Smart photonic crystal fiber optical sensor for tuberculosis detection with machine learning integration

Area of Science:

• Photonics and Biosensing
• Terahertz (THz) Technology
• Medical Diagnostics

Background:

• Tuberculosis (TB) remains a leading global infectious disease, particularly impacting low- and middle-income countries.
• Existing diagnostic methods can be time-consuming or lack accessibility, necessitating innovative detection solutions.
• Terahertz (THz) frequency bands offer unique properties for non-ionizing, label-free biosensing applications.

Purpose of the Study:

• To design and numerically analyze a novel hexagonal hollow-core photonic crystal fiber (HC-PCF) sensor for rapid tuberculosis cell detection.
• To optimize the sensor for high relative sensitivity (RS), low confinement loss (CL), and minimal effective material loss (EML) at 1.6 THz.
• To integrate machine learning algorithms for enhanced data analysis and accurate TB classification.

Main Methods:

• Design and simulation of a hexagonal HC-PCF structure using the finite element method (FEM) in COMSOL Multiphysics 6.1.
• Numerical analysis of sensor performance across a range of refractive indexes (RI) characteristic of TB-infected samples (1.345-1.349).
• Application of machine learning models (Random Forest Regressor, Support Vector Regressor) trained on simulated sensor optical responses.

Main Results:

• The proposed HC-PCF sensor achieved a maximum Relative Sensitivity (RS) of 95.53% for TB-relevant refractive indexes.
• Optimized sensor design yielded low Confinement Loss (CL) down to 9.307 × 10^-3 dB/m and minimal Effective Material Loss (EML).
• Machine learning models demonstrated precise prediction and classification capabilities for subtle refractive index variations indicative of TB.

Conclusions:

• The designed THz HC-PCF sensor shows significant potential for highly sensitive and accurate tuberculosis detection.
• The synergy of advanced photonic sensing and machine learning represents a promising approach for next-generation healthcare technologies.
• This biosensing platform offers a pathway towards faster and more reliable diagnostics for tuberculosis.