Next-generation synthetic trials in hematology with generative artificial intelligence

Developing new cancer drugs requires deep pockets, iron patience, and a level of frustration tolerance that matches the Greek mythos of Sisyphos: The budget needed to bring a single cancer drug to market is estimated to exceed a billion US dollars, spent over almost a decade in development time, and more often than not the undertaking still ends in failure [ 1 , 2 , 3 , 4 ]. One of the top reasons why cancer trials frequently falter is recruitment failure [ 5 ]. The situation will only worsen given the ongoing fragmentation of cancer entities into molecularly-defined subgroups addressed by targeted agents in the era of precision oncology. When multiple trials compete for the same shrinking pool of potentially eligible patients, the demand for individual control arms becomes a problem rather than a perk: a patient recruited into the control arm of one trial is a patient lost from the investigational arm of another. Trials begin to “cannibalize” each other, contributing to slower accrual, thereby increasing the likelihood of trial failure. Compounding this challenge, the therapeutic standard frequently changes during the course of a trial due to the approval of new treatments or changes in risk classification. Collectively, this slows the generation of evidence across the portfolio of trials, ultimately delaying or even denying patients access to potentially effective therapies (Fig. 1 ). So, if a standard-of-care control group for every trial remains a practical and regulatory necessity, can we create one instead of recruiting one? Fig. 1: Three generations of control arm design. Full size image In the past, trial inclusion and exclusion criteria often did not consider molecularly-defined subgroups, essentially rendering the entire patient population of a certain hematological entity as potential candidates for trial inclusion ( A ). With the advent of modern sequencing techniques came the fragmentation of cancer entities into subgroups according to diverging pathomechanisms, which could increasingly be exploited via targeted therapies. This, however, enables trials to “cannibalize” each other, as patients recruited into the standard-of-care (often chemotherapy-based) control arm of one trial, are lost from the investigational arm of another trial they could have been a suitable subgroup candidate for ( B ). Synthetic patient data generated by artificial intelligence could enable the generation of large representative synthetic patient cohorts drawn from previous clinical trials and real-world registries. By reflecting the standard of care, these synthetic cohorts could substitute for, or replace, control arms in precision hematology trials, enabling eligible subgroup patients to be enrolled in investigational arms ( C ). Created with Microsoft PowerPoint.