Combined cortical thickness and blink reflex recovery cycle to differentiate essential tremor with and without resting tremor

Abstract

Objective: To investigate the performance of structural MRI cortical and subcortical morphometric data combined with blink-reflex recovery cycle (BRrc) values using machine learning (ML) models in distinguishing between essential tremor (ET) with resting tremor (rET) and classic ET.

Methods: We enrolled 47 ET, 43 rET patients and 45 healthy controls (HC). All participants underwent brain 3 T-MRI and BRrc examination at different interstimulus intervals (ISIs, 100-300 msec). MRI data (cortical thickness, volumes, surface area, roughness, mean curvature and subcortical volumes) were extracted using Freesurfer on T1-weighted images. We employed two decision tree-based ML classification algorithms (eXtreme Gradient Boosting [XGBoost] and Random Forest) combining MRI data and BRrc values to differentiate between rET and ET patients.

Results: ML models based exclusively on MRI features reached acceptable performance (AUC: 0.85-0.86) in differentiating rET from ET patients and from HC. Similar performances were obtained by ML models based on BRrc data (AUC: 0.81-0.82 in rET vs. ET and AUC: 0.88-0.89 in rET vs. HC). ML models combining imaging data (cortical thickness, surface, roughness, and mean curvature) together with BRrc values showed the highest classification performance in distinguishing between rET and ET patients, reaching AUC of 0.94 ± 0.05. The improvement in classification performances when BRrc data were added to imaging features was confirmed by both ML algorithms.

Conclusion: This study highlights the usefulness of adding a simple electrophysiological assessment such as BRrc to MRI cortical morphometric features for accurately distinguishing rET from ET patients, paving the way for a better classification of these ET syndromes.

Keywords: blink reflex; cortical thickness; essential tremor; essential tremor plus; machine learning; rest tremor.

Figure 1

The top-performing machine learning models in differentiating between ET patients and healthy controls. At the top, the best XGBoost model (A); at the bottom, the best Random Forest model (B). On the left side of the figure, it is shown the ROC curve. On the right side, it is shown the relative importance of the features selected by the model in distinguishing between the two groups assessed via permutation method. Features are shown in descending order from the most to the less important feature. Rh, right; Lh, left; AUC, area under the curve; thicknessstd, standard deviation of thickness, which is the roughness; ISI, interstimulus interval.

Figure 2

The top-performing machine learning models in differentiating between rET patients and healthy controls. At the top, the best XGBoost model (A); at the bottom, the best Random Forest model (B). On the left side of the figure, it is shown the ROC curve. On the right side, it is shown the relative importance of the features selected by the model in distinguishing between the two groups assessed via permutation methods. Features are shown in descending order from the most to the less important feature. Rh, right; Lh, left; AUC, area under the curve; thicknessstd, standard deviation of thickness, which is the roughness; ISI, interstimulus interval.

Figure 3

The top-performing machine learning models in differentiating between ET patients and rET patients. At the top, the best XGBoost model (A); at the bottom, the best Random Forest model (B). On the left side of the figure, it is shown the ROC curve. On the right side, it is shown the relative importance of the features selected by the model in distinguishing between the two groups assessed via permutation methods. Features are shown in descending order from the most to the less important feature. Rh, right; Lh, left; AUC, area under the curve; thicknessstd, standard deviation of thickness, which is the roughness; ISI, interstimulus interval.