Trusting AI to save lives in India
The IBM Data Science Elite team puts ICP for Data to the test
With only one cardiologist for every 6,000 patients, there are not enough specialists to address India’s most pressing health concern: heart disease.
Leaders at Kolkata-based health tech company iKure realized they could fill that critical gap using wearable technology and machine learning. The start-up used the tools and know-how of the IBM Data Science Elite team to create a model to identify patients who have the highest risk of suffering from a heart attack, allowing doctors to see the most urgent cases first, and ultimately save lives.
But there’s one major, lingering question. Can AI be trusted with people’s lives? Taking this question to heart, the DSE team created a scenario that shows how IBM Cloud Private for Data could be used to address the issue of trust and transparency and drive better clinical outcomes.
Watch this demo to see what happens when a CEO logs onto to ICP for Data to easily check on the performance of his new model. In a matter of minutes, he can assess the bias and predict whether he can trust his AI model, all without relying on a team of data scientists to do it for him.
In this fictitious scenario, the CEO notices the dashboard is displaying a red alert. Bias has been detected. Male patients have been flagged as having a higher rate of cardiovascular disease. The patient data used to train the model might have a problem since it had triple the number of male patient data. But could there be other reasons for the bias?
The CEO decides to compare his data to a published risk model. The search field pulls up a healthcare accelerator, which acts as a ladder to AI jumpstart kit for workflow. He can easily evaluate the bias detected from his training data and select whether to keep it or remove it.
While this functionality is yet to come in ICP for Data, the Data Science Elite team developed a proof of concept that demonstrated how the platform can bring the power of AI to iKure’s data stored in an AWS, MySQL data store. iKure would be able to access and combine patient population data from its mobile healthcare information management system with EKG signal data. It could also classify the EKG data as normal or with anomalies and present a prioritized list of patient cases to the call center physician for review based on potential acuteness via a cloud-based web application.
“IBM Cloud Private for Data facilitated the model development and deployment of a predictive model for cardiac care for iKure,” said Sujay Santra, iKure’s CEO and founder. “IBM’s Data Science Elite team demonstrated the model development process in ICP for Data via Watson Studio with multiple AWS data sources. It also proved model accuracy using patient clinical and demographic variables and physician feedback with the added benefits of rapid model development, publication and iteration.”
Early iKure champion Julie Lockner, who directs IBM data and AI portfolio optimization, added:
“You have a stack that allows you to be agile no matter what cloud technology you have today or tomorrow. Standardizing on ICP for Data allows companies like iKure to get up and running quickly without needing to recode if they have to deploy or embed their application elsewhere.”
The latest version of IBM Cloud Private for Data (V1.2.1) includes premium add-ons from IBM and partners. This includes the IBM Streams for IBM Cloud Private for Data, which provides data engineers and developers with the ability to work directly with streaming data in analytics projects. Also new are industry accelerators for banking and cross-industry scenarios, designed specifically for IBM Cloud Private for Data to exploit built-in capabilities such as AI-driven auto data discovery and classification of business vocabulary of terms.
Bring AI to your data, wherever it resides. Learn more about ICP for Data.