Xiangmin Fan

Xiangmin Fan

Auto-generated profile, based on publicly available information

Xiangmin Fan

Institute of Software Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 January 2021 in Journal of Medical Internet Research
Verified
Journal Article
Open access
XFXiangmin Fan
Xiangmin Fan
DCDaren Chao
Daren Chao
ZZZhan Zhang
Zhan Zhang
DWDakuo Wang
Dakuo Wang
XLXiaohua Li
Xiaohua Li
FTFeng Tian
Feng Tian
Background: Artificial intelligence (AI)-driven chatbots are increasingly being used in health care, but most chatbots are designed for a specific population and evaluated in controlled settings. There is little research documenting how health consumers (eg, patients and caregivers) use chatbots for self-diagnosis purposes in real-world scenarios. Objective: The aim of this research was to understand how health chatbots are used in a real-world context, what issues and barriers exist in their usage, and how the user experience of this novel technology can be improved. Methods: We employed a data-driven approach to analyze the system log of a widely deployed self-diagnosis chatbot in China. Our data set consisted of 47,684 consultation sessions initiated by 16,519 users over 6 months. The log data included a variety of information, including users’ nonidentifiable demographic information, consultation details, diagnostic reports, and user feedback. We conducted both statistical analysis and content analysis on this heterogeneous data set. Results: The chatbot users spanned all age groups, including middle-aged and older adults. Users consulted the chatbot on a wide range of medical conditions, including those that often entail considerable privacy and social stigma issues. Furthermore, we distilled 2 prominent issues in the use of the chatbot: (1) a considerable number of users dropped out in the middle of their consultation sessions, and (2) some users pretended to have health concerns and used the chatbot for nontherapeutic purposes. Finally, we identified a set of user concerns regarding the use of the chatbot, including insufficient actionable information and perceived inaccurate diagnostic suggestions. Conclusions: Although health chatbots are considered to be convenient tools for enhancing patient-centered care, there are issues and barriers impeding the optimal use of this novel technology. Designers and developers should employ user-centered approaches to address the issues and user concerns to achieve the best uptake and utilization. We conclude the paper by discussing several design implications, including making the chatbots more informative, easy-to-use, and trustworthy, as well as improving the onboarding experience to enhance user engagement.

22 October 2020 in Proceedings of the Association for Information Science and Technology
Verified
Journal Article
Open access
PDF file
ZZZhan Zhang
Zhan Zhang
YGYegin Genc
Yegin Genc
AXAiwen Xing
Aiwen Xing
DWDakuo Wang
Dakuo Wang
XFXiangmin Fan
Xiangmin Fan
DCDaniel Citardi
Daniel Citardi
With the recent advances in Artificial Intelligence (AI) technology, patient‐facing applications have started embodying this novel technology to deliver timely healthcare information and services to the patient. However, little is known about lay individuals' perceptions and acceptance of AI‐driven, patient‐facing health systems. In this study, we conducted a survey with 203 participants to investigate their perceptions about using AI to consult information related to their diagnostic results and what factors influence their perceptions. Our results showed that despite the awareness and experience of patient‐facing AI systems being low amongst our participants, people had a generally positive attitude towards such systems. A majority of participants indicated a high level of comfortability and willingness to use health AI systems, and agreed AI could help them comprehend diagnostic results. Several intrinsic factors, such as education background and technology literacy, play an important role in people's perceptions of using AI to comprehend diagnostic results. In particular, people with high technology and health literacy, and education levels had more experiences with using AI and tended to trust AI outputs. We conclude this paper by discussing the implications of this work, with an emphasis on enhancing the trustworthiness of AI and bridging the digital divide.

7 November 2019 in Proceedings of the ACM on Human-Computer Interaction
Verified
Journal Article
Open access
PDF file
WSWei Sun
Wei Sun
YLYunzhi Li
Yunzhi Li
FTFeng Tian
Feng Tian
XFXiangmin Fan
Xiangmin Fan
HWHongan Wang
Hongan Wang
The degree and quality of instructor-student interactions are crucial for students' engagement, retention, and learning outcomes. However, such interactions are limited in live online lectures, where instructors no longer have access to important cues such as raised hands or facial expressions at the time of teaching. As a result, instructors cannot fully understand students' learning progresses. This paper presents an explorative study investigating how presenters perceive and react to audience flow prediction when giving live-stream lectures, which has not been examined yet. The study was conducted with an experimental system that can predict audience's psychological states (e.g., anxiety, flow, boredom) through real-time facial expression analysis, and can provide aggregated views illustrating the flow experience of the whole group. Through evaluation with 8 online lectures (N_instructors=8, N_learners=21), we found such real-time flow prediction and visualization can provide value to presenters. This paper contributes a set of useful findings regarding their perception and reaction of such flow prediction, as well as lessons learned in the study, which can be inspirational for building future AI-powered system to assist people in delivering live online presentations.

