Improvements to Healthcare through the use of Data Warehouse
Claude Louis-Charles, PhD
For many years, multiple organizations across all sectors of the economy had unintegrated data systems. With time, there was a realization that unintegrated data caused a lot of pain, struggles, and inconsistencies. It was discovered that it was not possible to look across an organization’s data and make an informed decision. This led to a rise in the concept of data warehousing, which required that the disparate systems in an organization that held different types of data be integrated. The data warehouses were integrated to act as decision support systems (DSS) (Padmanabhan & Patki, 2016). Now, the integration of data in companies is one of the core necessities for making informed decisions. Healthcare is one of the fastest growing, largest, and heavily information-based industry in the world. However, unlike other sectors such as transport, production, marketing, management, finance, and sales, healthcare did not benefit significantly from data warehousing and DSS with open arms. This was because data in the healthcare and medical field is completely different from the one in the other industries. However, with time there has been a need for integrating data in the healthcare industry. With technology, healthcare has opened up to adopting extensive DSS.
Previous Data Warehousing Gap in Healthcare
There was a need for data warehousing in the healthcare industry. However, as earlier stated, DSS did not benefit healthcare as well as it had other industries. Data needs in healthcare and medicine are completely different from the ones in other industries. Data collection in healthcare, compared to other industries is completely different. In the transport industry, examples of data include a customer reserving a seat, loading and delivery of cargo, flight, train, or bus taking off, and similar modes of transactions. In the business industry, data and transitions are in form of repetitive numerical data. On the other hand, in healthcare, there are never such repetitive forms of data. The data relates to outpatient and inpatient cases, emergency care, doctor visitations and procedures, and administering different kinds of treatment. Therefore, data in the healthcare industry is unique in most cases, unlike in other industries (Visscher et al., 2017).
Data in healthcare is mainly textual in comparison to other industries where it is numerical. The nature of the interactions between the patients and doctors or caregivers is different from the transactions in other industries, where the data is measurable, countable, and numerical. Doctors or caregiver and patients, in most cases, communicate verbally, which can be recorded in textual form. Doctors record the patients’ information in text form. For example, a hospital records a patient’s stay in text form, while the nurses record procedures in text form (Inmon, 2005). Data warehousing, on the other hand, for a long time, had been developed and made primarily for numerical data use. DSS was made to help integrate data that is highly dominated by numerical figures. Thus, healthcare could not benefit significantly from such DSS. However, with technology, research, and different approaches to data warehouses, textual DSS have been successfully developed to support the healthcare field. Integrating textual data in data warehouses has been achieved to accommodate information from different sources in the healthcare setting. Different doctors from different disciplines such as pediatrics, epidemiology, gynecology cardiology, and orthopedics can feed the data warehouse.
Initiatives Made Possible by DSS
Textual data warehouses have helped the healthcare industry harness, manage, and manipulate data in hospitals and the field at large in making it benefit from data warehousing just like other industries. Data warehouses have become key elements in improving healthcare in the world (Silver et al., 2011). Data has been brought together using DSS to make clearer pictures in various aspects of the industry. Quality data reporting and storage has benefited the industry and resulted in the rise of initiatives such as proactive treatment programs, chronic disease monitoring, and development of population decision support systems.
Proactive Treatment Programs
In the business world, automation of various steps and facilities has been developed to simplify the process of doing business. Automated dealerships based on data warehousing have been successfully integrated. In healthcare, doctors, hospitals, and patients have also benefited from automation services such as sending of health maintenance messages to patients based on DSS. To achieve such services in the healthcare field, sophisticated DDS are developed to distribute data in all medical institution applications as well as the hospital billing system. This will help to improve the quality of health care and benefit the patients by reducing medical costs through preventive treatment. Moreover, proactive programs support positive patient participation, outcomes, and satisfaction. Sending patients reminders of their upcoming tests, visits, immunizations, or even the status of their medical reports keeps them on their toes and helps them remain active and cognizant of their health status (Visscher, et al., 2017). Increasing the number of patients receiving such information increases the quality of healthcare.
In the scenario of newborn and childhood immunization, proactive programs become apparent. The pediatric tends to the child face-to-face by administering different medications to protect it from different dangers in the specific region. Also, the pediatric has to schedule visits for probably hundreds of children. Systems such as Electronic Health Systems (EHR) always remind the doctor the immunizations to offer and at what time. At the same time, such systems detail the child’s history. However, a doctor cannot perform immunization on absent children. DDS, on the other hand, ensure that both the doctor and the patients receive information on the visits, making processes such as immunization highly successful. DSS simplifies the scheduling of processes such as immunization by reporting a printout of patients who ought to be scheduled for visits. The data set includes the patients’ contact information, their medical histories, and their demographic. It also accurately connects patients and their doctors devoid of mistakes.
