Digital Voice Analysis as a Measure of Frailty and Distress (DIVAN)

Digital Voice Analysis as a Measure of Frailty and Distress. A Feasibility Study (DIVAN)

This study evaluates if it is possible to identify quantitative parameters from audio signals to describe the changes in patient's state in relation to frailty and distress.

Study Overview

• Status: Recruiting
• Conditions: Frailty; Distress, Emotional
• Intervention / Treatment: Other: Data acquisition: Speech acquisition; Diagnostic test: Data acquisition: G8 Screening tool; Diagnostic test: Data acquisition: Distress Thermometer

Detailed Description

Frailty is a common clinical syndrome especially in older adults that carries an increased risk for poor health outcomes including falls, incident disability, hospitalization, and mortality. The early detection of frailty is of importance in many patient populations to predict treatment outcomes, identify patient needs and coordinate efficient and meaningful care. An electronic assessment of the degree of distress in patients, who are unable to report, would be important to be able to routinely and objectively identify suffering in these patients. Digital voice analysis (DVA) gathers speech samples from individuals via different kinds of recording devices (smartphone, tablet, etc.) and examines a large variety of specific acoustic parameters such as for example frequency and voice quality features. This study is to analyse the potential to evaluate distress and frailty through digital voice analysis. On the contrary to the existing studies, it is intended to record audio and clinical evaluation data from the same subject multiple times during several weeks to be able to analyse temporal changes. This will allow to not only perform inter-subject but as well intra-subject comparisons of changes in audio features with changes of the patient's wellbeing over time. To make the patient speak as freely and relaxed as possible, the patient will describe different images. Different features will be extracted from the audios and potential candidates for a larger patient study will be identified, if data quantity permits using machine learning algorithms. Therefore this study evaluates if it is feasible to gather digital voice samples for voice analyses from cancer patients alongside conventional assessments for frailty (G8 questionnaire and distress (Distress Thermometer) to conduct first, preliminary analyses for identification of potential correlates between voice features and frailty or distress and between changes over time.

• Study Type: Observational
• Enrollment (Estimated): 100

Contacts and Locations

• Study Contact: Name: Marcus Vetter, PD Dr. med.; Phone Number: +41 61 925 2525; Email: marcus.vetter@ksbl.ch
• Study Contact Backup: Name: Jan Gärtner, Prof. Dr. med.; Phone Number: +41 61 319 7575; Email: jan.gaertner@pzhi.ch

Study Locations

• Switzerland
  • Basel, Switzerland, 4002
    • Recruiting
    • Palliativzentrum Hildegard, Basel
    • Contact: Jan Gärtner, Prof. Dr. med.; Phone Number: +41 61 319 7575; Email: jan.gaertner@pzhi.ch
    • Principal Investigator: Jan Gärtner, Prof. Dr. med.
  • Liestal, Switzerland, 4410
    • Recruiting
    • Kantonsspital Baselland, Klinik für Onkologie, Hämatologie und Immuntherapie
    • Contact: Marcus Vetter, PD Dr. med.; Phone Number: + 41 61 925 2525; Email: marcus.vetter@ksbl.ch
    • Principal Investigator: Marcus Vetter, PD Dr. med.

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No

• Sampling Method: Probability Sample

Study Population

Patient recruitment will be performed at the different participating clinical sites by the investigator

Description

Inclusion Criteria:

• Active cancer or haemato-oncological malignancy
• Adults (≥ 18 years)
• Ability to understand, speak and read German language fluently
• Ability to provide written consent
• Sufficient or corrected vision to see the images
• Sufficient auditory comprehension for participation in the study based on the therapist's clinical opinion
• Ability to concentrate for 20-30 minutes based on the investigator's clinical opinion
• Signed informed consent to the study

Exclusion Criteria:

• Aphonia, dysphonia or other obvious voice alterations of patient's voice
• Life-expectancy shorter ≤ 14 days as judged by a physician or nurse via "surprise question"
• Breathlessness whilst speaking
• Cognitive impairment as judged by physician or Mini-Cog in the G8 screening tool
• Severe physical, emotional or existential suffering because of which the enrollment and participation in the study would result in patient burden, as judged by the treating physicians and their multiprofessional team members

