JMIR Publications

ABSTRACT

Background:

The continuous monitoring and recording of patients’ pain status is a major problem in current research on postoperative pain management. In the generous number of original or review articles focusing on different approaches for pain assessment, many researchers have investigated how computer vision (CV) can help by capturing facial expressions. However, there is a lack of proper comparison of results between studies to identify current research gaps.

Objective:

The purpose of this systematic review and meta-analysis was to investigate the diagnostic performance of AI models for multilevel pain assessment from facial images.

Methods:

The PubMed, Embase, IEEE, Web of Science, and Cochrane Library databases were searched for related publications before September 30, 2023. Studies that used facial images alone to estimate multiple pain values were included in the systematic review. A study quality assessment was conducted using the quality assessment of diagnostic accuracy studies, 2nd edition (QUADAS-2) tool. The performance of these studies was assessed by metrics including sensitivity (SE), specificity (SP), log diagnostic odds ratio (LDOR) and area under the curve (AUC). The intermodel variability was assessed and presented by forest plots. The study was registered with PROSPERO (ID: CRD42023418181).

Results:

Forty-five reports were included in the systematic review. The reported test accuracies ranged from 0.27-0.99, and the other metrics, including the mean standard error (MSE), mean absolute error (MAE), intraclass correlation coefficient (ICC), and Pearson correlation coefficient (PCC) ranged from 0.31-4.61, 0.24-2.8, 0.19-0.83, and 0.48-0.92, respectively. Six studies were included in the meta-analysis. Their combined SE was 98% (95% CI 96%-99%), SP was 98% (95% CI 97%-99%), LDOR was 7.99 (95% CI 6.73-9.31) and AUC was 0.99 (95% CI 0.99-1). From the subgroup analysis, it was found that the diagnostic performance was acceptable, although imbalanced data were still emphasized as a major problem. All studies had at least one domain with a high risk of bias, and for 20% (9) of studies, there were no applicability concerns.

Conclusions:

This review summarized recent evidence in automatic multilevel pain estimation from facial expressions, and compared their test accuracy results during meta-analysis. Promising performance for pain estimation from facial images was established by current CV algorithms. Weaknesses in current studies were also identified, and suggested that larger databases and metrics evaluating multiclass classification performance could improve future studies.