Unified Mobile App for Streamlining Verbal Autopsy and Cause of Death Assignment in India: Design and Development Study
Bibliographic record
Abstract
Background: Verbal autopsy (VA) has been a crucial tool in ascertaining population-level cause of death (COD) estimates, specifically in countries where medical certification of COD is relatively limited. The World Health Organization has released an updated instrument (Verbal Autopsy Instrument 2022) that supports electronic data collection methods along with analytical software for assigning COD. This questionnaire encompasses the primary signs and symptoms associated with prevalent diseases across all age groups. Traditional methods have primarily involved paper-based questionnaires and physician-coded approaches for COD assignment, which is time-consuming and resource-intensive. Although computer-coded algorithms have advanced the COD assignment process, data collection in densely populated countries like India remains a logistical challenge. Objective: This study aimed to develop an Android-based mobile app specifically tailored for streamlining VA data collection by leveraging the existing Indian public health workforce. The app has been designed to integrate real-time data collection by frontline health workers and seamless data transmission and digital reporting of COD by physicians. This process aimed to enhance the efficiency and accuracy of COD assignment through VA. Methods: The app was developed using Android Studio, the primary integrated development environment for developing Android apps using Java. The front-end interface was developed using XML, while SQLite and MySQL were employed to streamline complete data storage on the local and server databases, respectively. The communication between the app and the server was facilitated through a PHP application programming interface to synchronize data from the local to the server database. The complete prototype was specifically built to reduce manual intervention and automate VA data collection. Results: The app was developed to align with the current Indian public health system for district-level COD estimation. By leveraging this mobile app, the average duration required for VA data collection to ascertainment of COD, which typically ranges from 6 to 8 months, is expected to decrease by approximately 80%, reducing it to about 1-2 months. Based on annual caseload projections, the smallest administrative public health unit, health and wellness centers, is anticipated to handle 35-40 VA cases annually, while medical officers at primary health centers are projected to manage 150-200 physician-certified VAs each year. The app's data collection and transmission efficiency were further improved based on feedback from user and subject area experts. Conclusions: The development of a unified mobile app could streamline the VA process, enabling the generation of accurate national and subnational COD estimates. This mobile app can be further piloted and scaled to different regions to integrate the automated VA model into the existing public health system for generating comprehensive mortality statistics in India.
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 | 0.008 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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".