CoChat

Soft, all-in-one, nanomembrane wearable system for advancing neonatal health monitoring in Ethiopia

Open access

The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index; 8 of the 14 sources its claims cite were checked for support.

Abstract

The neonatal period is critical and stressful, particularly in low-resource settings where existing monitoring methods for newborns are sporadic and labor-intensive. There is a pressing need for an affordable, user-friendly device that offers continuous and effective monitoring. Here, we present a soft, all-in-one, wearable system designed for continuous wireless monitoring of neonatal health in low-resource settings. Developed using advanced packaging technologies, this system features a chest-mounted patch and a forehead-mounted pulse oximeter that transmit real-time data to a smartphone app. The integrated device measures clinical-grade parameters, including electrocardiograms, heart rate, respiration rate, temperature, and blood oxygen saturation, showing excellent correlation with hospital-grade tabletop devices and reduced motion artifacts. This pilot study demonstrates a significant improvement over current monitoring methods by providing continuous oversight, ensures critical events are not missed, and automates the process for enhanced neonatal care, resulting in 84% satisfaction by parents interested in using the system at home.

Overview

CoChat Summary

TL;DR

This paper reports a soft, all-in-one wearable system—a chest patch plus forehead pulse oximeter—for continuous neonatal vital-sign monitoring in low-resource settings, tested in an Ethiopian NICU pilot with 25 neonates. It shows feasibility, generally improved agreement when compared against ECG-derived reference values, and high parent willingness to use the system at home, while highlighting training and device-appearance concerns.

Key findings

  • The system continuously measures ECG, heart rate, respiration rate, temperature, and SpO₂, transmitting wirelessly via Bluetooth Low Energy to a smartphone/tablet app; the chest patch runs 14 h per charge and the forehead oximeter 22 h, with a listed cost of <$60.
  • In the TASH NICU pilot (25 neonates, 798 data entries, 592 h), ECG-derived reference comparisons showed mean differences of 4.8 bpm for heart rate (95% CI [−7.5, 17]), 2.6 breaths/min for respiration rate (95% CI [−4.7, 9.8]), and −0.04% for SpO₂ (95% CI [−5.6, 5.5]); manual-reference comparisons were wider: 12 bpm (95% CI [−49, 72]), −1.4 breaths/min (95% CI [−25, 22]), and −1.6% (95% CI [−9.7, 6.6]).
  • Device characterization found PCB dry electrodes had an SNR of 25.35 dB versus 12.06 dB for gel electrodes; electrode connectors were limited to 30 mating cycles; adhesive maintained adhesion after 20 isopropyl-alcohol sanitization cycles; and a 180° bend test (n = 10,000) increased ground-plane resistance by only 14.34 milliohms.
  • Parent survey results: 84% said they would use the biopatch at home, 89% stated it was user-friendly, 89% agreed technical support is needed, and 58% preferred the biopatch over manual measurements for future use.

Methods

  • Device design/fabrication: flexible PCBs with elastomer encapsulation, reusable dry PCB electrodes, and a forehead PPG sensor; electronics included an nRF52832 BLE microcontroller, ADS1291 ECG ADC sampled at 250 Hz, TMP117 temperature sensor at 1 Hz, and MAX30102 PPG at 50 Hz. The app used offline-first edge processing, encrypted SQLite storage, cloud sync when connectivity was available, and NTP-based time synchronization.
  • Human subject pilot: approved by the Ethiopian Food and Drug Administration and IRB; 25 neonates aged 0–7 days admitted to TASH NICU were recruited using Schmettow’s sample-size methodology. First 10 patients used manual reference measurements (auscultation, clip oximeter, manual respiration count, axillary thermometer); next 15 used reusable suction cup ECG monitoring for heart and respiration rate. Nurses logged values, and parents completed usability/acceptability surveys.
  • Analysis: Bland-Altman comparisons for heart rate, respiration rate, and SpO₂; Pan-Tompkins QRS detection for ECG-derived heart rate; SpO₂ from red/IR AC/DC ratios; motion-quality index for ECG motion handling; and peel testing for adhesive strength (n = 20).

