This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
research:largescalepred [2016/09/21 11:52] prijnbeek |
research:largescalepred [2017/02/02 19:18] (current) prijnbeek [Datasets Running] |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | ====== Proof of concept study for large-scale patient-level predictive modeling in the OHDSI data network ====== | + | ====== Proof of concept study for large-scale patient-level predictive modelling in the OHDSI data network ====== |
<WRAP box justify round> | <WRAP box justify round> | ||
**Objective:** | **Objective:** | ||
- | The objective of the largeScalePrediction R OHDSI (Observational Health Data Science and Informatics) package is to investigate models estimated/developed using 5 commonly used classifiers for a single ‘at risk’ cohort (therapeutically treated depression cohort) and 22 ‘outcome’ cohorts. The study is implemented across the OHDSI collaborator network to externally validate the models and calculate their transportabilities across the world. | + | The objective of the large-scale patient-level predictive modelling study is to develop models using 5 commonly used classifiers for a single ‘at risk’ cohort (pharmaceutically treated depression cohort) and 22 ‘outcome’ cohorts. The study is implemented across the OHDSI collaborator network to externally validate the models and assess their transportabilities across the world. |
**Rationale:** | **Rationale:** | ||
Line 16: | Line 16: | ||
**Coordinating Institution(s):** Erasmus MC Rotterdam, The Netherlands | **Coordinating Institution(s):** Erasmus MC Rotterdam, The Netherlands | ||
- | ** Additional Participants:** To be added | + | ** Additional Participants (currently seeking additional collaborators):** \\ Martijn Schuemie, Marc Suchard, Patrick Ryan |
- | **Full Protocol:** To be added | + | **Full Protocol:** [[https://github.com/OHDSI/StudyProtocolSandbox/blob/master/largeScalePrediction/extras/OHDSI_Protocol_Large_Scale_Prediction_v1.0.docx|Large-Scale Patient-Level Prediction Protocol]] |
- | **Initial Proposal Date:** 2016-09-23 | + | **Initial Proposal Date:** 2016-08-01 |
**Launch Date:** 2016-09-23 | **Launch Date:** 2016-09-23 | ||
- | **Study Closure Date:** Pending | + | **Receive Results for Analysis Date:** TBD |
- | **Results Submission:** | + | **Study Closure Date:** TBD |
- | Upload the file export/studyResult.zip in the output folder to the study coordinator: | + | |
- | submitResults("c:/temp/study_results/export", key = "<key>", secret = "<secret>")\\ | + | **Results Submission:** Via the OHDSI Sharing module embedded in study. |
- | Where key and secret are the credentials provided to you personally by the study coordinator. | + | |
</WRAP> | </WRAP> | ||
===== Requirements ===== | ===== Requirements ===== | ||
- | **CDM:** V5 | + | **CDM:** V5 only |
**Table Accessed:** person, drug_exposure, observations | **Table Accessed:** person, drug_exposure, observations | ||
Line 40: | Line 39: | ||
**Database Dialects:** SQL Server, Postgres, Oracle | **Database Dialects:** SQL Server, Postgres, Oracle | ||
- | **Software:** R, Python | + | **Software:** R (>= 3.2.2, RTools), Java, Python (2.7) |
+ | |||
+ | **Hardware:** Recommended 8 cores, 64GB memory, 250GB free space | ||
- | ===== Code ===== | ||
- | [[https://github.com/OHDSI/StudyProtocols]] (to be added) | ||
- | ===== Discussion ===== | ||
- | [[http://forums.ohdsi.org/c/researchers]]// (to be added)// | ||
===== Datasets Run ===== | ===== Datasets Run ===== | ||
- | * CCAE, MDCD, MDCR, OPTUM | + | * CCAE (Janssen) |
+ | * MDCD (Janssen) | ||
+ | * MDCR (Janssen) | ||
+ | * Optum (Janssen) | ||
+ | ===== Datasets Running ===== | ||
+ | * Ajou University School of Medicine | ||
+ | * Erasmus MC | ||
+ | * Stanford | ||
+ | * Columbia University | ||
~~NOTOC~~ | ~~NOTOC~~ |