Modeling common finger movement patterns in daily activities: A quantitative framework for adaptive rehabilitation interfaces

Background Hand movement involves complex joint patterns that vary across tasks and individuals, and identifying the components that underlie functional hand use is essential. Objective We aimed to construct a Commonality Model that decomposes real-world finger motions into dynamic forms and quantify probabilistic transitions to develop rehabilitation systems for post-stroke patients. Methods Fifteen healthy young adults performed upper limb tasks based on a Motor Activity Log (MAL), with hand motion captured using a camera and analyzed using MediaPipe. Joint angle data were extracted, k-means clustering was used to classify the movement patterns, and silhouette analysis was performed to determine the optimal number of clusters. Euclidean distance was used to identify overlapping forms across tasks grouped into Common Forms (CFs). A first-order Markov model was constructed to calculate the transition probabilities from CFs to unique task-specific forms. Results Seven operationally defined CFs were identified as recurrent image-derived hand-joint configurations observed across multiple activities of daily living (ADL) related tasks. Some tasks were largely composed of CF-associated transitions, whereas others showed higher proportions of task-dependent Individual Forms. Conclusion The proposed Commonality Model provides an exploratory quantitative framework for identifying recurring and task-dependent hand-joint configurations during ADL-related movements in healthy young adults. Further studies are required to validate its reproducibility, generalizability, and clinical relevance in larger and clinical populations.

Authors

Institutions

Publication Details

Journal
Technology and Health Care
Published
2026-11-19
DOI
https://doi.org/10.1177/09287329261505704
Primary Topic
Stroke Rehabilitation and Recovery
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Modeling common finger movement patterns in daily activities: A quantitative framework for adaptive rehabilitation interfaces

Toyohiro Hamaguchi, Masahiro Abo, Kohei Koizumi, Ryota Suwabe et al.
Technology and Health Care
Stroke Rehabilitation and Recovery
article

Modeling common finger movement patterns in daily activities: A quantitative framework for adaptive rehabilitation interfaces

Toyohiro Hamaguchi, Masahiro Abo, Kohei Koizumi, Ryota Suwabe, Takeshi Saito
article en

Abstract

Background Hand movement involves complex joint patterns that vary across tasks and individuals, and identifying the components that underlie functional hand use is essential. Objective We aimed to construct a Commonality Model that decomposes real-world finger motions into dynamic forms and quantify probabilistic transitions to develop rehabilitation systems for post-stroke patients. Methods Fifteen healthy young adults performed upper limb tasks based on a Motor Activity Log (MAL), with hand motion captured using a camera and analyzed using MediaPipe. Joint angle data were extracted, k-means clustering was used to classify the movement patterns, and silhouette analysis was performed to determine the optimal number of clusters. Euclidean distance was used to identify overlapping forms across tasks grouped into Common Forms (CFs). A first-order Markov model was constructed to calculate the transition probabilities from CFs to unique task-specific forms. Results Seven operationally defined CFs were identified as recurrent image-derived hand-joint configurations observed across multiple activities of daily living (ADL) related tasks. Some tasks were largely composed of CF-associated transitions, whereas others showed higher proportions of task-dependent Individual Forms. Conclusion The proposed Commonality Model provides an exploratory quantitative framework for identifying recurring and task-dependent hand-joint configurations during ADL-related movements in healthy young adults. Further studies are required to validate its reproducibility, generalizability, and clinical relevance in larger and clinical populations.

Technology and Health Care
Jikei University School of Medicine (JP), Saitama Prefectural University (JP), Tokyo Dental College Ichikawa General Hospital (JP), The Jikei University Hospital (JP)
Stroke Rehabilitation and Recovery
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