Artificial intelligence system for predicting hand-foot skin reaction induced by vascular endothelial growth factor receptor inhibitors

Abstract Hand-foot skin reaction (HFSR) is a common adverse effect of vascular endothelial growth factor receptor (VEGFR) inhibitors that significantly impacts patients’ quality of life. Prevention and management of HFSR require individualized approaches, but risk factors remain unclear. This study...

Full description

Saved in:
Bibliographic Details
Main Authors: Taro Yamanaka, Jumpei Ukita, Dongyi Xue, Chihiro Kondoh, Seiwa Honda, Maiko Noguchi, Yoshiko Yonejima, Kiyomi Nonogaki, Kohji Takemura, Rika Kizawa, Takeshi Yamaguchi, Yuko Tanabe, Koichi Suyama, Keisuke Ogaki, Yuji Miura
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-93471-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850095102018453504
author Taro Yamanaka
Jumpei Ukita
Dongyi Xue
Chihiro Kondoh
Seiwa Honda
Maiko Noguchi
Yoshiko Yonejima
Kiyomi Nonogaki
Kohji Takemura
Rika Kizawa
Takeshi Yamaguchi
Yuko Tanabe
Koichi Suyama
Keisuke Ogaki
Yuji Miura
author_facet Taro Yamanaka
Jumpei Ukita
Dongyi Xue
Chihiro Kondoh
Seiwa Honda
Maiko Noguchi
Yoshiko Yonejima
Kiyomi Nonogaki
Kohji Takemura
Rika Kizawa
Takeshi Yamaguchi
Yuko Tanabe
Koichi Suyama
Keisuke Ogaki
Yuji Miura
author_sort Taro Yamanaka
collection DOAJ
description Abstract Hand-foot skin reaction (HFSR) is a common adverse effect of vascular endothelial growth factor receptor (VEGFR) inhibitors that significantly impacts patients’ quality of life. Prevention and management of HFSR require individualized approaches, but risk factors remain unclear. This study aimed to develop artificial intelligence (AI) models to predict grade ≥ 2 HFSR using clinical data and foot sole images from 93 instances of VEGFR inhibitor administration in 76 patients. Image-based, clinical information-based, and ensemble AI models achieved areas under the curve of 0.550, 0.693, and 0.699, respectively. At a high-specificity cutoff, the ensemble AI had a positive predictive value of 0.824, suggesting potential clinical utility for identifying high-risk patients. Feature importance analysis revealed heavier weight, good performance status, lack of prior VEGFR inhibitor exposure, and baseline skin toxicity as risk factors. These findings represent the first AI-based HFSR prediction models and provide insights for preventive interventions, but further accuracy improvements are needed.
format Article
id doaj-art-8a2e727896c247bcb4af4a24dbcf6fd5
institution DOAJ
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-8a2e727896c247bcb4af4a24dbcf6fd52025-08-20T02:41:31ZengNature PortfolioScientific Reports2045-23222025-03-011511710.1038/s41598-025-93471-xArtificial intelligence system for predicting hand-foot skin reaction induced by vascular endothelial growth factor receptor inhibitorsTaro Yamanaka0Jumpei Ukita1Dongyi Xue2Chihiro Kondoh3Seiwa Honda4Maiko Noguchi5Yoshiko Yonejima6Kiyomi Nonogaki7Kohji Takemura8Rika Kizawa9Takeshi Yamaguchi10Yuko Tanabe11Koichi Suyama12Keisuke Ogaki13Yuji Miura14Department of Medical Oncology, Toranomon HospitalM3 Inc.M3 Inc.Department of Medical Oncology, National Cancer Center Hospital EastM3 Inc.Mebix Inc.Department of Medical Oncology, Toranomon HospitalDepartment of Medical Oncology, Toranomon HospitalDepartment of Medical Oncology, Toranomon HospitalDepartment of Medical Oncology, Toranomon HospitalDepartment of Medical Oncology, Toranomon HospitalDepartment of Medical Oncology, Toranomon HospitalDepartment of Medical Oncology, Toranomon HospitalM3 Inc.Department of Medical Oncology, Toranomon HospitalAbstract Hand-foot skin reaction (HFSR) is a common adverse effect of vascular endothelial growth factor receptor (VEGFR) inhibitors that significantly impacts patients’ quality of life. Prevention and management of HFSR require individualized approaches, but risk factors remain unclear. This study aimed to develop artificial intelligence (AI) models to predict grade ≥ 2 HFSR using clinical data and foot sole images from 93 instances of VEGFR inhibitor administration in 76 patients. Image-based, clinical information-based, and ensemble AI models achieved areas under the curve of 0.550, 0.693, and 0.699, respectively. At a high-specificity cutoff, the ensemble AI had a positive predictive value of 0.824, suggesting potential clinical utility for identifying high-risk patients. Feature importance analysis revealed heavier weight, good performance status, lack of prior VEGFR inhibitor exposure, and baseline skin toxicity as risk factors. These findings represent the first AI-based HFSR prediction models and provide insights for preventive interventions, but further accuracy improvements are needed.https://doi.org/10.1038/s41598-025-93471-xHFSRVEGFR inhibitorDeep learningAI
spellingShingle Taro Yamanaka
Jumpei Ukita
Dongyi Xue
Chihiro Kondoh
Seiwa Honda
Maiko Noguchi
Yoshiko Yonejima
Kiyomi Nonogaki
Kohji Takemura
Rika Kizawa
Takeshi Yamaguchi
Yuko Tanabe
Koichi Suyama
Keisuke Ogaki
Yuji Miura
Artificial intelligence system for predicting hand-foot skin reaction induced by vascular endothelial growth factor receptor inhibitors
Scientific Reports
HFSR
VEGFR inhibitor
Deep learning
AI
title Artificial intelligence system for predicting hand-foot skin reaction induced by vascular endothelial growth factor receptor inhibitors
title_full Artificial intelligence system for predicting hand-foot skin reaction induced by vascular endothelial growth factor receptor inhibitors
title_fullStr Artificial intelligence system for predicting hand-foot skin reaction induced by vascular endothelial growth factor receptor inhibitors
title_full_unstemmed Artificial intelligence system for predicting hand-foot skin reaction induced by vascular endothelial growth factor receptor inhibitors
title_short Artificial intelligence system for predicting hand-foot skin reaction induced by vascular endothelial growth factor receptor inhibitors
title_sort artificial intelligence system for predicting hand foot skin reaction induced by vascular endothelial growth factor receptor inhibitors
topic HFSR
VEGFR inhibitor
Deep learning
AI
url https://doi.org/10.1038/s41598-025-93471-x
work_keys_str_mv AT taroyamanaka artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors
AT jumpeiukita artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors
AT dongyixue artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors
AT chihirokondoh artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors
AT seiwahonda artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors
AT maikonoguchi artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors
AT yoshikoyonejima artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors
AT kiyominonogaki artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors
AT kohjitakemura artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors
AT rikakizawa artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors
AT takeshiyamaguchi artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors
AT yukotanabe artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors
AT koichisuyama artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors
AT keisukeogaki artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors
AT yujimiura artificialintelligencesystemforpredictinghandfootskinreactioninducedbyvascularendothelialgrowthfactorreceptorinhibitors