The application of big data in the medical industry can play an active role in the following aspects:
(1) Serving residents. Resident health guidance service system to provide precision medicine, personalized health care guidance, so that residents can maintain continuity of services in the hospital, community and online. For example, it provides cardiovascular, cancer, hypertension, diabetes and other chronic disease intervention, management, health warning and health education (health care program subscription, push); at the same time, it reduces the length of hospitalization of patients, reduces the volume of emergency room visits, and increases the proportion of home care and the volume of outpatient doctor appointments.
(2) Serving Physicians. Clinical decision support, such as medication analysis, adverse drug reactions, disease complications, correlation analysis of treatment effects, antibiotic application analysis; or the development of personalized treatment plans.
(3) Service research. Including disease diagnosis and prediction, statistical tools and algorithms to improve clinical trial design, and analysis and processing of clinical trial data, such as identifying disease susceptibility genes and extreme performance populations for major diseases; and providing optimal treatment pathways.
The Internet is a magical big network, medical big data and software customization is also a model, here quote, the beginning of this hand technique of the number is a handful of seven in the middle of the three children of zero in the end of the Surabaya II five zero, according to the order of the combination can be found, I would like to say that, unless you want to do or know about this aspect of the contents of the, if it is just a hilarious thing to do, don't come.
(4) Service management organization. Normative medication evaluation, management performance analysis; evaluation of preventive interventions and measures for epidemics, acute diseases, etc.; public health monitoring, payment (or pricing), optimization of clinical pathways, etc.
(5) Public health services. Including monitoring and early warning of health-threatening factors, network platforms, community services, and other aspects.
In addition to the Internet companies that started utilizing big data earlier, the healthcare industry is probably one of the first traditional industries to let big data analytics flourish. The medical industry has long encountered the challenge of massive data and unstructured data, and in recent years many countries have been actively promoting the development of medical information technology, which makes many medical institutions have the funds to do big data analysis. As a result, the healthcare industry will be the first to enter the era of big data, along with industries such as banking, telecommunications and insurance. Below is a list of 15 applications in 5 major areas of the healthcare service industry (clinical operations, payment/pricing, R&D, new business models, and public health), scenarios in which the analysis and application of big data will play a huge role in improving healthcare efficiency and healthcare outcomes.
Clinical operations
There are five major scenarios for big data applications in clinical operations. McKinsey estimates that if these applications were fully adopted, national healthcare spending would be reduced by $16.5 billion a year in the U.S. alone.
1. Comparative Effectiveness Research
The optimal treatment pathway for a given patient can be found by comprehensively analyzing patient characteristic data and efficacy data and then comparing the effectiveness of multiple interventions.
Efficacy-based research includes comparative effectiveness studies. Studies have shown that for the same patient, healthcare providers vary in the approach and effectiveness of care, as well as in cost. Accurately analyzing large data sets that include patient sign data, cost data, and efficacy data can help physicians determine the most clinically effective and cost-efficient treatments. Realization of CER in the health care system will potentially reduce over-treatment (e.g., avoiding treatments that have more significant side effects than efficacy), as well as under-treatment. In the long run, both over- and under-treatment will have a negative impact on the patient's health, as well as incurring higher healthcare costs.
Many healthcare organizations around the world (e.g., NICE in the U.K., IQWIG in Germany, the Canadian General Pharmaceutical Inspection Service, etc.) have already begun to implement CER programs, with some initial success, and the Recovery and Reinvestment Act, passed in the U.S. in 2009, was a first step in this direction. Under this Act, the Federal Coordinating Council for Comparative Effectiveness Research (FCCER) was established to coordinate comparative effectiveness research across the federal government and to allocate $400 million in funding. There are a number of potential issues that will need to be addressed if this investment is to be successful, such as the consistency of clinical and insurance data, as the current lack of EHR standards and interoperability makes it difficult to integrate disparate datasets in a rush to deploy EHRs on a wide scale. Another example is the issue of patient privacy. It is not easy to provide sufficiently detailed data to ensure the validity of analysis results while protecting patient privacy. There are also institutional issues, such as current U.S. law that prohibits Medicare and the Centers for Medicare & Medicaid Services (Medicare payers) from using cost/benefit ratios to make reimbursement decisions, which would make it difficult for them to implement even if they were to find a better way to do so through big data analytics.
2. Clinical Decision Support Systems (CDSS)
Clinical Decision Support Systems (CDSS) can improve efficiency and quality of care. Current clinical decision support systems analyze entries entered by physicians and compare them to medical guidelines, thereby alerting physicians to prevent potential errors, such as adverse drug reactions. By deploying these systems, healthcare providers can reduce malpractice rates and claims, especially those resulting from clinical errors. In a study at the Metropolitan Pediatric Intensive Care Unit in the U.S., clinical decision support systems cut the number of adverse drug reaction events by 40 percent in just two months.
