Workflow, Data Mining and Advancing Patient Outcomes – Annotated Bibliography


At the center of hospital bustle, overwhelmed staff scramble to remain on top of the paperwork cycle. Miscommunication and frequent errors frustrate nurses and inhibit the delivery of healthcare. Approvals are delayed, patients are left waiting for long hours, and information is misplaced – proving a critical challenge for a healthcare facility. While most hospitals have already adopted EHRs, and medical software, other fundamental processes like patient transfers to other facilities remain disorganized.  Omitting a single step in hospital workflows can create detrimental impacts for patients and hospitals alike. Managing different types of patient workflow in a facility is key to smooth operations. Patient workflow management refers to streamlining various tasks needed to process information by automating predictable and repetitive procedures. Patient workflow solutions assist in minimizing human errors, improve compliance to rules and regulations, reduce redundancies, oversights and ensure patients receive quality treatments. Data mining is a potential approach for building knowledge obtained from practice data in decision making. This annotated bibliography demonstrates how workflow and data mining helps in advancing patient outcomes.

Annotated Bibliography

Baek, H., Cho, M., Kim, S., Hwang, H., Song, M., & Yoo, S. (2018). Analysis of length of hospital stay using electronic health records: A statistical and data mining approach. PLoS ONE, 13(4), 1–16.

            In this article, the authors presented the factors related to the hospital’s length of stay (LOS). The article notes that LOS is an essential measure of the effective utilization of medical practices to examine the effectiveness of patient quality care, functional evaluation, and hospital management. The authors of this article argue that a reduction in the LOS rate has been associated with a decrease in the risks of causing opportunistic ailments and side effects of medication. Furthermore, the article adds that a drop in LOS is linked to lower mortality rates and improved health outcomes. Moreover, the article notes that shorter stay in hospital facilities lowers the burden of increased cost and a high turnover in beds, increasing profit margins for the hospitals and reducing social costs. EHRs processes and data mining techniques are integral factors in assessing the impact of LOS in hospitals.   

de Leoni, M., van der Aalst, W. M. P., & Dees, M. (2016). A general process mining framework for correlating, predicting and clustering dynamic behavior based on event logs. Information Systems, 56, 235–257.

            This article explored various processes of mining study approaches and suggested a new model that hospitals can use in data mining. The study showed that process mining research usually starts by discovering the process that constitutes automatic learning of raw data through process models. According to the authors, during this learning process, uncovering and conformance of constrictions occur. The article highlights that a person would want to understand why things exist at such a juncture. However, this can only be attained through the correlation of various elements assembled in the research processes. These elements are usually based on effective workflow management, which explains the next stage to be implemented. The conformance perspective, data flow, the organization perspective and the time perspective are among the characteristics that determine the following action to be executed. However, this source also argues that data components could feature fixed and variable operating costs during the implementation procedure. This leads to confusion and critical challenges. To mitigate these challenges and confusion, this article proposes a model comprising a broad and extendable series of elements related to data flow, organization management, control flow, time resources, and conformance in future nursing studies. Moreover, the article also proposes that researchers utilize a generic model designed with dependent variables comprehensively explained using correlating independent variables.

Heath, S. (2017). E-consent forms useful for patient data sharing in research. Retrieved from

            This article explores different studies discussing e-consent tools and how they determine the sharing of patient information. The author highlights that using e-consent to access patient’s data needs maximum assurance of data security. Furthermore, the author shows that facilitating patient consent to share their information is essential with the growing need for patient data in quality healthcare delivery. The article adds that many research teams have shown that medical findings mainly utilize social determinants, genomic information and biospecimens to perform scientific solutions. Unfortunately, these researchers require the patient’s consent to use their data in advancing research in the clinical environment. The author notes that patients have always supported using their data to research in the medical fields with the condition that their privacy and confidentiality will be provided to their information. In addition, the author argues that he decided to use e-consent tools to obtain the patient’s data because there are numerous ways researchers get patient data. Each of them presents different characteristics and level of satisfaction to patients. But with e-consent tools, patients have a better understanding of how they can share their data via EHRs, learn about various research avenues and give permission for their data to be used on electronic machines such as computers and tablets. The author finishes by commenting that the assurance of the researcher should serve as the standard rule that creates ethical and clinical policies for collecting consent from patients.

Heath, S. (2018). AMIA outlines data use guideline for patient-centred care, PGHD. Retrieved from

            This resource delineates that AMIA is an excellent tool for delivering patient-centred care, especially when looking into healthcare providers can evaluate the social determinants of health. The article coincides that better governance of information leads to constructing seamless data applicable in inpatient settings. The author adds that social factors of health are at the center stage of healthcare. Therefore, this can be achieved by encouraging community care collaborations and integrating social health factors. Nevertheless, collaboration and integration alone are not enough as they need a skeleton of guidelines for obtaining data for quality care to become a reality in communities. To substantiate the presented arguments, this article relied on various pieces of research from other resources to show that patient-based care can be attained from external sources within the community. According to the author, the social determinants of care include sociodemographic status, environment, and educational accomplishments. These social determinants of health, if not well curbed, can impact the delivery of care. But the author shows that with the growing technology, social determinants can be handled differently. Adoption of EHRs and strict data governance will help in eradicating the limitations of care. AMIA acknowledges that the patient is the pillar in the development and refinement of nurse informatics.

USF Health. (n.d.). Data mining in healthcare. Retrieved from

            This study assessed the steps in a workflow process in an actual clinical setting to examine precise departmental information systems that addressed patient flow. The authors note that nursing departments that want to mitigate contemporary challenges and bring care reform should begin with getting access to operational and clinical data and establishing and maintaining goals towards improving the quality of care. Additionally, the authors argue that implementing electronic medical record (EMR) is key to understanding the level of performance in different healthcare organizations. This is because EMR assists in streamlining workflow and data mining. Finally, the article quotes that the Society for Imaging Informatics in Medicine (SIIM) acknowledged that quality data standards and better performance are significant indicators of improved workflow.


            Workflow management is associated with the effective handling of patient’s data. A streamlined workflow has been shown to minimize medication errors, improve the quality of care delivered, and increase HIPAA policies’ compliance. Even though the healthcare industry has gone through numerous struggles to design and redesign a robust workflow system, it should invest more funds in building an effective workflow structure and adopt modern data mining techniques to boost efficiency, minimize the cost of running hospitals, and eradicate unwanted pressure increase patient flow.

Share with your friends

Liked this paper? Hire one of our writers to write a unique hiqh quality for you! Order Unique Answer Now

Leave a Reply