A Platform to Build Mobile Health Apps: The Personal Health Intervention Toolkit (PHIT)
Bibliographic record
Abstract
Personal Health Intervention Toolkit (PHIT) is an advanced cross-platform software framework targeted at personal self-help research on mobile devices. Following the subjective and objective measurement, assessment, and plan methodology for health assessment and intervention recommendations, the PHIT platform lets researchers quickly build mobile health research Android and iOS apps. They can (1) create complex data-collection instruments using a simple extensible markup language (XML) schema; (2) use Bluetooth wireless sensors; (3) create targeted self-help interventions based on collected data via XML-coded logic; (4) facilitate cross-study reuse from the library of existing instruments and interventions such as stress, anxiety, sleep quality, and substance abuse; and (5) monitor longitudinal intervention studies via daily upload to a Web-based dashboard portal. For physiological data, Bluetooth sensors collect real-time data with on-device processing. For example, using the BinarHeartSensor, the PHIT platform processes the heart rate data into heart rate variability measures, and plots these data as time-series waveforms. Subjective data instruments are user data-entry screens, comprising a series of forms with validation and processing logic. The PHIT instrument library consists of over 70 reusable instruments for various domains including cognitive, environmental, psychiatric, psychosocial, and substance abuse. Many are standardized instruments, such as the Alcohol Use Disorder Identification Test, Patient Health Questionnaire-8, and Post-Traumatic Stress Disorder Checklist. Autonomous instruments such as battery and global positioning system location support continuous background data collection. All data are acquired using a schedule appropriate to the app's deployment. The PHIT intelligent virtual advisor (iVA) is an expert system logic layer, which analyzes the data in real time on the device. This data analysis results in a tailored app of interventions and other data-collection instruments. For example, if a user anxiety score exceeds a threshold, the iVA might add a meditation intervention to the task list in order to teach the user how to relax, and schedule a reassessment using the anxiety instrument 2 weeks later to re-evaluate. If the anxiety score exceeds a higher threshold, then an advisory to seek professional help would be displayed. Using the easy-to-use PHIT scripting language, the researcher can program new instruments, the iVA, and interventions to their domain-specific needs. The iVA, instruments, and interventions are defined via XML files, which facilities rapid app development and deployment. The PHIT Web-based dashboard portal provides the researcher access to all the uploaded data. After a secure login, the data can be filtered by criteria such as study, protocol, domain, and user. Data can also be exported into a comma-delimited file for further processing. The PHIT framework has proven to be an extensible, reconfigurable technology that facilitates mobile data collection and health intervention research. Additional plans include instrument development in other domains, additional health sensors, and a text messaging notification system.
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 | 0.004 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 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 | 0.001 |
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".