Current Research
01
Predictive model ( AI/ML) of post surgery prognosis of breast cancer using PLCO dataset patient data
Quantum Biosciences is developing an AI/ML powered predictive model on precision treatment of post primary surgery of breast cancer (stage 2A/2B). 95% of breast cancer patients get chemotherapy to avoid a relapse. Existing information suggests that only 15% of these patients benefit from the adjuvant chemotherapy and it interferes with a woman's reproductive health in the childbearing age group.
​
We are correlating the histological type and grade of the tumor with the lymph node status of the patient at surgery to create a predictive model for prognosis, hence determining the need for adjuvant chemotherapy. We will take into account the presence of the tumor marker (Ki 67), hormone receptors and the Her2 gene. Our goal is to provide health care providers with an effective tool to make an informed decision regarding adjuvant chemotherapy in a breast cancer patient (stage 2A/2B), which can get a woman the most precious few years she needs to complete her family.
02
A comprehensive analysis of Radiation Therapy Practices
Radiation therapy is the most resource intensive part of comprehensive cancer care and in recent years, has undergone significant technological advancements with improved imaging, treatment planning software, and radiation modalities. Despite these advances there is significant disparity in the availability and accessibility of these services
​
​
​
​
Our literature review of existing studies reveals huge disparity in the access to radiation therapy resources globally with low- and middle-income countries averaging only 0.4-1.0 centers /million population. Although the numbers look much favorable for the US, there is no comprehensive study to really compare the uniform availability of these services across different geographic and socio-economic regions of the country.
03
Digital Twin for Radiation Therapy Optimization
Cancer remains a leading cause of death globally, with current treatment strategies often limited by a lack of true personalization. Radiation therapy (RT) is a critical component of cancer treatment, yet its efficacy is often compromised by patient-specific biological variability. Traditional RT planning is typically based on population averages, failing to account for individual differences in tumor biology and patient response. Digital twin (DT) technology, which creates virtual replicas of physical entities, offers a novel approach to personalize cancer treatment by integrating multi-scale data (molecular, cellular, organ, organism, societal, geographic, family history, etc.). This research focuses on the development of a DT software platform to optimize RT for cancer patients.
We are conducting a cross-sectional observational study to investigate the current radiation therapy practices, identify barriers to advanced techniques, and explore opportunities for optimizing patient care. Our study aims at collecting data from over 100 radiation therapy centers on treatment planning, delivery techniques, technology utilization, and patient outcomes, our research aims to -
- Identify Disparities
- Optimize Patient Care
- Facilitate Technology Adoption
- Informed Policy Decisions
The successful completion of this study will show a path to the adoption of uniform radiation therapy practices and technology adoption across the country. Furthermore, it will serve as a tool to evaluate the availability and accessibility of these resources across different regions with their unique social and economic makeup. This can lead to it being used as a benchmark for health care reforms and to assist in equitable distribution of medical resources across the country.