Performance-weighted ensemble learning for detecting patients with FTD and ALS from short reading tasks

We developed a novel machine learning model named performance-weighted ensemble learning (PWEL) to detect frontotemporal dementia (FTD) and amyotrophic lateral sclerosis (ALS) using speech from word and sentence reading tasks. Overall, 197 participants (30 with FTD, 74 with ALS, and 93 healthy controls) were enrolled. The brief oral reading tasks consisted of 16 materials adapted from the Western Aphasia Battery and took 1 min to complete. For each task, 405 speech features (i.e., 384 acoustic, 17 linguistic, and 4 temporal) were extracted. Five-fold cross-validation highlighted acoustic features—especially Mel-Frequency Cepstral Coefficients—as key discriminators of FTD and ALS from healthy controls. PWEL, which included under-bagging and adaptive task selection, achieved an area under the curve of 0.840, a sensitivity of 0.828, and an overall accuracy of 0.792. The sensitivity for FTD subtypes was 0.700–0.933, and that for ALS reached 0.812. Our proposed model surpassed both a simple ensemble learning model and task-wise classification in overall sensitivity, accuracy, and macro-F1. Its internal robustness was supported by consistent performance across stratified cross-validation folds and three recording sites. In conclusion, PWEL is practical, scalable, and making it a promising tool for detecting neurodegenerative disorders.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-11
DOI
https://doi.org/10.1038/s41598-026-73857-1
Primary Topic
Dementia and Cognitive Impairment Research
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Performance-weighted ensemble learning for detecting patients with FTD and ALS from short reading tasks

Reiko Ohdake, Masahisa Katsuno, Gen Sobue, Hirohisa Watanabe et al.
1 links
Scientific Reports
Dementia and Cognitive Impairment Research
article

Performance-weighted ensemble learning for detecting patients with FTD and ALS from short reading tasks

Reiko Ohdake, Masahisa Katsuno, Gen Sobue, Hirohisa Watanabe, Manabu Ikeda, Kazuhiro Hara, Sayuri Shima, Takuto Sakuma, Yasuaki Mizutani, Aya Ogura, Shōhei Kato, Hiroyuki Watanabe, Yuki Ito, Maki Suzuki, Michihito Masuda, Mamoru Hashimoto, Kazuhiro Ishibashi
article en

Abstract

We developed a novel machine learning model named performance-weighted ensemble learning (PWEL) to detect frontotemporal dementia (FTD) and amyotrophic lateral sclerosis (ALS) using speech from word and sentence reading tasks. Overall, 197 participants (30 with FTD, 74 with ALS, and 93 healthy controls) were enrolled. The brief oral reading tasks consisted of 16 materials adapted from the Western Aphasia Battery and took 1 min to complete. For each task, 405 speech features (i.e., 384 acoustic, 17 linguistic, and 4 temporal) were extracted. Five-fold cross-validation highlighted acoustic features—especially Mel-Frequency Cepstral Coefficients—as key discriminators of FTD and ALS from healthy controls. PWEL, which included under-bagging and adaptive task selection, achieved an area under the curve of 0.840, a sensitivity of 0.828, and an overall accuracy of 0.792. The sensitivity for FTD subtypes was 0.700–0.933, and that for ALS reached 0.812. Our proposed model surpassed both a simple ensemble learning model and task-wise classification in overall sensitivity, accuracy, and macro-F1. Its internal robustness was supported by consistent performance across stratified cross-validation folds and three recording sites. In conclusion, PWEL is practical, scalable, and making it a promising tool for detecting neurodegenerative disorders.

Scientific Reports
Fujita Health University (JP), Aichi Medical University (JP), Nagoya Institute of Technology (JP), Okazaki City Hospital (JP), Japanese Red Cross Nagoya Daini Hospital (JP), Brain & Mind Research Center, Nagoya University (JP), Nagoya University (JP), Kindai University (JP), The University of Osaka (JP)
Ministry of Education, Culture, Sports, Science and Technology, Iran Telecommunication Research Center, Japan Society for the Promotion of Science, National Institute of Information and Communications Technology
Good health and well-being
Dementia and Cognitive Impairment Research
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon