Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Advances in Psychological Sciences and Applications
Winny N. Wishwadewa
Independent Paediatric Researcher
Religion Humanities Health Professions Neuroscience Social Sciences

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Unlocking the Potential of Machine Learning and Artificial Intelligence for Early Detection and Monitoring of Spinal Muscular Atrophy Type 3: A Narrative Review in Low- and Middle-Income Countries Ferry D. Satriono; Winny N. Wishwadewa
Advances in Psychological Sciences and Applications Vol. 2 No. 02 (2026): Articles in Press - Advances in Psychological Sciences and Applications
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/IISTR.apsa.002331

Abstract

Spinal Muscular Atrophy Type 3 (SMA3), or Kugelberg-Welander disease, is a later-onset and relatively milder form of SMA, but delayed recognition can still cause progressive weakness, loss of ambulation, scoliosis, fatigue, and reduced quality of life. In low- and middle-income countries (LMICs), early diagnosis and monitoring are often limited by subtle symptoms, restricted genetic testing, specialist shortages, fragmented follow-up, and weak referral systems. This paper presents a conceptual framework for using artificial intelligence (AI), machine learning (ML), and Internet of Things (IoT) enabled tools to improve SMA3 detection, monitoring, and care delivery in LMICs. The framework integrates multimodal data collection, including demographic, clinical, motor function, diagnostic, treatment, patient-reported, wearable, smartphone-based, and health system data. These inputs are processed through cloud-based data preparation, including standardization, cleaning, privacy protection, missing data handling, multimodal integration, and feature extraction. AI/ML models may support disease progression prediction, risk stratification, early detection of motor decline, treatment response prediction, phenotype clustering, and longitudinal monitoring. The resulting outputs include clinical decision support, personalized rehabilitation, early warning alerts, patient dashboards, national registries, efficient resource allocation, and policy evidence. Successful implementation requires low-cost digital tools, interoperability, ethical governance, multidisciplinary collaboration, local validation, and explainable AI. This approach may enable earlier intervention and improve outcomes for SMA3 patients in resource-limited settings.
Co-Authors Ferry D. Satriono