Health informatics
Health informatics is the study and implementation of computer science to improve communication, understanding, and management of medical information. It can be viewed as a branch of engineering and applied science.
The health domain provides an extremely wide variety of problems that can be tackled using computational techniques.
Health informatics is a spectrum of multidisciplinary fields that includes study of the design, development, and application of computational innovations to improve health care. The disciplines involved combine healthcare fields with computing fields, in particular computer engineering, software engineering, information engineering, bioinformatics, bio-inspired computing, theoretical computer science, information systems, data science, information technology, autonomic computing, and behavior informatics.
In academic institutions, health informatics includes research focuses on applications of artificial intelligence in healthcare and designing medical devices based on embedded systems. In some countries the term informatics is also used in the context of applying library science to data management in hospitals where it aims to develop methods and technologies for the acquisition, processing, and study of patient data, An umbrella term of biomedical informatics has been proposed.
Subject areas
Dutch former professor of medical informatics Jan van Bemmel has described medical informatics as the theoretical and practical aspects of information processing and communication based on knowledge and experience derived from processes in medicine and health care.The Faculty of Clinical Informatics has identified six high level domains of core competency for clinical informaticians:
- Health and Wellbeing in Practice
- Information Technologies and Systems
- Working with Data and Analytical Methods
- Enabling Human and Organizational Change
- Decision Making
- Leading Informatics Teams and projects.
Tools to support practitioners
- Assess information and knowledge needs of health care professionals, patients and their families.
- Characterize, evaluate, and refine clinical processes,
- Develop, implement, and refine clinical decision support systems, and
- Lead or participate in the procurement, customization, development, implementation, management, evaluation, and continuous improvement of clinical information systems.
Telehealth and telemedicine
is the distribution of health-related services and information via electronic information and telecommunication technologies. It allows long-distance patient and clinician contact, care, advice, reminders, education, intervention, monitoring, and remote admissions. Telemedicine is sometimes used as a synonym, or is used in a more limited sense to describe remote clinical services, such as diagnosis and monitoring. Remote monitoring, also known as self-monitoring or testing, enables medical professionals to monitor a patient remotely using various technological devices. This method is primarily used for managing chronic diseases or specific conditions, such as heart disease, diabetes mellitus, or asthma.These services can provide comparable health outcomes to traditional in-person patient encounters, supply greater satisfaction to patients, and may be cost-effective. Telerehabilitation is the delivery of rehabilitation services over telecommunications networks and the Internet. Most types of services fall into two categories: clinical assessment, and clinical therapy. Some fields of rehabilitation practice that have explored telerehabilitation are: neuropsychology, speech-language pathology, audiology, occupational therapy, and physical therapy. Telerehabilitation can deliver therapy to people who cannot travel to a clinic because the patient has a disability or because of travel time. Telerehabilitation also allows experts in rehabilitation to engage in a clinical consultation at a distance.
Decision support, artificial intelligence and machine learning in healthcare
A pioneer in the use of artificial intelligence in healthcare was American biomedical informatician Edward H. Shortliffe. This field deals with utilization of machine-learning algorithms and artificial intelligence, to emulate human cognition in the analysis, interpretation, and comprehension of complicated medical and healthcare data. Specifically, AI is the ability of computer algorithms to approximate conclusions based solely on input data. AI programs are applied to practices such as diagnosis processes, treatment protocol development, drug development, personalized medicine, and patient monitoring and care. A large part of industry focus of implementation of AI in the healthcare sector is in the clinical decision support systems.As more data is collected, machine learning algorithms adapt and allow for more robust responses and solutions. Numerous companies are exploring the possibilities of the incorporation of big data in the healthcare industry. Many companies investigate the market opportunities through the realms of "data assessment, storage, management, and analysis technologies" which are all crucial parts of the healthcare industry. The following are examples of large companies that have contributed to AI algorithms for use in healthcare:
- IBM's Watson Oncology is in development at Memorial Sloan Kettering Cancer Center and Cleveland Clinic. IBM is also working with CVS Health on AI applications in chronic disease treatment and with Johnson & Johnson on analysis of scientific papers to find new connections for drug development. In May 2017, IBM and Rensselaer Polytechnic Institute began a joint project entitled Health Empowerment by Analytics, Learning and Semantics, to explore using AI technology to enhance healthcare.
- Microsoft's Hanover project, in partnership with Oregon Health & Science University's Knight Cancer Institute, analyzes medical research to predict the most effective cancer drug treatment options for patients. Other projects include medical image analysis of tumor progression and the development of programmable cells.
- Google's DeepMind platform is being used by the UK National Health Service to detect certain health risks through data collected via a mobile app. A second project with the NHS involves analysis of medical images collected from NHS patients to develop computer vision algorithms to detect cancerous tissues.
- Tencent is working on several medical systems and services. These include AI Medical Innovation System, an AI-powered diagnostic medical imaging service; WeChat Intelligent Healthcare; and Tencent Doctorwork.
- Intel's venture capital arm Intel Capital recently invested in startup Lumiata which uses AI to identify at-risk patients and develop care options.
