Breast cancer affects around 1 in 8 women in the U.S. Although early detection efforts have resulted in decreased mortality rates, therapy selection remains complex. While this is partly due to the heterogeneous nature of the disease, in recent years, we have seen a significant rise in the number of therapeutic drugs approved to treat cancer patients. This creates added complexity in determining which patients will benefit most from selected treatments.
Health Benefit Consultants, Share Your Expert Insights in Our Survey
Dr. Anu Antony Dr. Anu Antony is the Chief Medical Officer of SimBioSys, a technology company that predicts tumor responses to therapy. Dr. Antony has dedicated the last 15 years of her career to the service of breast cancer patients as a board-certified surgeon specializing in oncologic reconstructive surgery. She completed her residency at Stanford […]
Given these challenges, there is a need for sophisticated and accurate forecasting software tools that incorporate precision cancer care to better guide and support clinical decision making. Technology and artificial intelligence, in particular, have the potential to improve decision making in the clinic and, consequently, change the lives of patients.
Histologically, breast cancer is classified according to the presence or absence of molecular markers such as the estrogen receptor (ER), progesterone receptor (PR) and human epidermal growth factor receptor 2 (HER2). These molecular markers are indicative of aggressiveness, and most importantly they serve as a guide for therapy.
In the past, the administration of systemic therapy before surgery was reserved for treating locally advanced breast cancer, while early breast cancer patients (patients with localized disease or disease spread to regional lymph nodes only) were candidates for breast conservation surgery or mastectomy. More recently, pre-surgery systemic treatment, referred to as neoadjuvant therapy, has become common practice for early breast cancer patients. These treatments facilitate breast conservation, make inoperable tumors operable and are primarily recommended for triple negative and HER2-positive breast cancer patients.
Early breast cancer clinical trials for neoadjuvant therapy have also implemented the use of pathological complete response (pCR). This indicates the absence of residual disease, as an indicator of long-term outcome and a clinical endpoint for drug approval.
A Deep-dive Into Specialty Pharma
A specialty drug is a class of prescription medications used to treat complex, chronic or rare medical conditions. Although this classification was originally intended to define the treatment of rare, also termed “orphan” diseases, affecting fewer than 200,000 people in the US, more recently, specialty drugs have emerged as the cornerstone of treatment for chronic and complex diseases such as cancer, autoimmune conditions, diabetes, hepatitis C, and HIV/AIDS.
In the U.S., the National Comprehensive Cancer Network offers guidelines for therapeutic interventions for the different subtypes of breast cancer. However, deciding among the 12 different neoadjuvant regimens recommended for HER2-negative disease and the nine different ones recommended for HER2-positive disease proves a challenge for clinicians when trying to select the right therapy for each patient.
The continual approval of new therapies and additions to the standard of care make it necessary for clinicians to have better tools to guide and support decision making in order to not overtreat or undertreat patients.
Predicting how a patient will respond to different therapies provides the clinician with an opportunity to evaluate and compare different treatments. These types of technologies are capable of guiding clinicians when confronted with the critical decision to escalate or de-escalate therapy. This has important implications for prognosis and quality of life as well as out-of-pocket expenses incurred by the patient.
Being able to predict clinical outcomes in patients treated with standard of care therapies has value not only in the clinic but for clinical trials as well. For example, drug developers can use this capability to compare the benefit a drug being tested to the current standard of care. They can use tools to predict what the study arm responses would have been with standard of care therapies to reveal the drug’s true benefit.
It can also be used for clinical trial design — to predict clinical outcomes — serving as a way to ensure that baseline responses to standard of care are similar among all study cohorts. Additionally, selecting the right tools to predict patient outcomes could give stakeholders a more comprehensive view of the tumor that could go beyond outcome prediction.
Overall, it’s important to gain a deeper understanding of how these approaches work. This will enable greater specificity and predictivity in the treatment of breast cancer in clinical trials and in the clinic.
Photo credit: andresr, Getty Images
Dr. Anu Antony is the Chief Medical Officer of SimBioSys, a technology company that predicts tumor responses to therapy. Dr. Antony has dedicated the last 15 years of her career to the service of breast cancer patients as a board-certified surgeon specializing in oncologic reconstructive surgery. She completed her residency at Stanford University Medical Center in general surgery and plastic surgery; holds a Master of Public Health in Biostatistics from the Harvard School of Public Health and an Executive MBA from the Northwestern Kellogg School of Management. Dr. Antony has held several prestigious positions in the Chicagoland area, including Professor and Vice-Chair of the Department of Surgery and Chief of Breast Reconstruction at Rush University Medical Center in Chicago, Vice-Chair of the University of Illinois Breast Cancer Center, and President of her regional and state professional societies.
