Engineered Predictive Medicine’s influence in minimising the impacts of autoimmune and viral conditions
Currently, Australia’s and other countries’ health care models implemented after World War 2 are treating their populations with a ‘reactive’ medical system. This is where a patient feels sick and the doctor then reacts to the symptoms and behaviours based on the given clinical information, blood tests or medical imaging in order to ascertain a diagnosis and then treatment (Wise, MacIntosh, Rajakulendran, & Khayat, 2016). A reactive medical system is flawed resulting in a human and financial cost as it treats problems as they arise rather than preventing the complications from manifesting.
I propose that engineering and science can be used in ‘predictive’ medicine to minimise the adverse complications of autoimmune and viral diseases. This will create a health system model that improves the prevention techniques of autoimmune and viral diseases rather than addressing them when they occur. I was diagnosed with Type 1 diabetes when I was 2 years old. My blood glucose was tested, and I was diagnosed before being admitted into intensive care as I demonstrated diabetic symptoms. Unfortunately, one third of children diagnosed with diabetes are admitted to intensive care with Diabetic Ketoacidosis or in a coma (US National Library of Medicine National Institutes of Health, 2016) (Rashed, 2011) (Cameron, Kilov, & Audehm, 2016). I passionately believe with a predictive medicine model using engineering and science, it would decrease intensive care admissions and save lives.
Engineering could assist the predictive healthcare model by supplying new technologies such as artificial intelligence to monitor body systems and enhance people’s own health management. Examples are toilets or toothbrushes engineered to sample body tissue and fluids and give readings as predictors of certain diseases. In the Type 1 diabetes community, urine samples could be monitored via a sensor in the toilet and warn potential patients of higher than normal glucose readings and ketones. Toothbrushes could indicate antibody or bacterial levels and predict viral infections preventing spread of the disease. This information could be correlated and produce a patient health report via mobile phone with recommendations such as to see a doctor.
Eric Dishman stated in a TEDMED that phones are revolutionary to the healthcare system and could use algorithms to detect behavioural cues (Dishman, 2009). This technology could also be used to detect reduced cognitive functions such as slurred speech which can be a sign of many autoimmune and viral conditions such as low blood glucose in Diabetes. Apps on watches could detect cardiac anomalies or breathing difficulties and report recommendations. Statistics, reference ranges and predictive analytics from clinical information could generate alarms for body system malfunctions and patient health including body temperature and white blood cell count (Gold, 2014).Genetic testing could alert patients to a myriad of genetic predisposed conditions allowing that patient to monitor specific organ function.
Predictive medicine will allow autonomous healthcare, reduce health infrastructure, prevent undue suffering and could even eliminate contagious diseases from spreading. It is important for all aspects of every community, providing opportunity to those who have limited access to hospitals and doctors. The Engineering course is a brilliant opportunity to open international discussion on this global issue and mindset.
Australian Institute of Health and Welfare. (2018). Emergency department care 2017–18. Canberra. Retrieved March 17, 2019, from https://www.aihw.gov.au/getmedia/9ca4c770-3c3b-42fe- b071-3d758711c23a/aihw-hse-216.pdf.aspx?inline=true Cameron, F., Kilov, G., & Audehm, R. (2016). Diagnosing type 1 diabetes and diabetic ketoacidosis in children. Diabetes & Primary Care in Australia, 97 – 100. Retrieved March 17, 2019, from http://pcdsa.com.au/wp-content/uploads/2016/07/DPCA1-3_97-100_wm.pdf Dishman, E. (2009, November). TEDMED: Take Healthcare off the mainframe. Retrieved March 17, 2019, from https://www.ted.com/talks/eric_dishman_take_health_care_off_the_mainframe?utm_cam paign=BeepBeepBites%20- %20Nieuwsbrief&utm_source=hs_email&utm_medium=email&_hsenc=p2ANqtz– VH9Cm3YAWRigFg2er1267o-dFD7htxvZ-QtUyPRIr7SMQSB5WHnZtKdDOg8kd8qq3ztv_ Gold, H. K. (2014, September 22). The rise of pred med. Retrieved March 17, 2019, from Aljazeera America: http://america.aljazeera.com/opinions/2014/9/predictive- medicineobamacaretechnologyhealthcaredoctors.html
Rashed, A. M. (2011). Pattern of presentation in type 1 diabetic patients at the diabetes center of a university hospital. Retrieved March 17, 2019, from US National Library of Medicine National Institutes of Health – NCBI: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3119963/ US National Library of Medicine National Institutes of Health. (2016, June 22). Ketoacidosis at first presentation of type 1 diabetes mellitus among children: a study from Kuwait. Retrieved March 17, 2019, from NCBI: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4916451/ Wise, A., MacIntosh, E., Rajakulendran, N., & Khayat, Z. (2016, March 29). Transforming health: Shifting from reactive to proactive and predictive care. Retrieved March 17, 2019, from MaRS: https://www.marsdd.com/news-and-insights/transforming-health-shifting-from- reactive-to-proactive-and-predictive-care/ Ziman, M. (2018, July 18). A new blood test could detect early stage melanoma in more than 80% of patients. The Conversation. Retrieved March 17, 2019, from https://medicalxpress.com/news/2018-07-blood-early-stage-melanoma-patients.html