Walden University Clustering Medical Discussion and Replies

Reply to: 

Discussion 1-

Healthcare systems can use Customer Relationship Management (CRM) databases and clustering techniques to help with population health goals (Athanasoulias 2019). At my healthcare system, we were not meeting our strategic goals for lung cancer screenings in many of our targeted hospital markets.

The American Cancer Society recommends lung cancer screenings for adults between the ages of 55 and 74 years old, with no signs or symptoms of lung cancer (Wender 2013). The candidate must be an active or former smoker with a 30-pack history, meaning the candidate must have smoked the equivalent of a pack a day for 30 years (or two packs a day for 15 years, for example). If the candidate is currently an active smoker, he or she should be encouraged to enter a smoking cessation program. If he or she is a former smoker, they must have quit within the past 15 years. Finally, the candidate must be generally in good health.

           Using clustering, or segmentation through our CRM database, we identified patients living in the targeted geographies and within the recommended age ranges who are self-reported smokers. After pulling their email addresses and mailing addresses, we used targeted E-mails and direct mail to encourage recipients to make an appointment with one of our primary care providers to discuss our lung screening program and schedule a screening.


Albright, S., & Winston, W., (2017). Business analytics: Data analysis and decision making

(6th ed.). Stamford, CT: Cengage Learning. Chapter 17, “Data Mining.”

Athanasoulias, G., Chountalas, P., “Increasing Business Intelligence Through a

CRM Approach: An Implementation Scheme and Application Framework,” (2019). International Journal of Information, Business and Management (2019), 11(2), 146-178., Available at SSRN: https://ssrn.com/abstract=3380772.

Crowson, M. (2017). SPSS: Introduction to Logistic Regression [Video file]. Retrieved from


Grande, T. [Todd Grande]. (2015, September 21). K-means cluster analysis in SPSS [Video file].

Retrieved from https://www.youtube.com/watch?v=YRue69W-dYU.

Wender, F., Barrera, E., Colditz, G., Church, T., Ettinger, D., Etzioni, R., Flowers, C., Gazelle,

G., Kelsey, D., LaMonte, S., Michaelson, J., Oeffinger, K., Shih, Y.-C.T., Sullivan, D., Travis, W., Walter, L., Wolf, A., Brawley, O. and Smith, R., (2013), American Cancer Society lung cancer screening guidelines. CA: A Cancer Journal for Clinicians, 63: 106-117. https://doi.org/10.3322/caac.21172

Discussion 2-

K-neartest neighbors (KNN or k-NN) is a non-parametric, supervised learning classifier, which uses proximity to make classifications or predictions about the grouping of an individual data point. While it can be used for either regression or classification problems, it is typically used as a classification algorithm, working off the assumption that similar points can be found near one another (IBM, n. d.). KNN is often depcited in graphs looking like a scatterplot and follows the most concentrated areas of data and can often be tied to the term “majority vote” because of its reasoning for pinpoint a particluar given data point. This type of classicification os great for weighing the options between two or more categories and and when voting is a great option to determine a favorable outcome. 

KNN uses data with several classes to predict the classification of the new sample point (IBM, n. d.). It is one of the simplest approaches to predict outcomes, as it has been dubbed the lazy-learning approach to data classification. There are supervised learning and unsupervised learning and the approach was created by two United Stated Air Force Officers who worked in aviation and they wnated it to be fast to learn by anyone who needed to use it. It is designed to use for its prediction power, quick calucltaion time and easy to interpret information (Chatterjee, 2020). These techniques are great for my staff at the state psychiatroc hospital due to lower educational backgrounds. The teachability of this method allows for little training time away from staff’s main duties. We could use this for form updates on the units and for predictions in the pharmacy in terms of medication drug usage and annual demand of each medication used. This can help us reduce costs in past years when we have ordered too many of a particluar medication or not enough and have had to succomb to the markets costs per unit, rather than buying in bulk shipments from a contract. 


Chatterjee, M. (2020). A Quick Introduction to KNN Algorithm. Retrieved from The Introduction of KNN Algorithm | What is KNN Algorithm? (mygreatlearning.com) 

IBM. (n. d.). What is the k-nearest neighbors algorithm. Retrieved from What is the k-nearest neighbors algorithm? | IBM 

Needs help with similar assignment?

We are available 24x7 to deliver the best services and assignment ready within 6-12hours? Order a custom-written, plagiarism-free paper

Order Over WhatsApp Place an Order Online

Do you have an upcoming essay or assignment due?

All of our assignments are originally produced, unique, and free of plagiarism.

If yes Order Similar Paper