Predicting training outcomes for developmental dyslexia from EEG data.

Giuseppe Di Dona; Denisa Adina Zamfira; Francesco De Benedetto; Chiara Turri; Camilla Venturini; Lisa Venniro; Daniela Perani; Luca Ronconi

doi:10.1016/j.ridd.2026.105365

PubMed · 42600369

Predicting training outcomes for developmental dyslexia from EEG data.

Giuseppe Di Dona·Denisa Adina Zamfira·Francesco De Benedetto·Chiara Turri·Camilla Venturini·Lisa Venniro·Daniela Perani·Luca Ronconi

View original source ↗Export metadata ↓

Abstract

Developmental dyslexia (DD) is characterised by lower-than-average reading abilities and is diagnosed in approximately 10% of individuals. The societal barriers may limit professional fulfilment and psychological wellbeing of individuals with DD, calling for the development of effective interventions to counteract them. As DD is associated with challenges in both phonological and visuo-attentional domains, different longitudinal training approaches were developed to strengthen them. However, they require a considerable amount of personal, social and economic resources and the outcomes may vary depending on individual differences in behavioural and neurophysiological functionality. Hence, predicting training outcomes might help in developing personalised treatment protocols and optimising the use of resources. In the present work we applied machine learning to resting-state EEG to predict longitudinal training outcomes in adults with DD enrolled in a randomized clinical trial. In particular, one group received a visuo-attentional training combined with transcranial alternating current stimulation (tACS), another group received visuo-attentional training with sham/placebo stimulation, and the third group received a phonological training with sham/placebo stimulation. The improvement in text reading speed was associated with spectral power in low-beta and individual frequencies in the alpha (IAF) and beta (IBF) bands, while the improvement in pseudoword reading was associated with IBF. The findings highlight the potential of capturing neural markers of treatment responsiveness in DD. Future studies should focus on the generalisability of predictive models to real-world settings, while investigating whether specific EEG markers predict responsiveness to distinct remediation protocols, thus supporting the development of personalised interventions.

Explore related subjects

Humans Dyslexia Electroencephalography Reading Transcranial Direct Current Stimulation Female Adult Machine Learning Male Treatment Outcome Young Adult Attention Predictive Learning Models EEG Learning disabilities Machine learning Training Journal Article Randomized Controlled Trial

Keep this discovery

BibTeX RIS

Giuseppe Di Dona, Denisa Adina Zamfira, Francesco De Benedetto, Chiara Turri, Camilla Venturini, Lisa Venniro, Daniela Perani, Luca Ronconi. 2026-08-14. Predicting training outcomes for developmental dyslexia from EEG data.. https://doi.org/10.1016/j.ridd.2026.105365

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

Journal Article; Randomized Controlled Trial resource Adult subject Attention subject EEG subject Electroencephalography subject Female subject Humans subject Journal Article subject Machine Learning subject Male subject Predictive Learning Models subject Randomized controlled trials study

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related citations

PubMed2026

Implicit and explicit statistical learning in reading: Evidence from a randomized controlled-learning study and computational modeling.

A key challenge in reading acquisition is understanding how learners extract the complex probabilistic mappings between print, meaning, and sound. Statistical learning (SL) theory offers a mechanistic account of how such mappings are acquired, whether implicitly through exposure or explicitly through instruction. We conducted a randomized controlled-learning study in Chinese, a writing system characterized by multiple sub-lexical regularities linking orthography, semantics, and phonology. Ninety-five 2nd-3rd graders with or at risk for dyslexia were randomly assigned to one of three groups: an implicit-SL training group exposed to repeated lexical and sublexical orthography-semantics-phonology associations, an explicit-SL training group receiving the same input plus explicit instruction on the sublexical print-sound mapping, and a no-SL control group. Both SL groups outperformed controls on the characters they were trained on, as well as on untrained characters that required generalization. However, only the explicit group demonstrated abstraction of print-sound mapping to novel items. Neural network simulations further revealed distinct mechanisms supporting implicit and explicit SL, consistent with a dual-system account of reading acquisition. Together, these findings (1) clarify how implicit and explicit learning distinctly support the discovery of statistical structure in written language and (2) underscore the implicit-explicit dual learning mechanism underlying reading acquisition.

Humans↗

PubMed2026

Functional Reading Activities to Motivate and Empower: Maintenance of Reading Outcomes for Young Adults With Intellectual and Developmental Disabilities Following a Randomized Controlled Trial.

PURPOSE: This study examined whether the effects of Functional Reading Activities to Motivate and Empower (FRAME), a functional, strategy-based reading comprehension intervention for young adults with intellectual and developmental disabilities (IDDs), were maintained 6 months following the completion of the intervention and explored participants' perceptions of the intervention's feasibility, relevance, and perceived impact. METHOD: Participants were 44 young adults with IDDs (ages 18-26 years) who participated in a previously reported randomized controlled trial (FRAME participants: n = 23; controls: n = 21). Trial outcomes were assessed via telepractice at pretest, posttest, and 6-month follow-up. Six-month maintenance analyses focused on outcomes that demonstrated significant posttest group differences: use of (a) reading comprehension strategies (proximal) and (b) reading comprehension questions (distal). Participant perceptions (social validity) were collected post-intervention from FRAME participants using a structured interview protocol with closed- and open-ended items. RESULTS: At the 6-month follow-up, FRAME participants demonstrated sustained but reduced improvements in strategy use relative to controls (p = .040). Between-groups differences were not maintained for reading comprehension questions (p = .091). Participants reported high acceptability and perceived relevance of FRAME, with qualitative themes reflecting perceived improvements in comprehension, self-improvement, and increased independence. CONCLUSION: Findings suggest that FRAME supports sustainable gains in reading comprehension strategy use and is perceived as meaningful and feasible for young adults with IDDs, although additional supports may be needed to promote sustained improvements in distal comprehension outcomes. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.33307218.

Humans↗

PubMed2026

Ictal electroencephalography and heart rate as treatment criteria in electroconvulsive therapy: a systematic review of the literature.

BACKGROUND: Decades before the emergence of precision medicine, psychiatrists raised the question of whether specific seizure characteristics could help optimize electroconvulsive therapy (ECT), as relationships between some of these characteristics and better outcomes were found. From 1990 onward, researchers focused on electroencephalography (EEG) and cardiovascular markers, which were broadly adopted by guidelines worldwide. However, the prognostic value of these markers is still controversial. Here, we provide a systematic summary of the studies on this topic. METHODS: We conducted a literature review on the use of ictal EEG and heart rate as outcome predictors in ECT using the PubMed, EMBASE, Cochrane and PsycINFO databases. RESULTS: Thirty-seven studies addressing more than 100 quality markers fulfilled our inclusion criteria. Single EEG markers were assigned to five categories (postictal inhibition, amplitude, coherence, regularity, and seizure duration). Heart rate and composite markers were considered separately. In contrast to single EEG markers, heart rate and composite markers could be consistently linked to better outcomes in patients with depression. Only a few studies on schizophrenia could be retrieved. CONCLUSION: Multiparametric markers outperformed single markers. Furthermore, changes in heart rate during seizures were related to better outcomes. Although clinical assessment remains the cornerstone of treatment guidance decisions, EEG and cardiac monitoring could help prevent insufficient seizures during the period preceding clinical improvement. Evidence on schizophrenia remains limited. More randomized trials are needed to analyze the role of composite markers as prognostic tools.

Humans↗