Big data analytics will make clinical decision support systems smarter, thanks to the growing ability to analyze unstructured data. For example, image analysis and recognition technologies can be used to recognize medical imaging (X-ray, CT, MRI) data, or to mine medical literature data to build a database of medical experts (as IBMWatson does), so as to give doctors advice on diagnosis and treatment. In addition, clinical decision support systems can improve the efficiency of treatment by enabling much of the workflow in the medical process to flow to caregivers and physician assistants, freeing physicians from time-consuming, simple consultation tasks.
3. Transparency of medical data
Improving the transparency of medical process data can make the performance of healthcare practitioners and healthcare organizations more transparent, and indirectly contribute to the improvement of the quality of healthcare services.
Based on the operational and performance datasets set by healthcare providers, data can be analyzed and visual process maps and dashboards can be created to promote information transparency. The goal of process mapping is to identify and analyze sources of clinical variation and medical waste and then optimize processes. Simply publishing cost, quality, and performance data, even without the accompanying material incentives, can often lead to improved performance and enable healthcare providers to deliver better services and thus be more competitive.
Data analytics can lead to streamlining of business processes, reducing costs through lean manufacturing, and finding more efficient employees who work in line with demand, leading to improved quality of care and a better patient experience, as well as additional growth potential for healthcare providers. The Centers for Medicare and Medicaid Services is testing dashboards as part of building a proactive, transparent, open, and collaborative government. In the same spirit, the U.S. Centers for Disease Control and Prevention .
Publicly releasing health care quality and performance data can also help patients make more informed health care decisions, which will also help health care providers improve their overall performance and thus become more competitive.
4. Remote Patient Monitoring
Data is collected from remote monitoring systems for chronically ill patients and analyzed and fed back to the monitoring device (to see if the patient is complying with the doctor's orders) to determine future medication and treatment plans.
In 2010, there were 150 million chronically ill patients in the United States, such as those with diabetes, congestive heart failure, and high blood pressure, who accounted for 80 percent of the health care costs of the health care system. Remote patient monitoring systems are very useful in treating patients with chronic diseases. Remote patient monitoring systems include home heart monitoring devices, blood glucose meters, and even microchip tablets, which are ingested by the patient and transmit data in real time to an electronic medical record database. As an example, remote monitoring can alert physicians to take timely treatment measures for patients with congestive heart failure and prevent emergencies, since one of the hallmarks of congestive heart failure is weight gain due to water retention, which can be prevented through remote monitoring. An added benefit is that by analyzing the data generated by the remote monitoring system, it is possible to reduce the length of hospital stays, reduce the number of emergencies, and achieve the goal of increasing the percentage of home care and outpatient doctor appointments.
5. Advanced analysis of patient records
Advanced analytics can be applied to patient records to determine who is susceptible to certain diseases. For example, advanced analytics can be applied to help identify patients who are at high risk of developing diabetes, so that they can receive preventive care programs as early as possible. These methods can also help patients find the best treatment options from among the disease management programs that already exist.
Payment/Pricing
For healthcare payers, big data analytics can be used to better price healthcare services. In the U.S., for example, this would have the potential to create $50 billion in annual value, half of which would come from lower national healthcare spending.
1. Automated systems
Automated systems (e.g., machine-learning technology) detect fraud. The industry assesses that 2% to 4% of medical claims are fraudulent or unjustified each year, so detecting claims fraud makes tremendous economic sense. With a comprehensive and consistent claims database and corresponding algorithms, it is possible to test claims for accuracy and detect fraud. This fraud detection can be retroactive or real-time. In real-time detection, automated systems can identify fraud before payments are made, avoiding significant losses.
2. Pricing programs based on health economics and efficacy studies
When it comes to drug pricing, pharma companies can participate in sharing therapeutic risk, for example, by developing a pricing strategy based on therapeutic outcomes. The benefits to healthcare payers are obvious, in terms of controlling the cost of healthcare expenditures. For patients, the benefits are more immediate. They have access to innovative medicines at a reasonable price, and these medicines have been subjected to efficacy-based research. For pharmaceutical product companies, the benefits of better pricing strategies are numerous. They can gain higher market access possibilities and also higher revenues through innovative pricing schemes with more targeted efficacy-based drug launches.
In Europe, there are now a number of pilot programs for pricing medicines based on health economics and efficacy.
Some healthcare payers are using data analytics to measure the services of healthcare providers and base pricing on service levels. Healthcare payers can pay based on healthcare outcomes, and they can negotiate with healthcare providers to see if the services provided by the provider meet specific benchmarks.