Limitations

  • Stated: this was a pilot study with only 25 patients; future iterations should use a hybrid rigid/flexible design to ruggedize the reusable portion; parents were wary of device appearance and exposed electrical components; training was the biggest parent concern; and the lack of a continuous measurement reference made it difficult to assess SpO₂ accuracy against the TASH NICU reference method.
  • Evident from the text: the study was single-center and short-term (median participation 31 h, range 5–84 h), with intermittent manual reference measurements and paper journal logging; some sensor validation tests used healthy adults rather than neonates, including the forehead oximeter breath-hold comparison (n = 15 adults) and electrode signal comparison on adult physiology.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1038/s41746-025-01974-8

Cites

21 of 21 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Fig. 1 Overview of a soft, all-in-one, nanomembrane wearable bioelectronic system to improve neonatal monitoring in Ethiopia. a Details of the current procedure that relies on manual, intermittent measurements for heart rate, respiration rate, blood oxygen, and temperature measurements. b Visualization of the proposed wearable and wireless system for continuous vital monitoring. A biopotential sensor measures ECG, and a medical-grade thermometer measures skin temperature at the chest. The forehead-mounted pulse oximeter is easily attached to a headband with Velcro and measures PPG from the forehead. Both devices are time-synced and communicate wirelessly via BLE to a custom mobile app. The Flutter framework allows compatibility across a wide range of consumer products, including smartphones, tablets, and computers, maximizing applicability with users’ pre-existing devices. The mobile app features an intuitive interface with high-contrast visual elements and real-time alerts for vital sign abnormalities. Due to limited and unpredictable internet connectivity, the app computes offline heart rate, respiration rate, oxygen saturation, and temperature, and saves all recorded data locally until it can be saved to the cloud for long-term storage for later reference. The app processes data compression and local storage optimization to operate reliably in non-connected multi-day environments, with automatic data synchronization when internet connectivity becomes available.
Fig. 1 Overview of a soft, all-in-one, nanomembrane wearable bioelectronic system to improve neonatal monitoring in Ethiopia. a Details of the current procedure that relies on manual, intermittent measurements for heart rate, respiration rate, blood oxygen, and temperature measurements. b Visualization of the proposed wearable and wireless system for continuous vital monitoring. A biopotential sensor measures ECG, and a medical-grade thermometer measures skin temperature at the chest. The forehead-mounted pulse oximeter is easily attached to a headband with Velcro and measures PPG from the forehead. Both devices are time-synced and communicate wirelessly via BLE to a custom mobile app. The Flutter framework allows compatibility across a wide range of consumer products, including smartphones, tablets, and computers, maximizing applicability with users’ pre-existing devices. The mobile app features an intuitive interface with high-contrast visual elements and real-time alerts for vital sign abnormalities. Due to limited and unpredictable internet connectivity, the app computes offline heart rate, respiration rate, oxygen saturation, and temperature, and saves all recorded data locally until it can be saved to the cloud for long-term storage for later reference. The app processes data compression and local storage optimization to operate reliably in non-connected multi-day environments, with automatic data synchronization when internet connectivity becomes available.CC BY · PubMed Central
Fig. 2 Mechanical design and characterization of the chest patch. a Exploded view of the device, including a wireless device, stretchable electrodes, soft encapsulation, and a biocompatible elastomer-based adhesive patch. b Circuit design for cardiovascular monitoring. c Incremental demonstration of removal and replaceable printed circuit board (PCB) electrodes using a flat flexible cable connector. d Signal performance comparison between PCB electrodes and traditional gel electrodes. e Degradation of the PCB electrodes over 40 mating cycles at the pressure-based connection point, showing the failure point of maximum matings for a single PCB electrode before needing replacement. f Peel test showing the integrity of reusable elastomer-based adhesive even after 20 cycles of isopropyl alcohol-based sanitization. g Temperature tracking performance of our device compared to a heat source with a low stabilization period from a 23 °C to 43 °C range, with high accuracy, showing accuracy across the operation range for health monitoring. h Photo of a fully encapsulated patch.
