AI-Powered Drug Response Prediction Shows Promise in Human Blood Cancers
核心洞察
ImpriMed (搜索)'s AI-powered drug response prediction technology, initially successful in veterinary oncology, is now being applied to human blood cancers like multiple myeloma (搜索) and AML (搜索).
Early data from clinical studies indicate that AI models can optimize treatment selection and improve survival rates in patients with newly diagnosed multiple myeloma (搜索) and non-Hodgkin lymphoma (搜索).
The technology uses ex vivo drug sensitivity testing and machine learning to predict patient responses to anticancer drugs, facilitating more precise treatment protocols.
ImpriMed (搜索), a company based in Mountain View, California, is expanding its AI-powered drug response prediction technology from veterinary to human oncology, with promising early results in blood cancers. The technology, which has already demonstrated significant improvements in outcomes for dogs with lymphoma (搜索) and leukemia (搜索), is now being applied to multiple myeloma (搜索) (MM), acute myeloid leukemia (AML (搜索)), and non-Hodgkin lymphoma (搜索) (NHL).
AI-Driven Personalized Cancer Treatment
ImpriMed (搜索)'s approach involves testing live cancer cells and using validated AI models, trained on extensive clinical outcome data, to predict the efficacy of various treatments. In veterinary oncology, this technology has led to a 4-fold increase in complete response rates and a 3-fold extension in median survival times for dogs with relapsed B-cell lymphoma (搜索) receiving AI-predicted therapies, according to a study published in Frontiers in Oncology.
"AI-powered drug response prediction technology enables veterinary oncologists to identify the most effective treatments for individual cancer patients before treatment begins, avoiding costly and time-consuming exploratory or 'wait-and-see' approaches," said Sungwon Lim, PhD, co-founder and CEO of ImpriMed (搜索).
Expansion to Human Blood Cancers
Building on this success, ImpriMed (搜索) has adapted its platform for human cancers, leveraging ex vivo drug sensitivity testing, genomic analysis, and machine learning. Early data from clinical studies, including those published in npj Precision Oncology, suggest that AI models can optimize treatment selection and improve survival rates in patients with newly diagnosed MM (NDMM), AML (搜索), and NHL.
For example, ImpriMed (搜索)'s AI-driven NDMM technology has been shown to predict patient response and survival time following first-line treatment by predicting the probability of early disease progression and stratifying patients into high vs low-risk subgroups. Similar outcomes have been observed with AML (搜索) and NHL technologies, which evaluate drug sensitivity tests for 21 and 18 anticancer drugs, respectively, to predict patient drug responses and facilitate more precise treatment protocols.
Development and Validation
The transition from veterinary to human applications required enhancements in data collection, development of cancer-specific predictive models, and rigorous clinical validation. ImpriMed (搜索) has partnered with major hospitals to collect human clinical samples and patient medical records, integrating ex vivo drug sensitivity testing with machine learning models to personalize treatment based on each patient's unique genetic and biological profiles.
Future Directions
While the current technology does not incorporate pharmacokinetic/pharmacodynamic (PK/PD) data, systematic biomarkers are used to refine predictions. Future plans include integrating more comprehensive datasets, including PK/PD information, to improve the accuracy of predictions. At the EHA-SfPM Precision Medicine Meeting, ImpriMed (搜索) showcased its technology for treating NHL, demonstrating its utility in predicting treatment responses and survival outcomes. Future work will focus on expanding its application to multi-drug regimens.
"Our study performed ex vivo drug sensitivity analyses on 52 patients with NHL, consisting of both aggressive and indolent lymphoma (搜索), and confirmed the high utility of drug sensitivity results in predicting treatment-specific response and survival of the NHL," Lim stated during the presentation. The company anticipates potential FDA approval for commercialization in the US in 2025.