Five scenarios of big data application in medical industry

Source: Biovalley October 20, 2015, 1989, Gartner proposed the concept of Bi In 2008, Gartner further upgraded the Bi concept to advanced analytics In 2011, McKinsey explained the concept of big data Although the names are different, the problems they are trying to solve have never changed However, today's big data analysis technology can process a large number of diverse real-time (volume, variety, velocity) data, that is, big data Compared with Bi 20 years ago, big data analysis can produce greater business value The development of big data storage and analysis technology also benefits from the surge of data volume and diversification of data types in business scenarios Therefore, before implementing big data analysis projects, enterprises should not only know what technology to use, but also know when and where to use it In addition to Internet companies that started using big data earlier, the medical industry may be one of the first traditional industries that let big data analysis carry forward The medical industry has long met the challenge of massive data and unstructured data In recent years, many countries are actively promoting the development of medical informatization, which makes many medical institutions have funds to do big data analysis Therefore, the medical industry, together with banking, telecommunications, insurance and other industries, will first step into the era of big data In its report, McKinsey points out that removing institutional barriers, big data analysis can help the U.S health service industry create $300 billion in added value a year This paper lists 15 applications in 5 major areas of medical service industry (clinical business, payment / pricing, R & D, new business model, public health) In these scenarios, the analysis and application of big data will play a huge role in improving medical efficiency and medical effect Clinical operation: in terms of clinical operation, there are five major scenarios of big data application McKinsey estimates that if these applications are fully adopted, the U.S alone will reduce national health spending by $16.5 billion a year 1 Comparative effect research: through comprehensive analysis of patient characteristic data and efficacy data, and then comparing the effectiveness of various interventions, we can find the best treatment way for specific patients Efficacy based research includes comparative effectiveness research (CER) Research shows that for the same patient, different providers of medical services, different methods and effects of medical care, there are also great differences in cost Accurate analysis of large data sets, including patient physical data, cost data and efficacy data, can help doctors determine the most effective and cost-effective treatment methods in clinic The implementation of CER in the medical care system will probably reduce the over treatment (such as avoiding the treatment methods with obvious side effects) and insufficient treatment In the long run, either over treatment or under treatment will have a negative impact on patients' health, as well as higher medical costs Many medical institutions around the world (such as nice in the UK, IQWiG in Germany, general drug inspection agency in Canada, etc.) have started the CER project and achieved initial success The recovery and Reinvestment Act passed by the United States in 2009 is the first step in this direction Under this act, the Federal Coordinating Committee coordinates the comparative effect research of the whole federal government and allocates 400 million dollars of investment For this investment to succeed, there are still a lot of potential problems to be solved, such as the consistency of clinical data and insurance data Currently, in the absence of EHR (electronic health record) standards and interoperability, the rapid deployment of EHR on a large scale may make it difficult to integrate different data sets For another example, it is not easy to provide enough detailed data to ensure the validity of the analysis results on the premise of protecting the patient's privacy There are also some institutional problems, such as the current US law forbids medical insurance institutions and centers for medical care and Medicaid Services (medical service payers) to use cost / benefit ratio to make reimbursement decisions, so even if they find better methods through big data analysis, it is difficult to implement 2 Clinical decision support system clinical decision support system can improve work efficiency and diagnosis and treatment quality The current clinical decision support system analyzes the entries entered by doctors and compares them with the medical guidelines, so as to remind doctors to prevent potential errors, such as adverse drug reactions By deploying these systems, medical service providers can reduce the rate of medical accidents and the number of claims, especially those caused by clinical errors In the study of the metropolitan pediatric intensive care unit in the United States, the clinical decision support system reduced the number of adverse drug reactions by 40% within two months Big data analysis technology will make clinical decision support system more intelligent, which benefits from the increasing ability to analyze unstructured data For example, we can use image analysis and recognition technology to identify medical image (X-ray, CT, MRI) data, or mining medical literature data to establish a medical expert database (as IBM Watson did), so as to give doctors diagnosis and treatment advice In addition, the clinical decision support system can also make most of the workflow in the medical process flow to the nursing staff and assistant doctors, so that doctors can free themselves from the time-consuming simple consultation work, so as