Fig. 2 Mechanical design and characterization of the chest patch. a Exploded view of the device, including a wireless device, stretchable electrodes, soft encapsulation, and a biocompatible elastomer-based adhesive patch. b Circuit design for cardiovascular monitoring. c Incremental demonstration of removal and replaceable printed circuit board (PCB) electrodes using a flat flexible cable connector. d Signal performance comparison between PCB electrodes and traditional gel electrodes. e Degradation of the PCB electrodes over 40 mating cycles at the pressure-based connection point, showing the failure point of maximum matings for a single PCB electrode before needing replacement. f Peel test showing the integrity of reusable elastomer-based adhesive even after 20 cycles of isopropyl alcohol-based sanitization. g Temperature tracking performance of our device compared to a heat source with a low stabilization period from a 23 °C to 43 °C range, with high accuracy, showing accuracy across the operation range for health monitoring. h Photo of a fully encapsulated patch.CC BY · PubMed Central
Fig. 3 Mechanical design and characterization of the forehead pulse oximeter. a Detailed view of the device, with a flexible portion that bends and attaches with Velcro. b Exploded view of the wireless device. c Circuit design for forehead-mounted pulse oximeter. d Mounting headband. e An optional cover for the device for parents who are wary of the device’s electrical appearance. f Demonstration of measurement agreement of our device compared to a commercial patient monitor, where the shaded regions indicate breath hold for desaturation. g Measured ground plane resistance changes of our device with a 180° bending test (n = 10,000), capturing negligible changes.
Fig. 3 Mechanical design and characterization of the forehead pulse oximeter. a Detailed view of the device, with a flexible portion that bends and attaches with Velcro. b Exploded view of the wireless device. c Circuit design for forehead-mounted pulse oximeter. d Mounting headband. e An optional cover for the device for parents who are wary of the device’s electrical appearance. f Demonstration of measurement agreement of our device compared to a commercial patient monitor, where the shaded regions indicate breath hold for desaturation. g Measured ground plane resistance changes of our device with a 180° bending test (n = 10,000), capturing negligible changes.CC BY · PubMed Central
Fig. 4 Data analysis and real-time measurement validation study. a Comparison of recorded heart rate data entries where the shaded regions indicate manually derived values with a pulse oximeter clip. b Comparison of recorded respiration rate data entries, where the shaded regions indicate manually derived values by counting over a 60 s duration. c Bland-Altman analysis for heart rate comparison between our device and manually collected reference for 10 observed neonatal patients (n = 281). d Bland-Altman analysis for heart rate comparisons between our device and ECG reference for 15 observed neonatal patients (n = 441). e Bland-Altman analysis for respiration rate comparisons between our device and manually collected reference for 10 observed neonatal patients (n = 267). f Bland-Altman analysis for respiration rate comparisons between our device and ECG reference for 15 observed neonatal patients (n = 441). g Bland-Altman analysis for SpO2 calculations between our device and manually collected reference for 10 observed neonatal patients (n = 289). h Bland-Altman analysis for SpO2 comparisons between our device and reference for 15 observed neonatal patients (n = 448).
Fig. 4 Data analysis and real-time measurement validation study. a Comparison of recorded heart rate data entries where the shaded regions indicate manually derived values with a pulse oximeter clip. b Comparison of recorded respiration rate data entries, where the shaded regions indicate manually derived values by counting over a 60 s duration. c Bland-Altman analysis for heart rate comparison between our device and manually collected reference for 10 observed neonatal patients (n = 281). d Bland-Altman analysis for heart rate comparisons between our device and ECG reference for 15 observed neonatal patients (n = 441). e Bland-Altman analysis for respiration rate comparisons between our device and manually collected reference for 10 observed neonatal patients (n = 267). f Bland-Altman analysis for respiration rate comparisons between our device and ECG reference for 15 observed neonatal patients (n = 441). g Bland-Altman analysis for SpO2 calculations between our device and manually collected reference for 10 observed neonatal patients (n = 289). h Bland-Altman analysis for SpO2 comparisons between our device and reference for 15 observed neonatal patients (n = 448).CC BY · PubMed Central
Fig. 5 System validation and acceptability in the NICU. a 10 s segment of filtered ECG data from a neonate in the study. b Derived heart rate values between our device and a known reference (BioRadio) on a healthy adult. c 10 s segment of filtered PPG data from a neonate in the study. d Results of the breath hold test on a healthy adult in comparison with a reference device. e 10 s segment of temperature sensor data from a neonate in the study. f Neonate undergoing traditional ECG-based continuous monitoring in TASH NICU. g Photos from patients observed in this study wearing our device system.
Fig. 5 System validation and acceptability in the NICU. a 10 s segment of filtered ECG data from a neonate in the study. b Derived heart rate values between our device and a known reference (BioRadio) on a healthy adult. c 10 s segment of filtered PPG data from a neonate in the study. d Results of the breath hold test on a healthy adult in comparison with a reference device. e 10 s segment of temperature sensor data from a neonate in the study. f Neonate undergoing traditional ECG-based continuous monitoring in TASH NICU. g Photos from patients observed in this study wearing our device system.CC BY · PubMed Central

