ABSTRACT
With the increasing availability of wearable devices, continuous monitoring of individuals' physiological and behavioral patterns has become significantly more accessible. Access to these continuous patterns about individuals' statuses offers an unprecedented opportunity for studying complex diseases and health conditions such as type 2 diabetes (T2D). T2D is a widely common chronic disease that its roots and progression patterns are not fully understood. Predicting the progression of T2D can inform timely and more effective interventions to prevent or manage the disease. In this study, we have used a dataset related to 63 patients with T2D that includes the data from two different types of wearable devices worn by the patients: continuous glucose monitoring (CGM) devices and activity trackers (ActiGraphs). Using this dataset, we created a model for predicting the levels of four major biomarkers related to T2D after a one-year period. We developed a wide and deep neural network and used the data from the demographic information, lab tests, and wearable sensors to create the model. The deep part of our method was developed based on the long short-term memory (LSTM) structure to process the time-series dataset collected by the wearables. In predicting the patterns of the four biomarkers, we have obtained a root mean square error of ±1.67% for HBA1c, ±6.22 mg/dl for HDL cholesterol, ±10.46 mg/dl for LDL cholesterol, and ±18.38 mg/dl for Triglyceride. Compared to existing models for studying T2D, our model offers a more comprehensive tool for combining a large variety of factors that contribute to the disease.
- W.H.O World Health Organization (2018).Google Scholar
- Wu, Y., Ding, Y., Tanaka, Y. and Zhang, W. Risk factors contributing to type 2 diabetes and recent advances in the treatment and prevention. International journal of medical sciences, 11, 11 (2014), 1185--1200.Google ScholarCross Ref
- Sartore, G., Chilelli, N. C., Burlina, S. and Lapolla, A. Association between glucose variability as assessed by continuous glucose monitoring (CGM) and diabetic retinopathy in type 1 and type 2 diabetes. Acta Diabetologica, 50, 3 (June 01 2013), 437--442.Google ScholarCross Ref
- The Relationship of Glycemic Exposure (HbA1c) to the Risk of Development and Progression of Retinopathy in the Diabetes Control and Complications Trial. Diabetes, 44, 8 (1995), 968--983.Google Scholar
- Kavakiotis, I., Tsave, O., Salifoglou, A., Maglaveras, N., Vlahavas, I. and Chouvarda, I. Machine Learning and Data Mining Methods in Diabetes Research. Computational and Structural Biotechnology Journal, 15 (01/ 2017).Google Scholar
- Desalvo, D. and Buckingham, B. Continuous Glucose Monitoring: Current Use and Future Directions. Current diabetes reports, 13 (08/ 2013).Google Scholar
- Gardner, B., Lally, P. and Wardle, J. Making health habitual: The psychology of 'habit-formation' and general practice. The British journal of general practice : the journal of the Royal College of General Practitioners, 62 (12/ 2012), 664--666.Google ScholarCross Ref
- Bagherzadeh Khiabani, F., Ramezankhani, A., Azizi, F., Hadaegh, F., Steyerberg, E. and Khalili, D. A tutorial on variable selection for clinical prediction models: Feature selection methods in data-mining could improve the results. Journal of clinical epidemiology (10/ 2015).Google Scholar
- Georga, E. I., Protopappas, V. C., Polyzos, D. and Fotiadis, D. I. Evaluation of short-term predictors of glucose concentration in type 1 diabetes combining feature ranking with regression models. Medical & Biological Engineering & Computing, 53, 12 (Dec/01 2015), 1305--1318.Google ScholarCross Ref
- J Simon, G., Schrom, J., Castro, M., Li, P. and J Caraballo, P. Survival Association Rule Mining Towards Type 2 Diabetes Risk Assessment. AMIA, Annual Symposium proceedings, 2013 (11/ 2013), 1293--1302.Google Scholar
- Casanova, R., Saldana, S., L. Simpson, S., Lacy, M., R. Subauste, A., Blackshear, C., Wagenknecht, L. and G. Bertoni, A. Prediction of Incident Diabetes in the Jackson Heart Study Using High-Dimensional Machine Learning. PLOS ONE, 11 (10/ 2016).Google Scholar
- Anderson, A. E., Kerr, W. T., Thames, A., Li, T., Xiao, J. and Cohen, M. S. Electronic health record phenotyping improves detection and screening of type 2 diabetes in the general United States population: A cross-sectional, unselected, retrospective study. Journal of Biomedical Informatics, 60 (apr/ 2016), 162--168. Google ScholarDigital Library
- Ozcift, A. and Gulten, A. Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms. Computer methods and programs in biomedicine, 104 (04/ 2011), 443--451. Google ScholarDigital Library
- Sudharsan, B., Peeples, M. and Shomali, M. Hypoglycemia Prediction Using Machine Learning Models for Patients With Type 2 Diabetes. Journal of diabetes science and technology, 9 (10/ 2014).Google Scholar
- San, P., Ling, S. H. and Nguyen, H. Deep learning framework for detection of hypoglycemic episodes in children with type 1 diabetes, 2016 (2016), 3503--3506.Google ScholarCross Ref
- Ibrahim, S., Chowriappa, P., Dua, S., Acharya, U. R., Noronha, K., Bhandary, S. and Mugasa, H. Classification of diabetes maculopathy images using data-adaptive neuro-fuzzy inference classifier. Medical & Biological Engineering & Computing (06/ 2015).Google Scholar
- Lipton, Z., Kale, D., Elkan, C. and Wetzel, R. Learning to Diagnose with LSTM Recurrent Neural Networks (11/ 2015).Google Scholar
- G, S., R, V. and K.P, S. Diabetes detection using deep learning algorithms. ICT Express, 4, 4 (dec/ 2018), 243--246.Google Scholar
- Cheng, H.-T., Koc, L., Harmsen, J., Shaked, T., Chandra, T., Aradhye, H., Anderson, G., Corrado, G., Chai, W., Ispir, M., Anil, R., Haque, Z., Hong, L., Jain, V., Liu, X. and Shah, H. Wide & Deep Learning for Recommender Systems. Proceedings of the 1st Workshop on Deep Learning for Recommender Systems (2016), 7--10. Google ScholarDigital Library
- Abadi, M., Agarwal, A., Barham, P. and Brevdo, E. TensorFlow: a system for large-scale machine learning. 12th USENIX conference on Operating Systems Design and Implementation (2016), 265--283. Google ScholarDigital Library
- Chollet, F. Keras (2015).Google Scholar
Index Terms
- Multi-modal Predictive Models of Diabetes Progression
Recommendations
Pharmacokinetics of insulin lispro in type 2 diabetes during closed-loop insulin delivery
A model described lispro PK during closed loop insulin delivery in T2D.The linear two-compartment model fitted well the data.Time-to-peak of lispro and its metabolic clearance rate (MCR) were estimated.Relationships between PK and metabolic/demographic ...
Profiling intra-patient type I diabetes behaviors
The methodology helps to identify the most common situations affecting blood glucose control for every single patient.Adjusting insulin therapy to the identified situations leads to more accurate blood glucose control.The insights provided by the method ...
Smart home health monitoring system for predicting type 2 diabetes and hypertension
AbstractHome health monitoring can facilitate patient monitoring remotely for diabetes and blood pressure patients. Early detection of hypertension and diabetes is extremely important, as these chronic diseases often result in life-threatening ...
Comments