Wenchang Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Wenchang Li has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Hongsheng Ma
Day Surgery Center, West China Hospital, Sichuan University, China
2 shared publications - Hongwei Shi
College of Computer Science, Sichuan University, Chengdu 610041, China
2 shared publications - Lisha Jiang
Day Surgery Center, West China Hospital, Sichuan University, China
2 shared publications - John Patrick Lalor
University of Notre Dame, Notre Dame, IN, USA
1 shared publication Qing Ye
1 shared publication- Siliang Tong
Nanyang Business School, Nanyang Technological University, Singapore 639798
1 shared publication
Latest Publications
- Open Access
- 24 September 2026
- Published by Elsevier in SSRN Electronic Journal
When Digital Navigation Changes the Patient Journey: A Field Experiment in Outpatient Care
Hospitals deploy digital navigation to reduce frictions in outpatient care with an expectation that better navigation will shorten patient journey duration. However, when patients themselves execute parts of the care process, digital navigation may change when they enter and which activities they undertake, potentially lengthening journey duration. We examine this tension in a large-scale field experiment involving 850,947 patients at a major hospital. Patients were randomly assigned access to digital navigation guiding them throughout outpatient visit. Take-up was only 3%, limiting the impact of deployment. However, among patients induced to use digital navigation by randomized access, journey duration increased by 93 minutes. The longer duration reflected two changes: patients checked in earlier and were less likely to be late for scheduled consultations, while undertaking more laboratory tests and report printing. Diagnostic examinations did not increase, a pattern consistent with scheduling constraints limiting immediate action. We show that digital navigation can reshape how patients execute multistage service processes and that its realized effects depend on both adoption and whether patients can act on the information provided. Accordingly, shorter journey duration may not be the right benchmark for evaluating digital navigation.
- 24 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessWhen Digital Navigation Changes the Patient Journey: A Field Experiment in Outpatient Care
Hospitals deploy digital navigation to reduce frictions in outpatient care with an expectation that better navigation will shorten patient journey duration. However, when patients themselves execute parts of the care process, digital navigation may change when they enter and which activities they undertake, potentially lengthening journey duration. We examine this tension in a large-scale field experiment involving 850,947 patients at a major hospital. Patients were randomly assigned access to digital navigation guiding them throughout outpatient visit. Take-up was only 3%, limiting the impact of deployment. However, among patients induced to use digital navigation by randomized access, journey duration increased by 93 minutes. The longer duration reflected two changes: patients checked in earlier and were less likely to be late for scheduled consultations, while undertaking more laboratory tests and report printing. Diagnostic examinations did not increase, a pattern consistent with scheduling constraints limiting immediate action. We show that digital navigation can reshape how patients execute multistage service processes and that its realized effects depend on both adoption and whether patients can act on the information provided. Accordingly, shorter journey duration may not be the right benchmark for evaluating digital navigation.
- Open Access
- 30 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Management Information Systems
From Stars to Insights: Exploration and Implementation of Unified Sentiment Analysis with Distant Supervision
Sentiment analysis is integral to understanding the voice of the customer and informing businesses’ strategic decisions. Conventional sentiment analysis involves three separate tasks: aspect-category detection, aspect-category sentiment analysis, and rating prediction. However, independently tackling these tasks can overlook their interdependencies and often requires expensive, fine-grained annotations. This paper introduces unified sentiment analysis, a novel learning paradigm that integrates the three aforementioned tasks into a coherent framework. To achieve this, we propose the Distantly Supervised Pyramid Network (DSPN), which employs a pyramid structure to capture sentiment at word, aspect, and document levels in a hierarchical manner. Evaluations on multi-aspect review datasets in English and Chinese show that DSPN, using only star rating labels for supervision, demonstrates significant efficiency advantages while performing comparably well to a variety of benchmark models. Additionally, DSPN’s pyramid structure enables the interpretability of its outputs. Our findings validate DSPN’s effectiveness and efficiency, establishing a robust, resource-efficient, unified framework for sentiment analysis.
