Pattern recognition and functional neuroimaging help to discriminate healthy adolescents at risk for mood disorders from low risk adolescents

Abstract

Introduction: There are no known biological measures that accurately predict future development of psychiatric disorders in individual at-risk adolescents. We investigated whether machine learning and fMRI could help to: 1. differentiate healthy adolescents genetically at-risk for bipolar disorder and other Axis I psychiatric disorders from healthy adolescents at low risk of developing these disorders; 2. identify those healthy genetically at-risk adolescents who were most likely to develop future Axis I disorders.

Methods: 16 healthy offspring genetically at risk for bipolar disorder and other Axis I disorders by virtue of having a parent with bipolar disorder and 16 healthy, age- and gender-matched low-risk offspring of healthy parents with no history of psychiatric disorders (12-17 year-olds) performed two emotional face gender-labeling tasks (happy/neutral; fearful/neutral) during fMRI. We used Gaussian Process Classifiers (GPC), a machine learning approach that assigns a predictive probability of group membership to an individual person, to differentiate groups and to identify those at-risk adolescents most likely to develop future Axis I disorders.

Results: Using GPC, activity to neutral faces presented during the happy experiment accurately and significantly differentiated groups, achieving 75% accuracy (sensitivity = 75%, specificity = 75%). Furthermore, predictive probabilities were significantly higher for those at-risk adolescents who subsequently developed an Axis I disorder than for those at-risk adolescents remaining healthy at follow-up.

Conclusions: We show that a combination of two promising techniques, machine learning and neuroimaging, not only discriminates healthy low-risk from healthy adolescents genetically at-risk for Axis I disorders, but may ultimately help to predict which at-risk adolescents subsequently develop these disorders.

Figure 1. Summary of pattern recognition analyses.

(1) Feature Extraction: the information from the beta images were transformed into an input vector. (2) Nested leave one out (LOO) Approach. We employed a nested (3-way) cross-validation, where we first excluded one matched pair of subjects to comprise the test set (test loop in light blue). We then performed a second split (validation loop in dark blue), where we removed 5000 voxels each iteration and repeatedly repartitioned the remaining 15 subject pairs into a validation set (1 pair) and training set (14 pairs) to compute the mean accuracy on the validation set. This procedure (removing voxels and computing mean accuracy) was repeated until all voxels were removed. We then selected the number of voxels that produced maximal accuracy on the validation set before applying it to the test set. The final accuracy was the mean accuracy over all test subjects (outer test loop in light blue). (3) We then generated a map training the GPC with all subjects and removing voxels until we obtained the mean number of voxels.

Figure 2. Summary of results from pattern recognition analyses.

A. Decision boundary and individual predictive probabilities. B. GPC weights overlaid on an anatomical template. The color code shows the relative weight of each voxel for the decision boundary (red scales: higher weights for healthy bipolar offspring and blue scales: higher weights for healthy controls). The discriminating pattern included clusters with higher weights for healthy bipolar offspring in the superior temporal sulcus (STS; x, y, z: -50, 11, -5) and in a posterior region of the ventromedial prefrontal cortex (VMPFC(p); x, y, z,: 0, 29, -14) and a cluster with higher weights for healthy controls in the anterior region of the ventromedial prefrontal cortex (VMPFC (a); x, y, z: -2, 51, -19) (x, y, z, are in Talairach coordinates).

Figure 3. Mean predictive probabilities (with standard error to the mean) for the comparison between healthy bipolar offspring with and without future onset of Axis I disorder, which in this sample was major depressive disorder and anxiety disorders.

Figure 4. We used the predictive probabilities from the classifier at-risk adolescents vs. controls as a score for the at-risk adolescents.

An ROC curve was used to evaluate if this score could be used to predict which of at-risk adolescents developed a future mood disorder. Each point on the ROC curve represents a sensitivity/specificity pair corresponding to a particular decision threshold. A test with perfect discrimination has a ROC curve that passes through the upper left corner (100% sensitivity, 100% specificity). The area under the ROC curve (AUC) was 0.78 (p<0.05).