دانلود رایگان مقاله انگلیسی معیارهای محرک: داده های بزرگ - الزویر 2018

INTRODUCTION

The US health care system is rapidly adopting electronic medical records (EMRs) and this will dramatically increase the quantity of clinical data available for sophisticated analysis during inpatient and outpatient care. Outpatient information that is becoming routinely available includes notifications of when patients fill their prescriptions and when they use their devices, such as an inhaler for asthma or chronic obstructive pulmonary disease, and noninvasive positive pressure ventilators for obstructive sleep apnea, as well as compliance with follow-up in outpatient clinics. Inpatient data include recent laboratory tests, imaging, vital sign monitoring with continuous electrocardiogram, carbon dioxide monitoring, pulse oximeters, and motion sensors that will monitor respiratory patterns and change in pulse. An integrated approach to analyzing this information creates the opportunity to improve health care quality, distribute resources adequately, and decrease cost. The types and quantity of information available and the ability to analyze it in ways that can affect patient management in real time are referred to as big data. In 2012, big data was described as “large volumes of high velocity, complex and variable data that requires advanced techniques and technologies to enable the capture, storage, distribution, management and analysis of the information.”1 Existing analytical techniques can be applied to the vast amount of existing patient-related health and medical data to reach a deeper understanding of outcomes, which can be applied to point-of-care management and assist physicians and their patients during the decision-making process and help determine the most appropriate treatment option. Numerous questions can be addressed with big data analytics and the potential benefits include detecting diseases at earlier stages, managing specific individual and population health, and detecting health care fraud more quickly and efficiently.2 Additionally, the McKinsey Global Institute estimates that big data analytics can generate more than $300 billion in savings in US health care through reduction of waste and inefficiency in clinical operations, research, and development.

SUMMARY

Aggregate warning systems, in combination with big data derived from the EMR, offers a great opportunity to detect clinical changes that precede a MET activation. Further studies are needed to determine if this will decrease the number of transfers to the ICU and cardiac arrests on the floors, as well as improve outcomes. Data interpretation depends significantly on the EMR available in each hospital and the resources available at each site. This variability affects both the afferent and the efferent limbs of the medical emergency systems. Real-time big data analytics have the potential to transform the way health care providers use technologies to gain insight from clinical and other data repositories and make informed decisions.2 In the future, the authors expect the use of big data analytics, including an AWSS, will allow providers to predict that a patient will meet clinical criteria to activate MET and enable intervention before the critical moment happens. More research is needed to determine if this early identification will affect patient clinical outcomes, including cardiac arrest, transfer to the ICU, length of stay, morbidity, and mortality.