Publications
2024 NEALS Poster - Machine Learning Model Predicts Listener Effort in ALS-related Dysarthria
The dysarthria occurring in ALS involves various deteriorating speech subsystems, challenging accurate quantification of progression. Speech-Language Pathologists (SLPs) use intelligibility ratings and Listener Effort (LE) assessments to quantify the severity of dysarthria. Recently, several Machine Learning (ML) methods have been proposed to assess patients' speech impairment, generally focusing on predicting the ALSFRS-R speech-related question. We have used ML on speech recordings to predict LE, a quantitative, clinically relevant measure of dysarthric speech.
Listener Effort can be reliably predicted by
medRxiv
Listener effort quantifies clinically meaningful progression of dysarthria in people living with amyotrophic lateral sclerosis
Indu Navar Bingham, Raquel Norel, Esteban G. Roitberg, Julián Peller, Marcos A Trevisan, Carla Agurto, Diego E. Shalom, Felipe Aguirre, Iair Embon, Alan Taitz, Donna Harris, Amy Wright, Katie Seaver, Stacey Sullivan, Jordan R. Green, Lyle W. Ostrow, Ernest Fraenkel, James D. Berry
Abstract
Amyotrophic lateral sclerosis (ALS) is a neurodegenerative motor neuron disease that causes progressive muscle weakness. Progressive bulbar dysfunction causes dysarthria and thus social isolation, reducing quality of life. The Everything ALS Speech Study obtained longitudinal clinical information and speech recordings from 292 participants. In a subset of 120 participants, we measured speaking rate (SR) and listener effort (LE), a measure of dysarthria severity rated by speech pathologists from recordings. LE intra- and inter-rater reliability was very high (ICC 0.88 to 0.92). LE correlated with other measures of dysarthria at baseline. LE changed over time in participants with ALS (slope 0.77 pts/month; p<0.001) but not controls (slope 0.005 pts/month; p=0.807). The slope of LE progression was similar in all participants with ALS who had bulbar dysfunction at baseline, regardless of ALS site of onset. LE could be a remotely collected clinically meaningful clinical outcome assessment for ALS clinical trials.
ISPOR 2023
Real-World Treatment Preferences Among People Living with ALS: A Discrete Choice Experiment
Biogen, Cambridge, MA
Trinity Life Sciences, Waltham, MA
NEALS Consortium, MA,
IBM Research, Yorktown Heights, NY
EverythingALS, Seattle, WA
Objective
Quantitatively assess which treatment attributes are most important to people living with amyotrophic lateral sclerosis (ALS; pALS) in the United States (US) when making treatment decisions. Through direct and indirect assessment of preference, pALS indicated a desire for efficacious treatment options that improve physical functioning and survival.
2023 IEEE International Conference on Digital Health (ICDH)
Remote Inference of Cognitive Scores in ALS Patients Using a Picture Description
Carla Agurto (IBM), Guillermo Cecchi (IBM), Bo Wen (IBM), Ernest Fraenkel (MIT), James Berry (MGH), Indu Navar (EverythingALS) and Raquel Norel (IBM)
Abstract
In this paper, we focused on another important aspect, cognitive impairment, which affects 35-50% of the ALS population. In an effort to reach the ALS population, which frequently exhibits mobility limitations, we implemented the digital version of the Edinburgh Cognitive and Behavioral ALS Screen (ECAS) test for the first time.
March 2023
Identifying amyotrophic lateral sclerosis through interactions with an internet search engine
Elad Yom-Tov (Microsoft Research) , Indu Navar (EverythingALS), Ernest Fraenkel (MIT) , James D. Berry (MGH)
Microsoft Research, Israel
EverythingALS, Seattle, WA
MIT, Cambridge, MA,
MGH, Harvard, MA
Abstract
We identified 285 anonymous Bing users whose queries indicated that they had been diagnosed with ALS and matched them to 1) 3276 control users and 2) 1814 users whose searches indicated they had ALS disease mimics. We tested whether the ALS group could be distinguished from controls and disease mimics based on search engine query data. Finally, we conducted a prospective validation from participants who provided access to their Bing search data. The model distinguished between the ALS group and controls with an area under the curve (AUC) of 0.81.
