stacked_line_chartAccess DatapersonADRC Portal Login
UDSv4 Digital Voice

About Digital Voice

Uniform Data Set Version 4 (UDSv4) provided Centers with the option to collect digital audio recordings of the cognition section of the UDS study. NACC and the Clinical Task Force (CTF) Technology Workgroup are collaborating to support ADRC adoption of digital voice as part of the UDSv4.

Why Digital Voice?

The implementation of digitally recording participant responses to neuropsychological tests is a cost-effective way to detect early changes in cognition. As our cognitive capabilities shift, we express them through vocal responses in subtle ways, such as changing word choices or sentence structures because of word finding problems, pausing, hesitating, and shifting as memory, attention, and executive functions are compromised.

Currently, there is no gold standard of methods for analyzing voice recordings in relation to cognition. However, just as with blood-based biomarkers, there is a growing, albeit still limited, set of literature suggesting that analysis of digital voice recordings as a method for differentiating those with and without cognitive impairment is promising.

ADRC Resources

Getting Started with Digital Voice

Additional Resources

Training Webinar: UDS 4.0 Digital Voice Training Workshop

NACC and the CTF Technology Workgroup hosted a training workshop focused on digital voice data collection. This workshop provided guidance on the consent process, recording procedures, and data storage for digital voice data. Leaders in the digital voice field presented research findings emphasizing the scientific importance and potential of digital voice data.

See presentation slides 

Speakers

  • Rhoda Au, PhD, MBA, Director of Neuropsychology for the Framingham Heart Study, Boston University
  • Brad Dickerson, MD, Leader of the Neuroimaging Core, Massachusetts ADRC
  • Sudeshna Das, PhD, Leader of the Data Core, Massachusetts ADRC
  • Jeffrey Kaye, PhD, Director of ORCATECH and Professor of Neurology at OHSU School of Medicine
  • Cody Karjadi, MS, Research Applications Developer Team Manager for the Framingham Heart Study, Boston University
  • Melissa Lamar, PhD, Professor and Clinical Neuropsychologist, Rush ADRC 
  • Nina Silverberg, PhD, ADRC Program Director, NIA

Digital Voice Data Collection Workgroups

NACC and the Clinical Task Force (CTF) Technology Workgroup are collaborating to support ADRC adoption of digital data modalities, starting with Digital Voice in UDSv4. The CTF Technology Workgroup's goal is to expand and enrich AD/ADRD data collection with less burden on participants and clinical staff. It aims to identify and develop guidelines for high impact digital data modalities that will be collected, integrated, and harmonized from across the ADRC Program and shared with researchers via the Data Front Door. 

The CTF Technology Workgroup consists of the CTF Technology Workgroup Parent and the following three sub-committees:

New Non-UDS Digital Instruments Committee

Co-leads: Jeff Kaye MD (OHSU), Kate Papp, PhD (Mass Gen/Harvard), Jason Hassenstab, PhD (Wash U) 

Covers a myriad of different assessments and/or technologies, from radar to robots! Focuses on identifying high value non-UDS assessments that ADRCs can adopt (with minimal burden for participants and clinical staff) and encouraging involvement of the diverse sub-populations or cohorts across the ADRC ecosystem.

In-Clinic UDS Digital Instruments Committee

Co-leads: Teresa Gomez-Isla, MD (Mass Gen/Havard), Kate Possin, PhD (UCSF), Hiroko Dodge, PhD (Mass Gen/Harvard)

Guides and supports the implementation of audio recording of traditional paper-based UDS measures, including reviewing and proposing in-clinic digital tests that acquire clinically meaningful data for incorporation into the UDS with minimal participant and staff burden.

Virtual Standard UDS Committee

Co-leads: Sudeshna Das, PhD (Mass Gen/Harvard), Zach Beattie, PhD (OHSU), Melissa Lamar, PhD (Rush ADRC)

Establishes guidelines and best practices for conducting virtual Unified Data Set (UDS) assessments, including defining the minimal virtual UDS dataset, providing recommendations for the virtual administration process, evaluating the equivalency of virtual and in-person evaluations, and addressing logistical considerations.

Get Involved

Frequently Asked Questions

What are the benefits of digital biomarkers to my ADRC?

There are many practical benefits to adding voice recording to your ADRC:

  • Acting as a QC tool to determine natural drift in standardization in any longitudinal study
  • Providing an easy, low-cost collection of data that can be done in a participant’s preferred language
  • Allowing additional scientific enablement at no additional participant burden
  • Increasing opportunities to explore acoustic and semantic features in novel forms

What are the benefits of digital biomarkers to participants?

While participants may not directly benefit at the outset, over time the features of voice data may:

  • Provide early indicators of cognitive impairment in preclinical or prodromal Alzheimer’s dementia
  • Help track disease progression and predict conversion to dementia

What are the benefits of digital biomarkers to science?

