Bipolar Speech Patterns: A Different Kind of Subtext

By Michael Ferguson
Friday, August 8, 2014
Specialty: 

Researchers are developing smartphone applications that may predict manic or depressive episodes based on speech patterns.

Although concerted pharmaco- and psychotherapeutic strategies can manage the intense emotional swings caused by bipolar disorder, the disorder’s unpredictability means these strategies can have limited efficacy.

As such, the ability to predict manic or depressive swings would give therapists a game-changing treatment tool. To that end, researchers around the globe are developing and testing apps that identify precursors of manic and depressive episodes by tracking activity levels, as well as changes in daily routine, sleep quality, social interaction and stress.

Vocal Cues

Researchers at the University of Michigan are testing an app that analyzes speech patterns to detect subtle variations that indicate mood changes. Dubbed PRIORI, the app functions in the phone’s background and records the patient’s side of any call. The recordings are encrypted and stored on servers that are in full compliance with patient privacy laws.

Weekly meetings with a care team establish a baseline for the patient’s mood. Because the sessions are recorded, the team can identify acoustic qualities in the patient’s speech and link those to the particular mood he or she is in.

Changes, such as long pauses, in vocal acoustics are recognized as indications of depressive states, and rapid topic changes and fast talking are linked to manic swings. With PRIORI, researchers hope to discover specific precursors to mood shifts so that patients know when they need to get help.

The technology is in the early phases of development and is being tested in a group of 60 people — 50 with bipolar disorder and 10 without — to confirm results of a smaller previous study that showed PRIORI’s efficacy.

Improved Data, Expanded Applications

PRIORI represents a potentially marked improvement over currently available smartphone applications. With existing apps, patients record data in a journal-like format, enabling them to identify events that might trigger mood swings, as well as remember their medication instructions and keep track of questions they want to ask their physician or psychologist at their next appointment. While these apps are valuable, they depend on patient compliance, whereas data collection is automatic with PRIORI.

University of Michigan researchers hope to apply their findings to other mental health disorders, such as schizophrenia and post-traumatic stress disorder, which can also cause changes in vocal patterns.

Research Abroad

Researchers at the University of Applied Sciences and Arts of Southern Switzerland are developing technology similar to PRIORI. The MONARCA wearable system includes an Android-based app that connects to wearable monitoring devices via Bluetooth. Sensors are located in specially designed wristwatches and socks. The sensors deliver information pertaining to sleep habits, pulse rates, location and social interaction.

With patients’ increased hesitance to volunteer personal information, the collection of adequate data could be challenging, but researchers hope nonetheless it will give a clearer picture of patient habits as their moods change.


Studies about MONARCA can be found at www.monarca-project.eu/deliverables/monarca-publications-alias.