Summary of Gamified Ai Approch For Early Detection Of Dementia, by Paramita Kundu Maji et al.
Gamified AI Approch for Early Detection of Dementia
by Paramita Kundu Maji, Soubhik Acharya, Priti Paul, Sanjay Chakraborty, Saikat Basu
First submitted to arxiv on: 26 May 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel gaming approach inspired by deep learning for early detection of dementia, combining health metrics data and facial image data through a cognitive assessment-based application. The study integrates a robust convolutional neural network (CNN)-based model, training MOD-1D-CNN on 1000 health metrics samples from Apollo Diagnostic Center Kolkata and MOD-2D-CNN on 1800 facial images collected by the research team. The proposed models demonstrate high accuracy in identifying dementia traits using real-life data: MOD-1D-CNN achieves a loss of 0.2692 and an accuracy of 70.50%, while MOD-2D-CNN reaches a loss of 0.1755 and an accuracy of 95.72%. A rule-based weightage method is applied to combine the models, offering lightweight and computationally efficient alternatives with lower parameter counts compared to state-of-the-art deep learning models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper develops a new gaming approach for detecting dementia early using health metrics data and facial images. The goal is to create an app that can identify signs of dementia through a game. To do this, the researchers trained special computer programs (models) on large datasets: 1000 health metrics samples from a hospital in Kolkata and 1800 facial images taken by the research team. These models were very accurate at identifying whether someone has dementia or not: one model got it right 70.5% of the time, while the other got it right 95.72% of the time. The researchers combined these models to make a final decision. |
Keywords
» Artificial intelligence » Cnn » Deep learning » Neural network
