Data supporting prediction of adjuvant therapy benefit using Histotype Px® Colorectal in U.S. colon cancer patients presented at Pathology Visions 2024
OSLO – November 4, 2024 – DoMore Diagnostics, a leader in AI and deep-learning for precision medicine for cancer, is pleased to announce that a poster with clinical data on Histotype Px® Colorectal (Histotype Px) in U.S. colon cancer patients was presented on November 3 at the Pathology Visions 2024 conference (Orlando, FL), organized by the U.S. Digital Pathology Association. Expanding on results presented earlier this year at the 2024 American Society of Clinical Oncology (ASCO) Annual Meeting, this study performed in collaboration with Ohio State University Comprehensive Cancer Center (OSUCCC) investigated the performance of Histotype Px in patients treated with and not treated with adjuvant chemotherapy (ACT) after surgery.
The pilot study included 159 stage II and stage III colon cancer patients (mean age 63 years; n=72 treated with ACT and n=87 not treated with ACT) that had been diagnosed and treated at OSUCCC between 2016 and 2020. The primary outcome of interest was cancer-specific mortality and secondary outcomes were time to recurrence and all-cause mortality. Standard hematoxylin and eosin (H&E) pathology slides were digitized locally and the images analyzed by the Histotype Px digital pathology AI tool.
Importantly, among patients who did not receive ACT, Histotype Px predicted ‘low-risk’ patients had excellent outcomes whereas patients predicted ‘high-risk’ had dismal outcomes. In patients who were treated with ACT, Histotype Px ‘high-risk’ patients had fewer cancer-specific deaths compared to ‘high-risk’ patients who did not receive ACT.
Univariate Cox proportional-hazards regression models were used to assess the association between Histotype Px risk groups (low-, medium- and high-risk) and disease outcome. There was a significant association between risk groups by Histotype Px and for low- vs high-risk for cancer-specific mortality (p<0.001; hazard ratio, HR = 15.7), recurrence (p<0.001; HR = 28.7) and all-cause mortality (p=0.017; HR = 4.4). Furthermore, Histotype Px was found to predict disease progression in both stage II (HR = 3.2 and 4.7 for cancer-specific mortality and recurrence, respectively) and stage III patients (HR = 6.0 and 4.4 for cancer-specific mortality and recurrence, respectively).
Although the number of patients is limited, these encouraging results indicate that Histotype Px may be predictive of treatment response in a population of U.S. colon cancer patients and will be followed up with larger data sets to further document Histotype Px as a clinical decision tool.
Principal Investigator Dr. Eric D. Miller, MD, PhD, Department of Pathology, OSUCCC said:
“According to current US clinical guidelines most high-risk stage II and all stage III colon cancer patients are recommended ACT, however many patients have a low risk of recurrence and do not benefit from this toxic treatment. The pilot validation data presented at Pathology Visions 2024 further supports the potential clinical utility of Histotype Px as a tool to guide treatment decisions to escalate or de-escalate ACT treatment. Further research including a larger and more diverse patient cohort and subsequent clinical studies are underway to strengthen these findings and to integrate this promising biomarker in the clinic.”
Torbjørn Furuseth, MD, CEO and co-founder of DoMore Diagnostics, commented:
"These Histotype Px validation results presented at Pathology Visions 2024 adds to the growing evidence across major cancer centers showing that Histotype Px may personalize treatment decisions for colorectal cancer worldwide. In particular, this initial validation in patients that had not been treated with ACT is important in indicating the predictive value of Histotype Px and is an important step towards clinical implementation and widespread adoption of our digital biomarker.”
Poster presented (Sunday November 3):
About DoMore Diagnostics
DoMore Diagnostics uses artificial intelligence to make personalized treatment decisions simple and accessible for all cancer patients. Its unique digital biomarkers predict patient outcomes from routine tumor tissue slides and can be seamlessly integrated into pathologists’ existing workflow. The lead product Histotype Px® Colorectal is a CE-IVDD marked outcome prediction marker for stage II and III colorectal adenocarcinoma that informs the decision of whether to provide adjuvant chemotherapy following surgical resection of the tumor.
About Colorectal Cancer and Histotype Px® Colorectal
Colorectal cancer is the third most common and second most deadly cancer but has seen little innovation in diagnostics and treatment the last decades. Adjuvant chemotherapy (ACT) may be provided after primary surgery to prevent the disease from recurring, however overtreatment is prevalent with up to 85% of patients with stage II and stage III not benefitting from ACT and only suffering side effects.
Histotype Px® is an advanced deep learning algorithm that analyzes digital histology slides, separating patients into distinct Low, Intermediate and High-risk groups to guide ACT treatment decisions. Data previously published in The Lancet and The Lancet Oncology showed that the test can accurately predict survival outcomes in colorectal cancer patients. Histotype Px® Colorectal was developed to provide clinicians with valuable information to guide personalized treatment decisions and improve patient outcomes.
For more information about the Histotype Px Colorectal biomarker, please visit:
The Lancet publication.
The Lancet Oncology publication.
Contact:
Torbjørn Furuseth, MD
torbjorn.furuseth@domorediagnostics.com