NewPneu: A Novel Cost Effective mHealth System for Diagnosing Childhood Pneumonia in Low-Resource Settings
Bibliographic record
Abstract
Pneumonia is the primary factor that kills many children especially in areas with limited resource settings. The current approach to diagnosing pneumonia involves the use of the Integrated Management of Childhood Illness (IMCI), which contains guidelines for observing high risk signs for early detection. However, due to lack of point of care monitoring devices, these observations are either inaccurate, invalid or costly. Furthermore, several mHealth solutions do not detect this disease and only provide guidelines.In this work, we propose a new low-cost system that captures biomedical data as recommended by doctors to identify Pneumonia. Among the system components, the hub unit is the critical element that collects biometric data from sensors, and samples it. Afterwords, the data is transmitted in real time via Bluetooth Low Energy (BLE) radio to a mobile Android-based device. The hub design is based on nRF52832 - Nordic Semiconductors microcontroller due to its low cost and high-speed ADC (i.e., SAADC). The time complexity of all software digital processing and band-pass filtering techniques for the hub is equal to O(1). The design is validated by examining the linear relationship between the applied and calculated frequencies (R2=1). Our real-world analysis reveals that there are more than 70% correlations for the SPO2 data, and more than 90% correlations for the RR data. This is captured between the gold standard measurements and our device. To further justify the accuracy, the two methods used to demonstrate that they are within the Line of Agreements (LoA) in terms of SpO2, based on Bland Altman analysis (i.e., lower and upper Line of Agreements (LoAs) are equal to 1.4 and 2.0; respectively). Furthermore, the accuracy in terms of RR is mostly within 2.8 and 3.6 LoAs. In comparison to the BioSignalPlux hub - PLUX Wireless Biosignals S.A., the battery life of this new design lasts for seven days compared to twenty-four hours for BioSignalPlux. The new hub is compact and can be packaged in a small case. Furthermore, the hub costs $10 USD in comparison to the BioSignalPlux and the Contec device that range from approximately $1,000 to $6,000 USD.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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".