Acute kidney injury (AKI) is a significant health challenge associated with adverse patient outcomes and substantial economic burdens. Many authors have sought to prevent and predict AKI. Here, we comprehensively review recent advances in the use of artificial intelligence (AI) to predict AKI, and the associated challenges. Although AI may detect AKI early and predict prognosis, integration of AI-based systems into clinical practice remains challenging. It is difficult to identify AKI patients using retrospective data; information preprocessing and the limitations of existing models pose problems. It is essential to embrace standardized labeling criteria and to form international multi-institutional collaborations that foster high-quality data collection. Additionally, existing constraints on the deployment of evolving AI technologies in real-world healthcare settings and enhancement of the reliabilities of AI outputs are crucial. Such efforts will improve the clinical applicability, performance, and reliability of AKI Clinical Support Systems, ultimately enhancing patient prognoses.

Acute kidney injury (AKI) is a significant health challenge associated with adverse patient outcomes and substantial economic burdens. Many authors have sought to prevent and predict AKI. Here, we comprehensively review recent advances in the use of artificial intelligence (AI) to predict AKI, and the associated challenges. Although AI may detect AKI early and predict prognosis, integration of AI-based systems into clinical practice remains challenging. It is difficult to identify AKI patients using retrospective data; information preprocessing and the limitations of existing models pose problems. It is essential to embrace standardized labeling criteria and to form international multi-institutional collaborations that foster high-quality data collection. Additionally, existing constraints on the deployment of evolving AI technologies in real-world healthcare settings and enhancement of the reliabilities of AI outputs are crucial. Such efforts will improve the clinical applicability, performance, and reliability of AKI Clinical Support Systems, ultimately enhancing patient prognoses.

Acute kidney injury (AKI) is a significant health challenge associated with adverse patient outcomes and substantial economic burdens. Many authors have sought to prevent and predict AKI. Here, we comprehensively review recent advances in the use of artificial intelligence (AI) to predict AKI, and the associated challenges. Although AI may detect AKI early and predict prognosis, integration of AI-based systems into clinical practice remains challenging. It is difficult to identify AKI patients using retrospective data; information preprocessing and the limitations of existing models pose problems. It is essential to embrace standardized labeling criteria and to form international multi-institutional collaborations that foster high-quality data collection. Additionally, existing constraints on the deployment of evolving AI technologies in real-world healthcare settings and enhancement of the reliabilities of AI outputs are crucial. Such efforts will improve the clinical applicability, performance, and reliability of AKI Clinical Support Systems, ultimately enhancing patient prognoses.

Acute kidney injury (AKI) is a significant health challenge associated with adverse patient outcomes and substantial economic burdens. Many authors have sought to prevent and predict AKI. Here, we comprehensively review recent advances in the use of artificial intelligence (AI) to predict AKI, and the associated challenges. Although AI may detect AKI early and predict prognosis, integration of AI-based systems into clinical practice remains challenging. It is difficult to identify AKI patients using retrospective data; information preprocessing and the limitations of existing models pose problems. It is essential to embrace standardized labeling criteria and to form international multi-institutional collaborations that foster high-quality data collection. Additionally, existing constraints on the deployment of evolving AI technologies in real-world healthcare settings and enhancement of the reliabilities of AI outputs are crucial. Such efforts will improve the clinical applicability, performance, and reliability of AKI Clinical Support Systems, ultimately enhancing patient prognoses.

Objective: To systematically translate the Fugl-Meyer Assessment (FMA) into a Korean version of the FMA (K-FMA). Methods: We translated the original FMA into the Korean version with three translators and a translation committee, which included physiatrists, physical therapists, and occupational therapists. Based on a test-retest method, each of 31 patients with stroke was assessed by two evaluators twice, once on recruitment, and again after a week. Analysis of intra- and inter-rater reliabilities was performed using the intra-class correlation coefficient, whereas validity was analysed using Pearson correlation test along with the Motricity Index (MI), Motor Assessment Scale (MAS), and Berg Balance Scale (BBS). Results: The intra- and inter-rater reliabilities were significant for the total score, and good to excellent reliability was noted in all domains except for the joint range of motion of the lower extremity domain of the K-FMA. The MI and MAS scores were significantly correlated with all domains, all with p<0.01. The results for the MI ranged from r=0.639 to r=0.891 and those for the MAS from r=0.339 to r=0.555. However, the BBS was not significantly correlated with any domain, as the K-FMA lacks balance evaluation items. Conclusion The K-FMA was found to have high reliability and validity. Additionally, the newly developed manual for the K-FMA may help minimise errors that can occur during evaluation and improve the reliability of motor function evaluation.

Objective: To systematically translate the Fugl-Meyer Assessment (FMA) into a Korean version of the FMA (K-FMA). Methods: We translated the original FMA into the Korean version with three translators and a translation committee, which included physiatrists, physical therapists, and occupational therapists. Based on a test-retest method, each of 31 patients with stroke was assessed by two evaluators twice, once on recruitment, and again after a week. Analysis of intra- and inter-rater reliabilities was performed using the intra-class correlation coefficient, whereas validity was analysed using Pearson correlation test along with the Motricity Index (MI), Motor Assessment Scale (MAS), and Berg Balance Scale (BBS). Results: The intra- and inter-rater reliabilities were significant for the total score, and good to excellent reliability was noted in all domains except for the joint range of motion of the lower extremity domain of the K-FMA. The MI and MAS scores were significantly correlated with all domains, all with p<0.01. The results for the MI ranged from r=0.639 to r=0.891 and those for the MAS from r=0.339 to r=0.555. However, the BBS was not significantly correlated with any domain, as the K-FMA lacks balance evaluation items. Conclusion The K-FMA was found to have high reliability and validity. Additionally, the newly developed manual for the K-FMA may help minimise errors that can occur during evaluation and improve the reliability of motor function evaluation.

Acute kidney injury (AKI) is a significant challenge in healthcare. While there are considerable researches dedicated to AKI patients, a crucial factor in their renal function recovery, is often overlooked. Thus, our study aims to address this issue through the development of a machine learning model to predict restoration of kidney function in patients with AKI. Methods: Our study encompassed data from 350,345 cases, derived from three hospitals. AKI was classified in accordance with the Kidney Disease: Improving Global Outcomes. Criteria for recovery were established as either a 33% decrease in serum creatinine levels at AKI onset, which was initially employed for the diagnosis of AKI. We employed various machine learning models, selecting 43 pertinent features for analysis. Results: Our analysis contained 7,041 and 2,929 patients’ data from internal cohort and external cohort respectively. The Categorical Boosting Model demonstrated significant predictive accuracy, as evidenced by an internal area under the receiver operating characteristic (AUROC) of 0.7860, and an external AUROC score of 0.7316, thereby confirming its robustness in predictive performance. SHapley Additive exPlanations (SHAP) values were employed to explain key factors impacting recovery of renal function in AKI patients. Conclusion: This study presented a machine learning approach for predicting renal function recovery in patients with AKI. The model performance was assessed across distinct hospital settings, which revealed its efficacy. Although the model exhibited favorable outcomes, the necessity for further enhancements and the incorporation of more diverse datasets is imperative for its application in real- world.