Big Data, Health Informatics, and the Future of Medicine
The ongoing convergence of emerging technologies in cloud computing, mobility, Internet of Things (IoT), machine learning, and big data analytics is currently revolutionizing the medical and healthcare industry in ways yet to be entirely understood by most practitioners, academicians, and researchers alike. The increasing availability of biomedical information and its correspondingly high growth rate is driving us quickly to the future where personalized medicine is not only possible but will significantly help to raise the global level of life expectancy in general. Today, a big data analytics lifecycle starting with data produced using machine learning and artificial intelligence-enabled genomic sequencing technologies, to intelligent data translation and correlations, and the aggregation of a possible report for clinicians, pharmacologists, and other related researchers is becoming easily accessible. The ability to be able to collect, analyze, translate, correlate and compare large amounts of data using innovative algorithms with the chance to merge all this information within a seamless cloud analytic environment for further studies is one of the fundamental driving forces for this change. Also as our understanding and detailed operational nature of the various so-called omics data — genomes, transcriptomes, exomes, epigenomes, etc. continues to progress forward, and our ability to advance life through better healthcare will become realistic and hence put pressure on researchers to do the needful. For all these to be possible, there is a need for researchers and scientists to begin the process of creating scalable theoretical structures to deal with these ever-increasing dataset. An agreeable global meta-data structure and other associated technical data methodologies will be critical to the expected evolution process (Costa, 2014; Datta, 2015)
Healthcare as Information Science
Over time, physicians have acquired, processed, and interpret data from various sources to deliver the most appropriate and enduring care for their patients. The continuous availability of high quality, accurate, and clinically relevant data is key to making continuously improved decisions, which has now resulted in healthcare data analytics(Kim & Groeneveld, 2017). “Medicine is going to become an information science. In 10 years or so, we may have billions of data points on each individual, and the real challenge will be to develop information technology that can reduce that to real hypotheses about that individual.”(Hood, 2019)
Today, we are now in a world of exponentially growing amounts of health-related data originating from disparate sources — electronic health records, doctors’ narratives, test and imaging results, including genomic and other “omic” data, effectively creating health informatics and big data overload challenge. This challenge has the potential to effectively transform healthcare delivery through computation to information science(Kim & Groeneveld, 2017). Hood (2019) already started the revolution in creating the Institute for Systems Biology in Seattle, a multidisciplinary group with interest in re-shaping medicine using new technologies and knowledge in biology and informatics to make its practice more predictive, preventive, and personal(Hood, 2019). The promise of big data analytics in healthcare is tremendous considering its application to multiple stages of health research — very large-scale population health management, disease risk prediction, precision medicine, and clinical decision support through machine learning algorithms.
Although Kim et al. (2017) advocates’ fellows-in-training to hold a basic understanding of the diversity of biomedical data and the innovative ways it can analyze and used. Such training and others must prepare medical practitioners for a “big data” world, including a precise understanding of existing challenges in the application of data science in medicine. In medicine, physicians are not only required to make an accurate prediction of future adverse events that may befall a patient but must hold a clear understanding of how their remediation might change the probability of those events(Kim & Groeneveld, 2017).
Diagnosis of Illness in the Future
Hood (2019) contends that healthcare is changing very fast, and it will soon transcend from reactive to proactive medicine. He sees a future of predictive, personalized, preventive, and participatory healthcare aptly termed “P4” medicine. Apart from digitizing medical records, test and imaging results, and physicians’ narratives, other exciting informatics overhauls are becoming commonplace. It is expected that individual genomes will become a part of standard medical records in a few years and so make the power of inferences and phenotypic information personal. That means pharmacogenomics — the practice of using an individual’s genetic makeup to choose drugs, will begin to flourish innately. The next will be emerging nano-technological approaches to measuring organ-specific proteins. These approaches provide a proactive mechanism for measuring over 2,500 proteins from a single drop of blood with specificity for interrogating health rather than diseases, turning medical practice dynamic. Detailed cell analysis with comprehensive abilities to analyze transcriptomes and RNAomes, proteomes, and metabolomes will form the third layer of healthcare transformation, supporting medical practitioners with actionable insights from the powerhouse (Hood, 2019).
It is therefore evident that the ongoing revolution in healthcare might still be in its infancy with the application of computational and mathematical tools and our ability to handle vast amounts of data as the next fundamental driving forces of the emerging revolution. A future where physicians can handle billions of patient’s data points, use computational analysis to compare individual genotype-phenotype correlations for deeper disease insights, perform detailed cell analysis, and aggregate other relevant environmental information while utilizing pharmacogenomics for the delivery of individualized patient drug and treatment is now near possible. Herein lies the promise of digitizing medicine and the future of healthcare.
References
Costa, F. F. (2014). Big data in biomedicine. Drug Discov Today, 19(4), 433–440. doi:10.1016/j.drudis.2013.10.012
Datta, S. K., Bonnet, C., Gyrard, A., Ferreira da Costa, R. P., & Boudaoud, K. (2015). Applying the Internet of Things for personalized healthcare in smart homes. 2015 24th Wireless and Optical Communication Conference WOCC.
Hood, L. (Producer). (2019, October 14). A Vision for Personalized Medicine. MIT Technology Review. Retrieved from https://www.technologyreview.com/s/417929/a-vision-for-personalized-medicine/
Kim, J., & Groeneveld, P. W. (2017). Big data, health informatics, and the future of cardiovascular medicine. In: Journal of the American College of Cardiology.
