- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes a model that exploits the pattern characteristics of medical time series. Before tokens enter the Transformer, it combines information from the current time point, its neighborhood, and the global context at the token formation stage. This reflects a key property of medical time series well, namely that the meaning of a local pattern depends on its surrounding context and the overall physiological state. I also appreciate that the paper goes beyond comparing classification performance. It analyzes the model from several angles, including ablations, robustness tests, and patient-level analysis.
However, a few aspects need improvement. First, the mathematical formulation should be organized more clearly, with all symbols defined and a consistent flow between equations. Second, the experiments mainly demonstrate gains in performance and robustness. They do not directly verify whether the proposed structure works as intended, for example whether the gates actually assign higher weights to meaningful positions depending on the context. If these points are addressed, I believe this would be a solid contribution.
Critical strengths
-
The paper takes a well-motivated direction by jointly considering three key aspects of medical time-series patterns: the local observation itself, its neighboring context, and the global state of the sample. I find this a sound way to approach the problem.
-
The proposed model is analyzed from multiple perspectives, including ablations, a controlled tokenizer comparison, robustness tests, and patient-level analysis. These experiments are well suited to demonstrating the merits of the architecture.
-
The evaluation protocol is careful. All experiments use subject-independent splits, which avoids data leakage across subjects. The paired short- and long-window setup on PTB-XL keeps labels, sample counts, and splits fixed, so it isolates the effect of the available temporal context.
Critical weaknesses
-
The proposed idea is well motivated, but it is difficult to verify whether the architecture actually implements the intended mechanism. Some symbols are used without definition, and the flow between equations is occasionally broken. The method section needs a clearer and more self-contained formulation, ideally with a notation table.
-
To show that the proposed design is meaningful, an interpretability analysis is needed. For example, the authors could visualize the learned gates and mixing coefficients and check whether the weights concentrate on specific ECG leads or on clinically relevant segments (e.g., the QRS complex or ST segment). Without such evidence, it is hard to tell whether the gains come from context-conditioned token formation as claimed.
Questions for authors
[Questions]
- What is the specific reason for choosing the SRS tokenizer as the controlled comparison?
- Several symbols in Eqs. (1)–(4), such as , , , and , are not clearly defined. Please define each symbol when it is first introduced.
- It remains unclear whether the proposed structure actually realizes the described methodology. In Eq. (7), the gate multiplies the input features before a nonlinear MLP and a second softmax inside , so a larger gate value does not necessarily mean a larger contribution to the aggregation. Could the authors explain how the design guarantees the intended behavior, or provide empirical evidence (e.g., the learned values of and )?
- Are 1 s and 10 s appropriate definitions of "short" and "long"? Clinically, 10 s still seems short. I understand this is a dataset limitation, but what is the practical difference in diagnostic content between the two settings?
- In Section 5.4, a performance drop under noise is expected. Wouldn't the relative degradation (e.g., F1_noisy / F1_clean) be more informative than absolute F1, especially since ReConTok starts from the highest clean score?
- Table 9 uses different branch configurations per dataset (e.g., Channel only for PTB, Temporal only for PTB-XL). Why is this, given that applying CoTGF to both branches is claimed as a key contribution? Were the same configurations used for Table 2?
[Optional]
- Transposing Table 4 (swapping rows and columns) would likely improve readability.
- Figure 2(a) is too small, and its legend and bubbles are hard to read. Please consider enlarging it.