Publications
2024 NEALS Conference
A Novel, Self-Administered, App-Based Assessment of Motor Movement in ALS
Christina Fournier (Emory University), Indu Navar (EverythingALS), Natalia Luchkina (EverythingALS), Christian Rubio (EverythingALS), and Stephanie Henze (EverythingALS)
Abstract
This study presents the ALS Motor App, a self-administered, AI-supported tool designed to remotely assess motor movement in individuals with ALS. The app evaluates 46 motor tasks across bulbar, upper extremity, trunk, and lower extremity regions through written descriptions and animated visuals. Users record their ability to perform tasks, with results stored in a central repository for review. Initial beta testing has refined the app using feedback from clinicians and people with ALS (pALS), with the tool now available on Google Play and the Apple Store. The app offers enhanced data granularity and accessibility, supporting adaptive algorithms that track motor decline and predict future care needs. Future work will validate the tool against standardized ALS measures and explore its reliability and predictive power for clinically relevant milestones.
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.
2024 NEALS Conference
Machine Learning Model Predicts Listener Effort in ALS-related Dysarthria
Indu Navar (EverythingALS), Esteban G. Roitberg (Universidad Nacional de San Martín and EverythingALS), Julian Peller (Humai and EverythingALS), Marcos A. Trevisan (Universidad de Buenos Aires and CONICET), Diego E. Shalom (Universidad de Buenos Aires and CONICET), Felipe Aguirre (EverythingALS), Gastón Bujía (EverythingALS), Iair Embon (EverythingALS), Alan Taitz (SRI International), Raquel Norel (IBM Research), Carla Agurto (IBM Research), Donna Harris (Temple University), Amy Wright (EverythingALS), Katie Seaver (EverythingALS), Stacey Sullivan (EverythingALS), Jordan R. Green (MGH Institute of Health Professions), Lyle W. Ostrow (Temple University), Ernest Fraenkel (MIT), and James D. Berry (Massachusetts General Hospital and Harvard Medical School)
Abstract
This study applies machine learning (ML) to predict Listener Effort (LE), a key measure of speech impairment in ALS-related dysarthria. Using 2,124 speech recordings from 125 participants (105 pALS, 20 controls) and manual LE ratings by Speech-Language Pathologists (SLPs) with excellent inter-rater reliability, ML models demonstrated robust predictive capabilities. A simple Lasso regression model achieved an R² of 0.83, with Speaking Rate and Whisper Confidence identified as the two most significant features. Advanced ensemble models achieved even higher accuracy (R² of 0.94). These findings highlight the potential of ML in quantifying LE, offering scalable and reliable tools to track ALS progression and evaluate therapeutic interventions.
2024 MND Conference
A Novel Web App-Based Assessment of Cognition in ALS Using Speech
Indu Navar (EverythingALS), Raquel Norel (IBM), Carla Agurto (IBM), Guillermo A. Cecchi (IBM), Bo Wen (IBM), Natalia Luchkina (EverythingALS), Stephanie Henze (EverythingALS), Alan Taitz (EverythingALS), Ahmad Al Khleifat (King’s College London), James Berry (MGH), Sharon Abrahams (University of Edinburgh), and Ammar Al-Chalabi (King’s College London)
Abstract
This study introduces a web app-based assessment for evaluating cognition in individuals with ALS, inspired by the Edinburgh Cognitive and Behavioral ALS Screen (ECAS). Data from 108 participants, including people with ALS and controls, were analyzed, with a subset completing repeated evaluations. Speech samples collected through picture description tasks were processed using Whisper Open AI for transcription, extracting acoustic and linguistic features. Linear regression models achieved Spearman correlations between 0.32 and 0.51 for predicting cognitive scores. The results highlight the potential of digitized, speech-based cognitive assessments as scalable, accessible alternatives to traditional methods, especially for individuals in remote or underserved areas. Future work will expand cohort size and refine methodologies to enhance accuracy and generalizability.
2024
A Roadmap to Incorporating Digital Endpoints in Clinical Trials 2024-2025
Authors and Contributors
EverythingALS Industry Consortia members, EverythingALS Scientific Advisory Board, regulatory advisors, and members of the ALS community, including pALS (people with ALS) and cALS (caregivers of people with ALS).
The collaborative effort included input from biopharmaceutical professionals, clinicians, technology developers, and advocacy representatives. The acknowledgment section specifically highlights the ALS community's vital role in shaping the research and insights presented.
Objective
This white paper advocates for the integration of digital health technologies (DHTs) into ALS clinical trials to enhance efficiency, accessibility, and patient-centricity. Traditional endpoints in ALS trials are burdensome and often lead to high attrition and prolonged durations. By leveraging DHTs, trials can enable continuous, remote, and quantitative patient monitoring, thus reducing bias, improving retention, and broadening accessibility. The roadmap outlined emphasizes interdisciplinary collaboration, agile methodologies, and regulatory alignment to optimize the clinical trial experience for both pALS and cALS. These efforts aim to accelerate innovation, improve disease tracking, and foster a participant-centered research paradigm for ALS care and therapeutics.
2024
Harnessing Remote Speech Tasks for Early ALS Biomarker Identification
Carla Agurto (IBM), Michele Merler (IBM), Esteban G. Roitberg (EverythingALS), Alan Taitz (formerly EverythingALS, now at SRI International), Marcos A. Trevisan (Universidad de Buenos Aires, CONICET), Diego E. Shalom (Universidad de Buenos Aires, CONICET), Julian Peller (EverythingALS), Lyle W. Ostrow (Temple University), Indu Navar (EverythingALS), Ernest Fraenkel (MIT), James Berry (MGH), Guillermo A. Cecchi (IBM), and Raquel Norel (IBM)
Abstract
This study investigates acoustic biomarkers for the early detection and monitoring of Amyotrophic Lateral Sclerosis (ALS). Using a dataset of 6,276 speech sessions from 291 participants, including 135 pALS, acoustic features were extracted via OpenSMILE and analyzed with machine learning classifiers. Results show up to 90% AUC in distinguishing ALS stages and 66% AUC for early detection. These findings highlight the potential of speech tasks as biomarkers to improve early diagnosis, track progression, and enhance the understanding of ALS
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.
October 2023
Muscle and Nerve
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.
_edited.png)