Key result
A 3D convolutional neural network using all group independent component analysis spatial maps from resting-state fMRI accurately classified lidocaine treatment response with an AUC of 96.61%.
Why the study?
Functional magnetic resonance imaging can assess and stratify patients with painful diabetic peripheral neuropathy, supporting the aim to use deep learning with resting state functional imaging to predict treatment response.
Does a 3D-CNN deep learning model using rs-fMRI accurately predict treatment response to intravenous lidocaine in patients with painful diabetic peripheral neuropathy?
Observational (n=43)
No
Does a 3D-CNN deep learning model using rs-fMRI accurately predict treatment response to intravenous lidocaine in patients with painful diabetic peripheral neuropathy?
Effect estimate: AUC 96.61%
Absolute Event Rate: 96.61% vs 43.75%
A 3D convolutional neural network using resting-state fMRI can accurately classify treatment response to intravenous lidocaine in patients with painful diabetic peripheral neuropathy.
Hypothesis-generating for rs-fMRI prediction of lidocaine response in diabetic neuropathy; requires prospective validation before clinical adoption.
Functional magnetic resonance imaging (fMRI) has been shown successfully to assess and stratify patients with painful diabetic peripheral neuropathy (pDPN). This supports the idea of using neuroimaging as a mechanism-based technique to individualise therapy for patients with painful DPN. The aim of this study was to use deep learning to predict treatment response in patients with pDPN using resting state functional imaging (rs-fMRI). We divided 43 painful pDPN patients into responders and non-responders to lidocaine treatment (responders n = 29 and non-responders n = 14). We used rs-fMRI to extract functional connectivity features, using group independent component analysis (gICA), and performed automated treatment response deep learning classification with three-dimensional convolutional neural networks (3D-CNN). Using gICA we achieved an area under the receiver operating characteristic curve (AUC) of 96.60% and F1-Score of 95% in a ten-fold cross validation (CV) experiment using our described 3D-CNN algorithm. To our knowledge, this is the first study utilising deep learning methods to classify treatment response in pDPN.
No takes yet. Share an insight, caveat, or question.
Teh et al. (2022) conducted an observational in Painful diabetic peripheral neuropathy (n=43). 3D-CNN deep learning using all group ICA spatial components (ASC) vs. 3D-CNN using pre-processed resting state data (RSP) was evaluated on Classification of treatment response (Area Under the Curve) (AUC 96.61%). A 3D convolutional neural network using all group independent component analysis spatial maps from resting-state fMRI accurately classified lidocaine treatment response with an AUC of 96.61%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: