Multimodal pre-screening can predict BCI performance variability: A novel subject-specific experimental scheme

• Published in: Computers in biology and medicine Vol. 168; p. 107658
• Main Authors: Borgheai, Seyyed Bahram, Zisk, Alyssa Hillary, McLinden, John, Mcintyre, James, Sadjadi, Reza, Shahriari, Yalda
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.01.2024; Elsevier Limited
• Subjects: Automation; Brain; Computer applications; EEG; Electroencephalography; Electroencephalography (EEG); Functional near-infrared spectroscopy (fNIRS); General linear model (GLM); Hemodynamics; Human-computer interface; Implants; Infrared spectra; Infrared spectroscopy; Internal Medicine; Investigations; Medical imaging; Multivariate linear regression (MLR) model; Near infrared radiation; Other; Performance prediction; Physiology; Prediction models; Predictive models; Regression analysis; Screening; Spectroscopy; Statistical analysis; Variability; Variation; Workloads; Predictive models; General linear model (GLM); Functional near-infrared spectroscopy (fNIRS); Electroencephalography (EEG); Multivariate linear regression (MLR) model
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.107658

Brain-computer interface (BCI) systems currently lack the required robustness for long-term daily use due to inter- and intra-subject performance variability. In this study, we propose a novel personalized scheme for a multimodal BCI system, primarily using functional near-infrared spectroscopy (fNIRS) and electroencephalography (EEG), to identify, predict, and compensate for factors affecting competence-related and interfering factors associated with performance. 11 (out of 13 recruited) participants, including five participants with motor deficits, completed four sessions on average. During the training sessions, the subjects performed a short pre-screening phase, followed by three variations of a novel visou-mental (VM) protocol. Features extracted from the pre-screening phase were used to construct predictive platforms using stepwise multivariate linear regression (MLR) models. In the test sessions, we employed a task-correction phase where our predictive models were used to predict the ideal task variation to maximize performance, followed by an interference-correction phase. We then investigated the associations between predicted and actual performances and evaluated the outcome of correction strategies. The predictive models resulted in respective adjusted R-squared values of 0.942, 0.724, and 0.939 for the first, second, and third variation of the task, respectively. The statistical analyses showed significant associations between the performances predicted by predictive models and the actual performances for the first two task variations, with rhos of 0.7289 (p-value = 0.011) and 0.6970 (p-value = 0.017), respectively. For 81.82 % of the subjects, the task/workload correction stage correctly determined which task variation provided the highest accuracy, with an average performance gain of 5.18 % when applying the correction strategies. Our proposed method can lead to an integrated multimodal predictive framework to compensate for BCI performance variability, particularly, for people with severe motor deficits. •Personalized predictive models based on the features extracted from a quick multimodal pre-screening phase was developed.•The analysis suggested two sources of variability, including competence and interfering confound.•The proposed predictive scheme was fruitful in predicting the optimal task/workload for specific subject and session.•The outcomes showed recording interfering factors can enrich and enhance BCI performance.