Identifying epilepsy psychiatric comorbidities with machine learning

Abstract

Objective People with epilepsy are at increased risk for mental health comorbidities. Machine‐learning methods based on spoken language can detect suicidality in adults. This study's purpose was to use spoken words to create machine‐learning classifiers that identify current or lifetime history of comorbid psychiatric conditions in teenagers and young adults with epilepsy. Materials and Methods Eligible participants were >12 years old with epilepsy. All participants were interviewed using the Mini International Neuropsychiatric Interview (MINI) or the MINI Kid Tracking and asked five open‐ended conversational questions. N‐grams and Linguistic Inquiry and Word Count (LIWC) word categories were used to construct machine learning classification models from language harvested from interviews. Data were analyzed for four individual MINI identified disorders and for three mutually exclusive groups: participants with no psychiatric disorders, participants with non‐suicidal psychiatric disorders, and participants with any degree of suicidality. Performance was measured using areas under the receiver operating characteristic curve (AROCs). Results Classifiers were constructed from 227 interviews with 122 participants (7.5 ± 3.1 minutes and 454 ± 299 words). AROCs for models differentiating the non‐overlapping groups and individual disorders ranged 57%‐78% (many with P < .02). Discussion and Conclusion Machine‐learning classifiers of spoken language can reliably identify current or lifetime history of suicidality and depression in people with epilepsy. Data suggest identification of anxiety and bipolar disorders may be achieved with larger data sets. Machine‐learning analysis of spoken language can be promising as a useful screening alternative when traditional approaches are unwieldy (eg, telephone calls, primary care offices, school health clinics).

A Feasibility Study Using a Machine Learning Suicide Risk Prediction Model Based on Open-Ended Interview Language in Adolescent Therapy Sessions

“…The NLP/ML pipeline used in this study followed similar techniques used by Pestian et al, focused on the term frequency of n-grams (contiguous sequence of n number of words) [18][19][20][21]. The text was normalized by expanding contractions and lemmatizing (replacing words by their root) [52].…”

“…Previous work focused primarily on support vector machines (SVMs) [18][19][20][21]; however, we also explored the performance of logistic regression (LR) and extreme gradient boosting (XGB) models. SVM models have demonstrated excellent performance in previous tasks classifying suicidal language from semi-structured interviews, perform well in high-dimensional spaces, and resist overfitting [18][19][20][21]. During SVM tuning, hyperparameters considered include: the regularization parameter (C), the kernel (radial basis function and linear kernels), the kernel coefficient (gamma, if applicable), and the class weight [49].…”

“…Speech is one of the most complex human activities [15], coordinating diverse brain regions, and is affected by physical, neurological, and mental health conditions [16]. Prior research has shown how machine learning models can classify these conditions based on the linguistic and acoustic markers in speech [16][17][18][19][20][21][22]. Underlying machine learning models' success is that these conditions cause neurophysiological changes that can be consistently measured with voice data (linguistic and acoustic markers) [17,21,23].…”

“…Prior research has shown how machine learning models can classify these conditions based on the linguistic and acoustic markers in speech [16][17][18][19][20][21][22]. Underlying machine learning models' success is that these conditions cause neurophysiological changes that can be consistently measured with voice data (linguistic and acoustic markers) [17,21,23]. While much of the brain's structure-function relationship remains unknown [24], studies on the brains of those with suicide attempts or who died by suicide have found notable differences compared to controls, including a decrease in gray matter and activity changes of specific brain regions [25,26].…”

“…This method of both data collection and analysis offers an objective and less biased approach to identifying people with suicidal thoughts and behaviors (STBs). While this study procedure has been successfully implemented to identify these individuals in a variety of settings, such as the ED, in-and outpatient clinics [18,19], and in a recent study of individuals with epilepsy and psychiatric comorbidities [21], it has yet to be implemented as part of outpatient mental health therapy sessions. This feasibility study was conducted in partnership with a child and adolescent mental health agency to understand how this technology integrates into a mental health professional's (MHP) workflow with adolescents and if the collected language samples can be analyzed with ML methods to predict risk for suicide.…”