Speaker 1: In healthcare, large amounts of heterogeneous medical data have become available in various healthcare organizations. This data could be an enabling resource for deriving insights for improving care delivery and reducing waste. The enormity and complexity of these datasets present great challenges in analyses and subsequent applications to a practical clinical environment. In this series of lectures, we will explore the intersection of healthcare and big data. At the end of this lecture, you should develop understanding of healthcare data, the different analytics algorithms, and understanding the big data systems. The healthcare industry is huge, and there are a lot of data coming out of healthcare. The United States' healthcare is incredibly expensive. Overall spending is $3.8 trillion in US per year. That's more than the value of 10 biggest companies plus 10 Beijing Olympics plus a Warren Buffett and a Bill Gates. But does it have to be that way? There is massive waste in healthcare unfortunately. The estimated waste in US healthcare alone is $765 billion. That's equivalent to the NASA's total budget for the past 50 years. Not only the cost is an issue, but also the quality of healthcare is poor. There are 200,000 to 400,000 preventable deaths per year in the US. That's 1,000 people per day. If we classify the preventable deaths against other causes of deaths, it will be the number 3 causes of deaths in the United States, after only heart disease and cancer. So, there are massive problems presented in modern healthcare, including high costs, high waste, and low quality. How can big data help? The hope is big data can lead to better care and lower cost. In big data, people talk about the 4 Vs. Volume Healthcare generates a large volume of data. For example, for genomic data each human genome requires 200 gigabytes of raw data or 125 megabytes if we store just SNPs. For medical imaging data, a single MRI is about 300 gigabytes. Medical imaging data generated in the US per year was estimated to be 100 petabyte. Variety Healthcare also generates a lot of different kind of information. Such as clinical information, including patient's demographics, diagnosis, procedure, medication, lab results, and the clinical notes. Patient also generated a lot of data, such as information coming out of arm body sensors and other devices that patients wear. Velocity Healthcare also generate a lot of real-time data, such as blood pressure measures, temperature, heart rate, drug dispensing levels at intensive care units. Veracity Unfortunately, healthcare data often comes with a lot of noise, a lot of missing data, a lot of errors, and a lot of false alarms. It is a big challenge in healthcare data analytics. While the landscape is changing for healthcare big data analytics, as more organizations figure out how to harness big data and implement the right infrastructure for generating actionable insights from a slew of new sources, some providers may still be wondering how big data can actually work for them. Luckily, a number of pioneering organizations have taken it upon themselves to test the waters of healthcare analytics, generating use cases that spur interest and help carve a path through the wilderness. In the following sections, we will explore some of the ways healthcare organizations have already found success by turning big data into a strategic asset that can help providers react quickly and effectively to the ongoing challenges of quality care delivery. One way big data could revolutionize healthcare is by improving hospital quality and patient safety in the intensive care units. The ICU is an area where big data analytics is becoming crucial for patient safety and quality care. The most vulnerable patients are prone to sudden downturns due to infection, sepsis, and other crisis events which are often difficult for busy staff to predict. However, a number of organizations have been working on integrating bedside medical device data into sensitive algorithms that detect plummeting vital signs hours before humans have a clue. At the University of California Davis, researchers are using routinely collected EHR data as the fodder for an algorithm that gives clinicians an early warning about sepsis, which has a 40% mortality rate and is difficult to detect until it's too late. Finding a precise and quick way to determine which patients are at high risk of developing the disease is critically important. At Massachusetts General Hospital, an analytics system called QPID is helping providers ensure that they don't miss critical patient data during admission and treatment. The system is also used to predict surgical risk, helping match patients with the right course of action that will keep them safest during their care. The last thing a doctor want to do is do harm to a patient or do something inappropriately. The system automates searches using national guidelines, and then it essentially shows the results in a dashboard with a red, yellow, or green risk indicator for the surgeon to see. Another area where healthcare analytics may make a significant impact is in precision medicine and personalized care. Precision medicine entered the healthcare industry's lexicon in a big way in recent years during President Obama's State of the Union address in 2015. The president's vision for a nationwide patient databank sparked hopes of a renewed commitment to genomic research and the development of personalized treatments, but the NIH isn't the only one who has been using big data to predict the course of diseases related to a patient's genetic makeup. Healthcare predictive analytics has been particularly instrumental in the fight against cancer and has also helped to target the development of preventative measures related to heart disease, diabetes, and even food poisoning based on genetic research. Population health management is as much about prevention as it is about treatment, and healthcare big data analytics equip providers with the tools they need to be proactive about their patients' needs. Targeting patients based on their past behaviors can help to predict future events, such as a diabetic ending up in the emergency room because he did not refill his medication or a child with asthma requiring a hospital admission due to environmental triggers of her disease. By harnessing EHR data, providers can even identify links between previously disparate diseases. A risk score developed by Kaiser Permanente researchers in 2013 allows clinicians to predict diabetic patients who are likely to develop dementia in the future, while the Army is attempting to curb the rampant rate of veteran suicides by leveraging a predictive risk model to identify patients who may be likely to harm themselves. Healthcare predictive analytics can even prevent bottlenecks in the urgent care department or emergency room by analyzing patient flow during peak times to give providers the chance to schedule extra staff or make other arrangements for access to care. Emergency department crowding is a complex problem affecting more than 130 million patient visits per year in the U.S. In the current world of scarce resources and little margin for error, it is essential to rigorously identify the specific causes of crowding so that targeted management interventions can have maximal effect. Finally, as hospitals begin to feel the financial pinch, they are turning to healthcare analytics to keep patients at home. At the University of Pennsylvania, informaticists can look at prior hospitalization histories to flag patients who may be returning to the inpatient setting within 30 days. Real-time EHR data analytics also helped a Texas hospital cut readmissions by 5% by drawing on nearly 30 data elements included in the patient's chart. This is one of the first prospective studies to demonstrate how detailed data in EHRs can be used in real-time to automatically identify and target patients at the highest risk of readmission early in their initial hospitalization when there is a lot that can be done to improve and coordinate their care, so patients will do well when they leave the hospital. Meanwhile, the Kaiser Permanente system has been working to refine its readmissions algorithms in order to better understand which returns to the hospital are preventable and which are not, a crucial distinction for value-based reimbursements. Classifying readmissions as potentially preventable or not preventable can be used to improve hospital performance. Administrators can sort potentially preventable readmissions into categories that are actionable for improvement. They can identify trends over time or across reporting units. Classifying readmissions as potentially preventable or not preventable can also be used to establish accountability across reporting units and reward top performers.

Speaker 2: In summary, healthcare analytics are not some future fantasies,

Speaker 1: but are already happening in the real world and disrupting clinical routines and practices. As new technologies emerge and consumer demand for control over personal well-being increases, it will be ever more important to understand how best to navigate the large collections of data for healthcare organizations and how to scale your data to keep it relevant.

Speaker 2: Thank you.