Text2Node: a cross-domain system for mapping arbitrary phrases to a taxonomy

Abstract Electronic health record (EHR) systems are used extensively throughout the healthcare domain. However, data interchangeability between EHR systems is limited due to the use of different coding standards across systems. Existing methods of mapping coding standards based on manual human experts mapping, dictionary mapping, symbolic NLP and classification are unscalable and cannot accommodate large …

Text2Node: a cross-domain system for mapping arbitrary phrases to a taxonomy Read More »

COVID-19 insurance products in Asia

When Taiwan started offering COVID-19 insurance products, people lined up at 6 A.M. to purchase the insurance products. During the most recent outbreak, 460,000 policies were sold in just one week. The buying frenzy turned the saying “Insurance is sold, not bought” upside down. COVID-19 has highlighted the pandemic protection gap in insurance and insurers …

COVID-19 insurance products in Asia Read More »

Explainable model of deep learning for outcomes prediction of in-hospital cardiac arrest patients

Abstract Introduction: Deep learning has outperformed traditional methods in predicting healthcare outcomes. However, deep learning models struggle with explainability and are considered a black box. This article demonstrated the output from Shapley additive explanations (SHAP) analysis can provide meaningful insight into a model’s predictions. Methods: Starting from Taiwan National Health Insurance Research Database, we selected …

Explainable model of deep learning for outcomes prediction of in-hospital cardiac arrest patients Read More »

Multi-task learning improves model performance in predicting rare catastrophic events in healthcare claims dataset

Abstract Background: In-hospital cardiac arrest (IHCA) is associated with high mortality and health care costs in the recovery phase. Predicting adverse outcome events, including readmission, improves the chance for appropriate interventions and reduces health care costs. However, studies related to the early prediction of adverse events of IHCA survivors are rare. Therefore, we used a …

Multi-task learning improves model performance in predicting rare catastrophic events in healthcare claims dataset Read More »

TMLS_Poster

Opening the machine learning black box in regulated industries

Learn from Lydia AI ML team’s workshop at the Toronto Machine Learning Scientists. Fairness and accountability are cornerstones in regulated industries such as finance and insurance. Explainability is expected of all machine learning models in order to comply with strict audit trails and regulatory oversight. It is often challenging to bridge the gap between the …

Opening the machine learning black box in regulated industries Read More »

The evolution of digital health infrastructure in APAC

The Asia-Pacific region (APAC) is a leader in investing in digital health infrastructure and patient-controlled access to personalized health data. While Taiwan has become the benchmark for this approach, governments throughout APAC are quickly following its example. Large-scale government investment in digital health infrastructure across APAC is creating new opportunities to improve patient outcomes and …

The evolution of digital health infrastructure in APAC Read More »

Scroll to Top