Publications by authors named "G Kiat Kee"
Background: Predicting the length of stay in advance will not only benefit the hospitals both clinically and financially but enable healthcare providers to better decision-making for improved quality of care. More importantly, understanding the length of stay of severe patients who require general anesthesia is key to enhancing health outcomes.
Objective: Here, we aim to discover how machine learning can support resource allocation management and decision-making resulting from the length of stay prediction.
Article Synopsis
- Transformer-based language models hold significant potential to improve healthcare but are not yet widely implemented due to a lack of comprehensive reviews and clear guidelines.
- The scoping review categorizes existing studies into six tasks: dialogue generation, question answering, summarization, text classification, sentiment analysis, and named entity recognition.
- Key findings highlight advancements, such as improved accuracy with models like BioBERT, alongside challenges like ethical concerns and difficulties managing complex medical terminology in clinical settings.
Article Synopsis
- Predicting major adverse cardiovascular events (MACE) is important due to high readmission rates and serious health consequences, but current models rely on limited patient data at a single time point.
- A new self-attention-based model was developed to predict MACE within 3 years using extensive time series data from electronic medical records, enhancing accuracy by considering multiple patient features.
- Transfer learning techniques were applied to enable effective predictions even in hospitals with less data, and the model's performance improved significantly, showing higher AUROC scores and confirming predictive effectiveness through survival analysis.
Loop diuretics are prevailing drugs to manage fluid overload in heart failure. However, adjusting to loop diuretic doses is strenuous due to the lack of a diuretic guideline. Accordingly, we developed a novel clinician decision support system for adjusting loop diuretics dosage with a Long Short-Term Memory (LSTM) algorithm using time-series EMRs.
View Article and Find Full Text PDFEpithelioid angiosarcoma occurring in the lower jaw of infants.
Minerva Pediatr (Torino)
October 2024