Using machine learning algorithms to enhance the diagnostic performance of electrical impedance myography

Abstract

Introduction/Aims We assessed the classification performance of machine learning (ML) using multifrequency electrical impedance myography (EIM) values to improve upon diagnostic outcomes as compared to those based on a single EIM value. Methods EIM data was obtained from unilateral excised gastrocnemius in eighty diseased mice (26 D2‐mdx, Duchenne muscular dystrophy model, 39 SOD1G93A ALS model, and 15 db/db, a model of obesity‐induced muscle atrophy) and 33 wild‐type (WT) animals. We assessed the classification performance of a ML random forest algorithm incorporating all the data (multifrequency resistance, reactance and phase values) comparing it to the 50 kHz phase value alone. Results ML outperformed the 50 kHz analysis as based on receiver‐operating characteristic curves and measurement of the area under the curve (AUC). For example, comparing all diseases together versus WT from the test set outputs, the AUC was 0.52 for 50 kHz phase, but was 0.94 for the ML model. Similarly, when comparing ALS versus WT, the AUCs were 0.79 for 50 kHz phase and 0.99 for ML. Discussion Multifrequency EIM using ML improves upon classification compared to that achieved with a single‐frequency value. ML approaches should be considered in all future basic and clinical diagnostic applications of EIM.

Combining electromyographic and electrical impedance data sets through machine learning: A study in D2‐mdx and wild‐type mice

“…We had more constrained sampling choices with the EIM data set than the EMG since measurements occur in the frequency domain and not in time‐domain as is the case with EMG. Nevertheless, the findings are consistent with what we have described previously for ML using EIM data in distinguishing healthy and myopathic muscle ex vivo, with AUCs of over 0.90, 18 supporting outstanding disease discrimination.…”

“…And like EMG, ML has been employed in EIM as another approach to data interpretation, improving its capability in disease discrimination in mouse models beyond that obtainable with just single frequency measurements. 18 Recently, EIM technology has been combined into a concentric needle EMG to create a single "impedance-EMG" or "iEMG" device to allow concurrent collection of both signals and improve diagnostic outcomes. 19,20 In this study, we sought to assess the potential of ML-based iEMG for discriminating healthy muscle from dystrophic muscle by studying a mouse model of Duchenne muscular dystrophy, the D2-mdx mouse.…”

“…Indeed, like EMG, EIM offers a rich array of measures including multiple primary parameters and a complex frequency dependence. And like EMG, ML has been employed in EIM as another approach to data interpretation, improving its capability in disease discrimination in mouse models beyond that obtainable with just single frequency measurements 18 . Recently, EIM technology has been combined into a concentric needle EMG to create a single “impedance‐EMG” or “iEMG” device to allow concurrent collection of both signals and improve diagnostic outcomes 19,20 …”

Electrical impedance myography combined with quantitative assessment techniques in paretic muscle of stroke survivors: Insights and challenges

“… Srivastava et al (2012) refined biomarkers from EIM and quantitative muscle ultrasound on the basis of machine learning to successfully classify the muscle affected by spinal muscular atrophy. Pandeya et al (2022) demonstrated that using multifrequency EIM values instead of single-frequency values can improve classification performance of machine learning. Similarly, Cheng et al (2022) reported that machine learning could estimate the total mass of muscles with the EIM and anthropometric parameters.…”

“…Computational Model Finite element model Ahad and Rutkove, 2009;Wang et al, 2011;Jafarpoor et al, 2011;Pacheck et al, 2016 • Finite element models have been demonstrated as a capable method to investigate the biophysical mechanisms of EIM in various diseases. Jafarpoor et al, 2013;Baidya and Ahad, 2016;Rutkove et al, 2017;de Cardoner et al, 2021;Schooling et al, 2020;Luo et al, 2022;Schrunder et al, 2022 • Finite element analysis provides a basic methodology to optimize electrode configuration for EIM Machine learning model Srivastava et al, 2012;Pandeya et al, 2022 • Combining biomarkers from EIM or other assessments could enhance the diagnostic performance of machine learning models. Kapur et al, 2018a,b;Pandeya et al, 2021a,b;Cheng et al, 2022 • Combining EIM and other biomarkers through machine learning can improve diagnostic accuracy for estimating muscle function parameters.…”