Anastasis Ridinet

Analysing data to help children with learning disabilities and other special education needs.
Thematic area: Health, Projects
Financing: IFAB for PMI
Enabling Technology: Big Data Analytics

The project examines data from some reading exercises on the RIDInet platform for integrated telerehabilitation (in presence and distance) of learning disorders and other Special Educational Needs. The exercises are parameterised by the clinicians according to the neuropsychological profile of the children, and carried out both in the studio and at home under adult supervision. The children choose the passages to be read from an extensive library: reading takes place in software-guided mode by highlighting the individual reading unit (grapheme, syllable, word), at the child’s natural tempo or at a preset speed. During the course of treatment, clinicians remotely monitor the child’s progress and can modify the performance parameters accordingly.

Goals

The aim is to carry out the analysis of data obtained during reading exercises of children with learning disabilities and other special educational needs. For the analysis, the learning curves will be compared to see if there are any changes to the parameters that predict the greatest and fastest improvement.

The initial challenge

To try to understand in more detail the different reading speed and accuracy profiles and their learning curves.

The solution

Data measurement includes:

  • Speed: calculated based on the time taken to read the text and expressed in syllables/second. The first speed of each individual is calculated by the clinician with an accurate initial test.
  • Accuracy: defined as the percentage of syllables read correctly, the number of incorrect syllables is scored by the parent
  • Success: an event that occurs when both speed and accuracy are above the target set by the clinician.

To optimise the logic of the self-adaptive increment, solutions are:

  • involve clinical experts for suggestions
  • analysing the manual mode, where speed is not influenced by the clinician’s settings
  • entering the age of individuals because from this one can trace the pathology by comparing the initial letter rate and statistical distribution of children
  • including PND (percentage of non-overlapping data) in the analysis
  • being able to put a graphic display of parameters on the clinician’s screen

Benefits

The project provides important information for developing detailed learning curves and calibrating reading difficulty levels to support the individual’s learning.

Partners

Respect for privacy in the data extraction and processing process

All data that were extracted and contributed to the processing and analysis process were treated in full compliance with Article 13 of the GDPR (General Data Protection Regulation) EU 2016/679. In the information notice on data processing, which was submitted to the parents of the patients taken care of through the RidiNet teletreatment platform, explicit and specific consent was requested for the possible processing of the data for the purposes of statistical and epidemiological research. The data were processed in strictly anonymous and aggregate form. For any other information on data from the RidiNet service, please visit the following web page: https://privacy.ridinet.it/

 

For further information, please contact: barbara.vecchi@ifabfoundation.org

Sustainable Development Goals

,

Share on:

You may also be interested in:

Stay updated on the latest IFAB events and projects.Subscribe to our monthly newsletter