Related Experiment Video
Updated: Mar 19, 2026
Subjective Refraction Test Using a Smartphone for Vision Screening
Published on: October 18, 2024
From blink to care: smartphone video-based functional analysis and personalized management in pediatric
Huimin Li1, Jing Cao1, Shuangshuang Duan2
1Eye Center of Second Affiliated Hospital, School of Medicine, China, Zhejiang Provincial Key Laboratory of Ophthalmology. Zhejiang Provincial Clinical Research Center for Eye Diseases, Zhejiang Provincial Engineering Institute on Eye Diseases, Zhejiang University, Hangzhou, China.
Insights
A new smartphone system offers early detection of congenital ptosis, improving visual and psychosocial outcomes. This tool accurately assesses ptosis morphology and function, enhancing pediatric eye care.
Area of Science:
- Ophthalmology
- Biomedical Engineering
- Artificial Intelligence in Healthcare
Background:
- Early detection of congenital ptosis is crucial for preventing vision loss and psychosocial issues in children.
- Clinical ptosis assessment faces challenges due to poor patient cooperation and limited specialist access.
Purpose of the Study:
- To develop and validate a novel smartphone-based system for comprehensive congenital ptosis evaluation.
- To assess the accuracy and applicability of morphological, functional, and AI-driven diagnostic modules.
Main Methods:
- A prospective, multicenter study involving 3164 blink clips and 1229 facial images.
- Development of three system modules: morphological assessment, functional analysis (levator dysfunction), and a domain-adapted dialogue model.
- Validation against manual assessments and real-world deployment with patient interaction.
Main Results:
- Morphological module achieved high accuracy (ICC > 0.90) compared to manual measurements.
- Functional module demonstrated excellent levator dysfunction identification (AUC 0.993) and robust stratification accuracy (0.91 internal, 0.89 real-world).
- Dialogue model showed improved performance over baseline, comparable to GPT-4o, with high patient satisfaction (4.93/5).
Conclusions:
- The smartphone platform provides precise ptosis evaluation with patient-centered interaction.
- This technology facilitates informed decision-making and personalized care in oculoplastic practice.
- Enables accessible and accurate ptosis assessment, overcoming traditional clinical limitations.
Abstract:
Early detection of congenital ptosis is critical to prevent visual and psychosocial impairment in children, yet clinical assessment is challenged by limited patient cooperation and specialist availability. In this prospective, multicenter study, we developed and validated a smartphone-based system comprising three modules: morphological assessment, functional analysis, and a domain-adapted dialogue model, using 3164 blink clips and 1,229 facial images. The morphological module showed high measurement accuracy with intraclass correlation coefficients over 0.90 versus manual assessments. The functional module identified levator dysfunction with an area under the curve of 0.993, achieving robust functional stratification accuracy in both internal (0.91) and real-world (0.89) cohorts. The dialogue model demonstrated improved correctness and applicability over its baseline in addressing ptosis-related queries, achieving overall performance comparable to GPT-4o in expert evaluation and a patient satisfaction score of 4.93/5 in real-world deployment. This smartphone platform enables precise ptosis evaluation with patient-centered interaction, facilitating informed decision-making and personalized care in oculoplastic practice. ClinicalTrials.gov NCT07078552.
