A smartphone application to determine body length for body weight estimation in children: a prospective clinical trial

An augmented reality mobile application for weight estimation in paediatric patients: A prospective single-blinded cross-sectional study

Introduction

Determining the exact weight of children is a challenging task during emergency situations. Current guidelines recommend the use of length-based weight-estimating tapes. However, healthcare providers must either always carry the tapes or take time to locate them. Moreover, they may not know how to use them. To address these issues, we developed an augmented reality smartphone application for length-based weight estimation called the Paediatric Augmented Reality Scale (PARS). We evaluated its performance and compared it to that of the Broselow tape (BT) and Paediatric Advanced Weight Prediction in the Emergency Room extra-long and extra-large (PAWPER-XL) tape methods.

Method

A prospective, single-blinded cross-sectional study was conducted with children aged 1 month to 12 years who visited the emergency department of the tertiary university hospital in Bucheon, South Korea between July 2021 and February 2022. This study aimed to evaluate the measurement agreement and performance of 3 methods: BT, PAWPER-XL and PARS.

Results

In all, 1090 participants were enrolled, and 639 (58.6%) were male. The mean age of the participants was 4.1 ± 2.8 years, with a mean height of 102.7 ± 21.7 cm and mean weight of 18.8 ± 9.5 kg. Compared to BT and PAWPER-XL, PARS exhibited lower mean absolute percentage error (9.60%) and root mean square percentage error (3.02%). PARS achieved a higher proportion of weights estimated within 10% of the actual weight (63.21%), outperform-ing BT (57.25%) and PAWPER-XL (62.47%). The intraclass correlation coefficients for the actual and estimated weights of BT, PAWPER-XL and PARS were 0.952, 0.969 and 0.973, respectively (P<0.001).

Conclusion

PARS exhibited a modestly better performance than BT and PAWPER-XL in estimating body weight. PARS-estimated body weights correlated fairly accurately with the actual body weights. PARS holds potential utility in paediatric emergencies.

Portable digital devices for paediatric height and length measurement: A scoping review and target product profile matching analysis

BACKGROUND

Routine anthropometry of children, including length/height measurement, is an essential component of paediatric clinical assessments. UNICEF has called for the accelerated development of novel, digital height/length measurement devices to improve child nutrition and growth surveillance programs. This scoping review aimed to identify all digital, portable height/length measurement devices in the literature or otherwise available internationally. We also assessed identified devices against the UNICEF Target Product Profile (TPP) to identify those of highest potential for clinical and public health use.

METHOD

We searched four databases (Medline, Embase, CINAHL and Global Health) and the grey literature between 1st January 1992 and 2nd February 2023. We looked for studies or reports on portable, digital devices for height or length measurement in children up to 18 years old. Citations were screened independently by two reviewers, with data extraction and quality assessment performed in duplicate and disagreements resolved. Devices were evaluated and scored against the 34 criteria of the UNICEF TPP.

RESULTS

Twenty studies describing twelve height/length measurement devices were identified, most of which used prospective validation designs. Additional devices were found in the grey literature, but these did not report key performance data so were not included. Across the twelve devices, only 10 of 34 UNICEF criteria on average could be fully assessed. Six met UNICEF's ideal accuracy standard and one device met the minimum accuracy standard. The Leica DistoD2 device scored highest (41%), followed by Autoanthro in a controlled environment (33%) and GLM30 (32%). These devices may be high potential for further assessment and development, though further research is required.

CONCLUSION

While 12 portable, digital devices exist for child height/length measurement, insufficient data are available to fully assess whether they meet the industry's needs. Although some devices show promise, further research is needed to test the validity of these devices in varying contexts, and continued development and commercialization will be important to improve reliability and precision of these devices for widespread use.

AiRDose: Developing and Validating an Augmented Reality Smartphone Application for Weight Estimation and Dosing in Children

OBJECTIVES

Inaccurate weight estimation is a contributing factor to medical error in pediatric emergencies, especially in the prehospital setting. Current American Heart Association guidelines recommend the use of length-based weight estimation tools such as the Broselow tape. We developed the AiRDose smartphone application that uses augmented reality to provide length-based weight estimates, as well as medication dosing, defibrillation energy, and equipment sizing recommendations; AiRDose was programmed to use Broselow conversions to obtain these estimates. The primary objective was to compare the length estimated by AiRDose with the actual length obtained by the standard tape measure. The secondary objectives were to compare the estimated weights and critical medication doses from AiRDose with current established methods.

