Forecasting Mood in Bipolar Disorder From Smartphone Self-assessments: Hierarchical Bayesian Approach
BackgroundBipolar 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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2020-04-01
|
| Series: | JMIR mHealth and uHealth |
| Online Access: | https://mhealth.jmir.org/2020/4/e15028 |
| _version_ | 1818381949092233216 |
|---|---|
| author | Busk, Jonas Faurholt-Jepsen, Maria Frost, Mads Bardram, Jakob E Vedel Kessing, Lars Winther, Ole |
| author_facet | Busk, Jonas Faurholt-Jepsen, Maria Frost, Mads Bardram, Jakob E Vedel Kessing, Lars Winther, Ole |
| author_sort | Busk, Jonas |
| collection | DOAJ |
| description | BackgroundBipolar 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.
ObjectiveThis 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.
MethodsWe 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.
ResultsThe 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.
ConclusionsOur 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. |
| first_indexed | 2024-12-14T02:42:42Z |
| format | Article |
| id | doaj.art-7333e0c236c34ff4b30f1b2da397e5bd |
| institution | Directory Open Access Journal |
| issn | 2291-5222 |
| language | English |
| last_indexed | 2024-12-14T02:42:42Z |
| publishDate | 2020-04-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR mHealth and uHealth |
| spelling | doaj.art-7333e0c236c34ff4b30f1b2da397e5bd2022-12-21T23:19:59ZengJMIR PublicationsJMIR mHealth and uHealth2291-52222020-04-0184e1502810.2196/15028Forecasting Mood in Bipolar Disorder From Smartphone Self-assessments: Hierarchical Bayesian ApproachBusk, JonasFaurholt-Jepsen, MariaFrost, MadsBardram, Jakob EVedel Kessing, LarsWinther, OleBackgroundBipolar 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. ObjectiveThis 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. MethodsWe 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. ResultsThe 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. ConclusionsOur 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.https://mhealth.jmir.org/2020/4/e15028 |
| spellingShingle | Busk, Jonas Faurholt-Jepsen, Maria Frost, Mads Bardram, Jakob E Vedel Kessing, Lars Winther, Ole Forecasting Mood in Bipolar Disorder From Smartphone Self-assessments: Hierarchical Bayesian Approach JMIR mHealth and uHealth |
| title | Forecasting Mood in Bipolar Disorder From Smartphone Self-assessments: Hierarchical Bayesian Approach |
| title_full | Forecasting Mood in Bipolar Disorder From Smartphone Self-assessments: Hierarchical Bayesian Approach |
| title_fullStr | Forecasting Mood in Bipolar Disorder From Smartphone Self-assessments: Hierarchical Bayesian Approach |
| title_full_unstemmed | Forecasting Mood in Bipolar Disorder From Smartphone Self-assessments: Hierarchical Bayesian Approach |
| title_short | Forecasting Mood in Bipolar Disorder From Smartphone Self-assessments: Hierarchical Bayesian Approach |
| title_sort | forecasting mood in bipolar disorder from smartphone self assessments hierarchical bayesian approach |
| url | https://mhealth.jmir.org/2020/4/e15028 |
| work_keys_str_mv | AT buskjonas forecastingmoodinbipolardisorderfromsmartphoneselfassessmentshierarchicalbayesianapproach AT faurholtjepsenmaria forecastingmoodinbipolardisorderfromsmartphoneselfassessmentshierarchicalbayesianapproach AT frostmads forecastingmoodinbipolardisorderfromsmartphoneselfassessmentshierarchicalbayesianapproach AT bardramjakobe forecastingmoodinbipolardisorderfromsmartphoneselfassessmentshierarchicalbayesianapproach AT vedelkessinglars forecastingmoodinbipolardisorderfromsmartphoneselfassessmentshierarchicalbayesianapproach AT wintherole forecastingmoodinbipolardisorderfromsmartphoneselfassessmentshierarchicalbayesianapproach |