![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Article
Open AccessDRG-LLaMA : tuning LLaMA model to predict diagnosis-related group for hospitalized patients
In the U.S. inpatient payment system, the Diagnosis-Related Group (DRG) is pivotal, but its assignment process is inefficient. The study introduces DRG-LLaMA, an advanced large language model (LLM) fine-tuned on ...
-
Article
Open AccessAuthor Correction: Synthesize high-dimensional longitudinal electronic health records via hierarchical autoregressive language model
-
Article
Publisher Correction: Scientific discovery in the age of artificial intelligence
-
Article
Open AccessSynthesize high-dimensional longitudinal electronic health records via hierarchical autoregressive language model
Synthetic electronic health records (EHRs) that are both realistic and privacy-preserving offer alternatives to real EHRs for machine learning (ML) and statistical analysis. However, generating high-fidelity E...
-
Article
Scientific discovery in the age of artificial intelligence
Artificial intelligence (AI) is being increasingly integrated into scientific discovery to augment and accelerate research, hel** scientists to generate hypotheses, design experiments, collect and interpret ...
-
Article
Open AccessEvidence-driven spatiotemporal COVID-19 hospitalization prediction with Ising dynamics
In this work, we aim to accurately predict the number of hospitalizations during the COVID-19 pandemic by develo** a spatiotemporal prediction model. We propose HOIST, an Ising dynamics-based deep learning m...
-
Chapter and Conference Paper
AutoMap: Automatic Medical Code Map** for Clinical Prediction Model Deployment
Given a deep learning model trained on data from a source hospital, how to deploy the model to a target hospital automatically? How to accommodate heterogeneous medical coding systems across different hospital...
-
Article
Artificial intelligence foundation for therapeutic science
Artificial intelligence (AI) is poised to transform therapeutic science. Therapeutics Data Commons is an initiative to access and evaluate AI capability across therapeutic modalities and stages of discovery, e...
-
Chapter and Conference Paper
\(\mathrm {CT^2}\) : Colorization Transformer via Color Tokens
Automatic image colorization is an ill-posed problem with multi-modal uncertainty, and there remains two main challenges with previous methods: incorrect semantic colors and under-saturation. In this paper, we...
-
Article
Open AccessHighly elevated polygenic risk scores are better predictors of myocardial infarction risk early in life than later
Several polygenic risk scores (PRS) have been developed for cardiovascular risk prediction, but the additive value of including PRS together with conventional risk factors for risk prediction is questionable. ...
-
Chapter
Introduction
Humans are the only species on earth that can actively and systematically improve their health via technologies in the form of medicine. Throughout history, human knowledge is the driving force for the progres...
-
Chapter
Health Data
Health data are diverse with multiple modalities. This chapter will introduce different types of health data, including structured health data (e.g., diagnosis codes, procedure codes) and unstructured data (e....
-
Chapter
Autoencoders (AE)
So far, we have presented various deep learning models for supervised learning where output labels (e.g., heart failure diagnosis) are available in the training data. However, unlabeled data are the norm in ma...
-
Chapter
Machine Learning Basics
Machine learning has changed many industries, including healthcare. The most fundamental concepts in machine learning include (1) supervised learning that has been used to develop risk prediction models for targe...
-
Chapter
Embedding
The clinically meaningful representations of medical concepts and patients are the key to health analytic applications. Standard machine learning approaches directly construct features mapped from raw data (e....
-
Chapter
Recurrent Neural Networks (RNN)
Recurrent Neural Networks (RNN) are a family of deep learning models for sequential data such as longitudinal patient records and time-series data. Two prominent RNN models, namely long short-term memory (LSTM...
-
Chapter
Attention Models
Accuracy and interpretability are two desirable properties of successful predictive models. Most of deep learning models try to achieve high accuracy without much consideration of interpretability. The attenti...
-
Chapter
Memory Networks
Memory network is a powerful extension of attention models. The memory network models have shown initial successes in natural language processing such as question answering. In particular, memory networks use ...
-
Chapter
Deep Neural Networks (DNN)
Neural networks are a family of machine learning models that consist of connected function units called neurons. They are built as powerful function approximators that accurately map input data x to output y (i.e...
-
Chapter
Convolutional Neural Networks (CNN)
Convolutional neural networks (CNN or ConvNet) are a specific type of neural networks for processing grid-like data such as images and time series. In healthcare applications, the CNN models are widely used in...