Stratification of amyotrophic lateral sclerosis patients: A crowdsourcing approach

Robert Kueffner; Neta Zach; Maya Bronfeld; Raquel Norel; Nazem Atassi; Venkat Balagurusamy; Barbara Di Camillo; Adriano Chio; Merit Cudkowicz; Donna Dillenberger; Javier Garcia-Garcia; Orla Hardiman; Bruce Hoff; Joshua Knight; Melanie L. Leitner; Guang Li; Lara Mangravite; Thea Norman; Liuxia Wang; The ALS Stratification Consortium, including; Wing Chung Wong; Jinfeng Xiao; Wen Chieh Fang; Jian Peng; Chen Yang; Huan Jui Chang; Gustavo Stolovitzky

doi:10.1038/s41598-018-36873-4

Stratification of amyotrophic lateral sclerosis patients: A crowdsourcing approach

Robert Kueffner^*, Neta Zach^*, Maya Bronfeld, Raquel Norel, Nazem Atassi, Venkat Balagurusamy, Barbara Di Camillo, Adriano Chio, Merit Cudkowicz, Donna Dillenberger, Javier Garcia-Garcia, Orla Hardiman, Bruce Hoff, Joshua Knight, Melanie L. Leitner, Guang Li, Lara Mangravite, Thea Norman, Liuxia Wang, The ALS Stratification Consortium, includingWing Chung Wong, Jinfeng Xiao, Wen Chieh Fang, Jian Peng, Chen Yang, Huan Jui Chang, Gustavo Stolovitzky

^*Corresponding author for this work

Department of Computer Science

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

52 Citations (Scopus)

40 Downloads (CityUHK Scholars)

Abstract

Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease where substantial heterogeneity in clinical presentation urgently requires a better stratification of patients for the development of drug trials and clinical care. In this study we explored stratification through a crowdsourcing approach, the DREAM Prize4Life ALS Stratification Challenge. Using data from >10,000 patients from ALS clinical trials and 1479 patients from community-based patient registers, more than 30 teams developed new approaches for machine learning and clustering, outperforming the best current predictions of disease outcome. We propose a new method to integrate and analyze patient clusters across methods, showing a clear pattern of consistent and clinically relevant sub-groups of patients that also enabled the reliable classification of new patients. Our analyses reveal novel insights in ALS and describe for the first time the potential of a crowdsourcing to uncover hidden patient sub-populations, and to accelerate disease understanding and therapeutic development.

© The Author(s) 2019

Original language	English
Article number	690
Journal	Scientific Reports
Volume	9
Online published	24 Jan 2019
DOIs	https://doi.org/10.1038/s41598-018-36873-4
Publication status	Published - 2019

Funding

We are grateful to the following people for their important assistance with this manuscript: The clinicians and researchers behind the Irish and Italian ALS registers and the pharmaceutical companies which provided data to the PRO-ACT dataset, that enabled this entire endeavor, the hundreds of participants on the crowdfunding effort that provided this challenge’s award. Prof. David Schoenfeld for his assistance with statistical considerations, and, of course, the solvers who participated in the challenge and the patients who inspired this effort. Data used in the preparation of this article were obtained from the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) Database. As such, the following organizations and individuals within the PRO-ACT Consortium contributed to the design and implementation of the PRO-ACT Database and/or provided data, but did not participate in the analysis of the data or the writing of this report: Neurological Clinical Research Institute at MGH, Northeast ALS Consortium, Novartis, Prize4Life Israel, Regeneron Pharmaceuticals Inc., Sanofi, Teva Pharmaceutical Industries Ltd.

