Continuous vital sign monitoring of individuals with acute Lassa fever using wearable biosensor devices
Page, B.; Klitting, R.; Pauthner, M. G.; Steinhubl, S.; Wegerich, S.; Kaiser, M.; Alhasan, F.; Konuwa, E.; Koroma, V.; Sumah, I.; Brima, J.; Kallon, T.; Jusu, B.; Mator-Mabay, S.; Massaquoi, I.; Kamara, M.; Kamara, F.; Jaward, E.; Massally, A.; Kanneh, Z.; McGraw, M.; Schieffelin, J.; Grant, D.; Andersen, K. G.
Show abstract
BackgroundLassa fever is a fulminant viral illness associated with high in-hospital mortality. This disease constitutes a serious public health concern in West Africa, in particular Nigeria and the Mano River Union region (Guinea, Liberia, and Sierra Leone). In Sierra Leone, continuous monitoring of critically ill patients is hindered by a lack of equipment and personnel. MethodsWe used wearable biosensor devices to remotely monitor hospitalized individuals with acute Lassa fever in order to describe vital sign trends that may be associated with clinical outcome and to evaluate the feasibility of this approach in a resource-limited setting. ResultsThe case fatality rate among participants (n=8) was 62.5%, with a median time from hospital admission to death of 2 days. Our results show that individuals who died (n=5) had higher mean heart rate (126 beats per minute) and respiratory rate (29 breaths per minute), as well as lower mean heart rate variability (10 ms), compared to those that survived (63 beats per minute, 22 breaths per minute, and 59 ms, respectively). Non-survivors also spent a greater proportion of their monitoring period in the age-specific tachycardia range (45.8%) compared to survivors (1.7%). ConclusionsAlthough real-time monitoring of vital signs using wearable biosensors may have the potential to identify decompensations earlier than traditional bedside vital sign collection in a resource-limited setting, technical improvements are still needed to enable widespread use of this tool, for both clinical and research purposes.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Effects of Electrocardiograms QRS Detection Algorithms in Heart Rate Variability Metrics 93%
- Ambulatory physiological measures obtained under naturalistic urban mobility conditions have acceptable reliability 92%
- A sweat lactate sensor for detecting anaerobic threshold in patients with heart failure: a prospective clinical trial (LacS-001) 92%
Similar papers in this journal
- Integrating remote monitoring into heart failure patients’ care regimen: A pilot study 93%
- Identifying clinical skill gaps of healthcare workers using a digital clinical decision support algorithm during outpatient pediatric consultations in primary health centers in Rwanda 92%
- Comprehensive profiling of social mixing patterns in resource poor countries: a mixed methods research protocol 92%
Similar papers in this journal
- Performance of digital Early Warning Score (NEWS2) in a cardiac specialist setting: retrospective cohort study 92%
- HEART rate variability biofeedback for LOng Covid symptoms (HEARTLOC): protocol for a feasibility study 92%
- Cumulative incidence of SARS-CoV-2 and associated risk factors among healthcare workers in the Eastern Cape, South Africa 92%
Similar papers in this journal
- Feasibility characteristics of wrist-worn fitness trackers in health status monitoring for post-COVID patients in remote and rural areas 93%
- Longitudinally Tracking Personal Physiomes for Precision Management of Childhood Epilepsy 93%
- Automated Image Transcription for Perinatal Blood Pressure Monitoring Using Mobile Health Technology 92%
Similar papers in this journal
- Comparison of feature-based indices derived from photoplethysmogram recorded from different body locations during lower body negative pressure 91%
- Age Prediction From 12-lead Electrocardiograms Using Deep Learning: A Comparison of Four Models on a Contemporary, Freely Available Dataset 91%
- High-Fidelity Measurement of Pulse Arrival Time in Critically Ill Children Using Standard Bedside Monitoring Equipment 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.