Rehabilitation of Burn Victims: Improving Quality of Life in Victims With Face and Neck Burn Through an Augmented Reality Coupled Pamphlet

Effect of augmented reality-based rehabilitation of hand burns on hand function in children: A randomized controlled trial

BACKGROUND

Despite the use of traditional rehabilitation methods, hand function may still remain impaired in children suffering from burn injuries.

PURPOSE

This study aimed to assess the impact of implementing an augmented reality (AR) rehabilitation booklet designed for pediatric hand burn on their hand functionality.

STUDY DESIGN

This was a randomized controlled trial.

METHODS

Seventy-two children, aged 8-14 years with a hand burn, were randomly allocated into intervention (n = 36) and control (n = 36) groups. Children in the control group received routine rehabilitation program, while in the intervention group, children performed exercises using a printed booklet with related AR application. The Jebsen-Taylor Hand Function Test was completed before the intervention at the time of the patients' discharge and 1 month later.

RESULTS

The results of analysis of covariance based on baseline- and fully-adjusted models showed significant intervention effect after discharge as well as after intervention for hand function (mean difference [95% confidence interval] for discharge: -8.2 [-15.0 to -1.4] and for after intervention: -74.0 [-88.8 to -59.1]) and the items (all p < 0.05), except for writing and lifting large light objects for both after discharge and after intervention measures (all p-value > 0.05).

CONCLUSIONS

A significant decrease in the total time taking to complete the Jebsen-Taylor hand function test was observed in the intervention group compared to the control group 1 month after discharge. Rehabilitation of children with hand burns, using printed educational booklet with related AR application, improves their hand function.

The evolution of augmented reality to augment physical therapy: A scoping review

Augmented reality is increasingly used in health care, yet little is known about how AR is being used in physical therapy practice and what clinical outcomes could occur with technology use. In this scoping review, a broad literature review was conducted to gain an understanding of current knowledge of AR use and outcomes in physical therapy practice. A structured literature search of articles published between 2000 to September 2023 that examined the use of AR in a physical therapy context was conducted. Reference lists of articles for full review were searched for additional studies. Data from articles meeting inclusion criteria were extracted and synthesized across studies. 549 articles were identified; 40 articles met criteria for full review. Gait and balance of neurological and older adult populations were most frequently targeted, with more recent studies including orthopedic and other populations. Approximately half were pilot or observational studies and half are experimental. Many studies found within group improvements. Of studies reporting between group differences, AR interventions were more effective in improving function almost half of the time, with 20%, 27% and 28% showing efficacy in disability, balance, and gait outcomes. AR in physical therapy holds promise; however, efficacy outcomes are unclear.

Implementing AI Models for Prognostic Predictions in High-Risk Burn Patients

BACKGROUND AND OBJECTIVES

Burn injuries range from minor medical issues to severe, life-threatening conditions. The severity and location of the burn dictate its treatment; while minor burns might be treatable at home, severe burns necessitate medical intervention, sometimes in specialized burn centers with extended follow-up care. This study aims to leverage artificial intelligence (AI)/machine learning (ML) to forecast potential adverse effects in burn patients.

METHODS

This retrospective analysis considered burn patients admitted to Chi Mei Medical Center from 2010 to 2019. The study employed 14 features, comprising supplementary information like prior comorbidities and laboratory results, for building models for predicting graft surgery, a prolonged hospital stay, and overall adverse effects. Overall, 70% of the data set trained the AI models, with the remaining 30% reserved for testing. Three ML algorithms of random forest, LightGBM, and logistic regression were employed with evaluation metrics of accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC).

RESULTS

In this research, out of 224 patients assessed, the random forest model yielded the highest AUC for predictions related to prolonged hospital stays (>14 days) at 81.1%, followed by the XGBoost (79.9%) and LightGBM (79.5%) models. Besides, the random forest model of the need for a skin graft showed the highest AUC (78.8%), while the random forest model and XGBoost model of the occurrence of adverse complications both demonstrated the highest AUC (87.2%) as well. Based on the best models with the highest AUC values, an AI prediction system is designed and integrated into hospital information systems to assist physicians in the decision-making process.

CONCLUSIONS

AI techniques showcased exceptional capabilities for predicting a prolonged hospital stay, the need for a skin graft, and the occurrence of overall adverse complications for burn patients. The insights from our study fuel optimism for the inception of a novel predictive model that can seamlessly meld with hospital information systems, enhancing clinical decisions and bolstering physician-patient dialogues.