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Access Output

10.1038/s41598-018-36873-4

Final Published version.pdfFinal Published version, 3.01 MBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Kueffner, R., Zach, N., Bronfeld, M., Norel, R., Atassi, N., Balagurusamy, V., Di Camillo, B., Chio, A., Cudkowicz, M., Dillenberger, D., Garcia-Garcia, J., Hardiman, O., Hoff, B., Knight, J., Leitner, M. L., Li, G., Mangravite, L., Norman, T., Wang, L., ... Stolovitzky, G. (2019). Stratification of amyotrophic lateral sclerosis patients: A crowdsourcing approach. Scientific Reports, 9, Article 690. https://doi.org/10.1038/s41598-018-36873-4

@article{8367a284e5884b1b827cc3ac2ffaf5dd,

title = "Stratification of amyotrophic lateral sclerosis patients: A crowdsourcing approach",

abstract = "Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease where substantial heterogeneity in clinical presentation urgently requires a better stratification of patients for the development of drug trials and clinical care. In this study we explored stratification through a crowdsourcing approach, the DREAM Prize4Life ALS Stratification Challenge. Using data from >10,000 patients from ALS clinical trials and 1479 patients from community-based patient registers, more than 30 teams developed new approaches for machine learning and clustering, outperforming the best current predictions of disease outcome. We propose a new method to integrate and analyze patient clusters across methods, showing a clear pattern of consistent and clinically relevant sub-groups of patients that also enabled the reliable classification of new patients. Our analyses reveal novel insights in ALS and describe for the first time the potential of a crowdsourcing to uncover hidden patient sub-populations, and to accelerate disease understanding and therapeutic development.{\textcopyright} The Author(s) 2019",

author = "Robert Kueffner and Neta Zach and Maya Bronfeld and Raquel Norel and Nazem Atassi and Venkat Balagurusamy and {Di Camillo}, Barbara and Adriano Chio and Merit Cudkowicz and Donna Dillenberger and Javier Garcia-Garcia and Orla Hardiman and Bruce Hoff and Joshua Knight and Leitner, {Melanie L.} and Guang Li and Lara Mangravite and Thea Norman and Liuxia Wang and {The ALS Stratification Consortium, including} and Wong, {Wing Chung} and Jinfeng Xiao and Fang, {Wen Chieh} and Jian Peng and Chen Yang and Chang, {Huan Jui} and Gustavo Stolovitzky and Rached Alkallas and Catalina Anghel and Jeanne Avril and Jaume Bacardit and Barbara Balser and John Balser and Yoav Bar-Sinai and Noa Ben-David and Eyal Ben-Zion and Robin Bliss and Jialu Cai and Anatoly Chernyshev and Chiang, {Jung Hsien} and Davide Chicco and Corriveau, {Bhavna Ahuja Nicole} and Junqiang Dai and Yash Deshpande and Eve Desplats and Durgin, {Joseph S.} and Espiritu, {Shadrielle Melijah G.} and Fan Fan and Philippe Fevrier and Fridley, {Brooke L.} and Adam Godzik",

year = "2019",

doi = "10.1038/s41598-018-36873-4",

language = "English",

volume = "9",

journal = "Scientific Reports",

issn = "2045-2322",

publisher = "Nature Publishing Group",

}

Kueffner, R, Zach, N, Bronfeld, M, Norel, R, Atassi, N, Balagurusamy, V, Di Camillo, B, Chio, A, Cudkowicz, M, Dillenberger, D, Garcia-Garcia, J, Hardiman, O, Hoff, B, Knight, J, Leitner, ML, Li, G, Mangravite, L, Norman, T, Wang, L, The ALS Stratification Consortium, including, Wong, WC, Xiao, J, Fang, WC, Peng, J, Yang, C, Chang, HJ & Stolovitzky, G 2019, 'Stratification of amyotrophic lateral sclerosis patients: A crowdsourcing approach', Scientific Reports, vol. 9, 690. https://doi.org/10.1038/s41598-018-36873-4

TY - JOUR

T1 - Stratification of amyotrophic lateral sclerosis patients

T2 - A crowdsourcing approach

AU - Kueffner, Robert

AU - Zach, Neta

AU - Bronfeld, Maya

AU - Norel, Raquel

AU - Atassi, Nazem

AU - Balagurusamy, Venkat

AU - Di Camillo, Barbara

AU - Chio, Adriano

AU - Cudkowicz, Merit

AU - Dillenberger, Donna

AU - Garcia-Garcia, Javier

AU - Hardiman, Orla

AU - Hoff, Bruce

AU - Knight, Joshua

AU - Leitner, Melanie L.

