Neural Network Analysis of Applicant Images for Life Insurance Underwriting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The underwriting process for life insurance is hindered by the need for invasive medical procedures and the risk of fraudulent information, as existing methods struggle to accurately assess health-related characteristics without direct medical examinations.

Innovation Solution

A system and method that analyze still and/or moving images and voice recordings using machine learning techniques, such as neural networks, to probabilistically determine personal and health-related characteristics, thereby facilitating the determination of appropriate insurance premiums and terms of coverage without requiring conventional medical examinations or fluid samples.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional medical examinations and fluid samples are required for underwriting, then measurement precision of health characteristics is improved, but device complexity and ease of operation deteriorate

Engineering Contradiction:

Improvehealth characteristic assessment accuracyVSAvoidunderwriting process convenience

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces mechanical/physical medical examination systems with an optical-based machine vision system. The processing element analyzes images captured by cameras to extract health-related information, substituting invasive medical procedures with non-contact optical analysis. This maintains measurement precision while dramatically improving ease of operation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediary processing element that acts as a mediator between the captured images and the underwriting decision. This processing element extracts health characteristics from images without requiring direct medical examination, serving as an intermediate step that preserves accuracy while simplifying the overall process.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If invasive medical procedures are used to assess health status, then reliability of health information is improved, but object-affected harmful factors increase

Engineering Contradiction:

Improvehealth information accuracyVSAvoidinvasiveness and fraud risk

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent replaces invasive mechanical medical procedures with optical image analysis. By using machine vision to extract health characteristics from images, the system eliminates the need for blood draws, physical examinations, and other invasive procedures, thereby removing the associated harmful factors while maintaining information reliability through advanced processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a visual copy of the applicant through captured images and analyzes this copy to extract health information. This copying approach allows assessment of health characteristics without physically interacting with or invading the applicant's body, eliminating invasive harmful factors while preserving measurement reliability through sophisticated image analysis.

Inventive Principle:

Principle #26Copying

3Ease of operation

If statistical techniques and proxy data are used to assess health, then ease of operation is improved, but measurement precision deteriorates

Engineering Contradiction:

Improveonline underwriting capabilityVSAvoidhealth characteristic determination accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent replaces statistical proxy methods with direct optical measurement through machine vision. By analyzing actual images of the applicant rather than using indirect statistical correlations from other data sources, the system achieves higher measurement precision while maintaining the ease of online operation through automated image processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20240027780A1Using images and voice recordings to facilitate underwriting life insurance

Publication Date: 2024.01.25 STATE FARM MUTAL AUTOMOBILE INSURANCE COMPANY

AI summary

A system and method for evaluating an insurance applicant as part of an underwriting process to determine one or more appropriate terms of life or other insurance coverage, such as premiums. A processing element employing a neural network is trained to correlate aspects of appearance and/or voice with personal and/or health-related characteristic. A database of images and/or voice recordings of individuals with known personal and/or health-related characteristics is provided for this purpose. The processing element is then provided with an image and/or voice recording of the insurance applicant. The image may be an otherwise non-diagnostic image, such as an ordinary “selfie.” The trained processing element analyzes the image of the insurance applicant, with their permission or affirmative consent, to determine the personal and/or health-related characteristic for the insurance applicant, and then, based upon that analysis, facilitates the underwriting process and/or suggests the one or more appropriate terms of insurance coverage.