The design and implementation of novel processes for cancer diagnosis and efficient cancer treatment is a booming field of research, R&D efforts, market reshaping, ethical and regulatory reflection, and dissemination of consensus guidelines by professional associations. Digital diagnostics substantially improve and support existing experimental processes. Importantly, digital diagnostics are entering the Healthcare market in a steady manner.
In particular, processes using and analyzing digitalized clinical patient data are changing positively the assessment of actions to be taken in favor of patients in many sectors. Most importantly for Blazar in oncology research and cancer treatment. We have focused on immunotherapies as their effects on cancer treatment were a true breakthrough. Additionally, the underlying cellular and molecular rationale is accessible with methods derived from clinical experience, cell biology, and artificial intelligence. Our team joins this expertise and has moved forward to use them for building better processes and products that can be predictive of treatment success with immunotherapy in solid tumor patients.
We have undertaken to use methods to predict response and resistance to therapies, applying clinical know-how, recent clinical trial treatment results, deep learning, machine learning, and statistical methodologies. With this approach we explore, identify and validate combinations of biomarkers, both known or novel and discovered by our team, to predict response to cancer therapies with our platform. Additionally, we generated software tools to facilitate analysis and annotation of patient biopsy and tumor resection prior to prescription and assist the pathologist with their tumor reporting (anapath).
There is an absolute and urgent need for an artificial intelligence platform for a more detailed understanding of the tumor microenvironment, tumor cell biology factors, patient genetic history, and immune system status. Blazar proposes methods to assist in clinical data analysis by assessing the probability of response to oncotherapies and providing potential explanations for patient non-response.
The main objective of our processes is to develop a highly accurate tool for predicting solid tumor response to therapy by stratifying patients through biomarker identification and improving patient quality of life and lifespan.
No compromises: we provide clinicians with useful tools to alleviate their workload, maintaining their autonomy and performance while they treat their patients in the best way possible.