Dataset Information

Forecasting Mood in Bipolar Disorder From Smartphone Self-assessments: Hierarchical Bayesian Approach.

ABSTRACT: BACKGROUND:Bipolar disorder is a prevalent mental health condition that is imposing significant burden on society. Accurate forecasting of symptom scores can be used to improve disease monitoring, enable early intervention, and eventually help prevent costly hospitalizations. Although several studies have examined the use of smartphone data to detect mood, only few studies deal with forecasting mood for one or more days. OBJECTIVE:This study aimed to examine the feasibility of forecasting daily subjective mood scores based on daily self-assessments collected from patients with bipolar disorder via a smartphone-based system in a randomized clinical trial. METHODS:We applied hierarchical Bayesian regression models, a multi-task learning method, to account for individual differences and forecast mood for up to seven days based on 15,975 smartphone self-assessments from 84 patients with bipolar disorder participating in a randomized clinical trial. We reported the results of two time-series cross-validation 1-day forecast experiments corresponding to two different real-world scenarios and compared the outcomes with commonly used baseline methods. We then applied the best model to evaluate a 7-day forecast. RESULTS:The best performing model used a history of 4 days of self-assessment to predict future mood scores with historical mood being the most important predictor variable. The proposed hierarchical Bayesian regression model outperformed pooled and separate models in a 1-day forecast time-series cross-validation experiment and achieved the predicted metrics, R2=0.51 and root mean squared error of 0.32, for mood scores on a scale of -3 to 3. When increasing the forecast horizon, forecast errors also increased and the forecast regressed toward the mean of data distribution. CONCLUSIONS:Our proposed method can forecast mood for several days with low error compared with common baseline methods. The applicability of a mood forecast in the clinical treatment of bipolar disorder has also been discussed.

SUBMITTER: Busk J

PROVIDER: S-EPMC7367518 | biostudies-literature | 2020 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Forecasting Mood in Bipolar Disorder From Smartphone Self-assessments: Hierarchical Bayesian Approach.

Busk Jonas J Faurholt-Jepsen Maria M Frost Mads M Bardram Jakob E JE Vedel Kessing Lars L Winther Ole O

JMIR mHealth and uHealth 20200401 4

<h4>Background</h4>Bipolar disorder is a prevalent mental health condition that is imposing significant burden on society. Accurate forecasting of symptom scores can be used to improve disease monitoring, enable early intervention, and eventually help prevent costly hospitalizations. Although several studies have examined the use of smartphone data to detect mood, only few studies deal with forecasting mood for one or more days.<h4>Objective</h4>This study aimed to examine the feasibility of for ...[more]

PMID: 32234702

Similar Datasets

Project description:BackgroundBipolar disorder is a serious mental illness that results in significant morbidity and mortality. Pharmacotherapy is the primary treatment for bipolar disorder; however, adjunctive psychotherapy can help individuals use self-management strategies to improve outcomes. Yet access to this therapy is limited. Smartphones and other technologies have the potential to increase access to therapeutic strategies that enhance self-management while simultaneously providing real-time user feedback and provider alerts to augment care.ObjectiveThis paper describes the user-centered development of LiveWell, a smartphone-based self-management intervention for bipolar disorder, to contribute to and support the ongoing improvement and dissemination of technology-based mental health interventions.MethodsIndividuals with bipolar disorder first participated in a field trial of a simple smartphone app for self-monitoring of behavioral targets. To develop a complete technology-based intervention for bipolar disorder, this field trial was followed by design sessions, usability testing, and a pilot study of a smartphone-based self-management intervention for bipolar disorder. Throughout all phases of development, intervention revisions were made based on user feedback.ResultsThe core of the LiveWell intervention consists of a daily self-monitoring tool, the Daily Check-in. This self-monitoring tool underwent multiple revisions during the user-centered development process. Daily Check-in mood and thought rating scales were collapsed into a single wellness rating scale to accommodate user development of personalized scale anchors. These anchors are meant to assist users in identifying early warning signs and symptoms of impending episodes to take action based on personalized plans. When users identified personal anchors for the wellness scale, the anchors most commonly reflected behavioral signs and symptoms (40%), followed by cognitive (25%), mood (15%), physical (10%), and motivational (7%) signs and symptoms. Changes to the Daily Check-in were also made to help users distinguish between getting adequate sleep and keeping a regular routine. At the end of the pilot study, users reported that the Daily Check-in made them more aware of early warning signs and symptoms and how much they were sleeping. Users also reported that they liked personalizing their anchors and plans and felt this process was useful. Users experienced some difficulties with developing, tracking, and achieving target goals. Users also did not consistently follow up with app recommendations to contact providers when Daily Check-in data suggested they needed additional assistance. As a result, the human support roles for the technology were expanded beyond app use support to include support for self-management and clinical care communication. The development of these human support roles was aided by feedback on the technology's usability from the users and the coaches who provided the human support.ConclusionsUser input guided the development of intervention content, technology, and coaching support for LiveWell. Users valued the provision of monitoring tools and the ability to personalize plans for staying well, supporting the role of monitoring and personalization as important features of digital mental health technologies. Users also valued human support of the technology in the form of a coach, and user difficulties with aspects of self-management and care-provider communication led to an expansion of the coach's support roles. Obtaining feedback from both users and coaches played an important role in the development of both the LiveWell technology and human support. Attention to all stakeholders involved in the use of mental health technologies is essential for optimizing intervention development.

