Machine learning as a new paradigm for characterizing localization and lateralization of neuropsychological test data in temporal lobe epilepsy.

In this study, we employed a kernel support vector machine to predict epilepsy localization and lateralization for patients with a diagnosis of epilepsy (n = 228). We assessed the accuracy to which indices of verbal memory, visual memory, verbal fluency, and naming would localize and lateralize seizure focus in comparison to standard electroencephalogram (EEG). Classification accuracy was defined as models that produced the least cross-validated error (CVϵ). In addition, we assessed whether the inclusion of norm-based standard scores, demographics, and emotional functioning data would reduce CVϵ. Finally, we obtained class probabilities (i.e., the probability of a particular classification for each case) and produced receiver operating characteristic (ROC) curves for the primary analyses. We obtained the least error assessing localization data with the Gaussian radial basis kernel function (RBF; support vectors = 157, CVϵ = 0.22). There was no overlap between the localization and lateralization models, such that the poorest localization model (the hyperbolic tangent kernel function; support vectors = 91, CVϵ = 0.36) outperformed the strongest lateralization model (RBF; support vectors = 201, CVϵ = 0.39). Contrary to our hypothesis, the addition of norm, demographics, and emotional functioning data did not improve the accuracy of the models. Receiver operating characteristic curves suggested clinical utility in classifying epilepsy lateralization and localization using neuropsychological indicators, albeit with better discrimination for localizing determinations. This study adds to the existing literature by employing an analytic technique with inherent advantages in generalizability when compared to traditional single-sample, not cross-validated models. In the future, class probabilities extracted from these and similar analyses could supplement neuropsychological practice by offering a quantitative guide to clinical judgements.

Neuropsychological function is improved among opioid dependent adults who adhere to opiate agonist treatment with buprenorphine-naloxone: a preliminary study.

BACKGROUND: Among persons with opioid use disorder (OUD), neuropsychological dysfunction is associated with depression, and better neuropsychological function is associated with opioid abstinence. However, it is unknown whether depressive symptomatology or adherence to opiate agonist treatment are associated with neuropsychological change over time. METHODS: We recruited 20 buprenorphine/naloxone-treated adults with OUD (M Age = 45.2 years [SD = 8.1]; 25% female) to complete baseline and 6 month visits containing a neuropsychological test battery and self-reported measures of depressive symptomatology and medication adherence. RESULTS: Depressive symptomatology was not significantly related to neuropsychological change (p's > .05). Greater adherence to buprenorphine/naloxone was associated with improvements in learning, memory, and global functioning (r's = .52-60; p's < .05). CONCLUSIONS: Among OUD patients, greater adherence to buprenorphine/naloxone is associated with improved neuropsychological functioning over time. In contrast, depressive symptomatology is not associated with neuropsychological functioning over time. Supporting adherence to buprenorphine/naloxone may improve and/or preserve learning and memory functioning in individuals treated for OUD. TRIAL REGISTRATION: NCT01108679 . Registered 21 April 2010.

Community-based "powerful tools" intervention enhances health of caregivers.

Family caregiving is prevalent and may have adverse impacts on health, particularly for elder caregivers who tend to have chronic health conditions which need ongoing self-management. Interventions that empower family caregivers to take care of themselves are needed. This study examined the impact on caregivers of participation in a self-care skill-building, self-efficacy enhancing, community-based program called powerful tools for caregiving (PTC). We assessed health-risk behaviors, self-care, and psychological well-being among 118 adult caregivers who participated in PTC in western Washington state between July 2001 and June 2004, about half of whom were aged 65 or older. Health-risk behaviors were reduced and self-care and psychological well-being improved significantly, overall and for each stratum of age (> or =65 years of age versus <65).