Spoken Language Analysis for Bipolar Disorder

Overseen By Jeremiah Joyce, MD, MS

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Mayo Clinic

Disqualifiers: Drug use, Paranoid delusions, Developmental delay, Aggression, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

20 Participants Needed

What You Need to Know Before You Apply

What is the purpose of this trial?

This research is being done to find if there are changes with voice and speech during episodes of mania.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

Is spoken language analysis for bipolar disorder safe for humans?

The research on spoken language analysis for bipolar disorder does not mention any safety concerns, suggesting it is generally safe for humans. ^{1 2 3 4 5}

How does spoken language analysis differ from other treatments for bipolar disorder?

Spoken language analysis for bipolar disorder is unique because it uses voice features as biomarkers to monitor mood changes, unlike traditional treatments that focus on medication or therapy. This approach allows for continuous, unobtrusive monitoring of mood states through everyday speech, providing a novel way to track and manage the condition. ^{1 4 6 7 8}

What data supports the effectiveness of the treatment Spoken Language in Mania for bipolar disorder?

Research shows that analyzing voice features can help identify mood states in people with bipolar disorder, making it a useful tool for understanding and managing mania. Voice features have been found to accurately classify manic states, suggesting that spoken language analysis could be an effective part of treatment. ^{1 4 6 8 9}

Who Is on the Research Team?

Mark Frye, MD

Principal Investigator

Mayo Clinic

Are You a Good Fit for This Trial?

This study is for English-speaking individuals with a confirmed diagnosis of Bipolar I Disorder who are currently hospitalized or in the Emergency Department due to mania. Participants must be able to give informed consent and understand the study's objectives. Those with drug use, paranoia about electronic surveillance, developmental delays, involuntary hospitalization, communicable diseases requiring isolation, or risk of aggression cannot join.

Inclusion Criteria

I am currently hospitalized or in the ER for mania as determined by my doctor.

I have been diagnosed with Bipolar I Disorder.

Provision of informed consent before any study procedures are performed

Exclusion Criteria

I have a guardian and cannot make medical decisions on my own.

I have a contagious disease that requires me to be isolated.

Currently involuntarily hospitalized

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

1 week

Recording Session During Hospitalization

While inpatient, participants will undergo a research interview with recorded audio

Approximately 48 hours

Follow-up

Participants are monitored for changes in voice and speech after treatment

Up to 1 month from enrollment

What Are the Treatments Tested in This Trial?

Interventions

• Spoken Language in Mania

Trial Overview The trial aims to investigate changes in voice and speech patterns during manic episodes by conducting research interviews with participants experiencing mania as part of their bipolar disorder.

How Is the Trial Designed?

Group I: Recording Session During Hospitalization Experimental Treatment 1 Intervention

While inpatient, participants will undergo a research interview with recorded audio.

Who Is Running the Clinical Trial?

Mayo Clinic

Lead Sponsor

Trials

3,427

Recruited

3,221,000+

Published Research Related to This Trial

This study identified specific speech features, such as the fourth formant (F4) and Linear Prediction Coefficient (LPC), that significantly differ between manic patients and healthy individuals, suggesting their potential as biomarkers for diagnosing bipolar mania.

The research involved 30 manic patients and 30 healthy controls, and found that changes in speech characteristics correlate with mood states, indicating that analyzing speech during natural dialogue could be a practical method for clinical diagnosis and evaluation of bipolar mania.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Analysis on speech signal features of manic patients. Zhang, J., Pan, Z., Gui, C., et al.[2019]

Voice features collected during phone calls can serve as accurate and objective markers for identifying manic or mixed states in patients with bipolar disorder, achieving an impressive accuracy with an area under the curve (AUC) of 0.89.

Combining these voice features with smartphone-generated behavioral data and self-monitored mood data slightly enhances the accuracy and sensitivity of classifying affective states, indicating a potential for improved monitoring of bipolar disorder in everyday settings.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Voice analysis as an objective state marker in bipolar disorder. Faurholt-Jepsen, M., Busk, J., Frost, M., et al.[2018]

A study involving 60 participants (20 with bipolar disorder, 20 with unipolar disorder, and 20 controls) found that individuals with bipolar disorder used more sensory-somatic language compared to those with unipolar disorder and controls, suggesting distinct linguistic patterns that could aid in diagnosis.

The research indicates that linguistic features, such as the use of the pronoun 'I' and the Referential Activity Intensity Index, can help differentiate between bipolar and unipolar disorders, potentially enhancing diagnostic accuracy beyond traditional self-report measures.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Linguistic analysis of autobiographical narratives in unipolar and bipolar mood disorders in light of multiple code theory. Mariani, R., Di Trani, M., Negri, A., et al.[2021]

In a study involving 12 euthymic male participants with bipolar disorder and 12 matched controls, it was found that bipolar patients had slower reaction times during language processing tasks, indicating potential difficulties in language processing despite similar accuracy levels.

