Han Yuan

Han Yuan
Duke-NUS Medical School · Centre for Quantitative Medicine

Bachelor of Science
For full text papers, please visit https://han-yuan-med.github.io/publications/

About

16
Publications
1,669
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
56
Citations
Citations since 2017
16 Research Items
56 Citations
2017201820192020202120222023010203040
2017201820192020202120222023010203040
2017201820192020202120222023010203040
2017201820192020202120222023010203040
Introduction
AI in Healthcare, AutoML with Interpretation
Skills and Expertise
Additional affiliations
January 2022 - June 2022
University of Zurich
Position
  • Research Assistant
July 2019 - February 2020
Harvard University
Position
  • Research Assistant
Education
August 2020 - July 2024
Duke-NUS Medical School
Field of study
  • Health Data Science
September 2015 - June 2019
Nankai University
Field of study
  • Biology
September 2015 - June 2019
Nankai University
Field of study
  • Mathematics

Publications

Publications (16)
Preprint
Full-text available
Objective: The proper handling of missing values is critical to delivering reliable estimates and decisions, especially in high-stakes fields such as clinical research. The increasing diversity and complexity of data have led many researchers to develop deep learning (DL)-based imputation techniques. We conducted a systematic review to evaluate the...
Preprint
Full-text available
Objective: Shapley additive explanations (SHAP) is a popular post-hoc technique for explaining black box models. While the impact of data imbalance on predictive models has been extensively studied, it remains largely unknown with respect to SHAP-based model explanations. This study sought to investigate the effects of data imbalance on SHAP explan...
Article
Nowadays, the interpretation of why a machine learning (ML) model makes certain inferences is as crucial as the accuracy of such inferences. Some ML models like the decision tree possess inherent interpretability that can be directly comprehended by humans. Others like artificial neural networks (ANN), however, rely on external methods to uncover t...
Preprint
Full-text available
Nowadays, the interpretation of why a machine learning (ML) model makes certain inferences is as crucial as the accuracy of such inferences. Some ML models like the decision tree possess inherent interpretability that can be directly comprehended by humans. Others like artificial neural networks (ANN), however, rely on external methods to uncover t...
Article
Background Medical decision-making impacts both individual and public health. Clinical scores are commonly used among various decision-making models to determine the degree of disease deterioration at the bedside. AutoScore was proposed as a useful clinical score generator based on machine learning and a generalized linear model. However, its curre...
Article
Full-text available
Background Ubiquitylation modification is one of the multiple post-transcriptional process to regulate cellular physiology, including cell signaling, cycle regulation, DNA repair and transcriptional regulation. Members of TRIM family proteins could be defined as E3 ubiquitin ligases as they contain a RING-finger domain, and alterations of TRIM prot...
Article
Objective Temporal electronic health records (EHRs) contain a wealth of information for secondary uses, such as clinical events prediction or chronic disease management. However, challenges exist for temporal data representation. We therefore sought to identify these challenges and evaluate novel methodologies for addressing them through a systemat...
Article
Background Scoring systems are highly interpretable and widely used to evaluate time-to-event outcomes in healthcare research. However, existing time-to-event scores are predominantly created ad-hoc using a few manually selected variables based on clinician's knowledge, suggesting an unmet need for a robust and efficient generic score-generating me...
Preprint
Full-text available
Objective: Temporal electronic health records (EHRs) can be a wealth of information for secondary uses, such as clinical events prediction or chronic disease management. However, challenges exist for temporal data representation. We therefore sought to identify these challenges and evaluate novel methodologies for addressing them through a systemat...
Preprint
Full-text available
Background: Medical decision-making impacts both individual and public health. Clinical scores are commonly used among a wide variety of decision-making models for determining the degree of disease deterioration at the bedside. AutoScore was proposed as a useful clinical score generator based on machine learning and a generalized linear model. Its...
Code
Description A novel interpretable machine learning-based framework to automate the development of a clinical scoring model for predefined outcomes. Our novel framework consists of six modules: variable ranking with machine learning, variable transformation , score derivation, model selection, domain knowledge-based score fine-tuning, and performanc...
Preprint
Full-text available
Scoring systems are highly interpretable and widely used to evaluate time-to-event outcomes in healthcare research. However, existing time-to-event scores are predominantly created ad-hoc using a few manually selected variables based on clinician's knowledge, suggesting an unmet need for a robust and efficient generic score-generating method. AutoS...
Conference Paper
Full-text available
Early prediction of adverse drug reaction (ADR) is crucial in clinical research. The development of electronic medical record (EMR) provides an excellent resource for retrospective studies to extract samples and establish models that can be used for prediction of clinical deterioration. However, classical statistical models like multivariate logist...
Data
Supplementary Tables in "Prediction of Adverse Drug Reaction using machine learning and deep learning based on an unbalanced electronic medical records dataset"
Article
Full-text available
Patients who underwent laparoscopic partial nephrectomy from the First Affiliated Hospital of Nanjing Medical University from May 2016 to May 2019 were randomly divided into ERAS and control group. The clinical indicators, preoperative and postoperative anxiety, depression and postoperative quality of life were compared between the two groups. The...
Article
Progression-free survival (PFS), defined as the time from randomization to progression of disease or death, has been indicated as an endpoint to support accelerated approval of certain cancer drugs by the U.S. FDA. The standard Kaplan-Meier (KM) estimator of PFS, however, can result in significantly biased estimates. A major source for the bias res...

Network

Cited By

Projects

Project (1)
Archived project
1 Provide a pragmatic reference to deal with esoteric clinical notes in Chinese. 2 Explore potential ADR inducement caused by Chinese patent drugs and analyze possible mechanisms. 3 Present the application of ensembling to enhance model performance on imbalanced datasets. 4 Demonstrate the effectiveness of multiple machine intelligence methods and give recommendations based on the procedure elapsed time and prediction performance.