In trials that used data from two US hospitals, the researchers were able to show that the algorithms in the model improved predictions as to the length of stay and time of discharge - but also the time of death of patients.
In a paper published in Nature in May, from Google's team, says of its predictive algorithm: "These models outperformed traditional, clinically-used predictive models in all cases". The AI test comes with an accuracy predictions as high as 95 percent.
The AI works by taking in the health information of the patients like age, gender, and ethnicity, which is then coupled with hospital information, prior diagnoses, lab records, and vital signs to accurately give out the details about the mortality.
Google's Medical Brain, in testing, has been able to disseminate even doctors' notes scribbled on old charts, or memos scratched into the margins of PDFs.
This enables the technology in some cases to help doctor make better predictions about how long a patient may stay in a hospital or when the likelihood that the patient may die.
Speaking on Fox and Friends Tuesday, Family Medicine Physician Dr. Mikhail Varshavski said that, while connecting vast quantities of health information could be beneficial for patients, data privacy is key.
Google's software impressed the experts by accessing over 175K data points which were not available earlier.
A big part of the reason why Google is so far ahead is because of its machine learning led approach.
Bloomberg report describes the health care manifestations of its finding and uses previously unusable data to reach the prediction of death risks among patients.
Andrew Burt, chief privacy officer for data company Immuta said, "Companies like Google and other tech giants are going to have a unique, nearly monopolistic, ability to capitalize on all the data we generate".
"Machines make mistakes and sometimes they make mistakes based on faulty data", Varshavski added. It knows the weather and traffic.
Technology companies have been investing in health for many years.
Dean, the AI boss, stresses this experimentation relies on serious medical counsel, not just curious software coders. The American giant technology company would like to implement this system in clinics and hospitals.
They also developed a way to show clinicians what exact data its model "looked at" for each patient it predicted an outcome for. Google could buy them, but that may not sit as well with regulators or consumers. At Google's annual developer conference in May, Lily Peng, a member of Medical Brain, walked through the team's research outmatching humans in spotting heart disease risk.