Related Experiment Video
Updated: Sep 14, 2025
05:19
Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
Published on: July 7, 2023
2.5K
Predicting depressive and manic episodes in patients with bipolar disorder using statistical process control methods
Vera M Ludwig1, Carl A Bittendorf2, Iris Reinhard3
1Department of Psychiatry and Psychotherapy, University Hospital Carl Gustav Carus, Dresden University of Technology.
Journal of Psychopathology and Clinical Science
|July 21, 2025
Summary
Passive sensing via smartphones did not reliably detect early bipolar disorder (BD) episodes. Self-reported mood via e-diary was more effective, but predicting future episodes remained challenging for both methods.
Area of Science:
- Digital phenotyping
- Psychopathology
- Bipolar disorder (BD) management
Background:
- Early detection of affective episodes is vital for managing bipolar disorder (BD).
- Passive sensing using smartphones and wearables offers potential for continuous monitoring of behavioral changes.
- Statistical Process Control (SPC) is a novel method for detecting process deviations, but its use in mobile sensing for BD is unexplored.
Purpose of the Study:
- To investigate the potential of Statistical Process Control (SPC) in detecting emerging affective episodes in bipolar disorder (BD) using passive sensing data.
- To compare the efficacy of passive sensing data with self-reported mood data in identifying manic and depressive episodes.
Main Methods:
- Utilized data from the BipoSense study, including 12 months of passive sensing data from smartphone apps, daily e-diary entries, and biweekly expert interviews.
- Applied SPC charts and multilevel analyses to assess 26 depressive and 20 (hypo)manic emerging episodes in 28 BD patients.
- Evaluated the performance of passive sensing parameters and self-rated mood in detecting current and pre-episode weeks.
Main Results:
- Passive sensing data did not robustly detect affective episodes or pre-episode weeks in bipolar disorder (BD) patients.
- Self-rated current bipolar mood from e-diaries outperformed passive sensing in predicting current episodes, though prediction of pre-episode weeks was limited.
- SPC, even with personalized limits and optimized settings, did not surpass clinical cutoffs and showed insufficient detection rates for clinical use due to false alarms.
Conclusions:
- Passive sensing, while a low-burden tool, currently lacks the sensitivity and specificity for reliable early detection of bipolar disorder (BD) affective episodes.
- Self-reported mood data shows more promise than passive sensing for detecting current episodes, but predicting future episodes remains a challenge.
- Future research should focus on mobile sensing parameters more closely aligned with psychopathology to improve detection accuracy and clinical utility.
Related Concept Videos
01:30Bipolar Disorder
145
Bipolar disorder is a chronic mental health condition marked by significant mood fluctuations, including episodes of mania and depression. Elevated energy levels, heightened mood or irritability, impulsive behavior, reduced sleep needs, rapid speech, racing thoughts, inflated self-esteem, and distractibility characterize mania. Individuals with bipolar disorder often alternate between depressive and manic states, with periods of emotional stability lasting an average of six months to a year.
145
01:24Mania and Antimanic Drugs: Overview
322
Mania, a psychological condition characterized by elevated mood, increased energy, and reduced sleep need, is part of the bipolar disorder cycle. The exact cause of mania isn't entirely known, but it is thought to be a combination of genetic, environmental, and neurological factors. Bipolar disorder involves alternating manic and depressive episodes. Mood stabilizers like lithium, antipsychotics, and anticonvulsants help manage these episodes. Lithium carbonate is particularly effective as...
322