Individualized, self-supervised deep learning for blood glucose prediction
Fuest, J.; Tacke, M.; Ullmann, L.; Washington, P.
Show abstract
The current standard for monitoring blood glucose levels in diabetes patients are continuous glucose monitoring (CGM) devices, which are costly and carry the risk of complications, such as allergic reactions or skin irritations from the adhesive used to attach the CGM sensor to the skin. CGM devices are also highly visible and can thus act as a discomforting disease-marker for diabetes patients. To mitigate these issues, we develop and test a novel method that is able to predict blood glucose levels with only non-invasive predictor variables and a very small number of target variable measurements by using individualization and self-supervised deep learning. Using only a single blood glucose measurements per week, our method (6387.47 glucose-specific MSE) outperforms traditional deep learning performed with hourly measurements (8191.23 glucose-specific MSE). Across eight experiments where blood glucose measurements are more than one hour apart, our approach outperforms traditional deep learning without exception. Our findings suggest that self-supervised, individualized deep learning could provide an avenue towards alternatives to CGM devices that would be less costly, non-invasive, and thus more accessible.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Evaluating Explanations from AI Algorithms for Clinical Decision-Making: A Social Science-based Approach 93%
- Practical Strategies for Extreme Missing Data Imputation in Dementia Diagnosis 92%
- A Transformer-Based Model Trained on Large Scale Claims Data for Prediction of Severe COVID-19 Disease Progression 92%
Similar papers in this journal
- Characterizing subgroup performance of probabilistic phenotype algorithms within older adults: A case study for dementia, mild cognitive impairment, and Alzheimer’s and Parkinson’s diseases 93%
- Modeling physician variability to prioritize relevant medical record information 92%
- Comparative Effectiveness of Medical Concept Embedding for Feature Engineering in Phenotyping 91%
Similar papers in this journal
- A novel interpretable deep transfer learning combining diverse learnable parameters for improved T2D prediction based on single-cell gene regulatory networks 94%
- Machine learning for classifying chronic kidney disease and predicting creatinine levels using at-home measurements 94%
- Mitigating Machine Learning Bias Between High Income and Low-Middle Income Countries for Enhanced Model Fairness and Generalizability 93%
Similar papers in this journal
- Racial disparities in continuous glucose monitoring-based 60-min glucose predictions among people with type 1 diabetes 94%
- Modular Clinical Decision Support Networks (MoDN)—Updatable, Interpretable, and Portable Predictions for Evolving Clinical Environments 93%
- Uncovering the effects of model initialization on deep model generalization: A study with adult and pediatric chest X-ray images 93%
Similar papers in this journal
- A methodology of phenotyping ICU patients from EHR data: high-fidelity, personalized, and interpretable phenotypes estimation 95%
- Mining for Equitable Health: Assessing the Impact of Missing Data in Electronic Health Records 93%
- Graph-Based Clinical Recommender: Predicting Specialists Procedure Orders using Graph Representation Learning 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.