Related Experiment Video
Updated: Jun 18, 2026
Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis
Published on: September 26, 2018
Development and validation of a new clinical decision support tool to optimize screening for retinopathy of
Aldina Pivodic1, Helena Johansson2,3, Lois E H Smith4
1Department of Clinical Neuroscience, Institute of Neuroscience and Physiology, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden aldina.pivodic@gu.se.
Insights
A new tool, DIGIROP-Screen, can accurately identify premature infants who do not need retinopathy of prematurity (ROP) screening, reducing unnecessary eye exams. This prediction tool ensures high sensitivity and specificity, improving ROP screening efficiency.
Area of Science:
- Neonatal ophthalmology
- Medical device development
- Clinical decision support systems
Background:
- Premature infants require frequent eye exams for retinopathy of prematurity (ROP).
- Current screening methods are costly and stressful, with a low yield for treatment-needed cases.
- There is a need for a tool to safely reduce ROP screening in infants not requiring treatment.
Purpose of the Study:
- To develop and validate DIGIROP-Screen, a prediction tool for ROP screening.
- To achieve 100% sensitivity and high specificity in identifying infants who do not need ROP treatment.
- To compare DIGIROP-Screen's performance against existing ROP prediction models.
Main Methods:
- Development of DIGIROP-Screen using data from infants born at 24-30 weeks gestational age (GA) from the Swedish National Registry for ROP.
- External validation of the tool using three international cohorts (N=1241).
- Application of multivariable logistic regressions and analysis of birth characteristics, ROP status, and postnatal age.
Main Results:
- ROP treatment was required in approximately 4% of infants in both development and validation groups.
- DIGIROP-Screen achieved 100% sensitivity and specificities of 53.1% (at birth) and 60.5% (at 8 weeks postnatal age) in the development group.
- External validation showed similar specificities (46.3% and 53.5%), with only one false negative in a severely malformed infant; other models had lower specificities (9.6%-45.2%).
Conclusions:
- DIGIROP-Screen is a clinical decision support tool that can safely identify infants not needing ROP screening among those born at 24-30 weeks GA.
- The tool demonstrated equal or superior sensitivity and specificity compared to existing ROP prediction models in European and North American populations.
- Further validation in new cohorts is recommended, with potential for modification using similar statistical approaches for specific clinical settings.
Background/Aims:
Prematurely born infants undergo costly, stressful eye examinations to uncover the small fraction with retinopathy of prematurity (ROP) that needs treatment to prevent blindness. The aim was to develop a prediction tool (DIGIROP-Screen) with 100% sensitivity and high specificity to safely reduce screening of those infants not needing treatment. DIGIROP-Screen was compared with four other ROP models based on longitudinal weights.
Methods:
Data, including infants born at 24-30 weeks of gestational age (GA), for DIGIROP-Screen development (DevGroup, N=6991) originate from the Swedish National Registry for ROP. Three international cohorts comprised the external validation groups (ValGroups, N=1241). Multivariable logistic regressions, over postnatal ages (PNAs) 6-14 weeks, were validated. Predictors were birth characteristics, status and age at first diagnosed ROP and essential interactions.
Results:
ROP treatment was required in 287 (4.1%)/6991 infants in DevGroup and 49 (3.9%)/1241 in ValGroups. To allow 100% sensitivity in DevGroup, specificity at birth was 53.1% and cumulatively 60.5% at PNA 8 weeks. Applying the same cut-offs in ValGroups, specificities were similar (46.3% and 53.5%). One infant with severe malformations in ValGroups was incorrectly classified as not needing screening. For all other infants, at PNA 6-14 weeks, sensitivity was 100%. In other published models, sensitivity ranged from 88.5% to 100% and specificity ranged from 9.6% to 45.2%.
Conclusions:
DIGIROP-Screen, a clinical decision support tool using readily available birth and ROP screening data for infants born GA 24-30 weeks, in the European and North American populations tested can safely identify infants not needing ROP screening. DIGIROP-Screen had equal or higher sensitivity and specificity compared with other models. DIGIROP-Screen should be tested in any new cohort for validation and if not validated it can be modified using the same statistical approaches applied to a specific clinical setting.