5 July 2023 in Journal of Medical Internet Research
Verified
Journal Article
Open access
YJYu Jing
Yu Jing
PQPeinuan Qin
Peinuan Qin
XFXiangmin Fan
Xiangmin Fan
WQWei Qiang
Wei Qiang
ZWZhu Wencheng
Zhu Wencheng
DWDakuo Wang
Dakuo Wang
Background: Neurodegenerative diseases (NDDs) are prevalent among older adults worldwide. Early diagnosis of NDD is challenging yet crucial. Gait status has been identified as an indicator of early-stage NDD changes and can play a significant role in diagnosis, treatment, and rehabilitation. Historically, gait assessment has relied on intricate but imprecise scales by trained professionals or required patients to wear additional equipment, causing discomfort. Advancements in artificial intelligence may completely transform this and offer a novel approach to gait evaluation. Objective: This study aimed to use cutting-edge machine learning techniques to offer patients a noninvasive, entirely contactless gait assessment and provide health care professionals with precise gait assessment results covering all common gait-related parameters to assist in diagnosis and rehabilitation planning. Methods: Data collection involved motion data from 41 different participants aged 25 to 85 (mean 57.51, SD 12.93) years captured in motion sequences using the Azure Kinect (Microsoft Corp; a 3D camera with a 30-Hz sampling frequency). Support vector machine (SVM) and bidirectional long short-term memory (Bi-LSTM) classifiers trained using spatiotemporal features extracted from raw data were used to identify gait types in each walking frame. Gait semantics could then be obtained from the frame labels, and all the gait parameters could be calculated accordingly. For optimal generalization performance of the model, the classifiers were trained using a 10-fold cross-validation strategy. The proposed algorithm was also compared with the previous best heuristic method. Qualitative and quantitative feedback from medical staff and patients in actual medical scenarios was extensively collected for usability analysis. Results: The evaluations comprised 3 aspects. Regarding the classification results from the 2 classifiers, Bi-LSTM achieved an average precision, recall, and F1-score of 90.54%, 90.41%, and 90.38%, respectively, whereas these metrics were 86.99%, 86.62%, and 86.67%, respectively, for SVM. Moreover, the Bi-LSTM–based method attained 93.2% accuracy in gait segmentation evaluation (tolerance set to 2), whereas that of the SVM-based method achieved only 77.5% accuracy. For the final gait parameter calculation result, the average error rate of the heuristic method, SVM, and Bi-LSTM was 20.91% (SD 24.69%), 5.85% (SD 5.45%), and 3.17% (SD 2.75%), respectively. Conclusions: This study demonstrated that the Bi-LSTM–based approach can effectively support accurate gait parameter assessment, assisting medical professionals in making early diagnoses and reasonable rehabilitation plans for patients with NDD.

13 May 2024 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Verified
Journal Article
Open access
KLKaiyan Ling
Kaiyan Ling
HZHang Zhao
Hang Zhao
XFXiangmin Fan
Xiangmin Fan
XNXiaohui Niu
Xiaohui Niu
Wenchao YinWenchao Yin
Wenchao Yin
XBXiaojun Bi
Xiaojun Bi
Touch pointing is one of the primary interaction actions on mobile devices. In this research, we aim to (1) model touch pointing for people with Parkinson's Disease (PD), and (2) detect PD via touch pointing. We created a mobile game called MoleBuster in which a user performs a sequence of pointing actions. Our study with 40 participants shows that PD participants exhibited distinct pointing behavior. PD participants were much slower and had greater variances in movement time (MT), while their error rate was slightly lower than age-matched non-PD participants, indicating PD participants traded speed for accuracy. The nominal width Finger-Fitts law showed greater fitness than Fitts' law, suggesting this model should be adopted in lieu of Fitts' law to guide mobile interface design for PD users. We also proposed a CNN-Transformer-based neural network model to detect PD. Taking touch pointing data and comfort rating of finger movement as input, this model achieved an AUC of 0.97 and sensitivity of 0.95 in leave-one-user-out cross-validation. Overall, our research contributes models that reveal the temporal and spatial characteristics of touch pointing for PD users, and provide a new method (CNN-Transformer model) and a mobile game (MoleBuster) for convenient PD detection.

27 May 2019 in CCF Transactions on Pervasive Computing and Interaction
Verified
Journal Article
Closed access
PDF file
NLNianlong Li
Nianlong Li
FTFeng Tian
Feng Tian
XFXiangmin Fan
Xiangmin Fan
YZYicheng Zhu
Yicheng Zhu
HWHongan Wang
Hongan Wang
GDGuozhong Dai
Guozhong Dai