Features of voice data are already showing promise in these areas:

  • Serving as a dementia screening tool to detect those at risk for dementia
  • Indicating the effectiveness of clinical trials
  • Associating with CSF biomarkers of disease

How do I obtain local IRB approval?

Please work with your local IRB to obtain regulatory approval for collecting digital voice data. You can reference this IRB protocol and consent language document for helpful tips and suggestions.

PLEASE NOTE: NACC will not share any raw voice recordings until robust voice de-identification standards have been determined by NACC, NIA, ADRCs, and the CTF Technology Workgroup. NACC will provide additional guidance on data submission and sharing as this process is further defined.

Can I use any recorder to capture voice data for UDSv4?

While many devices will record voice data, NACC has certain requirements for recording UDSv4 voice data:

  • Zoom H4N recorders are preferred
  • Limited background noise
  • At the beginning of the recording state staff ID, participant ID (NACCID), study visit date and number, and what is being recorded

Do we have to use more expensive, encrypted recorders to minimize risk to PHI if lost/misplaced? 

Not all recorders are encrypted, which may pose a significant risk if they contain PHI and are lost/misplaced. This is an important consideration, but, unfortunately, there is no "one size fits all" approach - each method has its own issues and concerns with relation to privacy and security. It is up to your local institution and ADRC if you want to purchase encrypted recorders, but at a minimum, your institution may want to adopt some best practices:

  • Immediately upon ending the visit/recording, upload the file to a secure cloud server and delete it from the recording device.
  • If you are capturing digital voice on an iPhone or other smartphone, there are many ways to encrypt files.

Do I need to process the voice data at my ADRC?

While all ADRCs are encouraged to keep voice files for their own use, all voice data will be uploaded to NACC:

  • Use NACC naming conventions: NACCID_DATE_TESTNAME
  • Store in WAV format whenever possible
  • Enter metadata of the test in the UDSv4 dVoice form (coming soon)

How do I submit digital voice data to NACC?

At this time NACC is asking ADRCs to record and store digital voice data locally at their ADRC. NACC will provide ADRCs with a Digital Voice data submission option via the ADRC Portal in the future. Learn more about the ADRC Portal.

PLEASE NOTE: NACC will not share any raw voice recordings until robust voice de-identification standards have been determined by NACC, NIA, ADRCs, and the CTF Technology Workgroup. NACC will provide additional guidance on data submission and sharing as this process is further defined.

What is the UDSv4 dVoice form?

The UDSv4 dVoice form, currently under development, will accompany any uploaded voice data. The form will include but is not limited to the following data variables:

  • VISIT DATE
  • NACC VISIT NUMBER
  • COGNITIVE TEST
  • TIME STAMPS (if more than 1 cogtest present in recording)
  • INTERVIEWER INITIALS
  • MASK (whether interviewer and/or participant had a mask)
  • VISIT LOCATION/SETTING
  • MICROPHONE LOCATION
  • DEVICE MANUFACTURER
  • DEVICE MODEL
  • NUMBER OF RECORDING SUBJECTS

How do you separate multiple speakers’ voices to focus on the participant’s voice?

It is sometimes helpful to analyze "conversations," but when needed there are automated methods available to efficiently "clean" vocal recordings down to a single speaker of interest.

What is the process for scrubbing an audio file to remove PHI? Who is handling that task?

De-identification tools are in process for voice masking and PII splicing; however, NACC won't share any vocal data until such de-identification processes are validated and complete on all vocal recordings. We are exploring the multiple levels of de-identification, but the most important task is to de-identify the voice prints themselves. NACC will notify the ADRC Program when voice masking technology with at least some level of PHI removal is available.

Is there a standard file type (WAV vs MP3) and minimum bit rates and bit depths?

This depends somewhat on the limitations of the recording equipment and/or platforms available to you (e.g., Zoom does not save to .WAV formats). However, this should not prohibit you from collecting voice recordings. (Google has a speech-to-text tool with their recommendations.)

Please see the Digital Voice Data Collection Manual for recommended devices and device settings.

Neuropsychologists are advised to prevent the release of stimulus materials, test procedures, etc., of neuropsychological data. Having these things recorded allows for the potential release of this information. In addition to the UDS Neuropsych Battery, other sites may include copyright-protected measures in their site-specific battery. 

There is no “one size fits all” when it comes to determining what can be shared and in what form. NACC is working to come up with an appropriate governance structure that ensures participant privacy and confidentiality protection. Similar to other clinical processes, each site is encouraged to share what is feasible, and NACC will respect any agreed upon limitations on what we can share with researchers to ensure that proprietary and copyright information is protected.