Noting the promise and potential big data analytics offers in the healthcare industry, it is equivalently important to consider the potential technical and socio-political challenges it will face during its development and in the wake of its implementation. Firstly some of the biggest technical challenges big data analytics must face include driving the collection of health data in real-time and minimizing lag between data collection and processing (W. Raghupathi and V. Raghupathi). Additionally, at a very minimum, the chosen big data analytics platform must support the crucial functions necessary for processing and handling the data. Thirdly, it is of paramount importance that the software platform is packaged with a user-friendly, menu-driven
…show more content…
Through the analysis of healthcare data, the most effective treatments in any situation can be delivered more easily as analytical platforms can make predictions and inferences about patients, leading to the suggestion of lifestyle changes (Kołodziej, Correia and Molina). The predictive and preventive potential of big data analytics is becoming more and more evident as the healthcare industry transitions from the use of standard, regression based models for analysis to newer algorithmic sub-disciplines such as graph analytics, machine learning and natural language processing (Shah, Pathak). An example of a healthcare provider that has implemented a big data analytics platform in various medical institutions to improve healthcare outcomes is Kaiser Permanente, which has contributed to an improvement in cardiovascular disease outcomes and saved approximately one billion dollars from reduced tests and office visits (Kayyali, Knott, Kuiken). Another example is that of Blue Shield of California, which has helped improve disease prevention rates and bolster care coordination through their system (Kayyali, Knott, Kuiken). Evidence of the rise of the preventive potential of big data analytics can be seen in the transition of the core …show more content…
Currently, the method of graph analytics is being used in hospitals to determine the relationship between several complex variables such as lab results, patient family history, diagnoses and medication history to identify patients who could potentially be at risk for various illnesses and complications (Shah, Pathak). The application of graph analytics in this manner could better inform doctors to deliver treatment at the most opportune times and prevent the oversight of such opportunity (Shah, Pathak). Additionally, the field of machine learning proposes to heuristically solve the problem of extracting meaning and insight from large bodies of text-based health data without having to initially organize the dataset (Redmore). The premise of this method is that the big data analytics platform will be pre-programmed to intelligently evolve its understanding of the dataset and adjust algorithmic decisions as it learns more about the data (Redmore). Natural language processing is another artificial intelligence method that seeks to interpret speech and text in a predictable manner, which is in contrast to machine learning, in which the optimal solution to a problem can be often difficult to backtrack (Redmore). Natural language processing works by separating and parsing the semantic, syntactical and
Through the analysis of healthcare data, the most effective treatments in any situation can be delivered more easily as analytical platforms can make predictions and inferences about patients, leading to the suggestion of lifestyle changes (Kołodziej, Correia and Molina). The predictive and preventive potential of big data analytics is becoming more and more evident as the healthcare industry transitions from the use of standard, regression based models for analysis to newer algorithmic sub-disciplines such as graph analytics, machine learning and natural language processing (Shah, Pathak). An example of a healthcare provider that has implemented a big data analytics platform in various medical institutions to improve healthcare outcomes is Kaiser Permanente, which has contributed to an improvement in cardiovascular disease outcomes and saved approximately one billion dollars from reduced tests and office visits (Kayyali, Knott, Kuiken). Another example is that of Blue Shield of California, which has helped improve disease prevention rates and bolster care coordination through their system (Kayyali, Knott, Kuiken). Evidence of the rise of the preventive potential of big data analytics can be seen in the transition of the core …show more content…
Currently, the method of graph analytics is being used in hospitals to determine the relationship between several complex variables such as lab results, patient family history, diagnoses and medication history to identify patients who could potentially be at risk for various illnesses and complications (Shah, Pathak). The application of graph analytics in this manner could better inform doctors to deliver treatment at the most opportune times and prevent the oversight of such opportunity (Shah, Pathak). Additionally, the field of machine learning proposes to heuristically solve the problem of extracting meaning and insight from large bodies of text-based health data without having to initially organize the dataset (Redmore). The premise of this method is that the big data analytics platform will be pre-programmed to intelligently evolve its understanding of the dataset and adjust algorithmic decisions as it learns more about the data (Redmore). Natural language processing is another artificial intelligence method that seeks to interpret speech and text in a predictable manner, which is in contrast to machine learning, in which the optimal solution to a problem can be often difficult to backtrack (Redmore). Natural language processing works by separating and parsing the semantic, syntactical and