Predictive Analytics Model Anticipates Pediatric Blood Clots

By Jessica Kent

May 19, 2021 – Using a predictive analysis model, healthcare providers can proactively identify pediatric patients at risk of developing blood clots or venous thromboembolisms (VTEs), according to a study published in Pediatrics.

Although hospital-related VTEs are on the rise in pediatric populations, it is challenging for healthcare providers to identify high-risk patients. Researchers noted that case-controlled studies have resulted in common pediatric models, but few of these models have been validated.

“Hospital-related blood clots are an increasing cause of morbidity in pediatrics,” said Shannon Walker, MD, the study’s lead investigator and clinical fellow of Pediatric Hematology-Oncology at Monroe Carell Jr. Children’s Hospital at Vanderbilt University.

Dig deeper

“The reason children get blood clots is very different from adults. There was no standardized protocol for preventing clots in pediatric patients, ”said Walker.

Although blood clots and VTEs are more common in adults than children, the Vanderbilt team noted that blood clot development is increased in pediatric populations.

“When we noticed an increase in blood clots and recognized that the adult strategy wouldn’t work for our patients, we wanted to look at each patient’s individual risk factors and how to focus our attention on targeted blood. clot prevention, ”said Walker.

The team has built and validated a predictive analysis model that can be automated to run within the EHR of each patient admitted to the hospital.

The model includes eleven risk factors, and researchers have based it on an analysis of more than 110,000 admissions to children’s hospital. The group then validated the tool on more than 44,000 individual recordings.

The team is currently studying how this model performs in combination with a targeted intervention in a clinical setting. The research is called Children’s Likelihood of Thrombosis (CLOT).

The prediction model calculates a risk score for each child admitted to hospital. The patients are randomized, so in half of the patients elevated scores are assessed by a haematologist. Next, each patient’s medical team and family discuss the patient’s score to determine a personalized prevention plan.

Regardless of randomization, all patients will continue to receive current standard of care.

“We are not using a one-size-fits-all plan. This is an additional level of assessment that allows for a highly personalized recommendation for any patient with an elevated score. The score is updated every day, so when risk factors change, the scores change accordingly, ”Walker said.

“We are assessing the use of this model as a clinical support tool in real time. We saw a clinical possibility of something we could improve on and have moved on to build the model – to identify high-risk patients and are currently running the CLOT trial, which will run through the end of the year. “

The study was made possible with the help of the Advanced Vanderbilt Artificial Intelligence Laboratory (AVAIL).

“AVAIL served as a catalyst, in this case bringing experts in a complex pilot development close to it so that a great synthesis could take place,” said Warren Sandberg, MD, PhD, lead sponsor of AVAIL.

The AVAIL program, currently in its second year, aims to support AI tools at VUMC through project incubation and curation, including facilitating clinical trials to evaluate their effectiveness.

“The unique thing about this particular project is that we were not only able to predict complications, but also test the model in a rigorous, pragmatic, randomized, controlled trial to see if it would benefit patients,” said Dan Byrne, senior biostatistician for the project and director of research on artificial intelligence for AVAIL.

“The future of this type of work is limitless. We can hopefully use this approach to predict and prevent pressure ulcers, septicemia, falls, readmissions, or virtually any complication before they occur. At Vanderbilt, we raise the bar when it comes to the science of personalized medicine and the application of artificial intelligence to medicine in a way that is both ethical and safe. “

Comments are closed.