Ecologically valid long-term mood monitoring of individuals with bipolar disorder using speech

Abstract

Speech patterns are modulated by the emotional and neurophysiological state of the speaker. There exists a growing body of work that computationally examines this modulation in patients suffering from depression, autism, and post-traumatic stress disorder. However, the majority of the work in this area focuses on the analysis of structured speech collected in controlled environments. Here we expand on the existing literature by examining bipolar disorder (BP). BP is characterized by mood transitions, varying from a healthy euthymic state to states characterized by mania or depression. The speech patterns associated with these mood states provide a unique opportunity to study the modulations characteristic of mood variation. We describe methodology to collect unstructured speech continuously and unobtrusively via the recording of day-to-day cellular phone conversations. Our pilot investigation suggests that manic and depressive mood states can be recognized from this speech data, providing new insight into the feasibility of unobtrusive, unstructured, and continuous speech-based wellness monitoring for individuals with BP.

E-health

“…Because of the general popularity of such approaches, many attempts are being made to develop social media E-health tools as well as apps for speech analysis of phone calls, particularly for manic episodes [7]. Despite an explosion of such applications like apps and blogs, and widespread uptake by the public, almost no research has been published establishing the validity or utility of such tools.…”

Internet-Based Cognitive-Behavioral Therapy for Depression: Current Progress and Future Directions

“…Examples of these innovations include using “passive” (i.e., no user input required) data collected from built-in smartphone sensors to predict elevated depressive symptoms and to suggest interventions; 22,23 differentiating depressive versus manic mood states from speech patterns detected from phone conversations; 24 predicting depressive symptoms from Facebook activity; 25 delivering CBT interventions via videogame format; 26 and using smartphone-based mental health apps to treat depression and anxiety. 27–29 …”

Mood state prediction from speech of varying acoustic quality for individuals with bipolar disorder

“…There is an opportunity to discover how speech cues can be automatically processed to augment objective measures available in clinical assessments. Mobile phones provide an effective platform for naturally monitoring these speech cues and have shown promise for BP [6, 7, 8]. However, changes in recording quality between different types of phones can severely decrease the predictive capabilities of a system.…”