An Intelligent Diabetes Software Prototype: Predicting Blood Glucose Levels and Recommending Regimen Changes
Bibliographic record
Abstract
Maintaining optimal blood glucose (BG) control is difficult for type 1 diabetes mellitus (T1DM) patients when typical daily regimens of food, insulin and exercise are altered. Artificial intelligence (AI) systems consisting of treatment algorithms calibrated through large datasets of patient specific information may offer a solution. Such a system can predict BG level changes resulting from regimen disturbances and recommend regimen changes for compensation. A software prototype based on neural network, fuzzy logic, and expert system concepts was developed and evaluated to determine feasibility and efficacy of a patient specific prediction model. BG data are the primary driver for adapting existing functions to patient specific prediction algorithms. Mean absolute percent error (MAPE) between actual and predicted BG values from inputs of daily insulin, food, and exercise information for an T1DM test subject was 10.5% using a calibrated model. The prototype is limited by the requirement for a rigid testing schedule, human error and situational circumstances such as alcohol consumption, illness, infection, stress, and significant hormonal imbalances. No significant conclusions regarding model validity can be drawn due to limited evaluation process and subject sample size, although the prototype has demonstrated viability as a learning tool for diabetes patients. Increased impetus for further development of this prototype and similar AI models may materialize when more effective diagnostic and data capture tools become available to reduce testing and improve accuracy of the model with more input data.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".