Recently, healthcare has been undergoing a digital revolution. Mobile devices and technologies are more frequently being incorporated in healthcare settings to improve a broad range of health outcomes. Healthcare has mainly used a “one-size-fits-all” approach to patient care in which generalized treatment plans are used rather than personalizing treatment plans based on the patient’s individual case. However, with recent advances in technology and more frequent use of big data in healthcare, there has been a shift from this “one-size-fits-all” patient care to more personalized medicine. For the past decade, Big Data has been coined as a term to describe the rapid increase in volume, variety and velocity of information available in all aspects of our lives . However, the term now refers not just to large data volumes, but to our increasing ability to analyze and interpret this large volume of data. A more specific definition of what Big Data is in the premise of health research was proposed by the Health Directorate of the Directorate-General for Research and Innovation of the European Commission, stating that Big Data in health includes high volume, high diversity, biological, clinical, environmental and lifestyle information collected from single individuals and large groups, in relation to their health and wellness status a various points in time [3,2].
The breadth of Big Data available in all aspects of healthcare include data collected from electronic healthcare records, social media, patient summaries, genomic and pharmaceutical data, clinical trials, telemedicine, mobile apps and socioeconomic indicators. With such a wide range of healthcare data available, the potential of Big Data in improving health is enormous. However, it is only valuable when used to drive decision making in clinical and research settings. To enable evidence-based decision making using the data, it is first necessary to have efficient processes, such as adequate algorithms and technologies to analyze and turn the high volumes of data into meaningful information. There are numerous ways in which big data analytics are being used in healthcare to save lives and improve efficiency and patient outcomes. Some examples include devising cancer patient treatment plans, preventing opioid abuse in the United States and improving medical imaging efficiency .
Improving cancer treatment to be more personalized to each patient is one example of the applications of big data analytics in healthcare. Medical researchers are using large amounts of data on treatment plans and recovery rates of cancer patients to find trends in treatments that have the highest rates of success. Using this data, researchers are building analytic tools that can quickly draw relevant information to help patients.
For instance, at Massachusetts General Hospital, a team designed a machine learning model which identifies imaging biomarkers on mammograms to predict if a patient is at risk of developing breast cancer . They conducted a study to compare the efficiency of a machine learning model versus a traditional model in predicting patient risk. The results of the study showed that the machine learning model the team created predicted patient risk better than traditional models with a predictive rate of 0.71 compared to a 0.61 rate from the traditional model . This is mainly because traditional models only include a small fraction of patient data such as family history, prior breast biopsies and hormonal reproductive history . The findings of this study show that big data analytics has real potential in improving targeted treatment plans.
In addition to targeted treatment plans, big data analytics is also being used to prevent addiction. For example, analysts at a company called Fuzzy Logix which is a company that develops high-performance analytics for Big Data, have been able to identify 742 risk factors that predict with a high degree of accuracy whether someone is at risk for abusing opioids. This shows that the applications of big data analytics in healthcare go way beyond just patient treatment.
Although use of big data in healthcare has huge potential, there is still more research and work to be done in the field. For instance, there are technical challenges with incompatible data systems and patient confidentiality issues. With more research and development in the field, big data could be beneficial in healthcare.
Edited by: Vicky Cadena