Innovative Applications
Introduction
The health of every citizen should be among the top priorities of a nation. Even better, the health of every citizen should be in the top of all the priorities of a nation. This is because a community, nor a society cannot function given that its citizens are unwell. Their compromised health compromises their productivity and thus, affects many other aspects such as the economy and the education sector. The labor force would not be functional with unhealthy workers and may cause the downfall of most industries. As such, the optimization of the health care industry should be always done. Among the part of the health industry that should be optimized is the way information is handled, relayed and analyzed. Moreover, this part is critical since there are many concerns regarding patient information such as privacy and the proper usage of information. Furthermore, this paper will address such issue provided a scenario that will be outlined in the succeeding parts of the paper.
Background Information
Computer Assisted Coding in which Natural Language Text Processing (NLP), along with voice recognition and document imaging are among the new applications being introduced by the United Americas University Healthcare System into the Electronic Health Record (EHR). As the Chief Information Compliance Officer, it would be my responsibility to be able to put in certain procedures, policies, and data architectural models that will help the enterprise avoid complications from the new applications being installed.
EHR allows the digitization of patient medical records and their clinical workflow. This is especially helpful in lowering the cost with data handling over the long run when done efficiently (Hydari, Telang and Marella, 2015). EHR essentially allows the storage of a patient’s medical diagnosis, family history, radiology images, and the like to be stored in one place—allowing healthcare professionals to have a quick overview of all relevant medical information for the sake of the patient. Meanwhile, Computer Assisted Coding which uses NLP is used to recognize phrases or terms, and context. This is helpful since it produces necessary codes within the context of the medical information which helps health professionals increase their productivity or efficiency. In essence, this feature will help in decreasing errors from mislabeling or misinformation. To put it simply, it may be compared to that of the autocorrect feature of phones or the spelling checks of word processing applications—it gradually remembers stored data and form suggestions on how information processing may be optimized (Rinkle, 2015).
Aside from Computer Assisted Encoding, the enterprise also wishes to introduce speech or voice recognition and document imaging to optimize EHR. Speech Recognition is simply means that the health care professional can input data through speech. This saves time as it allows the health care professionals to attend to other important matters instead of typing or writing long reports (Nuance Communications, 2016). On the other hand, document imaging is used to easily store medical records that were on paper. This means that all information, including paper-based documents are to be collected into a single database for easier access (Liette, Meyers and Olenik, 2008).
There are risks associated with the use of EHR and there should be policies that should be placed to minimize such risk.
Preparation
The enterprise should make necessary arrangements for the installation of the new applications. Among this is the recap of the HIPAA responsibilities of the health institution. Moreover, the enterprise should also make arrangements on the individuals that should be designated to cover all grounds such as privacy concerns and patient protection. Lastly, the enterprise should document accordingly. This includes the documentation of why and how security measures were put in place, and updates on them. It is best to have both electronic and paper copies for such documentation (“Health Information Privacy and Security”, 2013).
Risk Analysis
The risks associated with the use of such applications in EHR should be considered. The enterprise should review the standard guidelines set by the authority and identify the vulnerabilities of such applications. In speech recognition for example, it is risky since audio may be recorded and replayed. However, if one recognizes this vulnerability, the enterprise may put in other additional security measures in conjunction with the application (“Health Information Privacy and Security”, 2013).
Conduct Checklist
There should be a standard with regards to the use of EHR and all of its new applications. Among these standards are integrity and security. With regards to integrity, the appropriateness of the handling of the data in HER will be evaluated along with the following: information accuracy, and ethical actions. For security the following will be considered: access, securing of all information and report of suspicious security frauds (“Compliance Checklist for Electronic Health Records”, 2015).
Risk Management
The enterprise should implement an action plan that will mitigate all the risks and vulnerabilities in the system. Moreover, educating the people involved in EHR may significantly help to protect sensitive information. Educating them may also help them to follow strict guidelines and thus, manage risks. The patients should likewise be oriented about the system that the enterprise uses. In this way, they will be knowledgeable of the benefits of the system (“Health Information Privacy and Security”, 2013).
Data Collection, Use and Maintenance
Procedure and policies should be implemented when it comes to the collection, use and maintenance of health care data. First, the collection should be done by only the trained health care professionals. Document imaging should be likewise done only on documents that have been verified. The procedures done to collect data should be likewise documented. This will minimize errors and reduce the risks associated with the system. Second, the data should only be accessible for use and modification by those with authorization. Voice recognition comes in handy in this aspect. Moreover, for data maintenance, NLP will come in handy since it will optimize the interpretation of the many inputs and analysis that should be done. Data should likewise be organized using a specific model.
Data Architectural Model for the Enterprise
The data that EHR receives is not homogenous in nature, they are not always in the same context and come from multiple sources. The complexity of medical data and the ever changing clinical inputs makes the maintenance of EHR a challenging task. Furthermore, a data architectural model should be utilized to help address such problem (El-Sappagh, El-Masri, Riad and Elmogy, 2012).
The basic EAV design utilizes three columns that make up a table. One of the column is for entities such as the identification of the patient, the second one is for the attribute like the name, and the last is for the value. This basic design allows the addition of more columns and the addition of more entities, attributes and values. It allows the flexibility of the queries and storage. It helps prevent null values, but since it is centered on the attributes, there is complexity in its nature. As such a modified EAV design will be used—multiple data type scheme. This allows the values to be of any nature. The values may be numbers, texts or a true or false statement. This design is further improved by storing information with different nature or types into different tables—allowing sorting of data. This data model then allows easier indexing and the enhancement of ease with data mining (El-Sappagh, El-Masri, Riad, and Elmogy, 2012).
References
Compliance Checklist for Electronic Health Records. (2015). Retrieved April 16, 2016, from https://www.cms.gov/Medicare-Medicaid-Coordination/Fraud-Prevention/Medicaid-Integrity-Education/Downloads/ehr-compliance-checklist.pdf.
El-Sappagh, S.H., El-Masri, S., Riad, A.M. & Elmogy, M. (2012). Electronic Health Record Data Model Optimized for Knowledge Discovery. International Journal of Computer Science Issues, 9(5). 329-338.
Health Information Privacy and Security. (2013). HealthIT. Retrieved April 16, 2016, from https://www.healthit.gov/providers-professionals/ehr-privacy-security/10-step-plan.
Hydari, M.Z., Telang, R. & Marella, W. (2015). Electronic Health Records and Patient Safety. Communications of the ACM, 58 (11). 30-32.
Liette, E., Meyers, C. & Olenik, K. (2008). Is Document Imaging the Right Choice for Your Organization?” Journal of AHIMA, 79 (11). 58-60.
Nuance Communications. (2016). Speech-Enabled EHR. Nuance. Retrieved April 16, 2016, from http://www.nuance.com/for-healthcare/by-solutions/speech-enabled-ehr/index.htm.
Rinkle,V. (2015). Computer Assisted Coding—A Strong Ally, Not a Miracle Aid. Journal of Health Care Compliance.