Subgroup membership predicted distinct long-term literacy trajectories 68.2 months after intervention ended¶

Claim · All claims
Evidence · 1 study · associational r1 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? For the 39 participants tested at follow-up from Responder Subgroup 1 and Non-Responder Subgroups 1-3, subgroup membership differentiated directionality of longitudinal performance across word reading, spelling, pseudoword decoding, and reading comprehension. → Tan 2026

Evidence¶

Tan 2026¶

Tan, A.S.-C., & Ali, F. (2026). Uncovering subgroup heterogeneity in dyslexia intervention outcomes using explainable machine learning. npj Science of Learning. https://doi.org/10.1038/s41539-026-00429-3

q2 · i? · associational · r1

Longitudinal follow-up of 41 recruited participants; Responder Subgroup 2 and Non-Responder Subgroup 4 were omitted due to n = 1. Follow-up duration (T1-T2) averaged 68.2 months. Retained participants did not differ significantly from non-participants (p > 0.05; χ²(5) = 7.45, p = .19).

"the subgroups, based solely on the collection of predictor importance (not actual predictor values directly), were also able to demonstrate subsequent predictive potential of the longitudinal outcomes for Responder Subgroup 1, Non-responder Subgroup 1, 2 and 3."

Discussion¶

Related Claims¶

• Responder Subgroup 1 improved across all measures during intervention and maintained gains long-term except reading comprehension, which regressed — a narrower finding that bears on this claim
• Non-responder subgroups showed heterogeneous longitudinal trajectories despite similar short-term regression, including inverse trends in Non-Responder Subgroup 3 — a narrower finding that bears on this claim
• K-Means clustering of LIME feature-importance profiles identifies 2 responder and 4 non-responder subgroups within binary intervention-response classes — related