Related Experiment Video
Updated: Mar 21, 2026
12:27
Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
Published on: February 15, 2017
7.4K
Estimating paediatric normative values for nerve studies using clustering techniques.
G K Cooray1,2,3, D Motan2, K Howse2
1Karolinska Institutet, Stockholm, 171 77, Sweden.
Clinical Neurophysiology Practice
|March 20, 2026
Summary
This study used unsupervised clustering to establish normative electroneurography values for children aged 0-18 years. The data-driven method provides reliable paediatric nerve conduction data from mixed clinical findings.
Area of Science:
- Pediatric Neurology
- Clinical Electrophysiology
Background:
- Establishing normative electrophysiological values in children is challenging due to heterogeneous clinical data.
- Existing reference ranges may not fully capture developmental variations.
Purpose of the Study:
- To estimate normative values for paediatric electroneurography using an unsupervised clustering approach.
- To analyze motor and sensory nerve parameters in children aged 0-18 years.
Main Methods:
- Analysis of electroneurography studies from pediatric patients (2009-2024).
- Application of t-distributed stochastic neighbour embedding (t-SNE) for normative distribution identification within age groups.
- Derivation and modeling of mean, 5th, and 95th centiles using exponential fits.
Main Results:
- Normative values were estimated for ages 0-18 years.
- Motor amplitudes increased with age; conduction velocities showed rapid early rise, then plateaued.
- Distal motor latency had an initial dip followed by an increase; sensory amplitudes peaked between 1-8 years.
Conclusions:
- Unsupervised clustering effectively derives normative paediatric electroneurography values from mixed clinical data.
- The data-driven approach is practical, generalizable, and aids in identifying healthy individuals.
