# TAMI: Temporally Aligned, Missingness-Aware, and Interpretable Multimodal Fusion for Mental Health Assessment in Older Adults with Mild Cognitive Impairment

arXiv: https://arxiv.org/abs/2608.30857 · HTML: https://mlsanity.com/paper/2608.30857/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 86 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [AVEC 2019 Workshop and Challenge: State-of-Mind, Detecting Depression with AI, and Cross-Cultural Affect Recognition](https://mlsanity.com/paper/1907.11510/) (2019)
- [L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments](https://mlsanity.com/paper/2203.03339/) (2022)
- [Py-Feat: Python Facial Expression Analysis Toolbox](https://mlsanity.com/paper/2104.03509/) (2021)
- [HiQuE: Hierarchical Question Embedding Network for Multimodal Depression Detection](https://mlsanity.com/paper/2408.03648/) (2024)
- [MC-ViViT: Multi-branch Classifier-ViViT to detect Mild Cognitive Impairment in older adults using facial videos](https://mlsanity.com/paper/2304.05292/) (2023)
- [Reading Between the Frames: Multi-Modal Depression Detection in Videos from Non-Verbal Cues](https://mlsanity.com/paper/2401.02746/) (2024)
- [GRACE: Loss-Resilient Real-Time Video through Neural Codecs](https://mlsanity.com/paper/2305.12333/) (2023)
- [A Topic-Attentive Transformer-based Model For Multimodal Depression Detection](https://mlsanity.com/paper/2206.13256/) (2022)
- [Detection of Mild Cognitive Impairment Using Facial Features in Video Conversations](https://mlsanity.com/paper/2308.15624/) (2023)
- [Enhancing Depression Detection via Question-wise Modality Fusion](https://mlsanity.com/paper/2503.20496/) (2025)
- [Towards Stable Cross-Domain Depression Recognition under Missing Modalities](https://mlsanity.com/paper/2512.06447/) (2025)
- [Feasibility of Detecting Cognitive Impairment and Psychological Well-being among Older Adults Using Facial, Acoustic, Linguistic, and Cardiovascular Patterns Derived from Remote Conversations](https://mlsanity.com/paper/2412.14194/) (2024)

## Abstract (arXiv)

Depression and anxiety in older adults with Mild Cognitive Impairment (MCI) are frequently underdiagnosed due to limited access to care. Multimodal analysis of remote clinical interviews is a scalable screening approach, but existing methods have three limitations. First, they do not correct temporal misalignment across multimodal features extracted at different resolutions, inducing spurious cross-modal associations. Second, remote recordings exhibit uneven modality dropout, but missing values are often zero-filled, making them indistinguishable from valid near-zero measurements. Finally, they do not jointly attribute predictions to modalities, questions, and interview moments, limiting fine-grained clinical interpretation. We propose a Temporally-Aligned, Missingness-Aware, Interpretable (TAMI) multimodal fusion framework. TAMI aligns speech, language, facial, and physiological features within question-answer segments on a shared timeline, encodes modality-level missingness over time, and conditions fusion on question context. In interviews with 49 older adults with MCI, TAMI achieved area under the receiver operating characteristic curve (AUROC) scores of 0.68 (depression) and 0.69 (anxiety). Fine-grained temporal alignment of multimodal features produced the largest performance gain (Delta≥0.1). Multi-level interpretability analysis revealed that depression classification relied on eyegaze and open-ended questions, while anxiety classification depended on eyegaze and head pose, with attribution uniformly distributed across questions. Using only responses to the open-ended questions (5.1min), the depression model achieved an AUROC score of 0.67, which was not significantly different from using the full interview (19min) (p>0.05). Our findings support designing interview protocols centered on open-ended questions for depression screening in older adults with MCI.