What question did this study set out to answer?

To develop and evaluate a multi-frequency bioimpedance spectroscopy method coupled with hybrid artificial intelligence classifiers for diagnosing pancreatic diseases.

August 20, 2026Journal of Medical Engineering & Technology

Integrating artificial intelligence and bioimpedance spectroscopy for enhanced pancreatic disease diagnosis

View Full Paper

Ask AI

Bookmark

Authors

SFSergey Filist RARiad Taha Al-Kasasbeh TGTigran Gevorkyan

Discussion

Member takes

Overview

Diagnostic study shows hybrid neural networks and bioimpedance spectroscopy identify pancreatic diseases in patients aged 25–80, highlighting potential for noninvasive decision support.

Key Points

To develop and evaluate a multi-frequency bioimpedance spectroscopy method coupled with hybrid artificial intelligence classifiers for diagnosing pancreatic diseases.
Extracted amplitude-phase-frequency responses across four quasi-orthogonal leads to generate multi-frequency feature spaces for diagnostic classification.
Constructed a five-level hybrid classifier combining probabilistic neural networks and fuzzy inference systems within a clinical decision support framework.
Trained and evaluated the system in male and female patients aged 25 to 80 years across stages of pancreatic disease, validated against ultrasound, computed tomography, laparoscopy, and clinical examinations.
Achieved diagnostic quality indicator values ranging from a minimum of 63% to a maximum of 89% when differentiating among pancreatic cancer, chronic pancreatitis, and healthy tissue.
Demonstrated software and clinical sensitivity and specificity comparable to standard conventional diagnostic imaging and laboratory modalities.

Cite This Study

Filist et al. (2026) studied this question.

synapsesocial.com/papers/6a86b56c8a91293e6a1cccd5 https://doi.org/10.1080/03091902.2026.2714536

View Full Paper

Ask AI

Bookmark

August 20, 2026Journal of Medical Engineering & Technology

Integrating artificial intelligence and bioimpedance spectroscopy for enhanced pancreatic disease diagnosis

View Full Paper

Ask AI

Bookmark

Authors

SFSergey Filist RARiad Taha Al-Kasasbeh TGTigran Gevorkyan

Discussion

Member takes

Overview

Diagnostic study shows hybrid neural networks and bioimpedance spectroscopy identify pancreatic diseases in patients aged 25–80, highlighting potential for noninvasive decision support.

Key Points

To develop and evaluate a multi-frequency bioimpedance spectroscopy method coupled with hybrid artificial intelligence classifiers for diagnosing pancreatic diseases.
Extracted amplitude-phase-frequency responses across four quasi-orthogonal leads to generate multi-frequency feature spaces for diagnostic classification.
Constructed a five-level hybrid classifier combining probabilistic neural networks and fuzzy inference systems within a clinical decision support framework.
Trained and evaluated the system in male and female patients aged 25 to 80 years across stages of pancreatic disease, validated against ultrasound, computed tomography, laparoscopy, and clinical examinations.
Achieved diagnostic quality indicator values ranging from a minimum of 63% to a maximum of 89% when differentiating among pancreatic cancer, chronic pancreatitis, and healthy tissue.
Demonstrated software and clinical sensitivity and specificity comparable to standard conventional diagnostic imaging and laboratory modalities.

Cite This Study

Filist et al. (2026) studied this question.

synapsesocial.com/papers/6a86b56c8a91293e6a1cccd5 https://doi.org/10.1080/03091902.2026.2714536

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark