Case Study: iKure achieves trusted, bias-aware heart-attack risk detection to save lives with IBM Cloud Pak for Data

iKure - Customer Case Study

iKure, a Kolkata-based health‑tech company facing a severe shortage of cardiologists (about one cardiologist per 6,000 patients), set out to use wearable devices and machine learning to identify patients at highest risk of heart attack. To build and operationalize that capability, iKure partnered with the IBM Data Science and AI Elite team to create a predictive model within IBM Cloud Pak for Data.

Using IBM Cloud Pak for Data (including Watson OpenScale and a healthcare accelerator), the team combined iKure’s mobile patient records with EKG signal data to classify anomalies, detect and evaluate bias (training data had roughly three times as many male records), and produce a prioritized list of urgent cases for call‑center physicians. The IBM Cloud Pak for Data solution lets iKure check model performance in minutes, proved model accuracy with clinical/demographic variables and physician feedback, and enabled rapid, cloud‑agnostic deployment—helping clinicians triage patients faster and improving the likelihood of preventing heart attacks.

iKure

Sujay Santra

Founder and Chief Executive Officer