Monitoring Chronic Diseases
Chronic diseases are more sophisticated compared to other diseases. Chronic conditions such as obesity, cancer, and diabetes are some of the major health issues facing people. There has been little success at eradicating them. Managing, reporting, and saving data on such diseases requires quality reporting to guarantee positive impact on research and patient outcomes. Diabetes is one of the most common chronic ailments, facing a significantly growing population. Data management systems have been used to improve healthcare quality. Diabetes patients face the risk of acquiring other preventable high-cost diseases if the condition is not monitored properly. DSS have also helped identify many people who face the risk of getting the condition. Therefore, DSS have assisted greatly in the prevention of the disease. Reminding patients on their periodic tests has also improved healthcare by monitoring the condition and maintaining it at safe levels.
Data warehouses have been used as a surveillance system for chronic diseases. The system helps to get a better insight into various behavior risks that often lead to chronic conditions. Personal information is used to identify individuals of interest, their location, and the data related to them. Different behavioral risks by individuals based on different attributes such as age, location, marital status, and past health records are reported correctly by DSS. By using the health data collected, the study of the relationship between the various risk behaviors and certain chronic diseases such as mental health problems, cancer, and obesity is enhanced. In this way, major causes of certain chronic diseases can be established. This aids greatly in formulating the appropriate preventive measures. The DSS produce chronic diseases data important to multiple people and sectors such as the government. These parties can then use the data to decide on the right investments in healthcare for certain diseases.
Population Decision Support Systems
Data warehousing and DSS in the healthcare industry have made it possible to build a population decision support system that can monitor performance at different industry levels. After treatment, the patient can comment on their experience on the system. The system then collects all the data to evaluate the levels of customer satisfaction (George, Kumar & Kumar, 2015). Patients can comment by either rating their experience or sending a text that can be interpreted by the system or forwarded to the customer satisfaction assessment team. The patients can also benefit from a system that considers their busy calendar by giving them appointments at the most convenient times. The system’s workflow tools remind the caregivers of the patients that should be called to schedule important appointments and optimize any tests that might be taken during the visit (Roski, Bo-Linn & Andrews, 2014). If test results take a long time, the system helps schedule two encounters; one for taking the test, and the other for treatment based on the results.
On the other hand, caregivers benefit from a smooth workflow that entails knowledge of the patients they should attend to and at what time. The data warehouse schedules visit in a non-confusing manner, helping the doctors manage their patients as efficiently as possible. At the operational level, based on the number of patients, the management can then understand when to add more caregivers and when to reduce them (George, Kumar & Kumar, 2015). The management is also equipped with the data required to understand when to intervene with doctors, processes, or other inputs, to avoid minor hiccups from exploding into uncontrollable situations (McGinley, 2009). The smooth workflow creates a positive image of the health centers.
Data Warehouse Viewpoints
Data in a healthcare facility requires safe, quality, and correct integration from operational reporting, institution-wide reporting, and outreach opportunities.
Operational Reporting
At the operational reporting viewpoint, the management team at a health facility can spot gaps or problems using integrated data systems. After identifying the gaps, the management then offers solutions and increases the quality of healthcare offered by their team. The management can also compare different approaches by the physicians and practices. Initiatives to share the best approaches by the particular individuals are then started (Arunachalam, Page & Thorsteinsson, 2017). Moreover, the least working procedures and methods are abandoned. The viewpoint also offers an evaluation of how caregivers can be assessed using DSS. This helps reward the best performing medics and aids the least performing ones raise their standards.
Institution-Wide Reporting
It is important to assess the performance of a healthcare facility for rating and comparison with other facilities. Such DSS reports can also be used to identify the weak areas in the facilities and help in improving on the identified failings with the quality healthcare goal (Inmon, 2007). Detecting of areas that require additional resources can also be done on the data warehouse. The management can also use the data to avoid negative publicity, which ensures the growth of the facility. Data warehousing offers quick correct reports for the management team when they are reporting to the board members.
Outreach Opportunities
Outreach opportunities help deal with patients at individual levels using their files in the data warehouse. DSS provides a framework that makes it possible for both patient and caregivers to get alerts on important factors such as missed visits or tests. Personalized data in the data warehouse promotes proactive treatment by comparing a condition with all the risks associated and then offering an appropriate preventive measure.
Benefits of Data Warehousing In Healthcare
Quick access to desired data
Data warehousing has made it possible for one to access large sets of data within seconds (Inmon, 2007). This adds value to the health facilities as the managers can get daily or weekly reports on patients’ progress and alert doctors to particular cases that require special attention. The management can also monitor whether the caregivers adhere to the set standards.
Establishing and maintaining a smooth workflow
Hundreds of patients can be managed into different schedules. Timely reminders sent to patients and doctors for encounters support efficient workflow and quality preparation. Moreover, timely notices such as recalling patients for medications or vaccinations not administered, possibly due to shortages, help maintain the patients’ health (McGinley, 2009). Automation of services such as scheduling helps reduce the cumbersome manual process which is prone to mistakes.
Issues relating to the quality of care can also be identified with ease
The time spent on patients about their financial class can be identified and dealt with immediately. Caregivers can tend to spend more time focusing on the patients from higher income than those from a poor background (Koh & Tan, 2011). This is not ethical and can be detected using the DDS. According to Koh and Tan (2011), there should be no disparities in the provision of health care.
