A low-burden high-frequency prognostic digital speech biomarker to improve future confirmatory ALS and FTD trials


Changes in speech and language patterns in frontotemporal dementia (FTD) and amyotrophic lateral sclerosis (ALS) are well known but vary significantly by underlying disease and subtype. Changes in speech in ALS can occur due to cognitive impairment as well as limitations in speech motor skills and respiratory function. In contrast, language impairment in FTD reflects individual cognitive impairment and is used to distinguish between subtypes of the disorder.

Background and aims

To date, neither the course of language impairments nor a possible influence by speech motor and respiratory impairments have been investigated. In addition, until now, language skills have usually been assessed on the basis of clinical assessments, some of which have been carried out in writing.

PROSA aims at the development and validation of a new prognostic language biomarker for the ALS-FTD spectrum based on repeatable, short, high-frequency speech assessments that can be collected remotely.

  • Speech-based measures can be used to assess three core symptom groups in this pathological continuum including: cognition (language, executive function & memory), motor speech & respiratory function. The resulting biomarkers will improve the characterization of heterogeneity within patient groups and will help to predict the individual course of the disease. Such biomarkers could improve stratification of study groups and facilitate decisions about adaptive trial modifications or early termination in future studies.


PROSA is a longitudinal controlled study of DZNE and the company ki:elements funded by the TargetALS-Foundation. The study will be conducted as an addendum to two running DZNE cohort studies (DESCRIBE ALS and DESCRIBE FTD). Patients are already recruited for the main longitudinal cohorts. Yearly DESCRIBE visits will provide clinical information as well as basic clinical assessments for PROSA. In addition to the running cohorts PROSA will collect speech data over the telephone on a quarterly basis. All calls will be conducted either automatically by the software "Mili" or standardized by a study staff member. Data analysis is carried out by an AI.

Course of the study

A maximum of four telephone conversations lasting approximately 30 minutes are planned over a period of 12 months. All calls will be conducted by an automated software similar to an automatic telephone announcement or a study staff member. A subsequent questionnaire or personal interview will record how the conversation with Mili or the staff member was perceived.

The data will be pseudonymized and uploaded to a server of the DZNE and analyzed by the companies ki:elements and Winterlight Labs.

A full set of information about the study can be downloaded here (in German only): Flyer PROSA

Principle Investigators:
Prof. Dr. Anja Schneider, DZNE Bonn
Prof. Dr. Dr. Andreas Hermann, DZNE Rostock/Greifswald
Start of the study: 2023
Status: multi centric, recruiting active

Study Coordination / Project Management

Judith Baltes (DZNE Bonn)
+49 228 287-11451

Martha Kring (DZNE Rostock/Greifswald)
+49 381 494 149521

Welcome to our website, here you can inform yourself basically cookie-free.

We would be pleased if you would allow a cookie to be set for analysis purposes in order to optimise our provided information. All data are pseudonymous and are only used by the DZNE. We deliberately avoid third-party cookies. You can deselect this setting at any time here.

Your browser allows the setting of cookies: