James Liao

Dr. James Liao

orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 April 2021 in Journal of Neural Transmission
Verified
Journal Article
Closed access
PDF file
JLJames Liao
James Liao
PSPhilippe A. Salles
Philippe A. Salles
USUmar A. Shuaib
Umar A. Shuaib
HFHubert H. Fernandez
Hubert H. Fernandez

7 September 2023 in Parkinsonism & Related Disorders
Verified
Journal Article
Closed access
BBBrendan Baugher
Brendan Baugher
NSNathaniel Szewczyk
Nathaniel Szewczyk
JLJames Liao
James Liao

7 July 2023 in Parkinsonism & Related Disorders
Verified
Journal Article
Closed access
JYJeryl Ritzi T Yu
Jeryl Ritzi T Yu
CSClaire Sonneborn
Claire Sonneborn
OHOlivia Hogue
Olivia Hogue
DGDebolina Ghosh
Debolina Ghosh
ABAnne Brooks
Anne Brooks
BWBenjamin L Walter
Benjamin L Walter

24 July 2014 in PLOS ONE
Verified
Journal Article
Open access
PDF file
JLJames Liao
James Liao
RKRobert F. Kirsch
Robert F. Kirsch
We have demonstrated that 3D target-oriented human arm reaches can be represented as linear combinations of discrete submovements, where the submovements are a set of minimum-jerk basis functions for the reaches. We have also demonstrated the ability of deterministic feed-forward Artificial Neural Networks (ANNs) to predict the parameters of the submovements. ANNs were trained using kinematic data obtained experimentally from five human participants making target-directed movements that were decomposed offline into minimum-jerk submovements using an optimization algorithm. Under cross-validation, the ANNs were able to accurately predict the parameters (initiation-time, amplitude, and duration) of the individual submovements. We also demonstrated that the ANNs can together form a closed-loop model of human reaching capable of predicting 3D trajectories with VAF >95.9% and RMSE ≤4.32 cm relative to the actual recorded trajectories. This closed-loop model is a step towards a practical arm trajectory generator based on submovements, and should be useful for the development of future arm prosthetic devices that are controlled by brain computer interfaces or other user interfaces.

4 July 2025 in Nature Communications
Verified
Journal Article
Open access
PDF file
YYYasunori Yamada
Yasunori Yamada
MKMasatomo Kobayashi
Masatomo Kobayashi
KSKaoru Shinkawa
Kaoru Shinkawa
EBErhan Bilal
Erhan Bilal
JLJames Liao
James Liao
TATETSUAKI ARAI
TETSUAKI ARAI
Deep-neural-network-based artificial intelligence enables quantitative gait analysis with commodity sensors. However, current gait-analysis models are usually specialized for specific clinical populations and sensor settings due to the limited size and diversity of available datasets. We propose an approach that involves using synthetic gaits generated using a generative model learned via physics-based simulation with a broad spectrum of musculoskeletal parameters and evaluated its utility for data-efficient generalization of gait-analysis models across different clinical populations and sensor settings. The model trained solely on synthetic data estimates gait parameters with comparable or superior performance compared with real-data-trained models specialized for specific populations and sensor settings. Pre-training on synthetic data with self-supervised learning consistently enhances model performance and data efficiency in adapting to multiple gait-based downstream tasks. The results indicate that our approach offers an efficient means to augment data size and diversity for developing generalizable healthcare applications involving sensor-based gait analysis.

23 April 2025 in Movement Disorders
Verified
Journal Article
Open access
CPCamila C. Piccinin
Camila C. Piccinin
SASaar Anis
Saar Anis
JYJeryl Ritzi T. Yu
Jeryl Ritzi T. Yu
PSPhilippe A. Salles
Philippe A. Salles
HCHenry Mauricio Chaparro‐Solano
Henry Mauricio Chaparro‐Solano
IMIgnacio F. Mata
Ignacio F. Mata
Knowledge of the genetic factors in normal pressure hydrocephalus (NPH) is rapidly evolving, with significant advances in recent years. We conducted a systematic review examining genetic contributions to NPH risk. Ovid Embase, Ovid Medline, Web of Science, and Cochrane Central were searched from inception through October 14, 2024, for human studies in English reporting familial NPH cases, genetic variants associated with NPH, and associations with other neurogenetic disorders and exploring transcriptomics. Studies on secondary, obstructive, and congenital hydrocephalus were excluded, and findings were reported narratively. Of 2562 titles and abstracts screened, 56 met inclusion criteria, predominantly involving European populations. More than 30 familial cases were identified, and two cohorts found that 10%–16% of patients with NPH had relatives with NPH symptoms. Whole‐genome/exome sequencing, copy‐number variant analyses, and genome‐wide association studies showed risk variants enriched in NPH cohorts in or near CFAP43, SFMBT1, CWH43, AK9, RXFP2, PRKD1, HAVCR1, OTOG, MYO7A, NOTCH1, SPG11, MYH13, FOXJ1, AMZ1/GNA12, and C16orf95, alongside protective variants near SLCO1A2 and MLLT10. These genes are associated with blood‐brain and blood–cerebrospinal fluid barriers, cilia, and ependymal function. In addition, higher rates of pathological C9orf72 repeat expansions were observed in an NPH cohort compared with controls. NPH was also more prevalent in frontotemporal dementia cohorts without this expansion and co‐occurred with myotonic dystrophy type 1 in several cases. Despite heterogeneity in outcome measures, this review highlights the genetic contribution to NPH risk. Future research should encourage collaborations for big data generation, identify genetic variants addressing diversity, and integrate clinical, environmental, and shunt‐response data. © 2025 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.