Problem and Business Case: One of the largest diagnostic centers of a large hospital system wanted to understand if it is possible to predict the onset of a medical symptom in its patients using AI and Machine learning. This would help them proactively advise and treat patients.
INSOFE’s Approach: The data scientists needed to collect the data of hundreds of thousands of patients from disparate sources and converted them to the required format. Various machine learning algorithms are used to generate meaningful sequential patterns of the form “If the level of aaa is xxx now and in three months the level of bbb goes to yyy then there is a high potential for kkk”.
To have INSOFE faculty and data scientists solve your business problems, prep your engineering teams to face the real world complexities, visit here
This involved studying blood test data from different times of the same patient.
As algorithms generate many rules, we analyzed the credibility (statistical and business) of each rule.
Result: INSOFE scientists with no medical background were able to extract 4 different associations for 4 different medical conditions that were unknown to clinical doctors and were found valuable by customers.