Iterative Development, Validation, and Certification of a Smartphone System to Assess Neonatal Jaundice: Development and Usability Study

Abstract

Background Medical device development is an area facing multiple challenges, resulting in a high number of products not reaching the clinical setting. Neonatal hyperbilirubinemia, manifesting as neonatal jaundice (NNJ), is an important cause of newborn morbidity and mortality. It is important to identify infants with neonatal hyperbilirubinemia at an early stage, but currently there is a lack of tools that are both accurate and affordable. Objective This study aimed to develop a novel system to assess the presence of NNJ. The device should provide accurate results, be approved as a medical device, be easy to use, and be produced at a price that is affordable even in low-resource settings. Methods We used an iterative approach to develop a smartphone-based system to detect the presence of NNJ. We performed technical development, followed by clinical and usability testing in parallel, after which we initiated the regulatory processes for certification. We updated the system in each iteration, and the final version underwent a clinical validation study on healthy term newborns aged 1 to 15 days before all documentation was submitted for conformity assessment to obtain Conformité Européenne (CE) certification. We developed a system that incorporates a smartphone app, a color calibration card, and a server. Results Three iterations of the smartphone-based system were developed; the final version was approved as a medical device after complying with Medical Device Regulation guidelines. A total of 201 infants were included in the validation study. Bilirubin values using the system highly correlated with total serum or plasma bilirubin levels (r=0.84). The system had a high sensitivity (94%) to detect severe jaundice, defined as total serum or plasma bilirubin >250 µmol/L, and maintained a high specificity (71%). Conclusions Our smartphone-based system has a high potential as a tool for identifying NNJ. An iterative approach to product development, conducted by working on different tasks in parallel, resulted in a functional and successful product. By adhering to the requirements for regulatory approval from the beginning of the project, we were able to develop a market-ready mobile health solution.

Neonatal jaundice detection in low-resource Mexican settings: possibilities and barriers for innovation with mobile health

“…Extensive evidence shows that multi-stakeholder engagement in the development and adaptation of mHealth systems is essential for successful scale-up and implementation (50)(51)(52). Picterus JP's development followed an iterative process in which end users tested the device on a dummy and on newborns and then offered feedback to optimise the system (17). The device has also been tested on newborns by 61 Dutch maternity nurses in their routine home visits to monitor NNJ in both urban and rural regions (unpublished results).…”

“…Picterus JP consists of a smartphone app to capture and upload images of the newborn's skin, a calibration card for accurate colour calibration in the images and a server for image analysis and storage (Fig. 1) (17). The app has undergone validation in Norwegian hospitals (17,18) and in pilot studies in Mexico and the Philippines (19,20), demonstrating signi cant positive correlation between Picterus JP's bilirubin values and TSB levels as well as higher accuracy over VA.…”

“…1) (17). The app has undergone validation in Norwegian hospitals (17,18) and in pilot studies in Mexico and the Philippines (19,20), demonstrating signi cant positive correlation between Picterus JP's bilirubin values and TSB levels as well as higher accuracy over VA.…”

Neonatal jaundice detection in low-resource Mexican settings: possibilities and barriers for innovation with mobile health

“…Picterus JP consists of a smartphone app to capture and upload images of the newborn’s skin, a calibration card for accurate colour calibration in the images and a server for image analysis and storage (Fig. 1 ) [ 17 ]. The app has undergone validation in Norwegian hospitals [ 17 , 18 ] and in pilot studies in Mexico and the Philippines [ 19 , 20 ], demonstrating significant positive correlation between Picterus JP ’s bilirubin values and TSB levels as well as higher accuracy over VA.…”

“…1 ) [ 17 ]. The app has undergone validation in Norwegian hospitals [ 17 , 18 ] and in pilot studies in Mexico and the Philippines [ 19 , 20 ], demonstrating significant positive correlation between Picterus JP ’s bilirubin values and TSB levels as well as higher accuracy over VA.…”