An artificial intelligence tool called PhenopyCell can determine if patients with extensive-stage small cell lung cancer will benefit from chemotherapy using existing biopsy slides.
RT’s Three Key Takeaways:
- Predictive AI Tool: Researchers developed a tool called PhenopyCell that uses artificial intelligence to predict if patients with extensive-stage small cell lung cancer will respond to platinum-based chemotherapy before treatment begins.
- No Additional Biopsies: The system analyzes existing pathology slides from diagnostic biopsies, eliminating the need for further procedures, tissue collection, or added costs for patients.
- Immune Cell Organization: The tool identifies organized groups of immune cells surrounding tumor clusters as a biological marker for better treatment outcomes, which is not visible through manual analysis.
Results of a new study suggest that an artificial intelligence-powered pathology tool can predict whether a patient with extensive-stage small cell lung cancer (SCLC) will respond to platinum-based chemotherapy before treatment begins, according to a news release from Roswell Park.
The tool, named PhenopyCell, was verified by three collaborating institutions in a study published in the journal npj Precision Oncology. The research team was co-led by Prantesh Jain, MD, thoracic oncologist at Roswell Park, and Anant Madabhushi, PhD, of the Winship Cancer Institute of Emory University.
According to the study findings, approximately 70% of patients with SCLC have extensive-stage disease at the time of diagnosis. Currently, most patients receive a standard treatment of platinum-based chemotherapy and immunotherapy because there are no established biomarkers to distinguish subtypes or predict responses. Because the disease progresses rapidly and most patients survive only 12 to 13 months, identifying the most effective treatment early is critical for patient survival.
While new SCLC treatments have recently been approved by the Food and Drug Administration (FDA), they are effective in only a small number of patients.
“We are entering an era where we will have more tools than ever to offer people with small cell lung cancer,” said Jain, thoracic oncologist, in a news release. “But knowing which tool is right for which patient requires biological markers, and right now we don’t have them.”
PhenopyCell acts as a computational biomarker by combining data from pathology slides and medical records to determine how these factors correspond to patient outcomes. In a retrospective study, the team used the tool to analyze pathology slides from 281 patients treated at Roswell Park, Winship, and University Hospitals Cleveland Medical Center.
The tool predicted chemotherapy response by analyzing immune cells in tissue samples from diagnostic biopsies. Investigators found that the computational biomarker achieved greater accuracy than manual analysis when compared with actual patient outcomes.
The analysis revealed that tumors in patients with better outcomes contained more immune cells appearing in organized groups surrounding tumor clusters, indicating a better immune response. Patients with poor outcomes had fewer immune cells, which appeared in disorganized groups further away from the tumor. These immune cell arrangements were visible only with the use of the artificial intelligence tool.
Because the system works from existing diagnostic biopsy slides, there is no need for additional tissue collection or invasive procedures.
“In a disease where survival is measured in months and re-biopsy is rarely possible this, has the potential to become a uniquely powerful tool,” said Jain, in a news release.
