- 3497
- 230
- 0
- 0
- 0
- Help Ukraine
About the solution
Type 2 diabetes runs in Dimistris’ family. His grandfather died of complications related to the condition, his mother was diagnosed with the disease when he was 10 years old, and his Aunt Zacharoula also suffered from it.
“When they were diagnosed back in the 1970s, there were no data to show which medicine was most effective for a specific patient population. Today, 29 million Americans are living with diabetes. And now, in an emerging era of precision medicine, things are different. Increased access to troves of genomic information and the rising use of electronic medical records, combined with new methods of machine learning, allow researchers to process large amounts of data. This is accelerating efforts to understand genetic differences within diseases – including diabetes – and to develop treatments for them. The scientist in me feels a powerful desire to take part”, he explained.
So the mathematician is now using big data to optimise treatment.
“My students and I have developed a data-driven algorithm for personalized diabetes management that we believe has the potential to improve the health of the millions of Americans living with the illness. It works like this: The algorithm mines patient and drug data, finds what is most relevant to a particular patient based on his or her medical history and then makes a recommendation on whether another treatment or medicine would be more effective. Human expertise provides a critical third piece of the puzzle. We conducted our research through a partnership with Boston Medical Center, the largest safety-net hospital in New England that provides care for people of lower-income and uninsured people. And we used a data set that involved the electronic medical records from 1999 to 2014 of about 11,000 patients who were anonymous to us. Next, we developed an algorithm to mark precisely when each line of therapy ended and the next one began, according to when the combination of drugs prescribed to the patients changed in the electronic medical record data. All told, the algorithm considered 13 possible drug regimens. For each patient, the algorithm processed the menu of available treatment options. This included the patient’s current treatment, as well as the treatment of his or her 30 “nearest neighbours” in terms of the similarity of their demographic and medical history to predict potential effects of each drug regimen. The algorithm assumed the patient would inherit the average outcome of his or her nearest neighbours.
If the algorithm spotted the substantial potential for improvement, it offered a change in treatment; if not, the algorithm suggested the patient remain on his or her existing regimen. In two-thirds of the patient sample, the algorithm did not propose a change”, the scientist described.
Dimitris believes the algorithm could be applicable to other diseases, including cancer, Alzheimer’s disease, and cardiovascular disease.
Adapted from: https://bit.ly/33A1O8s
This solution shall not include mention to the use of drugs, chemicals or biologicals (including food); invasive devices; offensive, commercial or inherently dangerous content. This solution was not medically validated. Proceed with caution! If you have any doubts, please consult with a health professional.
DISCLAIMER: This story was written by someone who is not the author of the solution, therefore please be advised that, although it was written with the utmost respect for the innovation and the innovator, there can be some incorrect statements. If you find any errors please contact the patient Innovation team via info@patient-innovation.com
-
-
448
-
0
-
12602
Nightscout – an open source, do-it-yourself continuous glucose monitor in the Cloud
Type 1 diabetes mellitus
Diabetes insipidus
Diabetes mellitus
Diabetes mellitus (incl subtypes)
Diabetes mellitus inadequate control
Fulminant type 1 diabetes mellitus
Cystic fibrosis related diabetes
Gestational diabetes
Insulin-requiring type 2 diabetes mellitus
Latent autoimmune diabetes in adults
Diabetes with hyperosmolarity
Diabetes complicating pregnancy
Insulin resistant diabetes
Type 2 diabetes mellitus
Type 3 diabetes mellitus
Pancreatogenous diabetes
Glucose metabolism disorders (incl diabetes mellitus)
Nephrogenic diabetes insipidus
Acquired lipoatrophic diabetes
Congenital central diabetes insipidus
Hyperglycaemia
Carbohydrate metabolism disorder
Inborn errors of carbohydrate metabolism (excl glucose)
Pancreas
Mobile app
Software
Insulin injector
Insulin pen
Insulin injection
Diabetes mellitus management
-
-
-
433
-
0
-
10536
I-Port™ – Medication delivery device
Type 1 diabetes mellitus
Diabetes complicating pregnancy
Diabetes mellitus
Diabetes mellitus (incl subtypes)
Diabetes mellitus inadequate control
Latent autoimmune diabetes in adults
Insulin resistant diabetes
Insulin-requiring type 2 diabetes mellitus
Pancreatogenous diabetes
Type 2 diabetes mellitus
Type 3 diabetes mellitus
Gestational diabetes
Glucose metabolism disorders (incl diabetes mellitus)
Crohn's disease
Rheumatoid arthritis
Hypopituitarism
Dwarfism
Autoimmune disorders
Coagulopathy
Pancreas
Pituitary gland
Auto-injector
Insulin injector
Insulin pen
Insulin injection
Skin and subcutaneous tissue therapeutic procedures
Anticoagulant therapy
-
-
-
368
-
12
-
10196
Diabetic invents app to manage diabetes
Diabetes mellitus (incl subtypes)
Diabetes mellitus inadequate control
Acquired lipoatrophic diabetes
Diabetes mellitus
Diabetes with hyperosmolarity
Congenital central diabetes insipidus
Diabetes complicating pregnancy
Diabetes mellitus malnutrition-related
Diabetes insipidus
Cystic fibrosis related diabetes
Insulin-requiring type 2 diabetes mellitus
Type 1 diabetes mellitus
Congenital nephrogenic diabetes insipidus
Insulin resistant diabetes
Fulminant type 1 diabetes mellitus
Gestational diabetes
Latent autoimmune diabetes in adults
Type 2 diabetes mellitus
Type 3 diabetes mellitus
Pancreatogenous diabetes
Nephrogenic diabetes insipidus
Mobile app
-