基于三维点云数据的中医五行人面部特征与人格特质的关联性研究

doi:10.3969/j.issn.1006-7795.2026.03.016

首都医科大学学报

• 精神科中西医结合临床及认知神经基础 • 上一篇下一篇

基于三维点云数据的中医五行人面部特征与人格特质的关联性研究

林锦^1，2，贾竑晓^1，2*#，吕宏蓬^1，2*#，戴芷晴^1，2，姜新月³，段宇航^1,2，徐欢舒^1，2，赵子怡¹，2张云河⁴

1.首都医科大学附属北京安定医院，国家精神疾病医学中心，精神心理疾病国家临床医学研究中心，精神疾病创新药智能研发北京市重点实验室，北京 100088；2.人脑保护高精尖创新中心，首都医科大学，北京 100069；3.北京中医药大学第三临床医学院，北京 100029；4.赤峰市精神病防治院，内蒙古赤峰 024200

收稿日期:2026-02-02 修回日期:2026-03-09 出版日期:2026-06-21 发布日期:2026-06-25
通讯作者: 贾竑晓，吕宏蓬 E-mail:jhxlj@ccmu.edu.cn，molly731@126.com
基金资助:
国家自然科学基金项目（82305193，82474429），北京中医药薪火传承“新3+3”工程示范案例项目（2023-ZYSF-19），首都卫生发展科研专项（首发2026-2-2124），首都医科大学临床-基础合作平台培育项目（JLPYPT2025002）。

Facial features and personality traits in traditional Chinese medicine five-element typology based on 3D point-cloud data

Lin Jin^1，2, Jia Hongxiao^1，2*, Lü Hongpeng^1，2*, Dai Zhiqing^1，2, Jiang Xinyue³, Duan Yuhang^1,2, Xu Huanshu^1,2, Zhao Ziyi^1,2, Zhang Yunhe⁴

1.Beijing Anding Hospital, Capital Medical University；National Center for Mental Disorders；National Clinical Research Center for Mental Disorders；Beijing Key Laboratory of Intelligent Drug Research and Development for Mental Disorders， Beijing 100088, China; 2. Advanced Innovation Center for Human Brain Protection, Capital Medical University, Beijing 100069, China;3. Beijing University of Chinese Medicine Third Affiliated Hospital, Beijing 100029, China; 4. Chifeng Psychiatric Hospital,Chifeng 024200， Inner Mongolia Autonomous Region，China

Received:2026-02-02 Revised:2026-03-09 Online:2026-06-21 Published:2026-06-25
Supported by:
This study was supported by National Natural Science Foundation of China(82305193，82474429), Beijing Traditional Chinese Medicine Inheritance “New 3+3” Program Demonstration Case Project（2023-ZYSF-19）,Capital Health Development Scientific Research Special Project (2026-2-2124), Capital Medical University Clinical-Basic Cooperation Platform Cultivation Project(JLPYPT2025002).

摘要/Abstract

摘要： 目的基于中医五行人“形神一体”理论，采用三维点云面部数据客观量化面部特征，并评估面部特征对人格特质的可预测性。方法招募典型中医五行人健康受试者，采集三维点云面部数据与卡特尔16种人格因素问卷（Sixteen Personality Factor Questionnaire , 16PF）。采用深度学习算法自动定位面部标志点，提取39项面部特征。以各16PF因子为因变量、面部特征为自变量，控制年龄与性别，建立岭回归模型并进行10折交叉验证。以R²≥0.15筛选具有中等以上预测能力的因子，并通过置换重要性筛选关键面部特征，并评估性别对关键面部特征与人格关系的调节作用。结果共纳入804例受试者，面部特征对16PF中的幻想性、紧张性、实验性、有恒性与自律性达到中等以上预测能力。关键特征主要涉及面部起伏与曲率统计量、软组织形态及骨相与五官结构。纳入面部关键特征与性别的交互项后，模型预测性能未见明显提升。结论三维面部特征可在一定程度上预测16PF部分因子，提示面部特征与人格特质存在可量化的对应关系，为中医五行人“形神一体”理论提供了现代实证支持。

