An InetSoft generated mortality analysis dashboard (click to interact and explore infant mortality causes)
As covered by tech news site Futurism (click here for the article) the Children’s Hospital of Philadelphia has successfully trained machine learning algorithms to identify cases of sepsis in newborns significantly faster, greatly increasing the infants chance of survival.
“Using electronic health record data, such as vital signs like blood pressure and temperature, from 618 infants in the CHOP neonatal intensive care unit from 2014 to 2017, the team trained eight machine-learning models to compare vital signs to 36 potential indicators of infant sepsis. Because the data was retroactive, the research team was able to compare the machine-learning models’ accuracy to clinical findings. Of the eight models, six were able to accurately identify cases of sepsis up to four hours earlier than clinicians had.”
Weighing 36 potential indicators is just what machine learning was created for: tasks that require the type of pattern recognition that traditional computers lack, recognizing patterns at a level of complexity that human brains are incapable of processing. Having a machine learning model that you can repeatedly train to make better predictions is the equivalent of having a data scientist with a genius level IQ who is constantly experimenting and writing better predictive models for your organization. Curious as to how these ML models can be integrated with interactive visualizations and automated reporting? Click on the image below to open an InetSoft Customer Churn dashboard which includes a trainable predictive model of customer churn factors.
Click to train a machine learning model designed to predict customer churn
Keep following The Mashup for the latest in business intelligence, big data and machine learning.