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Cohort A: palliative care center; Patients from a palliative care center (Palliativzentrum Hildegard, Basel)	Other: Data acquisition: Speech acquisition; Speech test with synchronized audio and video recording. The speaking exercises and the audio and video recording will be done using a tablet computer and an application developed in-house. Freely available images showing different scenes will be integrated and displayed on the tablet to be described by the patient. The goal is to have at least two and maximum four of them described with several sentences by each patient per session. Parameters will be extracted from the patient's audio data to estimate the changes in distress and frailty.; Diagnostic test: Data acquisition: G8 Screening tool; The G8 screening tool consists of seven items dealing with food intake, weight loss, mobility, neuropsychological problem, body mass index, prescription drug, and self-perception of health, from the Mini-Nutritional Assessment (MNA) questionnaire and was developed specifically for elderly cancer patients. The total G-8 score lies between 0 and 17. A higher score indicates a better health status.; Diagnostic test: Data acquisition: Distress Thermometer; The distress thermometer (DT) is a measure of psychological distress in cancer patients. The instrument is a self-reported tool using a 0-to-10 rating scale.
Cohort B: mid-size cancer center; Patients from a mid-size cancer center (Tumorzentrum Baselland)	Other: Data acquisition: Speech acquisition; Speech test with synchronized audio and video recording. The speaking exercises and the audio and video recording will be done using a tablet computer and an application developed in-house. Freely available images showing different scenes will be integrated and displayed on the tablet to be described by the patient. The goal is to have at least two and maximum four of them described with several sentences by each patient per session. Parameters will be extracted from the patient's audio data to estimate the changes in distress and frailty.; Diagnostic test: Data acquisition: G8 Screening tool; The G8 screening tool consists of seven items dealing with food intake, weight loss, mobility, neuropsychological problem, body mass index, prescription drug, and self-perception of health, from the Mini-Nutritional Assessment (MNA) questionnaire and was developed specifically for elderly cancer patients. The total G-8 score lies between 0 and 17. A higher score indicates a better health status.; Diagnostic test: Data acquisition: Distress Thermometer; The distress thermometer (DT) is a measure of psychological distress in cancer patients. The instrument is a self-reported tool using a 0-to-10 rating scale.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Change of mean fundamental frequency extracted from the patient's audio data	Change of mean fundamental frequency extracted from the patient's audio data to estimate the changes in distress and frailty.	during a 16-week period for each patient
Change of first few formants (F1, F2)	Change of first few formants (F1, F2) extracted from the patient's audio data to estimate the changes in distress and frailty.	during a 16-week period for each patient
Change of jitter (variation in F0 from cycle to cycle)	Change of jitter (variation in F0 from cycle to cycle) extracted from the patient's audio data to estimate the changes in distress and frailty.	during a 16-week period for each patient
Change of shimmer (variation in peak-to-peak amplitude)	Change of shimmer (variation in peak-to-peak amplitude) extracted from the patient's audio data to estimate the changes in distress and frailty.	during a 16-week period for each patient
Change of skewness	Change of skewness extracted from the patient's audio data to estimate the changes in distress and frailty.	during a 16-week period for each patient
Change of kurtosis	Change of kurtosis extracted from the patient's audio data to estimate the changes in distress and frailty.	during a 16-week period for each patient
Change of voice strength (volume) of the vowel	Change of voice strength (volume) of the vowel extracted from the patient's audio data to estimate the changes in distress and frailty.	during a 16-week period for each patient
Change of duration of length of the answer	Change of duration of length of the answer extracted from the patient's audio data to estimate the changes in distress and frailty.	during a 16-week period for each patient
Change of verbal fluency	Change of verbal fluency extracted from the patient's audio data to estimate the changes in distress and frailty.	during a 16-week period for each patient
Change of word duration of individual words	Change of word duration of individual words extracted from the patient's audio data to estimate the changes in distress and frailty.	during a 16-week period for each patient
Change of duration of the breaks between the words	Change of duration of the breaks between the words extracted from the patient's audio data to estimate the changes in distress and frailty.	during a 16-week period for each patient

Collaborators and Investigators

• Sponsor: University Hospital, Basel, Switzerland
• Investigators: Principal Investigator: Marcus Vetter, PD Dr. med., Kantonsspital Baselland, Klinik für Onkologie, Hämatologie und Immuntherapie

Study record dates

Study Major Dates

• Study Start (Actual): November 19, 2022
• Primary Completion (Estimated): November 1, 2024
• Study Completion (Estimated): November 1, 2024

Study Registration Dates

• First Submitted: March 13, 2023
• First Submitted That Met QC Criteria: March 13, 2023
• First Posted (Actual): March 24, 2023

Study Record Updates

• Last Update Posted (Actual): April 22, 2024
• Last Update Submitted That Met QC Criteria: April 19, 2024
• Last Verified: April 1, 2024

More Information

Terms related to this study

• Keywords: Machine learning; Frailty monitoring; Distress monitoring; Digital voice analysis (DVA); Distress Thermometer; G8 geriatric screening tool
• Additional Relevant MeSH Terms: Pathologic Processes; Frailty
• Other Study ID Numbers: 2022-01461; th23Vetter

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No