Early warning signals observed in motor activity preceding mood state change in bipolar disorder.

INTRODUCTION: Alterations in motor activity are well-established symptoms of bipolar disorder, and time series of motor activity can be considered complex dynamical systems. In such systems, early warning signals (EWS) occur in a critical transition period preceding a sudden shift (tipping point) in the system. EWS are statistical observations occurring due to a system's declining ability to maintain homeostasis when approaching a tipping point. The aim was to identify critical transition periods preceding bipolar mood state changes. METHODS: Participants with a validated bipolar diagnosis were included to a one-year follow-up study, with repeated assessments of the participants' mood. Motor activity was recorded continuously by a wrist-worn actigraph. Participants assessed to have relapsed during follow-up were analyzed. Recognized EWS features were extracted from the motor activity data and analyzed by an unsupervised change point detection algorithm, capable of processing multi-dimensional data and developed to identify when the statistical property of a time series changes. RESULTS: Of 49 participants, four depressive and four hypomanic/manic relapses among six individuals occurred, recording actigraphy for 23.8 ± 0.2 h/day, for 39.8 ± 4.6 days. The algorithm detected change points in the time series and identified critical transition periods spanning 13.5 ± 7.2 days. For depressions 11.4 ± 1.8, and hypomania/mania 15.6 ± 10.2 days. CONCLUSION: The change point detection algorithm seems capable of recognizing impending mood episodes in continuous flowing data streams. Hence, we present an innovative method for forecasting approaching relapses to improve the clinical management of bipolar disorder.

Association between C-reactive protein levels and antipsychotic treatment during 12 months follow-up period after acute psychosis.

BACKGROUND: A potential role of inflammatory pathways in the pathology of schizophrenia has been suggested for at least a subgroup of patients. Elevated levels of the inflammatory marker C-reactive protein (CRP) have been observed, with associations to pathogenesis and symptoms. The current evidence regarding effects of antipsychotics on CRP levels is ambiguous. OBJECTIVES: To examine and compare the influence on CRP levels of three pharmacologically diverse new generation antipsychotics during a one-year follow-up in schizophrenia spectrum disorder. METHODS: In a multicenter, pragmatic and rater-blinded randomized trial, the effects of amisulpride, aripiprazole and olanzapine were compared in 128 patients with schizophrenia spectrum disorder. All had positive symptoms of psychosis at study entry. Clinical and laboratory assessments including the measurement of CRP levels were conducted at baseline, and 1, 3, 6, 12, 26, 39, and 52 weeks thereafter. RESULTS: For all antipsychotic drugs analysed together, there was an increase in CRP levels during the one-year follow-up. Aripiprazole, as opposed to amisulpride and olanzapine, was associated with a reduced CRP level after one week, after which the CRP level caught up with the other drugs. Compared to those previously exposed to antipsychotic drugs, antipsychotic-naïve patients had lower CRP levels at all follow-up time points, but with the same temporal patterns of change. CONCLUSION: Treatment with amisulpride, aripiprazole and olanzapine showed different effects on CRP levels in patients with schizophrenia spectrum disorders, modified by previous antipsychotics exposure status. This finding suggests that antipsychotic drugs may vary with respect to their influence on pro-inflammatory pathways. TRIAL REGISTRATION: ClinicalTrials.gov ID: NCT01446328; URL: http://www. CLINICALTRIALS: gov/.

Applying machine learning in motor activity time series of depressed bipolar and unipolar patients compared to healthy controls.

Current practice of assessing mood episodes in affective disorders largely depends on subjective observations combined with semi-structured clinical rating scales. Motor activity is an objective observation of the inner physiological state expressed in behavior patterns. Alterations of motor activity are essential features of bipolar and unipolar depression. The aim was to investigate if objective measures of motor activity can aid existing diagnostic practice, by applying machine-learning techniques to analyze activity patterns in depressed patients and healthy controls. Random Forrest, Deep Neural Network and Convolutional Neural Network algorithms were used to analyze 14 days of actigraph recorded motor activity from 23 depressed patients and 32 healthy controls. Statistical features analyzed in the dataset were mean activity, standard deviation of mean activity and proportion of zero activity. Various techniques to handle data imbalance were applied, and to ensure generalizability and avoid overfitting a Leave-One-User-Out validation strategy was utilized. All outcomes reports as measures of accuracy for binary tests. A Deep Neural Network combined with SMOTE class balancing technique performed a cut above the rest with a true positive rate of 0.82 (sensitivity) and a true negative rate of 0.84 (specificity). Accuracy was 0.84 and the Matthews Correlation Coefficient 0.65. Misclassifications appear related to data overlapping among the classes, so an appropriate future approach will be to compare mood states intra-individualistically. In summary, machine-learning techniques present promising abilities in discriminating between depressed patients and healthy controls in motor activity time series.

Predictors of treatment satisfaction in antipsychotic-naïve and previously medicated patients with acute-phase psychosis.

Background: Treatment satisfaction predicts treatment adherence and long-term outcome for patients with psychosis. It is therefore important to understand the underpinnings of patient satisfaction in psychosis treatment for optimal treatment delivery. Aims: To examine the associations between satisfaction and level and change in positive symptoms, insight, depression and side effects of antipsychotics in previously medicated and antipsychotic-naïve patients. Method: Data derive from a randomised trial, with 226 respondents at baseline and 104 at follow-up. The measures were the positive subscale and insight item from the Positive and Negative Syndrome Scale, Calgary Depression Scale, the UKU Consumer Satisfaction Rating Scale, and the UKU side effects scale. Structural equation modelling was used to test the model. The full information maximum likelihood estimator used all available data. Results: In the sample of 226 patients, 67.3% were male and 44.2% were antipsychotic-naïve. The mean age was 34.1 years. For previously medicated patients, satisfaction was predicted by level of insight (b = -2.21, ß = -0.42) and reduction in positive symptoms (b = -0.56, ß = -0.39). For antipsychotic-naïve patients, satisfaction was predicted by level and change of insight (b = -2.21, ß = -0.46), change in depression (b = -0.37, ß = -0.26) and side effects (b = -0.15, ß = -0.30). All predictors were significant at the 0.05 level. Conclusion: Reducing positive symptoms and side effects are important to enhance patient satisfaction. However, improving insight and reducing depression are more important in antipsychotic-naïve patients.