to improve the treatment efficiency 3 Transparency of medical data improving the transparency of medical process data can make the performance of medical practitioners and medical institutions more transparent and indirectly promote the improvement of medical service quality According to the operation and performance data set set set set up by the medical service provider, data analysis can be carried out and visual flow charts and dashboards can be created to promote information transparency The goal of the flow chart is to identify and analyze the sources of clinical variation and medical waste, and then optimize the flow Just publishing cost, quality and performance data, even if there is no corresponding material reward, can often promote the improvement of performance, so that medical service institutions can provide better services, so as to be more competitive Data analysis can simplify business processes, reduce costs through lean production, and find more efficient employees to meet the needs, so as to improve the quality of care and bring better experience to patients, as well as bring additional performance growth potential to medical service institutions Medicare and Medicaid are testing dashboards as part of building an active, transparent, open, collaborative government In the same spirit, the Centers for Disease Control and prevention has publicly released medical data, including business data Public release of healthcare quality and performance data can also help patients make more informed health care decisions, which will also help healthcare providers improve overall performance and become more competitive 4 Remote patient monitoring collects data from the remote monitoring system for chronic patients and feeds the analysis results back to the monitoring equipment (to check whether the patient is following the doctor's order), so as to determine the future medication and treatment plan In 2010, there were 150 million patients with chronic diseases in the United States, such as diabetes, congestive heart failure and hypertension, whose medical expenses accounted for 80% of the medical cost of the health care system Remote patient monitoring system is very useful for the treatment of patients with chronic diseases The remote patient monitoring system includes home cardiac monitoring equipment, blood glucose meter, and even chip tablet After the chip tablet is taken by the patient, the data is transmitted to the electronic medical record database in real time For example, remote monitoring can remind doctors to take timely treatment measures for patients with congestive heart failure to prevent emergencies, because one of the signs of congestive heart failure is weight gain caused by water conservation, which can be prevented by remote monitoring More benefits are that through the analysis of the data generated by the remote monitoring system, we can reduce the length of stay of patients, reduce the amount of emergency treatment, and achieve the goal of improving the proportion of home care and the amount of outpatient appointments 5 Advanced analysis of patient files advanced analysis in patient files can determine which people are susceptible to certain diseases For example, the application of advanced analysis can help identify patients with high risk of diabetes and enable them to receive preventive health care programs as early as possible These methods can also help patients find the best treatment plan from the existing disease management plan Payment / Pricing: for medical payers, big data analysis can better price medical services In the United States, for example, this would have the potential to create $50 billion a year, half of which would come from a reduction in national health spending 1 Automated systems automated systems (e.g., machine learning technology) detect fraud Industry insiders estimate that 2% - 4% of medical claims are fraudulent or unreasonable every year, so it is of great economic significance to detect claims fraud Through a comprehensive and consistent claim database and corresponding algorithm, we can detect the accuracy of claims and detect fraud This fraud detection can be retrospective or real-time In the real-time detection, the automation system can identify the fraud before the payment, and avoid the significant loss 2 Pricing plan based on health economics and efficacy research In drug pricing, pharmaceutical companies can participate in sharing treatment risks, such as making pricing strategies based on treatment effects The benefits to the payers are obvious, which helps to control the cost of health care For patients, the benefits are more immediate They can get innovative drugs at a reasonable price, and these drugs have been studied on the basis of efficacy For pharmaceutical companies, a better pricing strategy has many advantages They can get a higher market access possibility, or they can get a higher income through innovative pricing schemes and the introduction of more targeted curative drugs In Europe, there are some pilot drug pricing projects based on health economics and efficacy Some medical payers are using data analysis to measure the service provided by medical service providers, and pricing based on service level Medical service payers can pay based on medical effect They can negotiate with medical service providers to see whether the services provided by medical service providers meet specific benchmarks R & D medical product companies can use big data to improve R & D efficiency Take the United States, which will create more than $100 billion a year 1 Predictive modeling: in the R & D stage of new drugs, pharmaceutical companies can determine the most efficient input-output ratio through data modeling and analysis, so as to allocate the best resource combination The model is based on clinical medicine