Reduction of risks through early identification of risky area
Managers can detect risks through identification of gaps in the facilities (Wang, Kung & Byrd, 2018). According to Wang, Kung, and Byrd (2018), risky activities such as the interpretation of incomplete tests during treatment can be detected through time spent on the tests. This is vital as incomplete tests can lead to the wrong diagnosis, which can cause problems on the patient and the facilities. DSS can detect flaws and help remedy them to improve the patients’ outcomes.
Increased performance
Data warehousing increases the performance of the health facilities, giving them a positive image. Eventually, the popularity and preference of a facility goes up, giving it a chance to negotiate better contracts based on the improved performance.
Challenges of DDS in Healthcare
Leakage of patient data
It is mandatory to ensure the data security and privacy of patients’ information. Some of the consequences of patient data leakage include violations, lawsuits, and a bad image. These consequences can all negatively affect the facility. Therefore, it is necessary to ensure that unauthorized personnel do not get access to the patients’ data.
Convincing caregivers embrace data warehousing
Convincing the caregivers to embrace the importance of data warehouse is a challenge. The accuracy of reporting data to the DSS legitimizes the data warehouse and makes it a vital resource in the facility. However, caregivers can input summarized data or only portions of it. This would render the data useless. Many caregivers have raised concerns about the accuracy of data. At times, they ignore critical data about a patient in the data warehouse (Inmon, 2007).
The complexity of clinical data
This is mainly experienced when reporting patient care and outcomes. At times, patients can be allergic to certain medications that, according to the system, must be administered for their condition. The caregivers then opt for a different medication. Despite taking the right precautions, this can lead to negative ratings. The DSS must take into consideration all such scenarios. This is a complex situation as some cases cannot be predicted (Nelson & Staggers, 2016).
Conclusion
Data warehousing was initially not integrated into the healthcare industry mainly because of the difference in data types in comparison to other industries. DDS was developed for numerically dominated data. Therefore, it could not significantly benefit the healthcare industry as it is dominated by textual data. With time, technology has made it possible for the existence of textual data housing. The healthcare industry integrated DSS to benefit from data integration, just like other industries. Initiatives such as proactive treatment programs, chronic disease monitoring, and development of population decision support systems have been supported by data warehousing. Proactive programs have helped automate communication with the patient, reminding them of appointments, tests, or relevant information concerning their health. Also, monitoring chronic diseases has improved as a result of data warehousing as it has facilitated the collection of more accurate data. Besides, population decision support systems have made it possible to monitor the performance of healthcare providers. In healthcare data warehousing, there are several points of view. They include operational, institution-wide, and outreach opportunities. There are multiple benefits such as quick access to data associated with data warehousing in healthcare. Also, there are challenges such as the one of ensuring data security facing DSS in health care.
References
Arunachalam, S., Page, T., & Thorsteinsson, G. (2017). Healthcare data warehousing. I-manager's Journal on Computer Science, 4(4), 1-13.
George, J., Kumar, V., & Kumar, S. (2015, July). Data warehouse design considerations for a healthcare business intelligence system. Proceedings of the World Congress on Engineering, (1), 1-3.
Inmon, B. (2007, January 1). Data warehousing in a healthcare environment. Retrieved from http://tdan.com/data-warehousing-in-a-healthcare-environment/4584
Inmon, W. H. (2005). Building the data warehouse. Hoboken, NJ: John wiley & sons.
Koh, H. C., & Tan, G. (2011). Data mining applications in healthcare. Journal of Healthcare Information Management, 19(2), 64-72.
McGinley, P. (2009, August 3). Quality reporting through a data warehouse. Retrieved from https://www.psqh.com/analysis/quality-reporting-through-a-data-warehouse/
Nelson, R., & Staggers, N. (2016). Health informatics e-book: An interprofessional approach. Amsterdam, Netherlands: Elsevier Health Sciences.
Padmanabhan, R., & Patki, A. U. (2016). U.S. patent no. 9,430,505. Washington, DC: U.S. Patent and Trademark Office.
Roski, J., Bo-Linn, G. W., & Andrews, T. A. (2014). Creating value in health care through big data: opportunities and policy implications. Health Affairs, 33(7), 1115-1122.
Silver, M., Sakata, T., Su, H. C., Herman, C., Dolins, S. B., & O Shea, M. J. (2011). Case study: How to apply data mining techniques in a healthcare data warehouse. Journal of Healthcare Information Management, 15(2), 155-164.
Visscher, S. L., Naessens, J. M., Yawn, B. P., Reinalda, M. S., Anderson, S. S., & Borah, B. J. (2017). Developing a standardized healthcare cost data warehouse. BMC Health Services Research, 17(1), 396.
Wang, Y., Kung, L., & Byrd, T. A. (2018). Big data analytics: Understanding its capabilities and potential benefits for healthcare organizations. Technological Forecasting and Social Change, 126, 3-13.
