Dataset Information

Machine learning and individual variability in electric field characteristics predict tDCS treatment response.

ABSTRACT: Background: Transcranial direct current stimulation (tDCS) is widely investigated as a therapeutic tool to enhance cognitive function in older adults with and without neurodegenerative disease. Prior research demonstrates that electric current delivery to the brain can vary significantly across individuals. Quantification of this variability could enable person-specific optimization of tDCS outcomes. This pilot study used machine learning and MRI-derived electric field models to predict working memory improvements as a proof of concept for precision cognitive intervention.

Methods: Fourteen healthy older adults received 20 minutes of 2 mA tDCS stimulation (F3/F4) during a two-week cognitive training intervention. Participants performed an N-back working memory task pre-/post-intervention. MRI-derived current models were passed through a linear Support Vector Machine (SVM) learning algorithm to characterize crucial tDCS current components (intensity and direction) that induced working memory improvements in tDCS responders versus non-responders.

Main results: SVM models of tDCS current components had 86% overall accuracy in classifying treatment responders vs. non-responders, with current intensity producing the best overall model differentiating changes in working memory performance. Median current intensity and direction in brain regions near the electrodes were positively related to intervention responses (r=0.811,p<0.001 and r=0.774,p=0.001).

Conclusions: This study provides the first evidence that pattern recognition analyses of MRI-derived tDCS current models can provide individual prognostic classification of tDCS treatment response with 86% accuracy. Individual differences in current intensity and direction play important roles in determining treatment response to tDCS. These findings provide important insights into mechanisms of tDCS response as well as proof of concept for future precision dosing models of tDCS intervention.

SUBMITTER: Albizu A

PROVIDER: S-EPMC7731513 | biostudies-literature | 2020 Nov - Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning and individual variability in electric field characteristics predict tDCS treatment response.

Albizu Alejandro A Fang Ruogu R Indahlastari Aprinda A O'Shea Andrew A Stolte Skylar E SE See Kyle B KB Boutzoukas Emanuel M EM Kraft Jessica N JN Nissim Nicole R NR Woods Adam J AJ

Brain stimulation 20201010 6

<h4>Background</h4>Transcranial direct current stimulation (tDCS) is widely investigated as a therapeutic tool to enhance cognitive function in older adults with and without neurodegenerative disease. Prior research demonstrates that electric current delivery to the brain can vary significantly across individuals. Quantification of this variability could enable person-specific optimization of tDCS outcomes. This pilot study used machine learning and MRI-derived electric field models to predict w ...[more]

PMID: 33049412

Similar Datasets

Project description:ImportanceThe Undiagnosed Diseases Network (UDN) is a national network that evaluates individual patients whose signs and symptoms have been refractory to diagnosis. Providing reliable estimates of admission outcomes may assist clinical evaluators to distinguish, prioritize, and accelerate admission to the UDN for patients with undiagnosed diseases.ObjectiveTo develop computational models that effectively predict admission outcomes for applicants seeking UDN evaluation and to rank the applications based on the likelihood of patient admission to the UDN.Design, setting, and participantsThis prognostic study included all applications submitted to the UDN from July 2014 to June 2019, with 1209 applications accepted and 1212 applications not accepted. The main inclusion criterion was an undiagnosed condition despite thorough evaluation by a health care professional; the main exclusion criteria were a diagnosis that explained the objective findings or a review of the records that suggested a diagnosis. A classifier was trained using information extracted from application forms, referral letters from health care professionals, and semantic similarity between referral letters and textual description of known mendelian disorders. The admission labels were provided by the case review committee of the UDN. In addition to retrospective analysis, the classifier was prospectively tested on another 288 applications that were not evaluated at the time of classifier development.Main outcomes and measuresThe primary outcomes were whether a patient was accepted or not accepted to the UDN and application order ranked based on likelihood of admission. The performance of the classifier was assessed by comparing its predictions against the UDN admission outcomes and by measuring improvement in the mean processing time for accepted applications.ResultsThe best classifier obtained sensitivity of 0.843, specificity of 0.738, and area under the receiver operating characteristic curve of 0.844 for predicting admission outcomes among 1212 accepted and 1210 not accepted applications. In addition, the classifier can decrease the current mean (SD) UDN processing time for accepted applications from 3.29 (3.17) months to 1.05 (3.82) months (68% improvement) by ordering applications based on their likelihood of acceptance.Conclusions and relevanceA classification system was developed that may assist clinical evaluators to distinguish, prioritize, and accelerate admission to the UDN for patients with undiagnosed diseases. Accelerating the admission process may improve the diagnostic journeys for these patients and serve as a model for partial automation of triaging or referral for other resource-constrained applications. Such classification models make explicit some of the considerations that currently inform the use of whole-genome sequencing for undiagnosed disease and thereby invite a broader discussion in the clinical genetics community.

Project description:BackgroundUnique amongst brain stimulation tools, transcranial direct current stimulation (tDCS) currently lacks an easy or widely implemented method for individualizing dosage.ObjectiveWe developed a method of reverse-calculating electric-field (E-field) models based on Magnetic Resonance Imaging (MRI) scans that can estimate individualized tDCS dose. We also evaluated an MRI-free method of individualizing tDCS dose by measuring transcranial magnetic stimulation (TMS) motor threshold (MT) and single pulse, suprathreshold transcranial electrical stimulation (TES) MT and regressing it against E-field modeling. Key assumptions of reverse-calculation E-field modeling, including the size of region of interest (ROI) analysis and the linearity of multiple E-field models were also tested.MethodsIn 29 healthy adults, we acquired TMS MT, TES MT, and anatomical T1-weighted MPRAGE MRI scans with a fiducial marking the motor hotspot. We then computed a "reverse-calculated tDCS dose" of tDCS applied at the scalp needed to cause a 1.00 V/m E-field at the cortex. Finally, we examined whether the predicted E-field values correlated with each participant's measured TMS MT or TES MT.ResultsWe were able to determine a reverse-calculated tDCS dose for each participant using a 5 × 5 x 5 voxel grid region of interest (ROI) approach (average = 6.03 mA, SD = 1.44 mA, range = 3.75-9.74 mA). The Transcranial Electrical Stimulation MT, but not the Transcranial Magnetic Stimulation MT, significantly correlated with the ROI-based reverse-calculated tDCS dose determined by E-field modeling (R2 = 0.45, p < 0.001).ConclusionsReverse-calculation E-field modeling, alone or regressed against TES MT, shows promise as a method to individualize tDCS dose. The large range of the reverse-calculated tDCS doses between subjects underscores the likely need to individualize tDCS dose. Future research should further examine the use of TES MT to individually dose tDCS as an MRI-free method of dosing tDCS.

Dataset Information

Machine learning and individual variability in electric field characteristics predict tDCS treatment response.

Publications

Machine learning and individual variability in electric field characteristics predict tDCS treatment response.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure