Investigating the Data Addition Dilemma in Longitudinal TBI MRI

Clinical machine learning (CML) for brain MRI often assumes that more data guarantees better performance, yet added samples can reduce accuracy when they arise from a different distribution, a phenomenon known as the Data Addition Dilemma. We present a systematic study of this issue in longitudinal TBI MRI, where first longitudinal MRI session (S1) and follow-up scans (S2) differ substantially. Using a 14-subject, 28-scan cohort, we quantify the combined effects of intra-subject session shifts and inter-subject variability on severity classification. We evaluate four training schemes: (1) intra-session upper bound (S1  \(\rightarrow \)  S1), (2) cross-session OOD testing (S1  \(\rightarrow \)  S2), (3) pooled training (S1+S2  \(\rightarrow \)  S1, S2), and (4) LOSO-IPA, which adds one unlabeled S2 scan per patient. With a lightweight logistic-regression model on PCA features, we show that naive pooling can degrade accuracy, pooled training trades baseline performance for modest robustness gains, and LOSO-IPA recovers accuracy close to the intra-session limit. We recommend per-subject follow-up anchoring and diagonal CORAL alignment to mitigate session effects. These results clarify when additional data help or hinder CML workflows and provide a minimally invasive strategy for reliable longitudinal TBI severity assessment.