DNP 805 Topic 5 Discussion 1

DNP 805 Topic 5 Discussion 1 Select a specific clinical problem and post a clinical question that could potentially be answered using data mining. Identify data mining techniques you would apply to this challenge, and provide your rationale. Are there any specific data mining techniques you would not use? Support your decision. A specific clinical problem is unplanned hospital readmissions. Hospital readmission costs an estimated $25 billion dollars annually, and compromises patient safety (Olson, et al., 2016). A clinical question that could potentially be answered using data mining is “Which patients are at highest risks for hospital readmissions”. The data mining technique that appears most appropriate to analyze this clinical question would be the data relationship of classes which is using data to organize patients into groups to predict outcomes (Grand Canyon University, 2014). Data I would analyze for relationship trends might include: 1. Patients re-hospitalized within 30 days – to identify the patients in question 2. Age – to look for age groups at risk for re-hospitalization 3. Gender – to see of males or females is a possible predictor of re-hospitalization 4. Diagnoses – to identify diagnosis groups that increase risk of re-hospitalization 5. Complications – to identify any complications during hospitalization that may increase risk of re-hospitalization 6. Length of stay – to identify if length of stay trend may pose a risk of re-admission By identifying factors common among patients who experience re-hospitalization, the hope would be that patients could be identified as high risk upon admission to the hospital and care could be planned to avert the identified trends and reduce the risk of re-admission. By decreasing the re-admission rate, hospitals could save a significant amount of healthcare dollars and improve patient safety. Grand Canyon University. (2014). DNP-805 Lecture 5. Olson, C. H., Dey, S., Kumar, V., Monsen, K. A., & Westra, B. L. (2016). Clustering of elderly patient subgroups to identify medication-related readmission risks. International Journal of Medical Informatics, 8543-52. doi:10.1016/inf.2015.10.004 Select a specific clinical problem and post a clinical question that could potentially be answered using data mining. Identify data mining techniques you would apply to this challenge, and provide your rationale. Are there any specific data mining techniques you would not use? Support your decision. Data mining holds an important potential that would be beneficial for the healthcare industry to enable health systems to systematically use data and analytics to identify inefficiencies and best practices that improve care and reduce costs. Some medical experts believe that the opportunities to improve care and reduce costs concurrently could apply to as much as 30% of overall healthcare spending. This could be an overall win- win situation. Because of the complexity of healthcare and a slower rate of technology adoption, the health care industry lags behind these others in implementing effective data mining and analytic strategies.(Ben-chetrit, E., et., al 2012). The clinical problem and questions that I would encounter would be patients with diabetes mellitus. 1 Is the patient checking his blood sugar daily? 2 Diet control 3 Knowledge deficit. 4 history of obesity 5 family history of diabetes A lot of the patients do not follow their diabetes simply because of knowledge deficit. classes can be provided for the patients and the families. Data mining can help monitor patients and provide directions for the patients who do not have the understanding about how diet and exercise and taking medication can affect diabetes mellitus. Data mining can be a life saving tool for the patients. Reference Ben-Chetrit, E., et al., A simplified scoring tool for prediction of readmission in elderly patients hospitalized in internal medicine departments. Isr Med Assoc J, 2012. 14(12): p. 752-6. Select a specific clinical problem and post a clinical question that could potentially be answered using data mining. Identify data mining techniques you would apply to this challenge, and provide your rationale. Are there any specific data mining techniques you would not use? Support your decision. In the Cardiac Cath Lab, patients who have percutaneous translumenal coronary angiography (PTCA) with stent placement are placed on one of two daily anticoagulants after the procedure, Plavix or Brilinta. Some of our patients experience recurrent blockages even after PTCA, stent placement, and ongoing anticoagulant therapy. Data mining could provide data on each medication cohort and track the recurrent blockages in the population to correlate similarities in the groups who have the problems. By identifying the comorbidities of the patients who have recurring blockages and who need repeat PTCA, we could potentially identify those who are at higher risk and provide them with closer monitoring to provide preventive care rather than emergent PTCA. Information used to data mine should include: 1 Prior history of PTCA 2 Anticoagulant therapy: Plavix versus Brilinta 3 Comorbidities: a. Diabetes b. Smoker c. Hypertension d. Hyperlipidemia e. Obesity According to Linden and Yarnold (2016), “classification is the most popular data mining application in health care and has been used to improve diagnostic accuracy, identify high-risk patients and extract concepts in unstructured data” (p. 835). By classifying patients in the data base using data mining of the EHR, the healthcare team could identify those patients with the potential for recurrent blockages and provide preventive care. Reference Linden, A., & Yarnold, P. R. (2016). Using data mining techniques to characterize participation in observational studies: Data mining in observational studies. Journal of Evaluation in Clinical Practice, 22(6), 839-847. doi:10.1111/jep.12515