关键词: 中医五行人, 三维点云数据, 面部特征, 人格特质, 16种人格因素问卷（16PF）, 岭回归

Abstract: Objective To objectively quantify facial features using 3D point-cloud facial data under the traditional Chinese medicine (TCM) framework of “unity of form and spirit” (xing-shen unity), and to evaluate the predictability of personality traits from facial features in TCM five-element typology. Methods Typical healthy participants of TCM five elements type were recruited. The 3D point-cloud facial data and the Sixteen Personality Factor Questionnaire (16PF) were collected. A deep-learning algorithm was used to automatically localize 3D facial landmarks and extract 39 facial features. Ridge regression models were contructed for each 16PF factor as the dependent variable with facial features as predictors, adjusting for age and sex, and evaluated using 10-fold cross-validation. Factors with at least moderate predictive performance (R²≥ 0.15) were identified. Key facial features were identified based on permutation importance, and the moderating effect of sex on the associations between key facial features and personality traits was further assessed. Results A total of 804 participants were included. Facial features showed at least moderate predictive performance for five 16PF factors: Abstractedness (M), Tension (Q4), Openness to change (Q1), Rule consciousness (G), and Perfectionism (Q3). Key predictors mainly involved indices of facial surface undulation and curvature statistics, soft-tissue morphology, and craniofacial structure as well as facial component geometry. Following the inclusion of interaction terms between key facial features and sex, the model exhibited no substantial improvement in predictive performance. Conclusion The 3D facial features can predict several 16PF factors to a certain extent, suggesting a quantifiable correspondence between facial morphology and personality traits in TCM five-element typology, and providing modern empirical support for the TCM theory of xing-shen unity.

Key words: traditional Chinese medicine five-element typology, 3D point-cloud data, facial features, personality traits, Sixteen Personality Factor Questionnaire（16PF）, ridge regression

中图分类号:

林锦, 贾竑晓, 吕宏蓬, 戴芷晴, 姜新月, 段宇航, 徐欢舒, 赵子怡, 张云河. 基于三维点云数据的中医五行人面部特征与人格特质的关联性研究[J]. 首都医科大学学报, doi: 10.3969/j.issn.1006-7795.2026.03.016.

Lin Jin, Jia Hongxiao, Lü Hongpeng, Dai Zhiqing, Jiang Xinyue, Duan Yuhang, Xu Huanshu, Zhao Ziyi, Zhang Yunhe. Facial features and personality traits in traditional Chinese medicine five-element typology based on 3D point-cloud data[J]. Journal of Capital Medical University, doi: 10.3969/j.issn.1006-7795.2026.03.016.

