- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces KineGait, a multicenter dataset of 6-DoF knee kinematics, including 4,168 healthy participants for self-supervised pretraining and additional cohorts for disease classification. The authors also propose GaitReader, which segments gait recordings into individual cycles, learns DoF-specific gait vocabularies, and uses masked prediction and waveform reconstruction to learn representations from healthy subjects. The pretrained model is then fine-tuned to classify Healthy, ACLD, and KOA subjects. Experiments on internal and external test sets show improved classification performance over several baselines, particularly when fewer labeled training samples are available.
Critical strengths
The paper addresses a meaningful problem: learning useful gait representations from healthy subjects to reduce the need for labeled patient data. The KineGait dataset is a valuable contribution, with over 4,000 healthy participants and additional clinical data collected across multiple centers. The experiments are also fairly comprehensive, including comparisons with several existing methods, external testing, label-efficiency experiments, and ablation studies. The results show consistent improvements from pretraining, especially when fewer labeled samples are available.
Critical weaknesses
- Potential confounding in disease classification: Table B.3 shows substantial age and sex differences among the Healthy, ACLD, and KOA groups, while Table B.1 indicates that healthy controls were recruited from community sources and patients from hospitals. Since these factors can also affect gait patterns, it is unclear how much of the classification performance reflects disease-related features rather than differences between the cohorts. I think an age- and sex-matched or stratified evaluation would make the results more convincing.
- The contribution of the proposed pretraining method is not fully isolated: Although Table 1 shows good performance, most baselines use different input representations and do not have the same rhythm information as GaitReader. More importantly, removing the gait vocabulary reduces external accuracy only from 89.87% to 88.10% (Table 3), while removing the rhythm embedding causes a much larger drop to 68.10% (Table D.4). This raises the question of how much of the improvement comes from the proposed VQ-based pretraining rather than the cycle-level representation and rhythm information. A more controlled comparison would help clarify this.
Questions for authors
- Given the age, sex, and recruitment differences shown in Tables B.1 and B.3, could you provide an age- and sex-matched or stratified evaluation to better understand the impact of these factors on disease classification?
- Table D.4 shows a large performance drop when rhythm embeddings are removed. Could you explain why rhythm information has such a strong effect on external performance? Also, would it be possible to compare GaitReader with the strongest baselines using the same cycle-level inputs and rhythm information?
4 comments
Response to Reviewer eTXd (Part 2/2)
Q2: Removing rhythm mainly impairs KOA and Healthy recognition, with substantially larger recall decreases externally. ACLD recall changes little.
Recall values are means across five fold-specific models (%). Duration is the mean of subject-level cycle means (seconds).
| Test | Class | Full recall | w/o rhythm recall | Mean cycle duration |
|---|---|---|---|---|
| Internal | Healthy | 94.80 | 87.60 | 0.876 |
| Internal | ACLD | 92.50 | 92.19 | 1.411 |
| Internal | KOA | 90.83 | 76.67 | 1.796 |
| External | Healthy | 85.26 | 69.05 | 0.946 |
| External | ACLD | 85.24 | 83.50 | 1.197 |
| External | KOA | 97.63 | 53.90 | 2.314 |
The duration statistics help explain this pattern: KOA cycles are longer than Healthy cycles, with a larger difference externally (2.314 vs 0.946 s) than internally (1.796 vs 0.876 s). The longer cycles are consistent with reduced walking speed and cadence and increased stride time reported for KOA by Gök et al. (2002). Resampling cycles to 100 points removes their absolute duration; duration/interval inputs restore this information alongside morphology. Together, these observations help explain the larger external removal effect and support the value of rhythm information across the evaluated center populations.
The gain also depends on pretraining, not just rhythm inputs. With the same backbone and rhythm inputs, the following five-model mean external accuracies are obtained:
| Configuration | External Acc. (%) |
|---|---|
| Supervised backbone | 82.03 |
| Shape–attribute coupled reconstruction | 83.61 |
| Full GaitReader | 89.87 |
We further tested HeartLang and TS2Vec, the strongest internal and external baselines in Table 1, respectively. HeartLang already uses the same gait-cycle units as GaitReader; we add rhythm inputs and also test greater depth and bilateral cross-attention. For TS2Vec, we compare continuous and cycle-aligned inputs, each with and without rhythm. Values below are five-model mean accuracy (%); “Deeper” denotes four contextual layers.
| Model / variant | Internal Acc. | External Acc. |
|---|---|---|
| HeartLang: Original | 91.45 | 74.56 |
| HeartLang: Original + rhythm | 91.01 | 79.81 |
| HeartLang: Deeper | 90.29 | 78.35 |
| HeartLang: Deeper + rhythm | 90.14 | 80.38 |
| HeartLang: Deeper + rhythm + cross | 90.72 | 83.73 |
| TS2Vec: Original | 87.25 | 85.76 |
| TS2Vec: Original + rhythm | 89.28 | 85.57 |
| TS2Vec: Original + cycle | 86.52 | 70.06 |
| TS2Vec: Original + cycle + rhythm | 89.13 | 81.90 |
| Full GaitReader | 93.04 | 89.87 |
GaitReader retains its advantage on both test sets after the baselines receive cycle-level inputs and rhythm information. These comparisons support contributions from the learned gait representations alongside explicit timing.
Revised manuscript: class-wise recall and duration analysis in Appendix D.8, Table D.12 and Figure D.2 (p. 33); HeartLang/TS2Vec comparisons in Appendix D.6, Tables D.7–D.8 (p. 29); same-backbone pretraining comparisons in Table D.9 (p. 29; discussion on p. 30).
Thank the authors for their rebuttal and experiments
Thank the authors for their rebuttal and experiments.
For my first concern, I think it's good they have an additional dataset to verify the issue, but the number of new samples are still limited thus the evaluation result is still not convincing enough. And the issue of data source still exists.
My second concern about the rhythm embedding is addressed with their new experiments, I thus raise my ratings to 3.
Response to Reviewer eTXd
Thank you for your thoughtful follow-up. We appreciate your careful review and constructive feedback, which have helped us improve the paper and strengthen its evaluation.
Response to Reviewer eTXd (Part 1/2)
We thank the reviewer for the constructive review and for highlighting the need to examine demographic differences, explain the contribution of rhythm information to external performance, and strengthen the baseline comparisons. We provide additional analyses and controlled experiments addressing these points, and respond point by point below.
Q1: GaitReader maintains high classification performance in age- and sex-matched cohorts. We evaluate same-sex Healthy/ACLD/KOA triplets with maximum age differences of five and ten years, using the same five fold-specific Full models. Each matched cohort has equal class counts.
Values are five-model means (%).
The matched external accuracies remain 87.56% and 89.72%, compared with 35.56% and 39.17% for age-and-sex-only classifiers on the same cohorts. These results support the predictive value of gait representations beyond those demographic features.
Age differences also decrease under both matching settings. The pairwise absolute age SMDs are shown below; sex proportions are identical across the three classes in every matched cohort.
SMD uses the original-cohort pooled SD for each class pair as a fixed denominator across the original and both matched settings within each test set. The five-year setting yields closer age balance; the ten-year setting retains more subjects.
Revised manuscript: Appendix D.7 / Table D.10 (p. 31) for protocol and performance, and Table D.11 (p. 32) for demographic composition and age SMDs.