# Detecting cognitive impairments by agreeing on interpretations of linguistic features

arXiv: https://arxiv.org/abs/1808.06570 · HTML: https://mlsanity.com/paper/1808.06570/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Aug 2018.

## Built on by (most cited first, 6 of 6)

- [Comparing Acoustic-based Approaches for Alzheimer's Disease Detection](https://mlsanity.com/paper/2106.01555/) (2021)
- [Robustness and Sensitivity of BERT Models Predicting Alzheimer's Disease from Text](https://mlsanity.com/paper/2109.11888/) (2021)
- [DECK: Behavioral Tests to Improve Interpretability and Generalizability of BERT Models Detecting Depression from Text](https://mlsanity.com/paper/2209.05286/) (2022)
- [Impact of Environmental Noise on Alzheimer's Disease Detection from Speech: Should You Let a Baby Cry?](https://mlsanity.com/paper/2203.17110/) (2022)
- [Deep Insights into Cognitive Decline: A Survey of Leveraging Non-Intrusive Modalities with Deep Learning Techniques](https://mlsanity.com/paper/2410.18972/) (2024)
- [A Robust Classification Method using Hybrid Word Embedding for Early Diagnosis of Alzheimer's Disease](https://mlsanity.com/paper/2510.14332/) (2025)

## Abstract (arXiv)

Linguistic features have shown promising applications for detecting various cognitive impairments. To improve detection accuracies, increasing the amount of data or the number of linguistic features have been two applicable approaches. However, acquiring additional clinical data can be expensive, and hand-crafting features is burdensome. In this paper, we take a third approach, proposing Consensus Networks (CNs), a framework to classify after reaching agreements between modalities. We divide linguistic features into non-overlapping subsets according to their modalities, and let neural networks learn low-dimensional representations that agree with each other. These representations are passed into a classifier network. All neural networks are optimized iteratively. In this paper, we also present two methods that improve the performance of CNs. We then present ablation studies to illustrate the effectiveness of modality division. To understand further what happens in CNs, we visualize the representations during training. Overall, using all of the 413 linguistic features, our models significantly outperform traditional classifiers, which are used by the state-of-the-art papers.