Healthcare
Deep Learning and AutoML for Fall Risk Prediction Using Vision-Based Gait Analysis in INPH
- machine learning
- artificial intelligence
- deep learning
- AutoML
- medical imaging
- computer vision
- gait analysis
- fall risk prediction
- idiopathic normal-pressure hydrocephalus
- clinical AI
- predictive modeling
MLJAR tools were used in the following publication.
Quantitative analysis of gait and balance using deep learning on monocular videos and the timed up and go test in idiopathic normal-pressure hydrocephalus
Hee-Jin Cho, Sangwook Kim, Hosang Yu, Sungmoon Jeong, Kyunghun Kang
Kyungpook National University Chilgok Hospital, Republic of Korea | Korea Dementia Research Center (KDRC), Republic of Korea | AICU Corp., Republic of Korea
This peer-reviewed study presents a deep learning-based vision system for quantitative gait analysis using monocular video recordings in patients with idiopathic normal-pressure hydrocephalus (INPH). The authors extracted temporo-spatial gait parameters and applied automated machine learning (AutoML) to predict fall risk based on the Timed Up and Go (TUG) test. The ensemble model achieved excellent classification performance (AUC = 0.979), with gait velocity and stride time variability identified as key predictive features through SHAP explainability analysis. The research demonstrates how artificial intelligence, computer vision, and predictive analytics can support clinical decision-making and non-invasive fall risk assessment in neurological disorders.
Frontiers in Aging Neuroscience • October 14, 2025
Research Domains
Explore peer-reviewed and applied machine learning studies across diverse domains, including healthcare analytics, financial modeling, manufacturing optimization, and structured data classification problems.
Why Researchers and ML Engineers Choose MLJAR Studio
A private, AI-powered Python notebook designed for reproducible machine learning experiments, structured benchmarking, and applied research workflows - fully under your control.
Reproducible Machine Learning Experiments
Design structured pipelines, save experiment runs, and compare results across iterations with full transparency. Every validation setup, hyperparameter configuration, and model benchmark is recorded - making your research repeatable and defensible.
Local-First Execution & Data Control
Run all workflows directly on your machine. Sensitive datasets remain private, with no mandatory cloud uploads or external AI services required. Maintain full control over runtime environments and compliance requirements.
Autonomous Model Benchmarking & Optimization
Automatically compare candidate models, perform cross-validation, and run hyperparameter optimization while retaining full visibility into generated Python code and evaluation metrics. Accelerate experimentation without sacrificing methodological rigor.
Build Research-Grade ML Workflows Locally
Run automated model benchmarking, hyperparameter optimization, and autonomous experiments while keeping full control over your data.