Designing and Evaluating a Personalized, Human-Centered Dietary Decision Support System for Use Among People With Diabetes in an Indian Setting: Protocol for a Quasi-Experimental Study
Bibliographic record
Abstract
BACKGROUND: Human-centered dietary decision support systems are fundamental to diabetes management, and they address the limitations of existing diet management systems. OBJECTIVE: The objective of the proposed study is to evaluate the use of an interactive, telephone-linked, personalized, human-centered decision support system for facilitating the delivery of personalized nutrition care for patients with diabetes. METHODS: A quasi-experimental trial was conducted between the period of June and December 2018. Study participants were recruited from Community Health Center, Dharamshala, Kangra (urban population), and Model Rural Health Unit, Haroli Block, Una (rural population). Eligible participants included adults aged ≥30 years with controlled or uncontrolled diabetes, those who agreed to participate in the study, those who were available for follow-up interviews, and those with a telephone or computer at home. Diabetic status was determined via a physician's diagnosis. Individuals with mental or physical challenges that affected their ability to use an electronic diet record, those who were not available for a telephone follow-up, and those who were involved in other protocols related to dietary assessments were excluded. The study participants were randomized into the following two groups: the intervention group (telephone-linked dietary decision support system) and the control group (paper-based diet record). Study participants in the intervention group recorded their daily dietary intake by using a telephone-linked, personalized, human-centered dietary decision support system and received personalized feedback and diet education via SMS text messaging. Study participants in the control group were provided with only a paper-based diet record for documenting their daily dietary intake. Follow-up visits were conducted at 3 and 6 months from the baseline in both groups. Differences in diabetes knowledge, attitudes, and practices will be measured across groups. RESULTS: The collection of baseline data from 800 study participants in both the intervention (n=400) and control groups (n=400), which were stratified by urban (control group: n=200; intervention group: n=200) and rural settings (control group: n=200; intervention group: n=200), has been completed. Follow-up data collection for months 3 and 6 is ongoing and is expected to be completed by October 2019. CONCLUSIONS: We anticipate that the intervention group will show significant changes in nutrition knowledge, attitudes, and practices; satisfaction with care; and overall diabetes management. We also expect to see urban-rural differences across the groups. The uniqueness of our nutrient data capture process is demonstrated by its cultural and contextually relevant features-diet capture in both English and Hindi, diet conversion into caloric components, sustained diet data collection and participant adherence through telephone-linked care, and auto-generated reminders. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/13635.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.025 | 0.020 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.004 | 0.004 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.005 | 0.003 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.004 | 0.005 |
| Insufficient payload (model declined to judge) | 0.025 | 0.003 |
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 source (direct Gemma or distilled Codex), 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".