LOS ANGELES, CALIFORNIA – An international research team led by Dr. Etan Orgel at Children’s Hospital Los Angeles (CHLA) has developed a machine learning model designed to estimate a child’s risk of developing hearing loss after receiving the chemotherapy drug cisplatin. The tool, known as PedsHEAR, was built using routinely available clinical information and has demonstrated 95% predictive accuracy. Results of the study were published in the Journal of Clinical Oncology, and the model is now publicly accessible.
The project, which included collaborators from the Keck School of Medicine of USC and institutions across the U.S. and Canada, represents the first validated machine learning model specifically designed to forecast cisplatin-induced hearing loss in pediatric patients.
Cisplatin has been in use since the 1970s to treat various cancers, including brain and spinal tumors, neuroblastoma, and rhabdomyosarcoma. Although effective, it is known to cause significant side effects, with permanent hearing loss being among the most common in children.
From Clinical Observation to Predictive Modeling
Etan Orgel, MD, MS, Director of Quality and Patient Safety in the Cancer and Blood Disease Institute at CHLA
This research builds on two decades of work at CHLA aimed at reducing the burden of cisplatin-induced hearing loss. The hospital previously led the phase 3 Children’s Oncology Group trial for sodium thiosulfate (STS), which led to the 2022 FDA approval of STS as the first treatment to lower hearing loss risk in children undergoing cisplatin therapy. However, not all patients require STS, and clinicians face complex treatment planning decisions.
“We want to give families and providers the tools they need to understand their child’s risk and make an informed decision,” explains Dr. Orgel, who directs Quality and Patient Safety at CHLA’s Cancer and Blood Disease Institute. “This is the paradigm shift we’re aiming for—speaking in certainties for each child versus speaking in generalities by regimen.”
The PedsHEAR model was trained using data from more than 1,400 pediatric patients who received cisplatin treatment. Additional validation was conducted using separate datasets from the Children’s Oncology Group and a pediatric hospital in Texas. The tool outputs a percentage indicating the child’s probability of experiencing hearing loss, supporting informed decision-making early in the treatment process.
“My goal is for this to become a routine clinical tool. What’s unique about this model is that it only uses routinely available data, so any doctor can use it from day one of diagnosis to plan treatment. Ultimately, we aim to expand our approach to understand and predict risk for other common side effects of common chemotherapies.”
–Dr. Etan Orgel
The research team plans to expand the model’s applicability to young adults up to age 65 and to integrate genomic data to further refine its predictive accuracy.
About Children’s Hospital Los Angeles
Founded in 1901, Children’s Hospital Los Angeles is one of the largest providers of pediatric care in California and is consistently ranked among the top children’s hospitals in the country. CHLA is a leading pediatric research institution and a top recipient of National Institutes of Health funding. To learn more, visit CHLA.org.
Source: CHLA
