December 12, 2024Medical Engineering & Physics

The Fine K-Nearest Neighbor (FKNN) algorithm achieved an average classification accuracy of 99.8% and a Kappa value of 0.996 using ten-fold cross-validation.

View Full Paper

Ask AI

Bookmark

Why the study?

Diagnosing psychiatric disorders using subjective questionnaires is prone to error, prompting investigation into automated ECG-based classification to address limitations of EEG and standard CNNs.

Can an automated system using ECG signals and wavelet scattering networks accurately classify psychiatric disorders?

Population

233 subjects, including 198 diagnosed with multiple psychiatric disorders and 35 control subjects

Design

Diagnostic model development and validation study

Authors

HTHardik Telangore NSNishant Sharma NSNishant Sharma

Discussion

Member takes

Overview

ECG-based ML may aid psychiatric classification; hypothesis-generating and requires prospective validation before clinical use.

Structured PICO

Can an automated system using ECG signals and wavelet scattering networks accurately classify psychiatric disorders?

Population

233 subjects (198 diagnosed with multiple psychiatric disorders including bipolar disorder, depression, and schizophrenia, and 35 control subjects) providing 3570 ECG heartbeats.

Intervention

Automated identification of neuropsychiatric disorders using ECG signals analyzed with wavelet scattering-based feature extraction and Fine K-Nearest Neighbor (FKNN) machine learning algorithm.

Outcome

Average classification accuracy and Kappa value for identifying psychiatric disorders.surrogate

An automated machine learning approach using ECG signals and wavelet scattering networks can highly accurately classify psychiatric disorders such as bipolar disorder, depression, and schizophrenia.

Cite This Study

Telangore et al. (2024) studied this question.

synapsesocial.com/papers/6a7e05b9da6d5413e2cb625e https://doi.org/10.1016/j.medengphy.2024.104275

View Full Paper

Ask AI

Bookmark

December 12, 2024Medical Engineering & Physics

The Fine K-Nearest Neighbor (FKNN) algorithm achieved an average classification accuracy of 99.8% and a Kappa value of 0.996 using ten-fold cross-validation.

View Full Paper

Ask AI

Bookmark

Why the study?

Diagnosing psychiatric disorders using subjective questionnaires is prone to error, prompting investigation into automated ECG-based classification to address limitations of EEG and standard CNNs.

Can an automated system using ECG signals and wavelet scattering networks accurately classify psychiatric disorders?

Population

233 subjects, including 198 diagnosed with multiple psychiatric disorders and 35 control subjects

Design

Diagnostic model development and validation study

Authors

HTHardik Telangore NSNishant Sharma NSNishant Sharma

Discussion

Member takes

Overview

ECG-based ML may aid psychiatric classification; hypothesis-generating and requires prospective validation before clinical use.

Structured PICO

Can an automated system using ECG signals and wavelet scattering networks accurately classify psychiatric disorders?

Population

233 subjects (198 diagnosed with multiple psychiatric disorders including bipolar disorder, depression, and schizophrenia, and 35 control subjects) providing 3570 ECG heartbeats.

Intervention

Automated identification of neuropsychiatric disorders using ECG signals analyzed with wavelet scattering-based feature extraction and Fine K-Nearest Neighbor (FKNN) machine learning algorithm.

Outcome

Average classification accuracy and Kappa value for identifying psychiatric disorders.surrogate

An automated machine learning approach using ECG signals and wavelet scattering networks can highly accurately classify psychiatric disorders such as bipolar disorder, depression, and schizophrenia.

Cite This Study

Telangore et al. (2024) studied this question.

synapsesocial.com/papers/6a7e05b9da6d5413e2cb625e https://doi.org/10.1016/j.medengphy.2024.104275

View Full Paper

Ask AI

Bookmark