

Background:

• Current Point-Of-Care (POC) biosensors lack the speed and precision for time-critical disease stratification.
• Accurate stratification of inflammatory disease severity is crucial for effective treatment and patient outcomes.

Purpose of the Study:

• To develop a novel diagnostic biosensor for rapid and accurate stratification of inflammatory disease severity.
• To demonstrate the biosensor's capability using Interleukin-8 (IL-8) and Interleukin-6 (IL-6) as proof of concept.

Main Methods:

• Utilized electrochemical impedance spectroscopy (EIS) to detect inflammatory biomarkers IL-8 and IL-6 with a limit of detection (LOD) of 1 pg/mL.
• Employed a two-stage random forest machine learning model for classifying disease severity into four distinct states.

Main Results:

• Achieved a rapid turn-around time of less than 4 minutes for diagnoses.
• The biosensing scheme demonstrated a high classification accuracy of 98.437% for four-class stratification of inflammatory disease severity.
• The system successfully detected and stratified disease states based on IL-8 and IL-6 levels.

Conclusions:

• The proposed diagnostic biosensor offers a significant advancement over traditional lab techniques for disease stratification.
• This novel approach can enhance the diagnostic power of existing electrochemical biosensors, paving the way for precision therapy.
• The technology holds potential for improving patient outcomes through faster, actionable diagnoses and personalized treatment strategies.