To learn or not to learn? Model-based estimation of motor learning in a large, "in the wild", home rehabilitation database.

Overview

1. Department of Computer Science, University of Southern California, Los Angeles, California, United States of America
2. Department of Biokinesiology and Physical Therapy, University of Southern California, Los Angeles, California, United States of America
3. Flint Rehab, Irvine, California, United States of America
4. Department of Mechanical and Aerospace Engineering, University of California at Irvine, Irvine, California, United States of America

Abstract

Motor learning, defined as practice-related processes leading to relatively permanent changes in response capability, is critical for regaining motor function following brain injury. However, quantifying learning in real-world, unsupervised settings remains challenging. Here, we present a model-based framework for estimating the presence and extent of motor learning across multiple tasks and users from a large “in-the-wild” rehabilitation dataset collected via the FitMi sensor system. We analyzed 4,661 episodes from 398 users practicing 20 upper-limb tasks for at least 50 sessions. For each episode, we modeled the effect of daily dose (repetitions) on performance (repetitions per second) using a discrete-time first-order state-space model, in which a latent motor memory evolves through cumulative practice. The model employed a learning rate for memory updates and a forgetting time constant for decay. Simulation-based recovery confirmed the robustness of this procedure despite realistic noise and irregular practice schedules. We utilized a likelihood ratio test (LRT) to compare this learning model against a non-learning null model. Overall, 38.3% of episodes were classified as learning. Among these, 44.6%, which correspond to 17.1% of all episodes, exhibited a time constant exceeding 30 days, consistent with durable motor memory. In contrast, non-learning episodes exhibited short time constants (under 2 days), reflecting transient fluctuations. Task-level analysis revealed no clear dichotomy between learnable and non-learnable tasks. Among users practicing at least five tasks, 18% were non-learners and only 5% exhibited learning on all tasks, suggesting that generalizable improvements were rare. Our findings demonstrate that real-world rehabilitation induces detectable motor learning in specific tasks and users. Future research will incorporate user-level covariates, characterize higher-order learning dynamics, and validate findings against clinical outcomes to establish a link with functional recovery. These results offer a path toward optimizing post-stroke recovery through individualized task selection.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data, not to its authors' code: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

• osf:jdy7k — at OSF; found in “Data Availability”

Data Availability

The minimal data set is available on the Open Science Framework (OSF), a free and open-source platform that hosts a wide variety of research data and materials contributed by researchers from diverse fields. https://osf.io/jdy7k/.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 6 authors, 2 funders, 54 references.

Cite

This paper

Wen, Y., Ye, D., Poudel, R., Zondervan, D., Reinkensmeyer, D., & Schweighofer, N. (2026). To learn or not to learn? Model-based estimation of motor learning in a large, "in the wild", home rehabilitation database. PLOS digital health, 5(8), e0001598. https://doi.org/10.1371/journal.pdig.0001598

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.7554/elife.108684 [code]

Multi-timescale neural adaptation underlying long-term musculoskeletal reorganization.

Journal: eLife

In common: 3 references

[2] doi:10.1162/imag.a.1359 [code]

Distinct roles of brain network flexibility in motor learning across age.

Journal: Imaging neuroscience (Cambridge, Mass.)

In common: 2 references

[3] doi:10.1371/journal.pcbi.1014523 [code]

Coordinative structures as scale-free networks: Cascade and percolation dynamics in motor learning with empirical validation.

Journal: PLoS computational biology

In common: 1 reference

[4] doi:10.1186/s12974-026-03885-1 [code]

Shared transcriptomic signatures in perilesional and contralesional cortex after ischemic stroke.

Journal: Journal of neuroinflammation

In common: 1 reference

[5] doi:10.7554/elife.107423 [code]

A context-free model of savings in motor learning.

Journal: eLife

In common: 1 reference

[6] doi:10.1038/s41598-026-44365-z [code]

Foot-ground force quantifies impaired balance control mechanisms post-stroke.

Journal: Scientific reports

In common: 1 reference

[7] doi:10.1038/s41467-026-76109-y [code]

Assistive algorithms influence neural representations in motor brain-computer interfaces.

Journal: Nature communications

In common: 1 reference

[8] doi:10.1371/journal.pone.0354021 [code]

A genetic algorithm for self-supervised models of oscillatory neurodynamics.

Journal: PloS one

In common: 1 reference

[9] doi:10.3389/fnins.2026.1907378 [code]

Explainable machine-learning integration of pre-task and preparatory EEG: revealing complementary predictive information for expert action reliability.

Journal: Frontiers in neuroscience

In common: 1 reference

[10] doi:10.1038/s41467-026-75799-8 [code]

Behaviourally driven closed-loop beta-tACS enhances beta activity and motor behaviour.

Journal: Nature communications

In common: 1 reference

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.