Related Experiment Video
Updated: Apr 3, 2026
09:16
Multi-Modal Signals for Analyzing Pain Responses to Thermal and Electrical Stimuli
Published on: April 5, 2019
11.7K
Application of Intelligent Neonatal Pain Assessment Tools Based on Multimodal Data Fusion: A Systematic Review
Qiaojia Zhou1, Xuanni Huang1, Yuanhong Lv1
1Department of Neonatology, Shenzhen Children's Hospital, Shenzhen, People's Republic of China.
Journal of Pain Research
|April 2, 2026
Summary
Multimodal pain assessment significantly improves neonatal pain evaluation accuracy compared to single methods. Further research is needed to standardize approaches and ensure clinical applicability for better pain management.
Area of Science:
- Neonatal care
- Pain assessment
- Intelligent systems
Background:
- Effective neonatal pain assessment is vital for pain management but faces limitations with traditional scales and single-modal intelligent systems.
- Intelligent systems integrating multimodal data offer a promising alternative for objective and continuous pain assessment in neonates.
Purpose of the Study:
- To systematically review and synthesize current intelligent neonatal pain assessment methods utilizing multimodal data fusion.
- To evaluate the accuracy and limitations of existing multimodal approaches in neonatal pain assessment.
Main Methods:
- A systematic review of studies published up to September 12, 2025, was conducted.
- Databases searched included PubMed, Embase, Cochrane Library, and Web of Science.
- Methodological quality was assessed using QUADAS-2, and findings were synthesized.
Main Results:
- Nine studies met inclusion criteria, with seven comparing single-modal and multimodal assessments.
- All studies indicated multimodal approaches achieved higher accuracy than single-modal methods.
- While effective in assessing pain intensity (77.78%), challenges remain in handling missing data (44.44%) and external validation (33.33%).
Conclusions:
- Multimodal pain assessment demonstrates superior accuracy in neonatal pain evaluation.
- Heterogeneity in modalities and outcome indicators limits identifying optimal combinations.
- Further research on standardization, clinical applicability, and validation is crucial for clinical translation.
