Fisher Exact Test Calculation Using Precomputed Logarithmic Factorials

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Fisher's exact test calculations require significant processing time, especially in genome-wide association studies, due to the need for extensive computations on large quantities of summary tables, which can be cumbersome and time-consuming, especially in computer environments with limited resources.

Innovation Solution

A Fisher's exact test calculation apparatus and method that utilizes precomputation and a decision tree-based approach to efficiently determine the significance of test results by storing conditional expressions and results for common frequency patterns, allowing for faster magnitude comparisons and reducing the need for extensive factorial calculations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional Fisher's exact test calculation methods are used on large quantities of summary tables, then statistical significance can be determined, but processing time becomes excessively long

Engineering Contradiction:

Improvestatistical significance determinationVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent precomputes factorial values and their logarithms before performing Fisher's exact test calculations. By storing these precomputed values in memory, the system avoids repeated factorial calculations during the actual testing phase, significantly reducing processing time when analyzing large quantities of summary tables in genome-wide association studies

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent transforms the calculation from direct factorial computation to logarithmic domain operations. By using log(factorial) values and performing additions instead of multiplications, the system maintains calculation precision while dramatically improving computational efficiency for determining statistical significance

Inventive Principle:

Principle #35Parameter changes

2Reliability

If extensive factorial calculations are performed for each summary table, then accurate test results are obtained, but computational resources are overwhelmed

Engineering Contradiction:

Improvetest result accuracyVSAvoidcalculation speed

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system performs preliminary computation of factorial values and stores them in a lookup table before actual testing. This precomputation phase separates the heavy computational burden from the actual Fisher's exact test execution, allowing rapid retrieval of factorial values during testing while maintaining result accuracy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces direct factorial calculation mechanisms with logarithmic arithmetic operations. By computing log(factorial) values and using addition instead of multiplication, the system substitutes complex mechanical computation with simpler arithmetic operations that are faster and less resource-intensive

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11544350B2Fisher's exact test calculation apparatus, method, and program

Publication Date: 2023.01.03 NIPPON TELEGRAPH & TELEPHONE CORP

AI summary

A Fisher's exact test calculation apparatus includes: a condition storage 1 that has stored therein a condition for determining whether a result of Fisher's exact test corresponding to input is significant or not, the input being frequencies in a summary table; and a calculation unit 2 that obtains the result of Fisher's exact test corresponding to the frequencies in the summary table by inputting the frequencies in the summary table to the condition read from the condition storage 1.