PharmaShots Interview: Caris Life Sciences' Dr. Spetzler Shares Insight on AI-Based MI FOLFOXai Predictor

In a recent interview with PharmaShots, Dr. Spetzler, President and Chief Scientific Officer of Caris Life Sciences shared his insights on FOLFOXai and its importance in patients with metastatic colorectal cancer. He also highlights the data supporting the use of FOLFOXai as a predictor of CT efficacy in patients with mCRC.

Shots:

The validation studies of MI FOLFOXai demonstrated a 17mos. increase in OS, representing 71% difference as compared to those patients treated counter to the prediction
FOLFOXai is the first clinically validated AI-based predictor of chemotherapy efficacy in patients with mCRC
Caris offers MI GPSai providing a cancer type similarity assessment that compares the genomic (DNA) and transcriptomic (RNA) characteristics of the patient's tumor against other tumors in the Caris database

Tuba: Can we have a discussion of the study designs of validation studies utilizing AI-Based MI FOLFOXai Predictor?

David: MI FOLFOXai was validated using two independent data sets to compare the increased benefit arm to the decreased benefit arm. The first study was a blinded, prospective analysis of retrospectively tested samples from 149 cases. The second study involved 296 manually curated cases with real-world evidence obtained from insurance claims records, electronic medical records, and death registries.

Tuba: Please share the positive results from the validation studies of MI FOLFOXai?

David: The data published in Clinical Cancer Research demonstrated that the overall survival (OS) of patients with metastatic colorectal cancer (mCRC) treated in a manner consistent with the FOLFOXai prediction was 17 months longer than the OS of patients treated counter to the prediction. This represents a 71% difference in OS in patients treated with FOLFOX-FOLFIRI predicted to benefit from FOLFOX-FOLFIRI chemotherapy compared to those predicted to benefit from FOLFIRI-FOLFOX.

Researchers determined a significant difference in OS based on the FOLFOXai-predicted increased benefit or decreased benefit with FOLFOX-FOLFIRI chemotherapy in combination with bevacizumab.

Additionally, patients predicted to have a decreased benefit from FOLFOX-FOLFIRI chemotherapy had significantly better outcomes when treated with FOLFIRI-FOLFOX than those predicted to have an increased benefit and vice versa. Analysis of samples from the randomized Phase 3 TRIBE2 study, which compared standard chemotherapy with FOLFOX followed by FOLFIRI to the FOLFOXIRI combination, confirmed the ability of FOLFOXai to predict OS for both study arms.

Tuba: Discuss in detail the findings of exploratory analyses that show benefits in advanced EC/GEJC and PDAC?

David: Exploratory analyses found that FOLFOXai predicted a treatment benefit from oxaliplatin-containing regimens in patients with advanced esophageal/gastroesophageal junction cancers (EC/GEJC) and pancreatic ductal adenocarcinoma (PDAC). These analyses demonstrated FOLFOXai was predictive of OS, with a median OS difference of 10.1 months in the increased benefit cohort compared to decreased benefit (21.4 months versus 11.3 months) but not the nab-paclitaxel/gemcitabine cohort (median OS of 10.8 months for increased benefit versus 9.8 months for decreased benefit). Data from 104 patients with advanced EC/GEJC demonstrated that FOLFOXai was predictive of the efficacy of oxaliplatin-containing regimens also in this clinical setting (median OS for increased benefit: 14 months versus 8.9 months for decreased benefit).

Tuba: Did you think precision medicine has the potential to change clinicians approach to cancer indications?

David: Yes. The results of these analyses establish that precision medicine powered by AI has the potential to change how clinicians approach treatment for metastatic colorectal cancer and other cancers. These data show that the selection of initial therapy has implications for improved treatment outcomes and disease progression. The results of this study demonstrate that FOLFOXai should be considered as part of the initial therapeutic decision-making process in the clinical setting.

Tuba: Can you share the details of MI FOLFOXai in a nonscientific way for our readers?

David: MI FOLFOXai is the Caris Artificial Intelligence (AI)-based predictor intended to gauge the response a cancer patient might have to FOLFOX chemotherapy followed by FOLFIRI compared to FOLFIRI followed by FOLFOX, both of which are standard of care options and often used in combination. In the case of this study, MI FOLFOXai used machine-learning to test data from real-world evidence, as well as samples from a randomized controlled clinical trial. The results of these analyses demonstrate that MI FOLFOXai predicted a course of treatment that allowed patients with mCRC to live longer.

Tuba: Why would you choose colorectal cancer? Are you planning to deploy MI FOLFOXai Predictor in other cancer indications?

David: Colorectal cancer is the third most common cancer globally, with more than 1.8 million patients diagnosed with the disease each year. As many as 25% of colorectal cancer patients will present with Stage IV ' or metastatic' disease, where cancer has spread to other parts of the body, making the choice of treatment critical to the patient's prognosis. The results of recent analyses demonstrate that precision medicine powered by AI has the potential to change the approaches to treatment not only for metastatic colorectal cancer but also other cancers.

Tuba: What are Caris other AI-driven comprehensive molecular science offerings?

David: Apart from MIFOLFOXai, Caris also offers MI GPSai providing a cancer type similarity assessment that compares the genomic (DNA) and transcriptomic (RNA) characteristics of the patient's tumor against other tumors in the Caris database.

Source: Parkway Cancer Centre

About David Spetzler:

Dr. Spetzler is the President and Chief Scientific Officer of Caris Life Sciences and has joined the company in 2009. He leads the company's clinical testing service and the development of proprietary technologies to aid in the creation of precision medicine strategies for individual cancer patients and noninvasive technologies to identify and predict early-stage cancer.