Project description:BackgroundIndividuals with bipolar disorder (BD) are increasingly turning to smartphone applications (apps) for health information and self-management support. While reviews have raised concerns regarding the effectiveness and safety of publicly available apps for BD, apps surveyed may not reflect what individuals with BD are using. The present study had two aims: first, to characterize the use of health apps to support mood and sleep amongst people with BD, and second, to evaluate the quality, safety and functionality of the most commonly used self-management apps.MethodsA web-based survey was conducted to explore which apps people with BD reported using to support self-management of mood and sleep. The characteristics of the most commonly nominated apps were described using a standardized framework, including their privacy policy, clinical foundations, and functionality.ResultsRespondents (n = 919) were 77.9% female with a mean age of 36.9 years. 41.6% of participants (n = 382) reported using a self-management app to support mood or sleep. 110 unique apps were nominated in relation to mood, and 104 unique apps nominated in relation to sleep; however, most apps were only mentioned once. The nine most frequently nominated apps related to mood and sleep were subject to further evaluation. All reviewed apps offered a privacy policy, however user control over data was limited and the complexity of privacy policies was high. Only one app was developed for BD populations. Half of reviewed apps had published peer-reviewed evidence to support their claims of efficacy, but little research was specific to BD.ConclusionFindings illustrate the potential of smartphone apps to increase the reach of psychosocial interventions amongst people with BD. Apps were largely created by commercial developers and designed for the general population, highlighting a gap in the development and dissemination of evidence-informed apps for BD. There may be risks in using generic health apps for BD self-management; clinicians should enquire about patients' app use to foster conversations about their particular benefits and limitations.

Project description:ObjectiveThe Course and Outcome of Bipolar Youth study found that children and adolescents with bipolar spectrum disorders followed 1 of 4 distinct mood trajectories over 8 years of follow-up, with as many as 25% of participants showing a predominantly euthymic course. We evaluated whether similar patterns of illness course are observed in adolescents with bipolar I and II disorder who participated in a 2-year clinical trial.MethodA total of 144 adolescents with bipolar I or II disorder, identified shortly after a mood episode, were assessed over a 2-year period. Participants were randomly assigned to one of 2 psychosocial family treatments during the first 9 months of the study, and pharmacotherapy was provided throughout the 2 years. Using latent class growth analyses, we classified participants into distinct courses of illness based on mood ratings collected over the 2 years. We examined demographic and illness variables as predictors of these course classifications.ResultsLatent class growth analyses indicated four mood trajectories: "predominantly euthymic" (29.9% of sample), "ill with significantly improving course" (11.1%), "moderately euthymic" (26.4%), and "ill with moderately improving course" (32.6%). Adolescents in these classes were euthymic 77.7%, 53.6%, 44.1%, and 18.6% of the weeks of follow-up, respectively. Psychosocial treatment condition and baseline medication exposure were not associated with trajectories. However, youth with more severe baseline depressive symptoms, suicidality, lower quality of life scores, and minority race/ethnicity had more symptomatic courses of illness over time.ConclusionA substantial proportion (25%-30%) of youth with bipolar I or II disorder maintain euthymic states over extended periods of follow-up. Identifying youth who are more and less likely to remain stable over time may help guide psychosocial and pharmacological treatments after an illness episode.Clinical trial registration informationEffectiveness of Family-Focused Treatment Plus Pharmacotherapy for Bipolar Disorder in Adolescents; https://clinicaltrials.gov/; NCT00332098.

Dataset Information

Forecasting Mood in Bipolar Disorder From Smartphone Self-assessments: Hierarchical Bayesian Approach.

Publications

Forecasting Mood in Bipolar Disorder From Smartphone Self-assessments: Hierarchical Bayesian Approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets