The Method of Determining Effective Drug Combination - Research Paper Example

? Case study 4 Case study 4 Question There is need to embrace smarter method of determining effective drug combination because it helps physicians to make decisions about the right quantities of drugs to give patients. Health care units that do not use the analytics mean that physicians have to determine the kind and quantity of treatment given to patients based on their opinions leading to therapeutic errors in the care systems. The use of predictive analytics helps in reducing the risks associated with overdose that may reduce the physicians’ competencies. Additionally, the smarter prediction helps in reducing the drug combination time and operation expenses. It also helps in increasing the quality of health care because it enables hospitals to change from sick-care to effective predictive-care (Shmueli & Koppius, 2011). There is need to embrace analytics in the health care sectors with the intention of shunning medical experts’ diagnosis opinion without statistical learning approach. The predictive analytics is accurate, and has an arithmetical learning approach because one only needs to acquire knowledge on how to use the analytics (5th European & Developing Countries Clinical Trials Partnership Forum, 2010). Question 2 The predictive analytics plays a significant role in the provision of intelligent decision support that helps in lowering the healthcare treatment costs. Combination of effective DSS and smart analytics can help in preventing costly diagnostic errors because many sources of data can be processed and changed into meaningful information with time (Chih-Lin, Nick & David, 2000). This is especially vital in the current world where the demand for health care is higher than the supply. This means that the DSS helps improving the efficiency of health process. For examples, it helps in reducing test duplication and unfavorable events. Moreover, effective DSS reduces costs by helping the physicians to change the costly drug prescription patterns into cheaper and effective patterns. Additionally, analytics helps in reducing treatment costs because it prevents overtreatment and carrying out of unnecessary laboratory tests that are costly. It also results in the improvement of patient outcomes that help in reducing the rate of readmissions (Gilmer, O'Connor & Sperl-Hillen, 2012). Question 3 The DSS has played a vital part in the EuResit projects in various ways. First, the project deals with huge patient and therapist data. Besides, the DSS combined with predictive analytics has been helpful in the projects because they help in the faster data processing. This has helped is saving time consequently shortening the projects duration. Through this system, the medical experts could easily compare subjects’ data in the project. Additionally, DSS has been helpful in the projects since it has helped in reducing the project costs. Reduction of costs occurs due to the shortening of the data processing time. DSS is also used in the ViroLab in the projects to prevent the researchers from conducting the same tests twice (Michael, Kai, & Rema, 2007). The DSS has been valuable in determining the right combination of drugs in the projects. This is vital since it prevented the overdose of patients that could lead to drug resistance. The system did this by creating standard datum. The use of the DSS has also been helpful in providing immediate feedback, and conducting diagnosis in the project. This has been supportive in preventing the medical errors that result from poor diagnosis that eventually leads to drug related toxicity. However, the DSS has enabled the researchers to create precise patient model that has been helpful in reducing the occurrence of the toxicity. Additionally, the prevention of toxicity has also been achievable in the projects because of the DSS’ ability to predict the response of patients to the treatments used in the project (Peter, Mark, Brent, Swarna, et al, 2001). Question 4 The EuResists might face resistance from both medical expert and patients. Many patients might positively respond to the use of EuResist due to the efficiencies of predictive analytics and DSS. However, due to the project’s inaccuracies, the patients might not respond to therapy as expected (Zazzi, Incardona & Rosen-Zvi, et al 2012). For example, the result showed that patient’s response to the EuResist did not attain a very high percentage of the accuracy. The accuracy of the respond was only 75 percent. This means that predicting system is inaccurate by 25 percent that is a big percentage in therapeutic tests. This is not a satisfactory percentage of accuracy. As such, the project needs some improvement. In addition, the EuResist might be more accurate than the medical experts might. This because the DSS and predictive analytics are more accurate compared to the medical experts in diagnosis. The research outcome showed that EuResist could outperform the medical experts by about 90 percent. Some medical experts might also resist the EuResist because it threatens the clinical judgments. This is because the system is too rigid and it limits the thinking freedom of the clinicians (Zazzi, Kaiser, Sonnerborg & Struck, 2011). Question 5 The insurance firms that pay for drug treatment would support the EuResist because it helps in reducing the cost of treatments. The proportion of individuals with HIV is increasing and most of infected individuals depend on the insurance companies. The companies spend a lot on the drug treatment due to various reasons. One of the reasons is that many people with HIV are becoming resistant to drugs. This means that a lot of money has to be spent on medical researchers to find other effective drugs for the patients who are resistant to the drugs. Such drugs are usually expensive because of the high research expenses. This increases the insurance firms’ expenses. Such resistance to drugs is attributable to poor diagnosis that leads to poor drug combination. Additionally, the insurance firms have to incur expenses due to current high rate of medical errors. Many patients get wrong dosage of drugs due to medical errors made by physicians. This leads to poor health that requires more treatment. EuResist helps in preventing this problem since its accuracy is higher compared to the medical experts. Furthermore, the EuResist will help in reducing the insurance company expenses because it can maintain and improve health care. This is vital because it will reduce the quantity of drugs used by patients while improving the treatment quality. High quality treatments will also help in reducing the number of patients’ hospital visits, which can be advantageous to the insurance firms (Turban, Volonino & Wiley-Jossey, 2011). Question 6 Prediction engine has many benefits in the health care systems because it helps in optimizing the patients’ therapy because it is very effective in diagnosis. Additionally, it enables the patients to get feedbacks in time, saves time and improves the therapeutic quality. A physician only requires a patients’ blood and his demographic information to know his or her medical problems. This is vital because it helps in preventing medical errors. As a result, patients receive the right medication, in the right quantities, and at the right time. Additionally, predictive engine enable clinicians to lean through experience unlike the old system focusing on experts’ opinion. The predictive engines are forms of artificial intelligence that are not as complex as manual selection of therapies by the physicians (Euresist). EuResist’s statistical methods will substitute the expertise of the clinicians because its full usage in hospital will reduce the value of the experts’ experiences and imaginations. Medical experts use their experiences and opinion to determine the king of therapy for their patients. Since their experiences cannot be duplicated in computer applications, the full implementation of the systems in the hospitals will make their experiences useless. Hospitals will rely on the software instead of the experts because it has many advantages over the clinicians’ expertise. The software is very effective in reducing the medical costs, and is believed to be accurate. References Chih-Lin, C., W. Nick, S., & David A., K. (2000). A decision support system for cost-effective diagnosis. Artificial Intelligence in Medicine, 50149-161. Retrieved from http://ehis.ebscohost.com/eds/detail?vid=6&sid=5e54d123-08d8-4a54-b7d6- 41965df996ae%40sessionmgr112&hid=6&bdata=JnNpdGU9ZWRzLWxpdmU%3d#db= edselp&AN=S0933365710001053 Eurestist. (2013). IBM. Retrieved from ftp://ftp.software.ibm.com/software/solutions/videos/Euresist_300k.wmv 5th European & Developing Countries Clinical Trials Partnership Forum Arusha, Tanzania, 12 to 14 October 2009. (2010). Tropical Medicine & International Health, 15(8), S1-S32. Retrieved from http://ehis.ebscohost.com/eds/pdfviewer/pdfviewer?vid=5&sid=4af85c91-91d4-4a82- 99f7-a1c9fb3a05e7%40sessionmgr4&hid=110 Gilmer, T. P., O'Connor, P. J., Sperl-Hillen, J. M. et al (2012). Cost-Effectiveness of an Electronic Medical Record Based Clinical Decision Support System. Health Services Research, 47(6), 2137-2158. Retrieved from http://ehis.ebscohost.com/eds/detail?vid=6&sid=5e54d123-08d8-4a54-b7d6- 41965df996ae%40sessionmgr112&hid=107&bdata=JnNpdGU9ZWRzLWxpdmU% 3d#db=aph&AN=83327849 Michael P., J., Kai, Z., & Rema, P. (2007). Modeling the longitudinality of user acceptance of technology with an evidence-adaptive clinical decision support system. Decision Support Systems, Peter L., E., Mark, L., Brent A., B., Swarna, C. (2001). The introduction of a diagnostic decision support system (DXplain™) into the workflow of a teaching hospital service can decrease the cost of service for diagnostically challenging Diagnostic Related Groups (DRGs). International Journal of Medical Informatics, 79772-777. Shmueli, G., & Koppius, O. R. (2011). Predictive Analytics in Information Systems Research. MIS Quarterly, 35(3), 553-572. Retrieved from http://ehis.ebscohost.com/eds/pdfviewer/pdfviewer?sid=5e54d123-08d8-4a54-b7d6- 41965df996ae%40sessionmgr112&vid=4&hid=110 Turban, E., Volonino, L., Sipior, J. C., & Wiley, J. (2011). Information technology for management: Improving strategic and operational performance. Hoboken, NJ: John Wiley. Zazzi, M. M., Kaiser, R. R., Sonnerborg, A. A., Struck, D. D. et al (2011). Prediction of response to antiretroviral therapy by human experts and by the EuResist data-driven expert system (the EVE study). HIV Medicine, 12(4), 211-218. Retrieved from: http://ehis.ebscohost.com/eds/detail?vid=8&sid=5e54d123-08d8-4a54-b7d6- 41965df996ae%40sessionmgr112&hid=4&bdata=JnNpdGU9ZWRzLWxpdmU%3d #db=aph&AN=58788925 Zazzi, M., Incardona, F., Rosen-Zvi, M. et al (2012). Predicting Response to Antiretroviral Treatment by Machine Learning: The EuResist Project. Intervirology, 55(2), 123-127. Retrieved from http://ehis.ebscohost.com/eds/detail?vid=8&sid=5e54d123-08d8-4a54-b7d6- 41965df996ae%40sessionmgr112&hid=110&bdata=JnNpdGU9ZWRzLWxpdmU% 3d#db=aph&AN=70858922 Read More