AU - Li, Guang

AU - Mangravite, Lara

AU - Norman, Thea

AU - Wang, Liuxia

AU - The ALS Stratification Consortium, including

AU - Wong, Wing Chung

AU - Xiao, Jinfeng

AU - Fang, Wen Chieh

AU - Peng, Jian

AU - Yang, Chen

AU - Chang, Huan Jui

AU - Stolovitzky, Gustavo

AU - Alkallas, Rached

AU - Anghel, Catalina

AU - Avril, Jeanne

AU - Bacardit, Jaume

AU - Balser, Barbara

AU - Balser, John

AU - Bar-Sinai, Yoav

AU - Ben-David, Noa

AU - Ben-Zion, Eyal

AU - Bliss, Robin

AU - Cai, Jialu

AU - Chernyshev, Anatoly

AU - Chiang, Jung Hsien

AU - Chicco, Davide

AU - Corriveau, Bhavna Ahuja Nicole

AU - Dai, Junqiang

AU - Deshpande, Yash

AU - Desplats, Eve

AU - Durgin, Joseph S.

AU - Espiritu, Shadrielle Melijah G.

AU - Fan, Fan

AU - Fevrier, Philippe

AU - Fridley, Brooke L.

AU - Godzik, Adam

PY - 2019

Y1 - 2019

N2 - Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease where substantial heterogeneity in clinical presentation urgently requires a better stratification of patients for the development of drug trials and clinical care. In this study we explored stratification through a crowdsourcing approach, the DREAM Prize4Life ALS Stratification Challenge. Using data from >10,000 patients from ALS clinical trials and 1479 patients from community-based patient registers, more than 30 teams developed new approaches for machine learning and clustering, outperforming the best current predictions of disease outcome. We propose a new method to integrate and analyze patient clusters across methods, showing a clear pattern of consistent and clinically relevant sub-groups of patients that also enabled the reliable classification of new patients. Our analyses reveal novel insights in ALS and describe for the first time the potential of a crowdsourcing to uncover hidden patient sub-populations, and to accelerate disease understanding and therapeutic development.© The Author(s) 2019

AB - Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease where substantial heterogeneity in clinical presentation urgently requires a better stratification of patients for the development of drug trials and clinical care. In this study we explored stratification through a crowdsourcing approach, the DREAM Prize4Life ALS Stratification Challenge. Using data from >10,000 patients from ALS clinical trials and 1479 patients from community-based patient registers, more than 30 teams developed new approaches for machine learning and clustering, outperforming the best current predictions of disease outcome. We propose a new method to integrate and analyze patient clusters across methods, showing a clear pattern of consistent and clinically relevant sub-groups of patients that also enabled the reliable classification of new patients. Our analyses reveal novel insights in ALS and describe for the first time the potential of a crowdsourcing to uncover hidden patient sub-populations, and to accelerate disease understanding and therapeutic development.© The Author(s) 2019

UR - http://www.scopus.com/inward/record.url?scp=85060520844&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85060520844&origin=recordpage

U2 - 10.1038/s41598-018-36873-4

DO - 10.1038/s41598-018-36873-4

M3 - RGC 21 - Publication in refereed journal

C2 - 30679616

AN - SCOPUS:85060520844

SN - 2045-2322

VL - 9

JO - Scientific Reports

JF - Scientific Reports

M1 - 690

ER -

Stratification of amyotrophic lateral sclerosis patients: A crowdsourcing approach

Abstract

Funding

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this