Verification

Claims the paper makes

5 Valid · 1 Not valid · 3 Not checked · 75 Own results and interpretations

51 more claims

Create a free account to see all 84 claims and every source verdict.

See all claims — free account
  • Probably not a substantial claim. 9
  • It may state two separate claims as one. 21

Create a free account to see these claims.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

2 of 2

Citations

Cites

Show all 21 references

Research works printed but not linked: 1

  1. Aynalem, Y. A., Mekonen, H., Akalu, T. Y., Gebremichael, B. & Shiferaw, W. S. “Preterm Neonatal Mortality and its predictors in Tikur Anbessa Specialized Hospital, Addis Ababa, Ethiopia: a retrospective cohort study. Ethiopian J. health Sci. 31, 43–54 (2021).

Metadata

Authors
Zhou, L., Joseph, M., Lee, Y. J., Yadav, D., Nayak, L., Woodall, J., Matthews, J., Soltis, I., Mekuria, F. M., Yeshanew, K. H., Mamo, Y. K., Fekadu, A., Demtse, A., Gleason, R., & Yeo, W.-H.
Affiliations
  • Georgia Institute of Technology (US)
  • Addis Ababa University (ET)
  • Tikur Anbessa Hospital (ET)
  • Brighton and Sussex Medical School (GB)
Corresponding author
Yeo, Woon-Hong
Venue
npj Digital Medicine
Published
2025-09-25
Volume
8
Issue
1
Pages
575-575
ISSN
2398-6352 (ISSN-L)
OpenAlex
W4414490313
Cited by
3
References
21
Citations by year
2026: 3
FWCI
0.72
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Digital Medicine (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • PubMed Central (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Imlay Foundation,United States
  • Bill and Melinda Gates Foundation (INV- 006189)
Topics
  • Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
  • Physical Sciences › Engineering › Biomedical Engineering › Advanced Sensor and Energy Harvesting Materials
  • Physical Sciences › Engineering › Biomedical Engineering › Wireless Body Area Networks
Keywords
wearable sensors, nanomembranes, pulse oximetry, electrocardiogram, continuous vital sign monitoring, resource-limited settings, smartphone data transmission, motion artifact reduction, home-based neonatal care, Ethiopia

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Soft, all-in-one, nanomembrane wearable system for advancing neonatal health monitoring in Ethiopia. https://app.cochat.ai/papers/10.1038/s41746-025-01974-8
The paper
Zhou, L., Joseph, M., Lee, Y. J., Yadav, D., Nayak, L., Woodall, J., Matthews, J., Soltis, I., Mekuria, F. M., Yeshanew, K. H., Mamo, Y. K., Fekadu, A., Demtse, A., Gleason, R., & Yeo, W.-H. (2025). Soft, all-in-one, nanomembrane wearable system for advancing neonatal health monitoring in Ethiopia. npj Digital Medicine. https://doi.org/10.1038/s41746-025-01974-8

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.