Tolerance-based evaluation of a Shariah-compliant rehabilitation IoT framework for post-stroke hand gesture monitoring
The lack of affordable, continuous, and inclusive rehabilitation services creates disparities in patient outcomes, particularly for vulnerable groups, and raises concerns about fulfilling the ethical responsibility to ensure fair and compassionate healthcare delivery. To address these challenges...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Proceeding Paper |
| Language: | en |
| Published: |
IEEE
2026
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/127432/7/127432_Tolerance-based%20evaluation%20of%20a%20Shariah-compliant.pdf http://irep.iium.edu.my/127432/ https://ieeexplore.ieee.org/document/11345020 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The lack of affordable, continuous, and inclusive
rehabilitation services creates disparities in patient outcomes,
particularly for vulnerable groups, and raises concerns about
fulfilling the ethical responsibility to ensure fair and
compassionate healthcare delivery. To address these challenges
within a Shariah-compliant healthcare framework, this study
introduces a computational approach using the Rehabilitation
Internet of Things (RIoT) to enable remote, ethical, and Patientcentred rehabilitation. Hand Gesture-based data from 200 poststroke patients at Putrajaya Hospital were collected using the
MediaPipe Pose framework for real-time skeletal and hand
tracking. Features such as repetition count, and completion time
were extracted and analysed through predictive models,
including linear regression and ensemble methods, with
validation based on tolerance-based accuracy. Tolerance-based
accuracy evaluation demonstrated clinically meaningful
outcomes within a 20%–30% margin of agreement with manual
assessments. For hand strengthening (HS), the system achieved
71.5% accuracy at ±20% tolerance and 88.5% at ±30%,
reflecting strong reliability in measuring gross motor functions.
Hand opposition (HO), which relies on fine motor precision,
yielded 61.5% accuracy at ±20% and 84.5% at ±30%, indicating
acceptable reliability at broader thresholds despite higher
variability. These results affirm that RIoT can be regarded as a
clinically usable tool for remote rehabilitation monitoring,
particularly under ±30% tolerance. Furthermore, significant
correlations were observed between computational metrics and
established clinical outcomes, confirming the reliability of the
proposed framework. Beyond clinical utility, the framework
ensures patient data privacy and aligns with the Maqasid alShariah in upholding ʿAdl (justice), Taysīr (facilitation of
access), and preservation of Akhlāq (morality). Overall, the
findings highlight the potential for ASEAN healthcare systems
to adopt technology-driven rehabilitation strategies that
enhance patient autonomy. |
|---|