Visual Data Displays and Uses in Decision Making

Visual Data Displays and Uses in Decision Making Ronya Bentz, Lasondra Defreeze, Terri Dougherty, Grace Zhao HCS/438 September 24, 2012 Gerald Rintals Visual Data Displays and Uses in Decision Making Studying the measures of central tendency will help to verify if these measures of central tendency for the given data are correct. The information will assist in predicting specific health issues and interventions needed to improve health care. The measure of variation produces a conclusion through the Tele-care monitoring system.The types of central tendency conducted in this study were the mean and median. The description of data in this study uses the five-number summary. Variables were also used to predict key medical events and interventions, based on significance. According to Biddiss, Brownsell, Hawley (2009), â€Å"the data analysis was conducted using statistical software and logistic regression was used to predict the occurrence of key medical events/interventions taken from health care logs of health-care workers. Biddiss, Brownsell, Hawley 2009’s articles explain examples in the text are as follows: The 45 patients studied a total of 8576 alerts were generated. A total of 171 medical events which included the mean number of medical events for the year which was 3. 5, the median 2, and the quartile ranged between 1- 4. The mean average of key alerts per year was 49, with a median of 49, and an interquartile range of 47-51. The average percentage of total alerts that were medical events was 6. 4% with a median of 4 and an interquartile range of 1. 4-8 (p. 227-228).Because the focus of the study determined the average need for medical intervention in congestive heart failure, the use of the measure of central tendency is correct in this study. According to Bennett, Briggs, & Thiola, (2009), â€Å"variation is a measure of how much the data values are spread out. A distribution in which most data are clustered together has a low variation. † (p. 16). In the article, â€Å"predicting need for intervention in individuals with congestive heart failure using a home-based Tele-care monitoring system for 18 months† (Biddiss, Brownsell, & Hawley, 2009, p. 9); the authors monitored 45 elderly individuals with congestive heart failure who entered daily information, based of individual symptoms and health status. There are 14 variables to enter and generate the alert system. Systolic blood pressure| 2541| Heart rate| 1822| Daytime shortness of breath| 803| Need for extra pillows| 576| Night time shortness of breath| 480| Cough| 441| Weight gain| 422| Bloated stomach | 387| Dizziness| 339| Medication adherence| 327| Swollen ankles| 248| Angina| 191| Anxiety| 10| Urine excretion| Eight total alerts 8576| Biddiss, Brownsell, & Hawley, 2009, p. 29). As the data describes, the systolic blood pressure most triggered the alert system. It produced nearly 30% of the total alerts and the heart rate almost 9%. †¢Average of aler ts for 14 characteristics: 612 †¢Median: 405 †¢Distribution is right –skewed because the values are more spread to the right side. The graphing of a bell curve is the representation of the standard normal distribution. Also the table shows the mean value is zero and the standard deviation is one (Bennett, Briggs, & Triola, 2009).In Figure 2 of the study, the values are not depicted by normal distribution as they deviate greatly from the mean. This shows there is no symmetry in the values represented and displays too many variables. Because the study is measuring various variables not necessarily related to one another, it would follow that standard normal distribution would not apply in this study. The results of this study show factors of individuals who took part reported different symptoms and clinicians monitoring these concerns had determined if medical intervention was necessary.Heart rate, blood pressure, and weight were also considered and compared with the data reported by the participants. Because the study relied heavily on self-reporting by the participants, many of the variables were subject to embellishment. The clinical data supports reports of declining health, but in some cases may not correlate with information reported. The conclusions of the study are favorable, as increased monitoring of patients with chronic heart failure may result in occasional interventions that are not neccessary.This study provides an improvement in the knowledge of the patient’s condition and reaction to treatment. Reference Bennett. Briggs. , & Trola (2009). Statistical reasoning for everyday life, (3rd) Chapter 4: Describing Data. Retrieved from www. University of Phoenix. edu. Library database. Biddiss, E. , Brownsell, S. , & Hawley, M. S. (2009, March). Predicting need for intervention in individuals. Journal of Telemedicine and Telecare, 15(5), 226-231. University of Phoenix Library Telecare; 2009, 15:226-231. Retrieved from www. Univers ity of Phoenix . edu. Library database.