参考文献

［1］李元昊, 李福凤. 中医五行人的现代研究进展［J］. 中国中医药科技, 2023, 30(5): 1040-1043.
［2］Li J J, Yang X Y, Zhang H J, et al. The psychosomatic traits of “people with the five elements in traditional Chinese medicine”: a qualitative study［J］. Biomed Environ Sci, 2023, 36(11): 1068-1078.
［3］李佳佳, 贾竑晓, Han J D J, 等. 中医水形人之亚型内涵解析［J］. 中华中医药杂志, 2024, 39(8): 4402-4405.
［4］李佳佳, 贾竑晓, Han J D J, 等. 中医土形人之亚型内涵解析［J］. 中华中医药杂志, 2024, 39(1): 410-412.
［5］李佳佳, 贾竑晓, Han J D J, 等. 中医五形人“火形人”之亚型内涵解析［J］. 中华中医药杂志, 2023, 38(11): 5564-5567.
［6］李佳佳, 贾竑晓, Han J D J, 等. 中医五形人“金形人”之亚型内涵解析［J］. 中华中医药杂志, 2024, 39(6): 3165-3168.
［7］李佳佳, 贾竑晓, Han J D J, 等. 中医五形人“木形人”之亚型内涵解析［J］. 中华中医药杂志, 2024, 39(2): 988-991.
［8］首都医科大学附属北京安定医院(北京市心理卫生中心中国药物依赖治疗中心). 中医五行(形)人面部表型分类量化规范［EB/OL］. (2022-12-29)［2024-01-17 ］. https://www. ccopyright. com. cn /publicInquiry. html.
［9］戴芷晴, 林锦, 段宇航, 等. 中医五行人之木行人与金行人认知功能差异比较研究［J］. 首都医科大学学报, 2024, 45(3): 458-465.
［10］段宇航, 吕宏蓬, 滕飞, 等. 中医五行人之火行人与水行人认知功能差异比较研究［J］. 首都医科大学学报, 2024, 45(1): 111-117.
［11］Liu H M, Wang T, Cai Z Q. Exploring the impact of the big five personality traits on cognitive performance in scientific reasoning: an ordered network analysis［J］. Cogn Process, 2025, 26(4): 849-863.
［12］滕飞, 宋明康, 吕宏蓬, 等. 人格特质与认知功能的相关性研究进展［J］. 首都医科大学学报, 2024, 45(3): 466-471.
［13］Hu S L, Xiong J Y, Fu P C, et al. Signatures of personality on dense 3D facial images［J］. Sci Rep, 2017, 7(1): 73.
［14］Kachur A, Osin E, Davydov D, et al. Assessing the big five personality traits using real-life static facial images［J］. Sci Rep, 2020, 10(1): 8487.
［15］Lv H P, Wang T F, Zhang J, et al. Analysis of personality traits' correlation to facial width-to-height ratio (fWHR) and mandibular line angle based on 16 personality factor in Chinese college students［J］. PLoS One, 2022, 17(12): e0278201.
［16］靳枫. 基于三维成像技术的大学生五行体质面部特征研究［D］. 福州: 福建中医药大学, 2018.
［17］芦煜, 于长颖, 陈畑宇, 等. 基于人脸分析技术的中医阴阳五行人分类研究［J］. 中华中医药杂志, 2020, 35(8): 4112-4116.
［18］任慧霞, 马晓梅, 王锦玉, 等. 基于面部特征测量的中医五行人体质类型判别研究［J］. 中华中医药杂志, 2022, 37(3): 1635-1638.
［19］朱龙, 靳枫, 刘霏, 等. 福建地区五行体质的面部形态特征客观参数研究［J］. 中华中医药杂志, 2020, 35(10): 5188-5192.
［20］首都医科大学附属北京安定医院(北京市心理卫生中心、中国药物依赖治疗中心). 中医五行(形)人格量表［EB/OL］. (2022-12-29)［2024-01-17］. https://www.ccopyright.com.cn.
［21］Paulsen R R, Juhl K A, Haspang T M, et al. Multi-view consensus CNN for 3D facial landmark placement［C］//Computer Vision-ACCV 2018. Cham: Springer, 2019: 706-719.
［22］Cattell R B, Cattell H E P. Personality structure and the new fifth edition of the 16PF［J］. Educ Psychol Meas, 1995, 55(6): 926-937.［23］Yan L R, Wang Y, Ding C H, et al. Correlation among behavior, personality, and electroencephalography revealed by a simulated driving experiment［J］. Front Psychol, 2019, 10: 1524.

[1]	林锦, 贾竑晓, 吕宏蓬, 戴芷晴, 姜新月, 徐欢舒, 赵子怡, 张云河. 中医五行人之木行人与金行人兴奋-抑制平衡的比较研究[J]. 首都医科大学学报, 2026, 47(3): 541-548.
[2]	戴芷晴, 林锦, 段宇航, 滕飞, 吕宏蓬, 贾竑晓. 中医五行人之木行人与金行人认知功能差异比较研究[J]. 首都医科大学学报, 2024, 45(3): 458-465.
[3]	段宇航, 吕宏蓬, 滕飞, 戴芷晴, 林锦, 贾竑晓. 中医五行人之火行人与水行人认知功能差异比较研究[J]. 首都医科大学学报, 2024, 45(1): 111-117.

基于三维点云数据的中医五行人面部特征与人格特质的关联性研究

Facial features and personality traits in traditional Chinese medicine five-element typology based on 3D point-cloud data

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价