top of page
All Blogs

What Kind of Aggregation Should Be Used When Working with the Sepsis Dataset?

The Sepsis dataset (https://physionet.org/content/challenge-2019/1.0.0/) contains data for 40,336 patients, with hourly ICU readings of vital signs, lab values and clinical observations. When working on identifying KPIs, gathering insights and establishing correlations between the biomarkers, I did not pay much attention to the types of aggregations that should have been used i.e., average, minimum and maximum. At the beginning of the analysis, I had assumed that calculating

Evaluation Metrics in Data Science: Measuring What Matters

In the world of Data Science, building a machine learning model is only half the battle. The real challenge lies in understanding how well the model performs and whether its predictions can be trusted in real-world scenarios. This is where evaluation metrics play a crucial role. Machine learning models don't just need to make predictions—they need to make the right predictions for the right reasons. A model with 95% accuracy may seem impressive, but if it misses patients with

+1 (302) 200-8320

NumPy_Ninja_Logo (1).png

Numpy Ninja Inc. 8 The Grn Ste A Dover, DE 19901

© Copyright 2025 by Numpy Ninja Inc.

  • Twitter
  • LinkedIn
bottom of page