김민소 (Nanyang Technological University) | 한빛사논문 > 한빛사

한빛사논문

조회81

Nanyang Technological University

Nat. Protoc., Jan 09 2026, | https://doi.org/10.1038/s41596-025-01296-9 Deployment of a cloud-based passive defecation monitoring system for continuous gut health monitoring

Zhiquan Song^1,16, Minso Kim^1,16, Jeung Lee^2,16, Tae Hyung Kwon^2,16, Juhwan Kim¹, Ji Hong Kim¹, Seong-Geon Kim¹, Soh Kim², Bong-Hyun Jun³, Sang Hun Lee⁴, Walter G. Park⁵, Irene Sonu⁵, Michael J. Rosen⁶, Chi Wei Ong¹, Xiaotao Shen^1,7, Leonard Wei Tat Ng⁸, Gun Kim⁹, Sang Hoon Chae^8,10, Kewin Tien Ho Siah¹¹, Dean Ho¹², Shang Wei Song¹², Nicole Martinez-Martin¹³, Juha Song¹, Kuo Chao Yew¹⁴, Munho Kim¹⁰, Hen-Wei Huang^7,10, Sunny H. Wong^7,14, Brian J. Lee¹⁵ & Seung-min Park^1,7

¹School of Chemistry, Chemical Engineering and Biotechnology, Nanyang Technological University, Singapore, Singapore.
²Department of Civil and Environmental Engineering, Stanford University, Stanford, CA, USA.
³Department of Bioscience and Biotechnology, Konkuk University, Seoul, Republic of Korea.
⁴Department of Chemical and Biological Engineering, Hanbat National University, Daejeon, Republic of Korea.
⁵Division of Gastroenterology and Hepatology, Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
⁶Division of Pediatric Gastroenterology, Hepatology and Nutrition, Department of Pediatrics, Stanford University School of Medicine, Stanford, CA, USA.
⁷Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore.
⁸School of Materials Science and Engineering, Nanyang Technological University, Singapore, Singapore.
⁹School of Civil and Environmental Engineering, Nanyang Technological University, Singapore, Singapore.
¹⁰School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore.
¹¹Division of Gastroenterology and Hepatology, University Medicine Cluster, National University Hospital, Singapore, Singapore.
¹²Department of Biomedical Engineering, College of Design and Engineering, National University of Singapore, Singapore, Singapore.
¹³Center for Biomedical Ethics, Stanford University, Stanford, CA, USA.
¹⁴Department of Gastroenterology and Hepatology, Tan Tock Seng Hospital, Singapore, Singapore.
¹⁵School of Mechanical Engineering, Sungkyunkwan University, Suwon, Republic of Korea.
¹⁶These authors contributed equally: Zhiquan Song, Minso Kim, Jeung Lee, Tae Hyung Kwon.

Corresponding authors
Correspondence to Brian J. Lee or Seung-min Park.

Abstract

With the growing demand for accurate yet effortless health monitoring at home, most current approaches to stool analysis rely on self-reported diaries that are prone to recall bias and low adherence. Here we present a fully passive alternative: the Precision Health Integrated Diagnostic (PHIND) system, a smart-toilet-based platform that enables automated defecation monitoring without requiring users to alter their daily routines. By integrating optical and pressure sensors with cloud-based convolutional neural networks, the PHIND system classifies stool form according to the Bristol Stool Form Scale and records key defecatory parameters, including total event time, defecation duration and time to first stool drop. The protocol proceeds in three principal stages: (1) assembling and mounting the hardware onto a conventional toilet; (2) training convolutional neural network models for stool classification and event detection; and (3) image acquisition and deploying cloud infrastructure for real-time analysis, data storage and visualization. Compared with traditional methods that depend on user-reported stool diaries, PHIND provides objective, near real-time data free from recall error, enabling more reliable early detection and long-term management of gastrointestinal conditions. Researchers and clinicians can expect high classification accuracy and robust, longitudinal insights into defecation patterns. The complete protocol-from hardware setup to system validation-can typically be completed within 2 d, excluding printed circuit board manufacturing, which generally requires up to 15 d depending on the manufacturing provider.

논문소개전체 설명

This paper presents a fully passive stool monitoring system that automatically classifies stool form using the Bristol Stool Form Scale (BSFS) without requiring any user input. The system operates continuously in the background and does not require users to change their daily routines or lifestyle. By eliminating manual stool logging, it reduces recall bias and improves long term adherence, enabling objective and reliable gut health monitoring.

Importantly, the paper is written as a complete step by step protocol, guiding readers from start to finish on how to build, train, and deploy the BSFS based monitoring system in real world settings. This makes the approach not only scientifically validated but also reproducible and accessible for researchers and clinicians interested in passive, real world gastrointestinal health monitoring

논문정보