20K Distributed Learning Challenge

• ClinicalTrials.gov Identifier: NCT03564457
• Recruitment Status: Completed
• First Posted: June 20, 2018
• Last Update Posted: March 8, 2019
• Sponsor: Maastricht Radiation Oncology
• Collaborators: Radboud University Medical Center; The Netherlands Cancer Institute; Manchester Academic Health Science Centre; Catholic University of the Sacred Heart; Fudan University; Velindre Cancer Center; University of Michigan; Cardiff University
• Information provided by (Responsible Party): Maastricht Radiation Oncology

Study Description

Brief Summary:

Machine learn a predictive model from more than 20.000 non-small cell lung cancer patients from more than 5 health care providers from more than 5 countries.

Condition or disease	Intervention/treatment
Non Small Cell Lung Cancer	Other: No interventions will take place (observational)

Detailed Description:

All current innovations in medicine, including personalized medicine; artificial intelligence; (Big) data driven medicine; learning health care system; value based health care and decision support systems, rely on the sharing of data across health care providers. But sharing of data is hampered by administrative, political, ethical and technical barriers(Sullivan et al., 2011). This limits the amount of health data available for the above innovations and life sciences in general as well as other secondary uses such as quality improvement.

The investigators hypothesize that sharing questions rather than sharing data is a better approach and can unlock orders of magnitude more data while limiting privacy and other concerns. An infrastructure to bring questions to the data has been demonstrated to work recently in project such as euroCAT(Lambin et al., 2013; Deist et al., 2017), Datashield (Gaye et al., 2014) and OHDSI (Hripcsak et al., 2015). However, the scale of the prior work has been limited in terms of the number of data subjects, number of data providers and global coverage.

In the experience of the investigators, the main challenges of scaling up the infrastructure are 1) the effort necessary to make data FAIR at each site ("stations"), 2) the technical and legal governance ("track") and 3) the mathematics and engineering of learning applications ("trains") - together called the Personal Health Train (PHT) infrastructure. Since multiple years a global consortium of healthcare providers, scientists and commercial parties called CORAL (Community in Oncology for RApid Learning) have worked on all three PHT challenges.

The aim of this study is to show that the PHT distributed learning infrastructure can be scaled to many 1000s of patients, specifically the investigators aim to machine learn a predictive model from more than 20.000 non-small cell lung cancer patients from more than 5 health care providers from more than 5 countries.

Study Design

• Study Type: Observational
• Actual Enrollment: 20000 participants
• Observational Model: Cohort
• Time Perspective: Retrospective
• Official Title: Distributed Learning of a Survival Model in More Than 20.000 Lung Cancer Patients
• Actual Study Start Date: July 1, 2018
• Actual Primary Completion Date: October 1, 2018
• Actual Study Completion Date: October 1, 2018

Groups and Cohorts

Group/Cohort	Intervention/treatment
One group of 20.000 patients; No interventions will take place as this is an observational study	Other: No interventions will take place (observational); No interventions will take place (observational)

Outcome Measures

Primary Outcome Measures :

1. Overall survival [ Time Frame: 2 years after (any) treatment for non small cell lung cancer ]
   Overall survival

Eligibility Criteria

• Ages Eligible for Study: Child, Adult, Older Adult
• Sexes Eligible for Study: All
• Accepts Healthy Volunteers: No
• Sampling Method: Non-Probability Sample

Study Population

All patients with non-small cell lung cancer who have been treated in one of the participating hospitals

Criteria

Inclusion Criteria:

• Non small cell lung cancer
• Treated in one of the participating hospitals

Exclusion Criteria:

• No non small cell lung cancer
• Not treated in one of the participating centers

Contacts and Locations

Locations

Netherlands

MAASTRO clinic

Maastricht, Netherlands, 6229 ET

Sponsors and Collaborators

Maastricht Radiation Oncology

Radboud University Medical Center

The Netherlands Cancer Institute

Manchester Academic Health Science Centre

Catholic University of the Sacred Heart

Fudan University

Velindre Cancer Center

University of Michigan

Cardiff University

Investigators

• Principal Investigator: André Dekker, MD, PhD; Maastro Clinic, The Netherlands

More Information

• Responsible Party: Maastricht Radiation Oncology
• ClinicalTrials.gov Identifier: NCT03564457
• Other Study ID Numbers: 20K Distributed Learning
• First Posted: June 20, 2018
• Last Update Posted: March 8, 2019
• Last Verified: March 2019

• Studies a U.S. FDA-regulated Drug Product: No
• Studies a U.S. FDA-regulated Device Product: No

Additional relevant MeSH terms:

Lung Neoplasms; Respiratory Tract Neoplasms; Thoracic Neoplasms; Neoplasms by Site; Neoplasms; Lung Diseases; Respiratory Tract Diseases