Enhancing Box and Block Test with Computer Vision for Post-Stroke Upper Extremity Motor Evaluation
arXiv:2603.29101v1 Announce Type: new Abstract: Standard clinical assessments of upper-extremity motor function after stroke either rely on ordinal scoring, which lacks sensitivity, or time-based task metrics, which do not capture movement quality. In this work, we present a computer vision-based framework for analysis of upper-extremity movement during the Box and Block Test (BBT) through world-aligned joint angles of fingers, arm, and trunk without depth sensors or calibration objects. We apply this framework to a dataset of 136 BBT recordings collected from 48 healthy individuals and 7 individuals post stroke. Using unsupervised dimensionality reduction of joint-angle features, we analyze movement patterns without relying on expert clinical labels. The resulting embeddings show separati
View PDF HTML (experimental)
Abstract:Standard clinical assessments of upper-extremity motor function after stroke either rely on ordinal scoring, which lacks sensitivity, or time-based task metrics, which do not capture movement quality. In this work, we present a computer vision-based framework for analysis of upper-extremity movement during the Box and Block Test (BBT) through world-aligned joint angles of fingers, arm, and trunk without depth sensors or calibration objects. We apply this framework to a dataset of 136 BBT recordings collected from 48 healthy individuals and 7 individuals post stroke. Using unsupervised dimensionality reduction of joint-angle features, we analyze movement patterns without relying on expert clinical labels. The resulting embeddings show separation between healthy movement patterns and stroke-related movement deviations. Importantly, some patients with the same BBT scores can be separated with different postural patterns. These results show that world-aligned joint angles can capture meaningful information of upper-extremity functions beyond standard time-based BBT scores, with no effort from the clinician other than monocular video recordings of the patient using a phone or camera. This work highlights the potential of a camera-based, calibration-free framework to measure movement quality in clinical assessments without changing the widely adopted clinical routine.
Comments: Submitted to EMBC 2026
Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2603.29101 [cs.CV]
(or arXiv:2603.29101v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2603.29101
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: David Robinson [view email] [v1] Tue, 31 Mar 2026 00:39:48 UTC (9,976 KB)
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
announcefeaturevaluation
Migrating from Ralph Loops to duckflux
If you've been running coding agent tasks inside Ralph Loops , you already understand the core insight: iteration beats perfection. You've seen what happens when you hand a well-written prompt to an AI agent and let it grind until the job is done. This guide shows how to take that same philosophy and express it as a declarative, reproducible workflow in duckflux. You gain structure, observability, and composability without giving up the power of iterative automation. What are Ralph Loops? Ralph Wiggum is an iterative AI development methodology built on a deceptively simple idea: feed a prompt to a coding agent in a loop until the task is complete. Named after the Simpsons character (who stumbles forward until he accidentally succeeds), the technique treats failures as data points and bets
What is Algorithmic Trading, and Why is it the Silent Force Behind Today's Market Volatility?
What is Algorithmic Trading, and Why is it the Silent Force Behind Today's Market Volatility? Algorithmic trading is a method of executing orders using automated, pre-programmed trading instructions that account for variables such as time, price, and volume. It is the silent force behind today's market volatility because these algorithms, often powered by AI, can react to market events and execute trades at speeds far beyond human capability, creating rapid price swings and influencing liquidity across global exchanges. This phenomenon is particularly relevant NOW as markets grapple with inflation, interest rate hikes, and geopolitical tensions, making algorithmic reactions a significant factor in daily market movements. Understanding Algorithmic Trading: The Core Idea At its heart, algori
Unlock Blog Growth: Implement Structured Data for Blogs Now!
Mastering Blog Structured Data: Your SEO Superpower Ever wonder how some blogs seem to magically appear at the top of search results, even for super niche topics? They're not using a secret incantation; they're likely leveraging a powerful SEO technique: structured data. As the official blog of BlogMe , we live and breathe content creation, SEO, and the latest AI insights. And let me tell you, structured data is a game-changer. If you're serious about getting your blog noticed, understanding and implementing structured data for blogs isn't just a good idea – it's essential. Think of search engines like Google as incredibly smart, but very literal, librarians. They want to organize information so they can serve it up to users quickly and accurately. Structured data is essentially a detailed
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Products
Agentic AI deployment best practices: 3 core areas
The demos look slick. The pressure to deploy is real. But for most enterprises, agentic AI stalls long before it scales. Pilots that function in controlled environments collapse under production pressure, where reliability, security, and operational complexity raise the stakes. At the same time, governance gaps create compliance and data exposure risks before teams realize... The post Agentic AI deployment best practices: 3 core areas appeared first on DataRobot .
The agentic AI cost problem no one talks about: slow iteration cycles
Imagine a factory floor where every machine is running at full capacity. The lights are on, the equipment is humming, the engineers are busy. Nothing is shipping. The bottleneck isn’t production capacity. It s the quality control loop that takes three weeks every cycle, holds everything up, and costs the same whether the line is moving... The post The agentic AI cost problem no one talks about: slow iteration cycles appeared first on DataRobot .
What to look for when evaluating AI agent monitoring capabilities
Your AI agents are making hundreds — sometimes thousands — of decisions every hour. Approving transactions. Routing customers. Triggering downstream actions you don t directly control. Here s the uncomfortable question most enterprise leaders can t answer with confidence: Do you actually know what those agents are doing? If that question gives you pause, you re not alone. Many... The post What to look for when evaluating AI agent monitoring capabilities appeared first on DataRobot .
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!