Artificial Intelligence Medical Compendium

PURPOSE: Recently, an improved food frequency questionnaire focused on assessing daily sodium (Na) intake (Food Frequency Questionnaire [FFQ]-Na: 73 questions; time to be filled in [t]: 25 min) was developed with higher accuracy over other dietary an... read more 

Identifying relevant input features which contribute to the output of a clinical prediction model can enhance the model explainability. To allow the explainability to be more personalized, instance-wise feature selection (IWFS) methods can be adopted... read more 

OBJECTIVE: This study aimed to develop a deep learning model classifier capable of predicting the extraction/non-extraction binary decision using lateral cephalometric radiographs (LCRs) and intraoral scans (IOS) to serve as an additional decision-su... read more 

BACKGROUND: Swallowing dysfunction is a common consequence of neurological disorders such as stroke, and may lead to malnutrition, aspiration, and reduced quality of life. Nurses are key members of the interdisciplinary team involved in the early det... read more 

Active learning fosters critical thinking, autonomy, and deep learning. Whereas team-based learning (TBL) is common, inquiry-based learning (IBL) offers a more student-centered, inquiry-driven alternative. This study aimed to compare the pedagogical ... read more 

BACKGROUND: Accurate risk stratification for overall survival (OS) in patients with oropharyngeal squamous cell carcinoma (OPSCC) is critical for guiding personalized treatment and surveillance. A deep learning (DL) model was developed and validated ... read more 

INTRODUCTION AND OBJECTIVES: An AI model that performs well during training does not guarantee similar performance in clinical practice and should be carefully evaluated before implementation. We aimed to evaluate a voxel-level trained AI model (AURO... read more 

PURPOSE: To evaluate and compare the performance of diffusion-weighted imaging (DWI) using compressed sensing (CS) and DWI using CS with model-based deep learning reconstruction (DL-DWI) in detecting and differentiating liver metastases from hepatic ... read more 

People often physically cling to others when afraid and doing so can downregulate negative emotional experiences (e.g., Coan et al., 2006). However, in some situations, physical touch may fail to downregulate emotional experiences-such as when an ind... read more 

Behavioural Artificial Intelligence Technology (BAIT) has recently been proposed to codify expert reasoning for sepsis surveillance. We provide preliminary cross-institutional data from two Southeast Asian hospitals (N = 1042 suspected sepsis episode... read more