A Biomedical Case Study Showing That Tuning Random Forests Can Fundamentally Change the Interpretation of Supervised Data Structure Exploration Aimed at Knowledge Discovery
Knowledge discovery in biomedical data using supervised methods assumes that the data contain structure relevant to the class structure if a classifier can be trained to assign a case to the correct class better than by guessing. In this setting, acceptance or rejection of a scientific hypothesis ma...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | BioMedInformatics |
Subjects: | |
Online Access: | https://www.mdpi.com/2673-7426/2/4/34 |
_version_ | 1797622141859921920 |
---|---|
author | Jörn Lötsch Benjamin Mayer |
author_facet | Jörn Lötsch Benjamin Mayer |
author_sort | Jörn Lötsch |
collection | DOAJ |
description | Knowledge discovery in biomedical data using supervised methods assumes that the data contain structure relevant to the class structure if a classifier can be trained to assign a case to the correct class better than by guessing. In this setting, acceptance or rejection of a scientific hypothesis may depend critically on the ability to classify cases better than randomly, without high classification performance being the primary goal. Random forests are often chosen for knowledge-discovery tasks because they are considered a powerful classifier that does not require sophisticated data transformation or hyperparameter tuning and can be regarded as a reference classifier for tabular numerical data. Here, we report a case where the failure of random forests using the default hyperparameter settings in the standard implementations of R and Python would have led to the rejection of the hypothesis that the data contained structure relevant to the class structure. After tuning the hyperparameters, classification performance increased from 56% to 65% balanced accuracy in R, and from 55% to 67% balanced accuracy in Python. More importantly, the 95% confidence intervals in the tuned versions were to the right of the value of 50% that characterizes guessing-level classification. Thus, tuning provided the desired evidence that the data structure supported the class structure of the data set. In this case, the tuning made more than a quantitative difference in the form of slightly better classification accuracy, but significantly changed the interpretation of the data set. This is especially true when classification performance is low and a small improvement increases the balanced accuracy to over 50% when guessing. |
first_indexed | 2024-03-11T09:06:07Z |
format | Article |
id | doaj.art-93bf94a8c1714895a4aff0953f8bfc4c |
institution | Directory Open Access Journal |
issn | 2673-7426 |
language | English |
last_indexed | 2024-03-11T09:06:07Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | BioMedInformatics |
spelling | doaj.art-93bf94a8c1714895a4aff0953f8bfc4c2023-11-16T19:21:21ZengMDPI AGBioMedInformatics2673-74262022-10-012454455210.3390/biomedinformatics2040034A Biomedical Case Study Showing That Tuning Random Forests Can Fundamentally Change the Interpretation of Supervised Data Structure Exploration Aimed at Knowledge DiscoveryJörn Lötsch0Benjamin Mayer1Institute of Clinical Pharmacology, Goethe-University, Theodor-Stern-Kai 7, 60590 Frankfurt am Main, GermanyInstitute of Clinical Pharmacology, Goethe-University, Theodor-Stern-Kai 7, 60590 Frankfurt am Main, GermanyKnowledge discovery in biomedical data using supervised methods assumes that the data contain structure relevant to the class structure if a classifier can be trained to assign a case to the correct class better than by guessing. In this setting, acceptance or rejection of a scientific hypothesis may depend critically on the ability to classify cases better than randomly, without high classification performance being the primary goal. Random forests are often chosen for knowledge-discovery tasks because they are considered a powerful classifier that does not require sophisticated data transformation or hyperparameter tuning and can be regarded as a reference classifier for tabular numerical data. Here, we report a case where the failure of random forests using the default hyperparameter settings in the standard implementations of R and Python would have led to the rejection of the hypothesis that the data contained structure relevant to the class structure. After tuning the hyperparameters, classification performance increased from 56% to 65% balanced accuracy in R, and from 55% to 67% balanced accuracy in Python. More importantly, the 95% confidence intervals in the tuned versions were to the right of the value of 50% that characterizes guessing-level classification. Thus, tuning provided the desired evidence that the data structure supported the class structure of the data set. In this case, the tuning made more than a quantitative difference in the form of slightly better classification accuracy, but significantly changed the interpretation of the data set. This is especially true when classification performance is low and a small improvement increases the balanced accuracy to over 50% when guessing.https://www.mdpi.com/2673-7426/2/4/34data scienceartificial intelligencemachine-learningdigital medicine |
spellingShingle | Jörn Lötsch Benjamin Mayer A Biomedical Case Study Showing That Tuning Random Forests Can Fundamentally Change the Interpretation of Supervised Data Structure Exploration Aimed at Knowledge Discovery BioMedInformatics data science artificial intelligence machine-learning digital medicine |
title | A Biomedical Case Study Showing That Tuning Random Forests Can Fundamentally Change the Interpretation of Supervised Data Structure Exploration Aimed at Knowledge Discovery |
title_full | A Biomedical Case Study Showing That Tuning Random Forests Can Fundamentally Change the Interpretation of Supervised Data Structure Exploration Aimed at Knowledge Discovery |
title_fullStr | A Biomedical Case Study Showing That Tuning Random Forests Can Fundamentally Change the Interpretation of Supervised Data Structure Exploration Aimed at Knowledge Discovery |
title_full_unstemmed | A Biomedical Case Study Showing That Tuning Random Forests Can Fundamentally Change the Interpretation of Supervised Data Structure Exploration Aimed at Knowledge Discovery |
title_short | A Biomedical Case Study Showing That Tuning Random Forests Can Fundamentally Change the Interpretation of Supervised Data Structure Exploration Aimed at Knowledge Discovery |
title_sort | biomedical case study showing that tuning random forests can fundamentally change the interpretation of supervised data structure exploration aimed at knowledge discovery |
topic | data science artificial intelligence machine-learning digital medicine |
url | https://www.mdpi.com/2673-7426/2/4/34 |
work_keys_str_mv | AT jornlotsch abiomedicalcasestudyshowingthattuningrandomforestscanfundamentallychangetheinterpretationofsuperviseddatastructureexplorationaimedatknowledgediscovery AT benjaminmayer abiomedicalcasestudyshowingthattuningrandomforestscanfundamentallychangetheinterpretationofsuperviseddatastructureexplorationaimedatknowledgediscovery AT jornlotsch biomedicalcasestudyshowingthattuningrandomforestscanfundamentallychangetheinterpretationofsuperviseddatastructureexplorationaimedatknowledgediscovery AT benjaminmayer biomedicalcasestudyshowingthattuningrandomforestscanfundamentallychangetheinterpretationofsuperviseddatastructureexplorationaimedatknowledgediscovery |