Deliverable 6 - Chronic Diseases and Population Health Management

Running head: BIG DATA IN DIABETES MANAGEMNT 1

BIG DATA IN DIABETES MANAGEMNT 8

Big Data in Diabetes Management

Kimberly Huff

Rasmussen College

Author Note

Deliverable 3 Submitted January 21, 2021

Big Data

Many organizations use big data for the sole purpose of data analytics. However, before firms can get valuable information about big data, they may need knowledge of various significant data sources. As a PHM program leader, I would focus on diabetes management and find out the significant data sources used to analyze patients who have diabetes. Examples of substantial data sources include the media, cloud, the web, IoT, and databases (Russom, 2011). The different sources of big data are aimed at providing data for purposes of customer analytics, industrial analytics, business process analytics, and analytics for fraud detection. In our case, healthcare information can be found in many sources throughout the web.

The best big data that may use in diabetes management would be artificial intelligence and IoT. Digital health takes into account advanced medical technologies and digital communication (Al-Turjman, 2019). Machine learning enables us to take into account the identification, prediction of patterns, and inductive reasoning. Today, diabetes management is facing a whole lot of challenges, including the decreased number of diabetologists and an increase in the number of patients (Eswari, Sampath, & Lavanya, 2015). With the use of artificial intelligence, diabetologists can take full responsibility for their patients (Ross, Anderson, Kodate, Thompson, Cox, & Malik, 2014). Robust data analysis will ensure that gaps in care are identified, and the necessary measures are taken to mitigate risks.

Less digital ways of acquiring patient information in the past included ADT alerts, demographics, and ICD-10 codes (Nyenwe, Ashby, Tidwell, Nouer, & Kitabchi, 2011). Although there are effective ways, they may not provide varied data on patients with diabetes. They also do not help in proper analysis, and therefore integrating artificial intelligence and IoT may help in obtaining and analyzing big data for diabetes patients.

When building the PHM it is beneficial to use data from various sources to improve positive patient outcomes. In order to develop a comprehensive portrait of a patient’s clinical, financial, and social risks, healthcare providers must collect key data from across the care field before they are able to leverage risk scoring frameworks and target interventions to individuals. By combining diagnosis and procedure codes, organizations can better understand which treatment pathways are most effective for certain conditions. This process offers a more patient centered approach to care.

Utilization of ADT alerts such as patient demographics, vitals, laboratory results, progress notes, and allergy alerts offers patient safety promotion and ensures that individuals are being given treatments that will improve their conditions. Once the information is in a format that can be easily accessible it is easier to analyze when needed. Using these resources for the PHM offers improved quality of care while promoting best practices and patient safety.

Patient demographics can be used to group patients into categories such as age groups which can then be used to target specific interventions that are appropriate for the largest number of people in these specific groups. A patient’s vital signs can be used in a variety of ways to predict risks, understand the development of chronic diseases, and prevent acute events. Lab results offer similar opportunities to flag risks and chart the effectiveness of ongoing interventions, such as monitoring a diabetic patient’s blood glucose levels over time and offers a way to represent the data. Progress notes are an important source of patient data but can be very time consuming when in a narrative form. This process can be very time consuming. Allergies can have major implications for a patient’s quality of life and interaction with the health care system. Ensuring allergies are up to date can improve patient safety and decrease incident of unwanted interactions.

Using these resources help improve the quality and outcomes of the PHM. The goal is to improve patient outcomes. Using ICD-10 codes and ADT processes within the PHM helps to Identify patients at high risk of developing chronic diseases such as diabetes. They also help to maintain protocols in place for management of many other chronic illnesses. Utilizing these programs within the PHM is an essential part of succeeding in the value-based care environment.

References

Al-Turjman, F. (Ed.). (2019). Artificial Intelligence in IoT. Springer.

Eswari, T., Sampath, P., & Lavanya, S. (2015). Predictive methodology for diabetic data analysis in big data. Procedia Computer Science, 50, 203-208.

Nyenwe, E. A., Ashby, S., Tidwell, J., Nouer, S. S., & Kitabchi, A. E. (2011). Improving diabetes care via telemedicine: Lessons from the Addressing Diabetes in Tennessee (ADT) project. Diabetes Care, 34(3), e34-e34.

Ross, A. J., Anderson, J. E., Kodate, N., Thompson, K., Cox, A., & Malik, R. (2014). Inpatient diabetes care: complexity, resilience and quality of care. Cognition, technology & work, 16(1), 91-102.

Russom, P. (2011). Big data analytics. TDWI best practices report, fourth quarter, 19(4), 1-34.