R&D
Medical product companies can use big data to improve R&D efficiency. Taking the U.S. as an example, this would create more than $100 billion in value per year.
1. Predictive modeling
Pharmaceutical companies can use data modeling and analysis in the R&D phase of a new drug to determine the most efficient input-to-output ratio, so as to equip themselves with the optimal combination of resources. Models are based on data sets from the preclinical phase of a drug's clinical trials as well as data sets from the early clinical phase to predict clinical outcomes in as timely a manner as possible. Evaluation factors include product safety, efficacy, potential side effects, and overall trial results. Predictive modeling can reduce the cost of research and development for pharmaceutical product companies by allowing them to hold off on studying suboptimal drugs or stop expensive clinical trials on suboptimal drugs after predicting the clinical outcome of the drug through data modeling and analysis.
In addition to R&D costs, pharma companies get a faster payback. Through data modeling and analysis, pharmaceutical companies can bring drugs to market faster, producing more targeted drugs with higher potential market returns and treatment success rates. It turns out that the average new drug takes about 13 years to develop and bring to market, and using predictive modeling can help pharmaceutical companies bring new drugs to market three to five years earlier.
2. Statistical Tools and Algorithms to Improve Clinical Trial Design
The use of statistical tools and algorithms can improve the design of clinical trials and make it easier to recruit patients during the clinical trial phase. Mining patient data to assess whether recruited patients are eligible for a trial speeds up the clinical trial process, suggests more effective clinical trial designs, and enables the identification of the most appropriate clinical trial sites. For example, sites that have a large number of potentially eligible patients for a clinical trial may be ideal, or they may be able to balance the size and characteristics of the trial patient population.
3. Analysis of clinical trial data
Analysis of clinical trial data and patient records can identify additional indications for a drug and detect side effects. After analyzing clinical trial data and patient records, drugs can be repositioned or marketed for additional indications. Real-time or near-real-time collection of adverse reaction reports can facilitate pharmacovigilance (pharmacovigilance is a system of safety assurance for marketed drugs that monitors, evaluates and prevents adverse drug reactions). Or in cases where clinical trials hint at something but there are not enough statistics to prove it, analysis based on big data from clinical trials can now give evidence.
These analytic programs are very important. It can be seen that the number of drug withdrawals has reached record highs in recent years, and drug withdrawals can be devastating for pharmaceutical companies. the painkiller Vioxx, which was withdrawn from the market in 2004, cost Merck $7 billion, and 33 percent of shareholder value in just a few days.
4. Personalized therapy
Another promising big data innovation in research and development is the development of personalized therapies through the analysis of large datasets, such as genomic data. This application examines the relationship between genetic variation, susceptibility to specific diseases, and response to particular drugs, and then takes into account an individual's genetic variation in the drug development and dosing process.
Personalized medicine can improve health care outcomes, such as providing early detection and diagnosis of disease symptoms before they occur in patients. In many cases, patients are treated with the same regimen but have different outcomes, in part because of genetic variation. Adopting different regimens for different patients, or adjusting drug dosages to fit the patient's condition, can reduce side effects.
Personalized medicine is still in its early stages. McKinsey estimates that in some cases, healthcare costs can be reduced by 30% to 70% by reducing the amount of medication prescribed. For example, early detection and treatment can significantly reduce the burden of lung cancer on the health system, as surgery at an early stage costs half as much as later treatment.
5. Analysis of Disease Patterns
Analysis of disease patterns and trends can help medical product companies make strategic R&D investment decisions, helping them optimize their R&D focus and optimize the resources they are equipped with.
New Business Models
Big data analytics can bring new business models to the healthcare services industry.
Aggregating Patient Clinical Records and Medicare Datasets
Aggregating patient clinical records and Medicare datasets and performing advanced analytics will improve decision-making for healthcare payers, healthcare providers, and pharmaceutical companies. For pharmaceutical companies, for example, they will be able to not only produce drugs with better efficacy, but also ensure that they are marketable. The market for clinical records and Medicare datasets is just beginning to develop, and the rate of expansion will depend on how quickly the healthcare industry completes the development of EMRs and evidence-based medicine.
Public Health
The use of big data can improve public health surveillance. Public ****health departments can rapidly detect infectious diseases, conduct comprehensive outbreak surveillance, and respond quickly by integrating disease surveillance and response programs through a nationwide database of patients' electronic medical records. This will provide many benefits, including reduced medical claims expenditures, lower rates of infectious disease infection, and faster detection of new infectious diseases and outbreaks by health departments. By providing accurate and timely public health counseling, there will be a significant increase in public health risk awareness and a reduction in the risk of infectious disease infection. All of this will help make people's lives better.