Bipolar patients exhibited abnormal patterns of prefrontal activation during language tasks, suggesting that their brain responses differ from those of healthy individuals, particularly as task demands increased.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The nature of abnormal language processing in euthymic bipolar I disorder: evidence for a relationship between task demand and prefrontal function. Curtis, VA., Thompson, JM., Seal, ML., et al.[2007]

A study involving 56 patients with bipolar disorder demonstrated that vocal features from verbal fluency tasks can effectively distinguish between mixed and non-mixed acute episodes, achieving high accuracy rates (up to 86%).

The findings suggest that these vocal biomarkers could be easily integrated into clinical practice to enhance the diagnostic accuracy for bipolar mixed episodes, potentially leading to better treatment outcomes.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Vocal features obtained through automated methods in verbal fluency tasks can aid the identification of mixed episodes in bipolar disorder. Weiner, L., Guidi, A., Doignon-Camus, N., et al.[2023]

Bipolar disorder is complex and varies greatly among individuals, making it crucial to identify specific subgroups that respond differently to treatments, which can improve patient management and outcomes.

Key factors such as the presence of mixed features during depressive episodes, comorbidities, and early environmental exposures significantly influence treatment response and risk of suicide, highlighting the need for tailored and integrated treatment approaches.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The clinical characterization of the adult patient with bipolar disorder aimed at personalization of management. McIntyre, RS., Alda, M., Baldessarini, RJ., et al.[2023]

The Mood Swings Questionnaire (MSQ), a web-based self-report screening tool for bipolar disorder, was accessed 278,279 times in its first year, with 65% of 4829 participants receiving a preliminary diagnosis of bipolar disorder, indicating its potential effectiveness for early detection.

Participants found the MSQ helpful and reassuring, with over 70% expressing intent to follow up with a health professional, highlighting the tool's role in promoting help-seeking behavior and addressing the significant personal and social impacts of bipolar disorder.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Take-up and profile of individuals accessing a web-based bipolar self-test screening measure. Parker, G., Fletcher, K., Blanch, B., et al.[2018]

In a study of 13,497 adults with bipolar-I disorder, it was found that Black individuals had significantly lower odds (40%-49%) of receiving antimanic medications compared to White individuals, indicating a racial disparity in treatment access.

No significant disparities were observed for Hispanic individuals compared to Whites in terms of antimanic medication use, suggesting that the focus for improving treatment should particularly address the needs of Black patients with bipolar disorder.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Longitudinal racial/ethnic disparities in antimanic medication use in bipolar-I disorder. Busch, AB., Huskamp, HA., Neelon, B., et al.[2021]

This study explores how speech patterns can indicate mood states in individuals with bipolar disorder, using unstructured speech data collected from everyday phone conversations.

Preliminary results suggest that it is possible to recognize manic and depressive states from this speech data, highlighting the potential for continuous and unobtrusive monitoring of mental health in people with bipolar disorder.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

ECOLOGICALLY VALID LONG-TERM MOOD MONITORING OF INDIVIDUALS WITH BIPOLAR DISORDER USING SPEECH. Karam, ZN., Provost, EM., Singh, S., et al.[2022]

Citations

1. England pubmed.ncbi.nlm.nih.gov

Analysis on speech signal features of manic patients. [2019]

2. United States pubmed.ncbi.nlm.nih.gov

Voice analysis as an objective state marker in bipolar disorder. [2018]

3. Netherlands pubmed.ncbi.nlm.nih.gov

Linguistic analysis of autobiographical narratives in unipolar and bipolar mood disorders in light of multiple code theory. [2021]

4. Denmark pubmed.ncbi.nlm.nih.gov

The nature of abnormal language processing in euthymic bipolar I disorder: evidence for a relationship between task demand and prefrontal function. [2007]

5. United States pubmed.ncbi.nlm.nih.gov

Vocal features obtained through automated methods in verbal fluency tasks can aid the identification of mixed episodes in bipolar disorder. [2023]

6. Italy pubmed.ncbi.nlm.nih.gov

The clinical characterization of the adult patient with bipolar disorder aimed at personalization of management. [2023]

7. Netherlands pubmed.ncbi.nlm.nih.gov

Take-up and profile of individuals accessing a web-based bipolar self-test screening measure. [2018]

8. United States pubmed.ncbi.nlm.nih.gov

Longitudinal racial/ethnic disparities in antimanic medication use in bipolar-I disorder. [2021]

9. United States pubmed.ncbi.nlm.nih.gov

ECOLOGICALLY VALID LONG-TERM MOOD MONITORING OF INDIVIDUALS WITH BIPOLAR DISORDER USING SPEECH. [2022]