AI Tools Accelerate Cancer Drug Testing and Clinical Trial Enrollment

Scientists at the University of Utah have developed a new "lab-on-a-chip" device that uses artificial intelligence to rapidly predict cancer cell sensitivity to targeted therapies for children with T-cell acute lymphoblastic leukemia (T-ALL), an aggressive and difficult-to-treat cancer. The device, called μPharma, delivers results in under four hours rather than many days—offering a potential pathway to same-day precision medicine when every minute counts.

Researchers say the tool, which is not yet used in clinical settings, may help reduce unnecessary treatments and side effects by quickly identifying which therapies a patient's cancer cells are sensitive to. The platform identifies a patient's drug response profile without directly exposing the patient's cancer cells to drugs. Using digital microfluidics to move tiny droplets across the chip and automate the labor-intensive liquid-handling steps, it reduces the number of cells and reagents required, minimizes human error, and speeds up the process.

In a study published in Med, scientists demonstrated that μPharma accurately predicted responses to two targeted therapies currently being investigated for T-ALL—dasatinib and venetoclax—and revealed a previously unrecognized link between drug response and a key molecular marker. The platform can detect differences in drug susceptibility at the level of individual cancer cells. This is important because if a particular drug is effective for some but not all a patient's cancer cells, the surviving cancer cells could bounce back.

A pediatric oncologist at Huntsman Cancer Institute and associate professor of pediatrics at the University of Utah stated that innovation in treatment selection is a pressing need within pediatric malignancies. "Personalized treatment selection accomplished in 'real-time' will be part of the future of cancer therapeutics, and μPharma represents an encouraging step in that direction," the physician said.

An investigator and member of the Experimental Therapeutics Program at Huntsman Cancer Institute and assistant professor of molecular pharmaceutics at the University of Utah said the team has worked hard to develop this technology, and seeing it perform well is a key step toward bringing it into the clinic to help patients. The project is a collaboration between researchers at the University of Utah, St. Jude Children's Research Hospital, and the University of Pennsylvania.

A clinician would place a small sample of a patient's cancer cells into the device. Inside, the cells are held between two plates that are spaced just wider than the thickness of a human hair. Electric currents precisely move tiny droplets of chemicals to and from the cells, fully automating lab processes that are usually time and labor-intensive. An assistant professor of biomedical engineering at the University of Utah stated that the next step is validation of this technology using primary leukemia cells in a realistic clinical environment.

Meanwhile, City of Hope hospital system has deployed HopeLLM, an internally trained AI platform designed to support oncology care and research across its national network spanning Southern California, Phoenix, Chicago, Atlanta, and dozens of clinics. The System EVP and Chief Digital and Technology Officer describes the organization as operating "as a system, not as a single entity," with any technology deployed functioning across that complex footprint.

HopeLLM addresses a familiar challenge in cancer care: overwhelming documentation. Some patients could have thousands of pages of notes associated with their care over many years. HopeLLM is able to intake that information and quickly summarize it for the physician. The time savings are substantial, with physicians often spending hours reviewing records after hours. By summarizing complex histories, the system can save two to three hours per patient.

The platform analyzes multimodal data—including clinical records, claims, genomics, radiology, and pathology—to identify trials suited to a patient. It can also reverse the process, scanning patient populations to identify candidates when new trials open. "When a patient comes in for care, we wanted to be able to let them know right away what trials they are eligible for," the executive explained. That immediacy matters in oncology, where timing can determine whether a patient gains access to a potentially lifesaving therapy.

City of Hope evaluated commercial tools before building its own. Many struggled with longitudinal oncology data and failed to integrate into real clinical workflows. Designing internally allowed the team to reflect how their oncologists actually think and practice. Licensed clinicians retain final decision authority. "No algorithm really gets moral authority," the executive said. "AI can assist… but it can't own clinical accountability."

Beyond matching individual patients, HopeLLM is transforming feasibility assessments across the network. City of Hope has evaluated more than 200 trials using the platform. Tasks that once took weeks can now be completed in minutes, enabling teams to identify eligible patients across multiple locations quickly. The executive describes this as part of a national clinical trials model: centralized coordination paired with geographically distributed research sites. The approach improves access to trials while allowing studies to launch across multiple regions almost simultaneously.

T-ALL is a challenging subtype of acute lymphoblastic leukemia, the most common childhood cancer. While complete remission rates have improved, many survivors experience long-term effects from intensive chemotherapy. Rapidly determining drug response could help clinicians personalize treatments sooner, reducing exposure to ineffective therapies and side effects.