- 30 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Management Information Systems
Open AccessFrom Stars to Insights: Exploration and Implementation of Unified Sentiment Analysis with Distant Supervision
Sentiment analysis is integral to understanding the voice of the customer and informing businesses’ strategic decisions. Conventional sentiment analysis involves three separate tasks: aspect-category detection, aspect-category sentiment analysis, and rating prediction. However, independently tackling these tasks can overlook their interdependencies and often requires expensive, fine-grained annotations. This paper introduces unified sentiment analysis, a novel learning paradigm that integrates the three aforementioned tasks into a coherent framework. To achieve this, we propose the Distantly Supervised Pyramid Network (DSPN), which employs a pyramid structure to capture sentiment at word, aspect, and document levels in a hierarchical manner. Evaluations on multi-aspect review datasets in English and Chinese show that DSPN, using only star rating labels for supervision, demonstrates significant efficiency advantages while performing comparably well to a variety of benchmark models. Additionally, DSPN’s pyramid structure enables the interpretability of its outputs. Our findings validate DSPN’s effectiveness and efficiency, establishing a robust, resource-efficient, unified framework for sentiment analysis.
- Open Access
- 18 September 2022
- Published by Association for Computing Machinery (ACM)
- p. 89-94
An Intelligent Patient Admission Model of Day Surgery Using Heterogeneous Data with Semi-Supervised Learning
- 18 September 2022
- Published by Association for Computing Machinery (ACM)
- p. 89-94
Open AccessAn Intelligent Patient Admission Model of Day Surgery Using Heterogeneous Data with Semi-Supervised Learning
- Open Access
- 12 November 2021
- Published by JMIR Publications Inc. in JMIR Preprints
An Intelligent Patient Admission Model of Day Surgery Using Heterogeneous Data with Semi-Supervised Learning: A Case Study of Laparoscopic Cholecystectomy (Preprint)
BACKGROUND Day surgery has many advantages including shortening hospital stay, decreasing the risk of hospital-associated infections, and increasing cost efficiency over traditional surgery, it has gained a great reputation and popularity in recent years. However, the patients’ admission criteria of day surgery at present were mainly based on expert experience, which was a lack of scientific evidence. OBJECTIVE Our study is to investigate the day surgery patient’s admission criteria and build an intelligent machine learning model of day surgery patients who underwent laparoscopic cholecystectomy, to ensure patients’ safety and medical quality, providing reference and inspiration for other day surgery admission decisions. METHODS We analyzed the clinical data of day surgery patients who underwent laparoscopic cholecystectomy at West China Hospital from Jan 1st 2009 to Dec 31st 2021 and developed a semi-supervised artificial intelligence algorithm, SDSPA algorithm, which is built by self-training and uses both structured data like patient characteristics and unstructured clinical diagnosis to assist surgeons to make quick admission decisions. RESULTS After comparing several classifiers with self-training in our experiment, the performance of LightGBM with unstructured text processed by BERT were the best, obtaining an accuracy of 0.85 and an f1-score of 0.83, as well as reaching 0.97 on the precision score, which is an important indicator related to patients’ safety. CONCLUSIONS The application of our SDSPA algorithm can make the patient admission of day surgery more intelligent, and maximize the utilization of medical resources while ensuring patients’ safety.
- 12 November 2021
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessAn Intelligent Patient Admission Model of Day Surgery Using Heterogeneous Data with Semi-Supervised Learning: A Case Study of Laparoscopic Cholecystectomy (Preprint)
BACKGROUND Day surgery has many advantages including shortening hospital stay, decreasing the risk of hospital-associated infections, and increasing cost efficiency over traditional surgery, it has gained a great reputation and popularity in recent years. However, the patients’ admission criteria of day surgery at present were mainly based on expert experience, which was a lack of scientific evidence. OBJECTIVE Our study is to investigate the day surgery patient’s admission criteria and build an intelligent machine learning model of day surgery patients who underwent laparoscopic cholecystectomy, to ensure patients’ safety and medical quality, providing reference and inspiration for other day surgery admission decisions. METHODS We analyzed the clinical data of day surgery patients who underwent laparoscopic cholecystectomy at West China Hospital from Jan 1st 2009 to Dec 31st 2021 and developed a semi-supervised artificial intelligence algorithm, SDSPA algorithm, which is built by self-training and uses both structured data like patient characteristics and unstructured clinical diagnosis to assist surgeons to make quick admission decisions. RESULTS After comparing several classifiers with self-training in our experiment, the performance of LightGBM with unstructured text processed by BERT were the best, obtaining an accuracy of 0.85 and an f1-score of 0.83, as well as reaching 0.97 on the precision score, which is an important indicator related to patients’ safety. CONCLUSIONS The application of our SDSPA algorithm can make the patient admission of day surgery more intelligent, and maximize the utilization of medical resources while ensuring patients’ safety.