Clinical trials are designed to produce new knowledge about a certain disease, drug or treatment. During these studies, a huge amount of data is collected about participants, therapies, clinical procedures, outcomes, adverse events and so on. A multicenter, randomized, phase III clinical trial in Hematology enrolls up to hundreds of subjects and evaluates post-treatment outcomes on stratified sub- groups of subjects for a period of many years. Therefore, data collection in clinical trials is becoming complex, with huge amount of clinical and biological variables. Outside the medical field, data warehouses (DWs) are widely employed. A Data Ware-house is a “collection of integrated, subject-oriented databases designed to support the decision-making process”. To verify whether DWs might be useful for data quality and association analysis, a team of biomedical engineers, clinicians, biologists and statisticians developed the “I2ECR” project. I2ECR is an Integrated and Intelligent Environment for Clinical Research where clinical and omics data stand together for clinical use (reporting) and for generation of new clinical knowledge. I2ECR has been built from the “MCL0208” phase III, prospective, clinical trial, sponsored by the Fondazione Italiana Linfomi (FIL); this is actually a translational study, accounting for many clinical data, along with several clinical prognostic indexes (e.g. MIPI - Mantle International Prognostic Index), pathological information, treatment and outcome data, biological assessments of disease (MRD - Minimal Residue Disease), as well as many biological, ancillary studies, such as Mutational Analysis, Gene Expression Profiling (GEP) and Pharmacogenomics. In this trial forty-eight Italian medical centers were actively involved, for a total of 300 enrolled subjects. Therefore, I2ECR main objectives are: • to propose an integration project on clinical and molecular data quality concepts. The application of a clear row-data analysis as well as clinical trial monitoring strategies to implement a digital platform where clinical, biological and “omics” data are imported from different sources and well-integrated in a data- ware-house • to be a dynamic repository of data congruency quality rules. I2ECR allows to monitor, in a semi-automatic manner, the quality of data, in relation to the clinical data imported from eCRFs (electronic Case Report Forms) and from biologic and mutational datasets internally edited by local laboratories. Therefore, I2ECR will be able to detect missing data and mistakes derived from non-conventional data- entry activities by centers. • to provide to clinical stake-holders a platform from where they can easily design statistical and data mining analysis. The term Data Mining (DM) identifies a set of tools to searching for hidden patterns of interest in large and multivariate datasets. The applications of DM techniques in the medical field range from outcome prediction and patient classification to genomic medicine and molecular biology. I2ECR allows to clinical stake-holders to propose innovative methods of supervised and unsupervised feature extraction, data classification and statistical analysis on heterogeneous datasets associated to the MCL0208 clinical trial. Although MCL0208 study is the first example of data-population of I2ECR, the environment will be able to import data from clinical studies designed for other onco-hematologic diseases, too.

I2ECR: Integrated and Intelligent Environment for Clinical Research / Zaccaria, GIAN MARIA. - (2018 Apr 23). [10.6092/polito/porto/2707999]

I2ECR: Integrated and Intelligent Environment for Clinical Research

ZACCARIA, GIAN MARIA
2018-04-23

Abstract

Clinical trials are designed to produce new knowledge about a certain disease, drug or treatment. During these studies, a huge amount of data is collected about participants, therapies, clinical procedures, outcomes, adverse events and so on. A multicenter, randomized, phase III clinical trial in Hematology enrolls up to hundreds of subjects and evaluates post-treatment outcomes on stratified sub- groups of subjects for a period of many years. Therefore, data collection in clinical trials is becoming complex, with huge amount of clinical and biological variables. Outside the medical field, data warehouses (DWs) are widely employed. A Data Ware-house is a “collection of integrated, subject-oriented databases designed to support the decision-making process”. To verify whether DWs might be useful for data quality and association analysis, a team of biomedical engineers, clinicians, biologists and statisticians developed the “I2ECR” project. I2ECR is an Integrated and Intelligent Environment for Clinical Research where clinical and omics data stand together for clinical use (reporting) and for generation of new clinical knowledge. I2ECR has been built from the “MCL0208” phase III, prospective, clinical trial, sponsored by the Fondazione Italiana Linfomi (FIL); this is actually a translational study, accounting for many clinical data, along with several clinical prognostic indexes (e.g. MIPI - Mantle International Prognostic Index), pathological information, treatment and outcome data, biological assessments of disease (MRD - Minimal Residue Disease), as well as many biological, ancillary studies, such as Mutational Analysis, Gene Expression Profiling (GEP) and Pharmacogenomics. In this trial forty-eight Italian medical centers were actively involved, for a total of 300 enrolled subjects. Therefore, I2ECR main objectives are: • to propose an integration project on clinical and molecular data quality concepts. The application of a clear row-data analysis as well as clinical trial monitoring strategies to implement a digital platform where clinical, biological and “omics” data are imported from different sources and well-integrated in a data- ware-house • to be a dynamic repository of data congruency quality rules. I2ECR allows to monitor, in a semi-automatic manner, the quality of data, in relation to the clinical data imported from eCRFs (electronic Case Report Forms) and from biologic and mutational datasets internally edited by local laboratories. Therefore, I2ECR will be able to detect missing data and mistakes derived from non-conventional data- entry activities by centers. • to provide to clinical stake-holders a platform from where they can easily design statistical and data mining analysis. The term Data Mining (DM) identifies a set of tools to searching for hidden patterns of interest in large and multivariate datasets. The applications of DM techniques in the medical field range from outcome prediction and patient classification to genomic medicine and molecular biology. I2ECR allows to clinical stake-holders to propose innovative methods of supervised and unsupervised feature extraction, data classification and statistical analysis on heterogeneous datasets associated to the MCL0208 clinical trial. Although MCL0208 study is the first example of data-population of I2ECR, the environment will be able to import data from clinical studies designed for other onco-hematologic diseases, too.
File in questo prodotto:
File Dimensione Formato  
conv_zaccaria_final.pdf

accesso aperto

Tipologia: Tesi di dottorato
Licenza: Creative commons
Dimensione 8.59 MB
Formato Adobe PDF
8.59 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11583/2707999
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo