Neural Network Disease Spectroscopy with Electromechanical IR Sensors

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing biofluid analysis methods for disease detection are invasive, require expensive equipment, and are limited by temporal fluctuations and limited multiplexing, making them unsuitable for real-time, portable, and cost-effective monitoring.

Innovation Solution

A Neural Network Enabled Disease Spectroscopy (NNEDS) platform using plasmonic nano-micro electromechanical systems (NMEMS) with advanced machine learning techniques to identify unique spectral fingerprints in biofluids, employing a chip with electromechanical IR sensors to detect discrete IR absorption data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If traditional biofluid analysis methods are used, then disease detection can be performed, but the methods are invasive and require expensive equipment

Engineering Contradiction:

Improvecost-effectivenessVSAvoidequipment complexity

Core Design Contradiction:

Ease of manufactureVSDevice complexity

Solution Approach 1:

The device segments the infrared spectrum into multiple discrete spectral bands using an array of electromechanical sensors, each tuned to detect a specific band. This segmentation enables parallel processing of spectral data and reduces the complexity of single-sensor systems while maintaining comprehensive detection capability

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent replaces traditional mechanical scanning methods with an array of parallel electromechanical sensors that simultaneously detect multiple spectral bands. This substitution eliminates the need for mechanical movement and reduces equipment complexity while maintaining measurement precision

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If traditional biofluid analysis methods are used, then disease detection can be performed, but they are limited by temporal fluctuations and cannot provide real-time monitoring

Engineering Contradiction:

Improvereal-time monitoring capabilityVSAvoidtemporal response time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The device enables continuous real-time monitoring by continuously irradiating the biofluid sample with infrared light and continuously detecting spectral responses. The system maintains uninterrupted measurement, eliminating temporal gaps and providing ongoing health monitoring

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The system performs preliminary spectral fingerprint identification using machine learning algorithms to quickly classify disease states before clinical intervention is needed, enabling early detection and rapid response

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If traditional biofluid analysis methods are used, then disease detection can be performed, but they have limited multiplexing capability

Engineering Contradiction:

Improvemultiplexing capabilityVSAvoidnumber of detectable spectral bands

Core Design Contradiction:

Adaptability or versatilityVSQuantity of substance

Solution Approach 1:

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent transitions from single-sensor sequential measurement to multi-sensor parallel measurement across multiple spectral dimensions. This dimensional expansion enables simultaneous detection of multiple spectral bands, significantly increasing multiplexing capability

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

4Measurement precision

If a chip with multiple electromechanical IR sensors is used, then discrete spectral bands can be detected simultaneously, but the device complexity increases

Engineering Contradiction:

Improvespectral detection precisionVSAvoidsensor array complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent merges multiple electromechanical sensors into a single integrated chip that detects multiple spectral bands simultaneously. This consolidation reduces system complexity by eliminating the need for separate detection devices while maintaining high measurement precision through parallel sensing

Inventive Principle:

Principle #5Merging (Combining)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables rapid, label-free, and portable disease diagnosis with high specificity and sensitivity, suitable for large-scale community screening and real-time health monitoring, comparable to mass spectrometry performance.

Implementation Method 1

a nanopatterned metasurface configured to absorb IR light within a discrete spectral band centered at a predefined wavelength

Methodology Applied

Scientific EffectPlasmonic resonance: Absorption (EM radiation)

Implementation Method 2

Each electromechanical IR sensor of the electromechanical IR sensors may comprises a piezoelectric resonator

Methodology Applied

Scientific EffectPiezoelectric effect: Piezoelectric Effect

Data Source

PatentUS20250321185A1Neural network enabled disease spectroscopy

Publication Date: 2025.10.16 RGT UNIV OF CALIFORNIA

AI summary

Described herein are devices, systems. and methods for detecting diseases using neural network enabled disease spectroscopy. Using an infrared (IR) light source. a biofluid sample is irradiated. IR responses within discrete spectral bands are detected using electromechanical IR sensors with piezoelectric resonators having nanopatterned metasurfaces tuned to each discrete spectral band. A discrete set of values corresponding to the IR responses is generated upon which a trained neural network is executed to generate a disease stage classification for the biofluid sample.