Fall detection and pre-impact prediction technologies in older adults: a scoping review of translational maturity and public health integration
Abstract
Objective: To map the current landscape of wearable and sensor-based fall detection and pre-impact prediction technologies relevant to older adults and to evaluate their translational maturity within public health contexts.
Methods: A scoping review was conducted following PRISMA-ScR guidelines. Four electronic databases (PubMed, Web of Science, Scopus, and IEEE Xplore) were systematically searched for studies published between January 2005 and September 2025. Eligible studies reported the development or validation of fall detection or pre-impact prediction systems incorporating wearable, vision-based, environmental, or multimodal sensing modalities. In total, 243 studies were included in the overall synthesis, with a predefined subgroup of 21 studies involving real-world or mixed real-world validation in older adult populations (≥65 years).
Results: Across the 243 included studies, wearable inertial measurement unit (IMU)-based systems constituted the dominant technological stream, and post-fall detection remained the most frequently investigated functional objective. However, more than half of studies relied primarily on laboratory-based simulated fall protocols. Within the real-world validated older adult subgroup (n = 21), 71.4% focused on post-fall detection, 19.0% investigated pre-impact prediction, and 9.5% addressed fall risk modeling. While technical performance metrics such as sensitivity and specificity were frequently reported under controlled conditions,…
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.