Early assessment and what is known as precision medicine result in encouraging survival rates. Precision medicine affects not only the diagnosis but also the ability to identify the risk of suffering from breast cancer before it even appears—or at the very least nip it in the bud in the very early stages.
Applying Big Data techniques to mammogram and breast ultrasound readings allows doctors to diagnose the disease in early cancerous lesions. Obtaining a clear diagnosis is synonymous with obtaining an earlier, more precise and safer diagnosis. Analyzing data brings us closer to an intrinsic element of medical practice.
Leveraging Big Data for urologic oncology is the keystone of precision medicine. This reality is transforming various activities such as the diagnosis, prognosis and treatment of various types of cancer. Data resulting from various Big Data techniques help predict future risks of suffering the disease and help isolate agents for both the origin and causes of the various tumors.
Big Data involves analyzing medical history data—coupled with other environmental, work, social, genetic and family data—allowing predictive analyses for women or groups of women at varying levels of susceptibility to developing breast cancer.
Much of this information comes from medical records, which means that the health professionals tackling this illness invest great efforts in exploring, observing and deductively analyzing the data. Acquiring and analyzing data using Big Data methods and techniques presents a great opportunity to enhance the turnaround and certainty of the diagnosis, as well as searching for individual therapies that could be applied to patients exhibiting a genetic predisposition. However, progress in this area faces a significant roadblock. Ensuring patients’ privacy and the safety of their clinical data is a key legal barrier but also slams the brakes of research and improved treatment safety and efficiency.
One of the major concerns of health systems is to achieve a sustainable model due to the increase in the population’s average age, the increased cost of new medicines, especially oncology, and the unwanted and adverse effects of medications. Without being able to analyze patient data, applying treatments with the immediacy and scientific evidence required in these cases is virtually impossible. The fact is that in developed countries most cases of breast cancer are diagnosed in advanced stages.
Regina Barzilay, an MIT professor and a breast cancer survivor herself, is part of the Computer Science and Artificial Intelligence Laboratory. When she was diagnosed, she found it strange that most of the cancer treatments offered by specialized centers were based on clinical trial results. This meant that—in the vast majority of cases—they came from only 3% of patients and did not take into account the remaining 97%. The data of this 97% is locked up in their medical history. Once more, data is a gold mine that is not always explored.
Regina explains that “since the 1960s, radiologists have noticed that women show unique and widely variable patterns of breast tissue visible on mammograms. These patterns can represent the influence of genetics, hormones, pregnancy, lactation, diet, weight loss and weight gain, etc. We can now take advantage of this detailed information to be more precise in our risk assessment at the individual level—personalizing detection around a specific woman's risk of developing cancer rather than adopting a one-size-fits-all approach.”
Detecting who is going to have cancer in the future, with a forecast period of up to 5 years, will save many lives. The goal is to detect the disease before the first symptoms appear. For this, analyzing data is critical. Because knowing the past allows us, yet again, to look forward with optimism.