Related Experiment Video
Updated: Jan 20, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Activity in Memory Brain Networks During Encoding Differentiates Mild Cognitive Impairment Converters from
Naiara Aguirre1, Víctor Costumero1,2, Lidón Marin-Marin1
1Department of Basic and Clinical Psychology and Psychobiology, Jaume I University, Castelló de la Plana, Spain.
Mild cognitive impairment patients who convert to Alzheimer's disease show higher brain network activation, potentially as a compensatory mechanism. This hyperactivation in the medial temporal lobe network may help distinguish converters from non-converters.
Area of Science:
- Neuroscience
- Medical Imaging
- Cognitive Science
Background:
- Alzheimer's disease (AD) is linked to memory deficits, particularly affecting the medial temporal lobe (MTL) and precuneus.
- Understanding brain network alterations in early stages like mild cognitive impairment (MCI) is crucial for early diagnosis and intervention.
Purpose of the Study:
- To investigate the impact of Alzheimer's disease on brain networks involving the hippocampus and precuneus during memory encoding.
- To explore potential differences in network activation between MCI converters (MCIc), MCI non-converters (MCIn), and AD patients.
Main Methods:
- Functional magnetic resonance imaging (fMRI) was used during a memory encoding task in 68 MCI patients, 21 AD patients, and 20 healthy controls (HC).
- Independent component analysis (ICA) was applied to analyze brain networks associated with the MTL and precuneus.
- MCI patients were clinically followed for 18 months to determine conversion status.
Main Results:
- Healthy controls outperformed MCI converters and AD patients in memory tasks.
- MCI converters exhibited significantly higher activation in the MTL-associated network (including hippocampus, parahippocampus, fusiform gyrus) compared to MCIn and AD patients.
- The precuneus network, linked to the default mode network, showed a negative correlation with behavioral performance.
Conclusions:
- Hyperactivation in the hippocampal network among MCI converters may serve as a compensatory mechanism.
- This heightened activation has potential diagnostic value for differentiating MCI converters from non-converters.
- The findings offer insights into early brain changes associated with Alzheimer's disease progression.
Related Concept Videos
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Flyback Converter
A flyback converter is a buck-boost converter, which can both buck and boost. It has electrical isolation between the input and the output using a coupled inductor or a "flyback transformer." This coupled inductor enables a turns ratio that provides both voltage step-up and step-down capability, like in a regular transformer but with energy storage using the air-gap of the coupled inductor.
DC/DC Boost Converter
Boost converters provide a versatile solution to stepping up DC voltages in many applications where a DC voltage needs to be increased without the need to convert it to AC, using a transformer, and then rectifying the transformer output. Boost converters are step-up converters that use an inductor as an energy storage device that supports the output with additional energy in addition to the DC input...
05:58Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment
16:08Brain Imaging Investigation of the Impairing Effect of Emotion on Cognition
DC/DC Buck Converter
While it is simple to step up or down AC voltages and currents using transformers, stepping up or down DC voltages and currents in an efficient and regulated manner requires switching power converters. The DC/DC buck converter chops the input DC voltage using a series input switch, and the chopped voltage is filtered through the L-C low-pass filter to extract the average output voltage. The diode...