Near perfect classification of cardiac biomarker Troponin-I in human serum assisted by SnS2-CNT composite, explainable ML, and operating-voltage-selection-algorithm

Goswami, Partha Pratim and Deshpande, Tushar and Rotake, Dinesh Ramkrishna and Singh, Shiv Govind (2023) Near perfect classification of cardiac biomarker Troponin-I in human serum assisted by SnS2-CNT composite, explainable ML, and operating-voltage-selection-algorithm. Biosensors and Bioelectronics, 220. ISSN 0956-5663

[img] Text
1-s2.0-S0956566322009551-main.pdf - Published Version

Download (13MB)


The high worldwide mortality and disproportionate impact of cardiovascular diseases have emerged as the most significant global health burden, unfortunately, unmet by the traditional detection methods. Therefore, developing a rapid, sensitive, selective, and rugged biosensor for the precise classification/quantification of cardiac biomarkers is a stepping stone for the future generation of cardiac healthcare. We demonstrate a facile, time-efficient, and scalable biosensor for classifying the FDI approved gold standard cardiac biomarker Troponin-I (cTnI) in untreated human serum matrix, built-on 2-D SnS2 and 1-D MWCNT composite transducer and decision-tree based explainable machine learning (ML) algorithm. The proposed methodology is further enhanced using an inimitable Operating-Voltage-Selection-Algorithm (OVSA), which boosts ML accuracy to ∼100%. The near-perfect classification is realized by strategically incorporating this two-step algorithm-first the OVSA, then the heuristic and ML approaches on the selected dataset. Dynamic concentrations of the biomarker (100 fg/mL to 100 ng/mL) are estimated with high sensitivity, ∼71 (ΔR/R) (ng/mL)−1cm−2 and low limit of detection (0.02 fg/mL), aiding to the prediction and prognosis of acute myocardial infarction. The hyperparameter tuning and feature engineering improve the decision process of the ML algorithm, fostering robustness against data variability. Feature importance indices, namely the Gini index, Permutation Importance, and SHAP values, portray ‘Voltage’ as the most important feature, further justifying our insight into the OVSA. The biosensor's specificity, selectivity, reproducibility and stability are effectively demonstrated with the sampling to result reporting time of just 20 min, establishing it as a potential candidate for clinical testing.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Singh, Shiv Govind
Item Type: Article
Uncontrolled Keywords: Biomarker; Chemiresistive biosensor; Feature importance; Machine learning; ML Explainability; SnS2-CNT Composite; acute heart infarction; algorithm; Article; concentration (parameter); decision making; decision tree; electric potential; Gini coefficient; gold standard; heuristics; human; limit of detection; machine learning; operating voltage selection algorithm; prediction; prognosis; reproducibility; algorithm; genetic procedures; heart infarction; machine learning; Chemiresistive biosensor; CNTs composites; Feature importance; Machine learning explainability; Machine-learning; Operating voltage; Selection algorithm; SnS2-CNT composite; Voltage selection; Biosensors; Cardiology; Classification (of information); Decision trees; Diagnosis; Heart; IV-VI semiconductors; Supervised learning; Tin compounds; Algorithms; Biomarkers; Biosensing Techniques; Humans; Machine Learning; Myocardial Infarction; Reproducibility of Results; Troponin I; Biomarkers
Subjects: Electrical Engineering
Electrical Engineering > Process Control
Electrical Engineering > Power System
Divisions: Department of Electrical Engineering
Depositing User: Mr Nigam Prasad Bisoyi
Date Deposited: 16 Aug 2023 11:22
Last Modified: 16 Aug 2023 11:22
Publisher URL:
OA policy:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 11554 Statistics for this ePrint Item