AGA Tech Summit

Predictive analytics with large data sets are being pursued to individualize IBD therapy


 

EXPERT ANALYSIS FROM 2019 AGA TECH SUMMIT

SAN FRANCISCO – Predictive analytics of large quantities of data using machine learning present a powerful tool for improving therapeutic choices, according to a summary of work performed in inflammatory bowel disease (IBD) and presented at the 2019 AGA Tech Summit, sponsored by the AGA Center for GI Innovation and Technology.

This type of work is relevant to many fields of medicine, but studies conducted in IBD have provided particularly compelling evidence that predictive analytics will improve outcomes and lead to more cost effective delivery of care, according to Akbar K. Waljee, MD, MSc, an associate professor in the division of gastroenterology at University of Michigan, Ann Arbor, and a staff physician and researcher at the VA Ann Arbor Healthcare system.

“We collect large amounts of clinical data every day in the delivery of health care, but we are now only just beginning to leverage [these] data to guide treatment,” Dr. Waljee said. He has now published several papers on the role of precision analytics of big data to improve treatment choices in IBD, as well as other diseases. These analyses are relevant for determining both who to treat with a certain drug and who to not treat with it.

In one example, data from 1,080 IBD patients taking thiopurines were used to develop a machine learning algorithm that analyzed multiple readily available variables, such as a complete blood count with differential and a chemistry panel, to predict whether someone was or was not in remission. This was then used to compare the mean yearly clinical event rates (new steroids prescriptions, hospitalizations, and abdominal surgeries) between the two groups (1.08 vs. 3.95 events) to show the associated clinical benefit of using this algorithm.

“The heterogeneity of response to therapies for IBD is well established. If machine learning predicts effective choices, there will be an opportunity to accelerate the time to disease control, as well as save costs by avoiding therapies not likely to be effective,” Dr. Waljee explained.

In another example, an algorithm was developed to predict the likelihood of achieving a corticosteroid-free biologic remission at 1 year in Crohn’s disease patients when patients were evaluated 6 weeks after initiating the gut-selective biologic vedolizumab. Again, it was based on an analysis of numerous variables, including laboratory data, sex, and race. Based on the model drawn from the analysis of 472 patients, 35.8% of the patients predicted to be in corticosteroid-free biologic remission at 1 year achieved this endpoint, whereas only 6.7% of the patients predicted to fail achieved the endpoint.

“This suggests that we can use an algorithm relatively early in the course of this biologic to predict who is going to respond,” reported Dr. Waljee. Again, patients with a low likelihood of response at 6 weeks can be started on an alternative treatment, which could potentially accelerate the time to disease control and avoid the costs of an ineffective and expensive treatment.

IBD is a particularly attractive focus of precision analytics with big data. IBD has a relatively unpredictable relapsing/remitting course and a heterogeneous response to available therapies. Algorithms predictive of response circumvent the inherent delays from evaluating disease control over an extended period.

“With ever increasing concern about costs of care and access to care, these treatment algorithms promise to use resources more efficiently,” Dr. Waljee said.

Next Article: