And we can talk about​

High Quality RWE.

Deepening in the process:

01 - Viability study.

Description:

Ensure that the key variables selected for the study are in the EMRs.

Task involved:

  • Concept Sheet.
  • Technical/technological viability.
  • Viability Study report.

Objectives:

  • Fit-for-purpose study design.
  • Transparent protocol development.

Exemplar:

BigCOPData
BigCOVIData
HNC-TACTIC
Oraculum

02 - Study definition.

Description:

Protocol and SAP/PAP (Statistical Analysis Plan) documentation preparation. 

Task involved:

  • Multidisciplinary study team created.
  • External and internal project kick off meeting.
  • Deep background literature review.
  • Study population and main clinical variables refined.
  • Observational, Predictive and Exploratory design and planning.
  • Protocol/SAP development.

Objectives:

  • Sites selection.
  • Data Science team and Clinical/Research team alignment.
  • Final SAP and PAP documentation.

03 - NLP Execution.

Description:

Evaluation of the quantity and quality of data for NLP development.

Task involved:

  • Internal validation.
  • Data-driven quality assessment and quality checks across the complete research study process.
  • Specific ML/NLP Models training and improvement.
  • NLP Processing of population documentation.

Objectives:

  • Determining ‘data quality’ of RWD.
  • Fit-for-purpose NLP.
  • Construction of study data base.

03.1 - Data-driven quality assessment:

Summary statistics for:

  • Population demographics.
  • Study key variables.

Objectives:

  • To guarantee data quality to answer objectives.
  • To adapt analysis strategy:
    • Missing values.
    • Data source heterogeneity.
    • Adjust population selection criteria.
  • To implement contingency strategies where needed.

03.2 - Fit-for-purpose NLP

Fit-for-purpose NLP models are built based on the objectives of the study.

Advanced NLP goes beyond codifying or one-time extraction of variables from text. It requires a deep clinical understanding of how EHRs are populated and what inferences need to be made to extract knowledge from each situation and for a given purpose.

 

This is unique to Savana's methodology.

This is unique to Savana's methodology.

Task involved

  • Data assessment by clinical experts.
  • Scientific inferences to build ad-hoc models.
  • Creating a structured database for each study
  • NLP model external validation.

Objectives

  • Developing ‘fit-for-purpose’ NLP models.
  • Evaluating ‘NLP models quality’.

04 - External evaluation.

Description:

Within the selected and approved sites, we evaluate them and SM4RS launch. 

Task involved:

  • All PIs and sites involved.
  • SM4RS Launched.
  • PIs annotation using SAVANA Evaluation Tool.

Objectives:

  • NLP models quality evaluation.

04.1 - External Evaluation Methodology:

04.2 - Evaluation of the NLP system:

05 - Data analysis.

Description:

Descriptive and predictive data analysis.

Task involved:

  • Definition of the study objectives.
  • Tailored clinical analysis.
  • Traditional and AI-based analytics
  • Complex variables definition.

Objectives:

  • Predictive, observational and exploratory models built.
  • Early results presented.

06 - Study report creation.

Description:

Results analysis evaluation.

Task involved:

  • Evaluation of study results.
  • Compare and contextualize study results with previous publish data.
  • Discuss study results with sponsor and study medical committee.

Objectives:

  • Final report writing.
  • Interpretation and results presented.

07 - Final report study.

Description:

Manuscripts development.

Exemplar:

Clinical characteristics and prognostic factors for ICU admission of patients with covid-19: Retrospective Study Using Machine Learning and Natural Language Processing.

Read publication

Clinical Management of COPD in a Real-World Setting. A Big Data Analysis.

Read publication

Generate deeper and more agile clinical evidence, thanks to the use of AI

Fill in this form carefully so that we can check if there is a match between you and us:

We will contact you even if we are not interested in your research project.

AI + RWE

©2023 Savana. All rights reserved.
©2023 Savana. All rights reserved.

Enrol in a project