METHODS

In this prospective validation study, lengths and estimated weights were obtained for children presenting to 2 emergency departments using AiRDose, Broselow, and a standard tape measure; actual weight was recorded from the patient chart. Using the AiRDose estimated weights, hypothetical doses of epinephrine and lorazepam were calculated and compared with doses recommended via Broselow and to actual weight-based doses. Spearman rank correlation coefficients were calculated. We defined an acceptable difference of 20% between AiRDose and standard measurements as clinically relevant.

RESULTS

Five hundred forty-nine children (mean age, 4.8 years; standard deviation [SD], 2.9 years) were recruited. There were 99.6% of AiRDose lengths within a 20% difference of tape-measure lengths. There was a significant correlation between AiRDose and tape-measure length measurements (r = 0.989, P < 0.0001), and between AiRDose and Broselow weights (r = 0.983, P < 0.0001) and AiRDose and actual weights (r = 0.886, P < 0.0001). AiRDose lorazepam and epinephrine doses correlated significantly with Broselow lorazepam (r = 0.963, P < 0.0001) and epinephrine (r = 0.966, P < 0.0001) doses.

CONCLUSIONS

Anthropometric estimates and medication dose recommendations provided by AiRDose strongly correlate with established techniques. Further study will establish the feasibility of using AiRDose to accurately obtain weight estimates and medication doses for pediatric patients in the prehospital setting.

Automated Size Recognition in Pediatric Emergencies Using Machine Learning and Augmented Reality: Within-Group Comparative Study

Background

Pediatric emergencies involving children are rare events, and the experience of emergency physicians and the results of such emergencies are accordingly poor. Anatomical peculiarities and individual adjustments make treatment during pediatric emergency susceptible to error. Critical mistakes especially occur in the calculation of weight-based drug doses. Accordingly, the need for a ubiquitous assistance service that can, for example, automate dose calculation is high. However, few approaches exist due to the complexity of the problem.

Objective

Technically, an assistance service is possible, among other approaches, with an app that uses a depth camera that is integrated in smartphones or head-mounted displays to provide a 3D understanding of the environment. The goal of this study was to automate this technology as much as possible to develop and statistically evaluate an assistance service that does not have significantly worse measurement performance than an emergency ruler (the state of the art).

Methods

An assistance service was developed that uses machine learning to recognize patients and then automatically determines their size. Based on the size, the weight is automatically derived, and the dosages are calculated and presented to the physician. To evaluate the app, a small within-group design study was conducted with 17 children, who were each measured with the app installed on a smartphone with a built-in depth camera and a state-of-the-art emergency ruler.

Results

According to the statistical results (one-sample t test; P=.42; α=.05), there is no significant difference between the measurement performance of the app and an emergency ruler under the test conditions (indoor, daylight). The newly developed measurement method is thus not technically inferior to the established one in terms of accuracy.

Conclusions

An assistance service with an integrated augmented reality emergency ruler is technically possible, although some groundwork is still needed. The results of this study clear the way for further research, for example, usability testing.

Accuracy of parental estimate of child's weight in a paediatric emergency department

OBJECTIVES

To determine the accuracy of using parental estimate of a child's weight compared to actual weight in a paediatric emergency setting.

METHODS

Prospective, observational study. Age, weight and height data were collected from children aged 1 month up to 11 years with an Australian Triage score of 3 or higher. This was compared with a parent weight estimate. Analysis is descriptive.

RESULTS

A total of 450 children were studied with a mean age of 4 years 4 months. A total of 85.3% of parents were willing to provide a weight estimate (n = 384). The mean difference between the parent estimate (where provided) and the actual weight was 0.33 kg (measured weight > estimated; 95% confidence interval [CI] -6.9 kg to +7.6 kg). There was 75% agreement within 10% of the measured weight (95% CI 71-79%) and 92% agreement within 20% of the measured weight (95% CI 89-95%). Weight was more commonly underestimated than overestimated. Children of Polynesian/Pacific ethnicity were less likely to have an accurate parental weight estimation.

CONCLUSIONS

Parent estimate is an accurate weight estimation method when parents are willing to give an estimate. There is ethnic variation in accuracy that should be taken into account when applying this method.