Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 Mar;12(2):295-302.
doi: 10.1177/1932296817706375. Epub 2017 May 12.

Machine Learning Methods to Predict Diabetes Complications

Arianna Dagliati  1   2   3 , Simone Marini  1   2   3 , Lucia Sacchi  1   2 , Giulia Cogni  3 , Marsida Teliti  3 , Valentina Tibollo  3 , Pasquale De Cata  3 , Luca Chiovato  3 , Riccardo Bellazzi  1   2   3
Affiliations

Machine Learning Methods to Predict Diabetes Complications

Arianna Dagliati et al. J Diabetes Sci Technol. 2018 Mar.

Abstract

One of the areas where Artificial Intelligence is having more impact is machine learning, which develops algorithms able to learn patterns and decision rules from data. Machine learning algorithms have been embedded into data mining pipelines, which can combine them with classical statistical strategies, to extract knowledge from data. Within the EU-funded MOSAIC project, a data mining pipeline has been used to derive a set of predictive models of type 2 diabetes mellitus (T2DM) complications based on electronic health record data of nearly one thousand patients. Such pipeline comprises clinical center profiling, predictive model targeting, predictive model construction and model validation. After having dealt with missing data by means of random forest (RF) and having applied suitable strategies to handle class imbalance, we have used Logistic Regression with stepwise feature selection to predict the onset of retinopathy, neuropathy, or nephropathy, at different time scenarios, at 3, 5, and 7 years from the first visit at the Hospital Center for Diabetes (not from the diagnosis). Considered variables are gender, age, time from diagnosis, body mass index (BMI), glycated hemoglobin (HbA1c), hypertension, and smoking habit. Final models, tailored in accordance with the complications, provided an accuracy up to 0.838. Different variables were selected for each complication and time scenario, leading to specialized models easy to translate to the clinical practice.

Keywords: Data Mining; Machine Learning; Microvascular Complications; Risk Predictions; Type 2 Diabetes.

PubMed Disclaimer

Conflict of interest statement

Declaration of Conflicting Interests: The author(s) declared the following potential conflicts of interest with respect to the research, authorship, and/or publication of this article: RB is a shareholder in Biomeris s.r.l., which designs software to support clinical research.

Figures

Figure 1.
Figure 1.
The data mining pipeline.
Figure 2.
Figure 2.
Nomogram for the LR model for retinopathy within 5 years.
Figure 3.
Figure 3.
Nomogram for the LR model for nephropathy within 5 years.
Figure 4.
Figure 4.
Nomogram for the LR model for neuropathy within 5 years.
See this image and copyright information in PMC

References

    1. Ramesh AN, Kambhampati C, Monson JRT, Drew PJ. Artificial intelligence in medicine. Ann R Coll Surg Engl. 2004;86(5):334-338. - PMC - PubMed
    1. Ford NJ. Artificial intelligence: the very idea. Int J Info Manage. 1987;7(1):59-60.
    1. CB Insights. 90+ artificial intelligence startups in healthcare. 2016. Available at: https://www.cbinsights.com/blog/artificial-intelligence-startups-healthc....
    1. Han D, Wang S, Jiang C, et al. Trends in biomedical informatics: automated topic analysis of JAMIA articles. J Am Med Inform Assoc. 2015;22(6):1153-1163. - PMC - PubMed
    1. Kohavi R, Provost F. Glossary of terms special issue on applications of machine learning and the knowledge discovery process. Mach Learn. 1998;30(2/3):271-274.

Publication types