A smartphone-interfaced, low-cost colorimetry biosensor for selective detection of bronchiectasis via an artificial neural network

Abstract

Exhaled breath (EB) contains several macromolecules that can be exploited as biomarkers to provide clinical information about various diseases. Hydrogen peroxide (H₂O₂) is a biomarker because it indicates bronchiectasis in humans. This paper presents a non-invasive, low-cost, and portable quantitative analysis for monitoring and quantifying H₂O₂ in EB. The sensing unit works on colorimetry by the synergetic effect of eosin blue, potassium permanganate, and starch-iodine (EPS) systems. Various sampling conditions like pH, response time, concentration, temperature and selectivity were examined. The UV-vis absorption study of the assay showed that the dye system could detect as low as ∼0.011 ppm levels of H₂O₂. A smart device-assisted detection unit that rapidly detects red, green and blue (RGB) values has been interfaced for practical and real-time application. The RGB value-based quantification of the H₂O₂ level was calibrated against NMR spectroscopy and exhibited a close correlation. Further, we adopted a machine learning approach to predict H₂O₂ concentration. For the evaluation, an artificial neural network (ANN) regression model returned 0.941 R ² suggesting its great prospect for discrete level quantification of H₂O₂. The outcomes exemplified that the sensor could be used to detect bronchiectasis from exhaled breath.

Fig. 1. Fabricated smartphone-assisted sensor prototype.

Fig. 2. SI dye response toward H₂O₂. (a) pH adjusted SI dye solution before and after adding 0.3 ppm H₂O₂ solution at room temperature. (b) (b) Absorbance spectra of neutral SI dye solution before and after adding 0.3 ppm H₂O₂.

Fig. 3. Eosin blue dye response toward H₂O₂. (a) pH adjusted EB dye solution before and after adding 0.3 ppm H₂O₂ solution at room temperature. (b) Absorbance spectra of pH 12 EB dye solution before and after adding 0.3 ppm H₂O₂ solution.

Fig. 4. KMnO₄ dye response toward H₂O₂. (a) pH adjusted KMnO₄ dye solution before and after adding 0.3 ppm H₂O₂ solution at room temperature. (b) Absorbance spectra of neutral KMnO₄ dye solution before and after adding 0.3 ppm H₂O₂ solution.

Fig. 5. Dyes sensitivity towards H₂O₂ detection. (a and b) UV-vis absorption curve with change in H₂O₂ concentration and corresponding calibration plot of eosin blue dye, respectively. (c and d) UV-vis absorption curve with H₂O₂ concentration shift and corresponding calibration plot of KMnO₄ dye, respectively. (e and f) UV-vis absorption curve with varying H₂O₂ concentration and corresponding calibration plot of starch dye, respectively.

Fig. 6. Temperature effect on H₂O₂ detection in EPS dye solutions system.

Fig. 7. Selectivity analysis of biomarkers in different dye solutions (a) Eosin Blue dye solutions (b) KMnO₄ dye solution (c) SI dye solution.

Fig. 8. 3D plot, representing RGB value corresponding to the H₂O₂ level.

Fig. 9. Comparison of NMR data and colorimetric data for quantification of H₂O_2.

Fig. 10. (a) Flow diagram of regression analysis using artificial neural network (ANN) regression algorithm. (b) The ANN machine learning algorithm plot shows the linear fit between the target and output value (left) and the change in color of the colorimetric dye solution after detecting H₂O₂ in the range of 0.1 to 200 ppm level (right).