AMIA 2022 Annual Symposium
ALS Community Pressing Issues: Lessons from a Survey
A. Anvar (EverythingALS), J. Berry (MGH) , E. Fraenkel (MIT), I. Navar (EverythingALS), G. A. Cecchi (IBM), R. Norel (IBM)
EverythingALS, Seattle, WA
MGH, Cambridge, MA
MIT, Harvard, Cambridge, MA
IBM Thomas J. Watson Research Center, Yorktown Heights, NY
Abstract
We gathered survey data to identify the unmet needs expressed by Amyotrophic Lateral Sclerosis (ALS) patients, caregivers, and advocates. Natural Language Processing was used to summarize free text data. Identified needs, named anchor topics were selected manually from the data. Text embedding was used to score participant answers to anchor topics. Despite a broad range of opinions among cohorts, we detected pain control, better access to information and ALSFRS-R alternatives as
important ALS community issues. Natural Language Processing (NLP) and Artificial Intelligence (AI) was used to analyze the unstructured text data to obtain a deeper understanding of respondents’ answers.
Multimodal dialog based speech and facial biomarkers capture differential disease progression rates for ALS remote patient monitoring,
M. Neumann, O. Roesler, J. Liscombe, H. Kothare, D. Suendermann-Oeft, J. D. Berry, E. Fraenkel, R. Norel, A. Anvar, I. Navar, A. V. Sherman, J. R. Green and V. Ramanarayanan (2021).
In Proc. of: The 32nd International Symposium on Amyotrophic Lateral Sclerosis and Motor Neuron Disease, Virtual, December 2021.
Objective
Identify audiovisual speech markers that are responsive to clinical progression of Amyotrophic Lateral Sclerosis (ALS).
Lessons learned from a large-scale audio-visual remote data collection for Amyotrophic Lateral Sclerosis research.
Vikram Ramanarayanan, Michael Neumann , Aria Anvar, Oliver Roesler , Jackson Liscombe , Hardik Kothare , David Suendermann-Oeft , James D. Berry , Ernest Fraenkel , Raquel Norel , Alexander V. Sherman, Jordan R. Green and Indu Navar
Modality.AI, MGH Institute of Health Professions, Massachusetts Institute of Technology, IBM Thomas J. Watson Research Center, EverythingALS, Peter Cohen Foundation, Harvard University, University of California, San Francisco
Investigating the Utility of Multimodal Conversational Technology and Audiovisual Analytic Measures for the Assessment and Monitoring of Amyotrophic Lateral Sclerosis at Scale.
M. Neumann, O. Roesler, J. Liscombe, H. Kothare, D. Suendermann-Oeft, D. Pautler, I. Navar, A. Anvar, J. Kumm, R. Norel, E. Fraenkel, A. Sherman, J. Berry, G. Pattee, J. Wang, J. Green, V. Ramanarayanan: Investigating the Utility of Multimodal Conversational Technology and Audiovisual Analytic Measures for the Assessment and Monitoring of Amyotrophic Lateral Sclerosis at Scale . Accepted at Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czech Republic, August - September 2021
Accepted at Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czech Republic, August - September 2021.
Abstract
We investigate the utility of audiovisual dialog systems combined with speech and video analytics for real-time remote monitoring of depression at scale in uncontrolled environment settings. We collected audiovisual conversational data from participants who interacted with a cloud-based multimodal dialog system, and automatically extracted a large set of speech and vision metrics based on the rich existing literature of laboratory studies. We report on the efficacy of various audio and video metrics in differentiating people with mild, moderate and severe depression, and discuss the implications of these results for the deployment of such technologies in real-world neurological diagnosis and monitoring applications.
Towards A Large-Scale Audio-Visual Corpus for Research on Amyotrophic Lateral Sclerosis
A. Anvar, D. Suendermann-Oeft, D. Pautler, V. Ramanarayanan, J. Kumm, J. Berry, R. Norel, E. Fraenkel, and I. Navar: Towards A Large-Scale Audio-Visual Corpus for Research on Amyotrophic Lateral Sclerosis. In Proc. of AAN 2021, 73th Annual Meeting of the American Academy of Neurology, Virtual, April 2021.
In Proc. of AAN 2021, 73th Annual Meeting of the American Academy of Neurology, Virtual, April 2021
Objective
This presentation describes the creation of a large, open data platform, comprising speech and video recordings of people with ALS and healthy volunteers. Each participant is interviewed by Modality.AI’s virtual agent, emulating the role of a neurologist or speech pathologist walking them through speaking exercises [Fig 1] The collected data is made available to the academic and research community to foster acceleration of the development of biomarkers, diagnostics, therapies, and fundamental scientific understanding of ALS.