- Kheiron Medical developed deep learning software to detect breast cancers in mammograms.
- Fractal Analytics has incubated Qure.ai which focuses on using deep learning and AI to improve radiology and speed up the analysis of diagnostic x-rays.
- Neuralink has come up with a next generation neuroprosthetic which intricately interfaces with thousands of neural pathways in the brain. Their process allows a chip, roughly the size of a quarter, to be inserted in place of a chunk of skull by a precision surgical robot to avoid accidental injury.
It also works in the field of medical imaging. Similar robots are also being made by companies such as UBTECH and Softbank Robotics. The Indian startup Haptik recently developed a WhatsApp chatbot which answers questions associated with the deadly coronavirus in India. With the market for AI expanding constantly, large tech companies such as Apple, Google, Amazon, and Baidu all have their own AI research divisions, as well as millions of dollars allocated for acquisition of smaller AI based companies. Many automobile manufacturers are beginning to use machine learning healthcare in their cars as well. Companies such as BMW, GE, Tesla, Toyota, and Volvo all have new research campaigns to find ways of learning a driver's vital statistics to ensure they are awake, paying attention to the road, and not under the influence of substances or in emotional distress. Examples of projects in computational health informatics include the COACH project. Computational health informatics aids in identifying population inequities.
Clinical Research Informatics
Clinical research informatics is a sub-field of health informatics that tries to improve the efficiency of clinical research by using informatics methods. Some of the problems tackled by CRI are: creation of data warehouses of health care data that can be used for research, support of data collection in clinical trials by the use of electronic data capture systems, streamlining ethical approvals and renewals, maintenance of repositories of past clinical trial data. CRI is a fairly new branch of informatics and has met growing pains as any up and coming field does. Some issue CRI faces is the ability for the statisticians and the computer system architects to work with the clinical research staff in designing a system and lack of funding to support the development of a new system.Researchers and the informatics team have a difficult time coordinating plans and ideas in order to design a system that is easy to use for the research team yet fits in the system requirements of the computer team. The lack of funding can be a hindrance to the development of the CRI. Many organizations who are performing research are struggling to get financial support to conduct the research, much less invest that money in an informatics system that will not provide them any more income or improve the outcome of the research. Ability to integrate data from multiple clinical trials is an important part of clinical research informatics. Initiatives, such as PhenX and Patient-Reported Outcomes Measurement Information System triggered a general effort to improve secondary use of data collected in past human clinical trials. CDE initiatives, for example, try to allow clinical trial designers to adopt standardized research instruments.
A parallel effort to standardizing how data is collected are initiatives that offer de-identified patient level clinical study data to be downloaded by researchers who wish to re-use this data. Examples of such platforms are Project Data Sphere, dbGaP, ImmPort or Clinical Study Data Request. Informatics issues in data formats for sharing results are important challenges within the field of clinical research informatics. There are a number of activities within clinical research that CRI supports, including:
- More efficient and effective data collection and acquisition
- Improved recruitment into clinical trials
- Optimal protocol design and efficient management
- Patient recruitment and management
- Adverse event reporting
- Regulatory compliance
- Data storage, transfer, processing and analysis
- Repositories of data from completed clinical trials
One of the fundamental elements of biomedical and translation research is the use of integrated data repositories. A survey conducted in 2010 defined "integrated data repository" as a data warehouse incorporating various sources of clinical data to support queries for a range of research-like functions. Integrated data repositories are complex systems developed to solve a variety of problems ranging from identity management, protection of confidentiality, semantic and syntactic comparability of data from different sources, and most importantly convenient and flexible query.
Development of the field of clinical informatics led to the creation of large data sets with electronic health record data integrated with other data. Types of data repositories include operational data stores, clinical data warehouses, clinical data marts, and clinical registries. Operational data stores established for extracting, transferring and loading before creating warehouse or data marts. Clinical registries repositories have long been in existence, but their contents are disease specific and sometimes considered archaic. Clinical data stores and clinical data warehouses are considered fast and reliable. Though these large integrated repositories have impacted clinical research significantly, it still faces challenges and barriers. Following is a list of major patient data warehouses with broad scope, with variables including laboratory results, pharmacy, age, race, socioeconomic status, comorbidities and longitudinal changes:
| Warehouse | Sponsor | Main location | Extent | Access |
| Epic Cosmos | Epic Systems | United States | 296 million patients | Free for participating organizations |
| PCORnet | Patient-Centered Outcomes Research Institute | United States | 140 million patients | Free for participating organizations |
| OLDW | Optum | United States | 160 million patients | For a fee, or for free through certain academic institutions |
| EHDEN | Innovative Health Initiative of the European Union | Europe | 133 million patients | Free for discovery. May have fees for secondary use. |
One big problem is the requirement for ethical approval by the institutional review board for each research analysis meant for publication. Some research resources do not require IRB approval. For example, CDWs with data of deceased patients have been de-identified and IRB approval is not required for their usage. Another challenge is data quality. Methods that adjust for bias assume that a complete health record is captured. Tools that examine data quality help in discovering data quality problems.