Batch Safety Analysis

philipgodfrey

Batch Safety Analysis.dva

1. Which dataset did you use?

Life Sciences

 

2. How did you analyze or prepare the data?

The data was prepared by focusing on a single product (OracleVax) and then prepared the data by normalizing fatalities and serious adverse events per 100 patients, to enable fair comparison across vaccine batches with different administration volumes.

Each batch was scored based on:

• Serious adverse event rate (per 100 patients)
• Fatality rate (per 100 patients)

Outlier batches with significantly elevated rates were flagged as “abnormal"

Further analysis included plotting these normalised events over time, as well as exploring by Reporter Type, key patient demographics and also missing data identified during the exploration.

 

3. Who is the intended audience for your visualization?

Pharmaceutical safety bodies / regulatory bodies, medical researchers, to inform decision-making for future trials and medicine safety.

 

4. What is your visualization about, and what question or problem does it address?

The visualization aims to answer the question:

Are there identifiable batch-level or patient-level risk signals that indicate elevated safety concerns now or in the near future?

It focuses on a particular product (OracleVax) and aims to investigate:

• Time-series trends of normalized SAE and fatality rates
• Patient demographics (age band, gender)
• Medical history indicators to identify vulnerable subgroups
• Reporter Type segmentation to assess potential reporting bias or differential risk signals

Which hopes to help answer the questions posed below:

• Are any batches exhibiting disproportionately high SAE or fatality rates?
• What is the projected risk profile over the next 6 months?
• Does prior medical history increase likelihood of adverse outcomes?
• Do specific medical settings correlate with higher adverse event reporting?
• Is missing batch data concentrated in particular time periods or reporting channels?

 

5. Did you use any Oracle Analytics AI features when building your visualization (ex. AI Assistant)? If so, please describe how they were used

Exploratory analysis using Auto-Insights.

 

6. Did you upload your visualization image and dva file?

Yes - and video uploaded to show level of analysis in workbook