Background: Hand function assessment heavily relies on specific task scenarios, making it challenging to ensure validity and reliability. Additionally, the wide range of assessment tools, and limited and expensive data recording, and analysis systems, further aggravate the issue. However, the ubiquitous smartphones in our daily life, they provide a promising opportunity to address these challenges. Implementing the built-in high-efficiency sensors in smartphones can be used as effective tools for hand function assessment.Objective: This study aims to systematically evaluate existing studies on hand function evaluation using smartphones.Methods: An extensive database search was conducted by an Information Specialist. Two reviewers independently screened all studies, with a third reviewer involved in resolving discrepancies. The final included studies were rated according to the Mixed Methods Appraisal Tool (MMAT). One reviewer extracted data on publication, demographic information, hand function types, sensors used for hand function assessment, and statistical or machine learning methods. Accuracy was checked by another reviewer. The data were synthesized and tabulated based on each of the four research questions.Results: 46 studies were included. 11 types of hand dysfunction-related diseases were identified, such as Parkinson's Disease, wrist injury, stroke, and hand injury. Six types of hand dysfunctions were found including abnormal range of motion, tremors, bradykinesia, decline of fine-motor skills, hypokinesia, and non-specific dysfunction related to hand arthritis. Among all built-in smartphone sensors, the accelerometer was the most used, followed by the smartphone camera. Most studies used statistical methods for data processing, whereas machine learning (ML) algorithms were also applied for disease detection, disease severity evaluation, prediction, and feature aggregation. Limitations of the review include the nascent field of smartphone-based hand function assessment and the variability in literature quality.
Conclusions:This systematic review highlights the potential of smartphone-based hand function assessment. The review suggests that a smartphone is a promising tool in hand function evaluation without the constant involvement of therapists. ML is a conducive method to classify levels of hand dysfunction by smartphones. Future research could (1) explore a gold standard for smartphone-based hand function assessment; (2) take advantage of smartphones' multiple built-in sensors to assess hand function comprehensively; (3) focus on developing ML methods for processing collected smartphone data and (4) focus on real-time assessment during rehabilitation training.
