Research Overview

In the Medical and Human Support Engineering Laboratory, we conduct research on estimating and predicting changes in human states from biomedical and clinical time-series data, based on biomedical measurement, medical AI, image and signal processing, and machine learning. We aim to develop non-contact and unobtrusive sensing technologies and time-series AI to support healthcare, education, and daily life, targeting data such as blood pressure, blood glucose, facial images, ear-canal pressure pulse waves, and ICU/clinical time-series data.

Biomedical and clinical data are not merely “numerical values at a single time point,” but time-series information that changes over time. In our laboratory, we study AI technologies that predict future state changes and risks from such temporal patterns and support decision-making in medical, educational, and daily-life settings. In particular, we aim to advance medical and human support engineering by viewing intradialytic hypotension, blood glucose fluctuations, hemodynamic changes, psychophysiological states, and clinical time-series data from the perspective of future prediction.

Laboratory website: https://sites.google.com/view/mhselab

researchmap: https://researchmap.jp/kou_oiwa/

ORCID: https://orcid.org/0000-0002-7508-171X

Research Themes

Biomedical and Clinical Time-Series AI for Future Prediction

The central research concept of our laboratory is to develop an AI platform that predicts future changes in human states from biomedical and clinical time-series data naturally obtained in medical, educational, and daily-life settings, thereby supporting human decision-making and actions. By integrating facial images, biological signals, clinical data, behavioral information, and environmental information, we are developing practical biosensing technologies through a workflow consisting of measurement, feature extraction, prediction, and support.

For example, we analyze time-series data such as facial color, facial skin temperature, and facial expression changes obtained from facial images; ear-canal pressure pulse waves measurable with earphones or headphones; and blood pressure, laboratory values, and treatment records collected in medical settings. Through these analyses, we aim to detect future changes in human states and potential risks at an early stage.

Future Prediction of Intradialytic Hypotension

Intradialytic hypotension, which occurs during hemodialysis, is an important clinical issue that affects both patient burden and clinical management. In our laboratory, we study AI technologies for early detection of signs preceding intradialytic hypotension by using blood pressure data measured during dialysis, as well as visible and infrared facial images, facial color changes, facial temperature changes, and facial expression changes.

Conventional blood pressure measurement may not capture changes until hypotension has already occurred. Therefore, we analyze subtle changes contained in facial image time-series data to identify signs that appear before blood pressure decreases. Through this approach, we aim to support early decision-making by medical staff and contribute to medical safety.

Keywords: intradialytic hypotension, facial image monitoring, visible and infrared image analysis, time-series AI, clinical AI, medical safety support

Related publications

Kosuke Oiwa, Takehiro Okama, Satoshi Suzuki, Yoshitaka Maeda, Akio Nozawa, “Construction of a Hypotension Prediction Model Using Deep Learning With Visible and Infrared Facial Images of Hemodialysis Patients,” IEEE Access, 2025.

Estimation of Blood Glucose and Blood Pressure Changes Using Multispectral Facial Images

Low-burden monitoring of vital signs such as blood glucose and blood pressure is important for daily health management and early detection of disease-related risks. In our laboratory, we use multispectral facial images, including visible and near-infrared images, to extract optical features associated with changes in blood glucose and blood pressure. Our goal is to develop non-contact and non-invasive remote vital-sign sensing technologies.

Facial images may contain information related to skin blood flow, hemodynamics, and metabolic states. We analyze spatial features and time-series changes in multispectral images and aim to construct models that estimate biological information such as blood glucose and blood pressure while considering individual differences.

Keywords: multispectral facial images, near-infrared images, blood glucose estimation, blood pressure estimation, non-contact vital-sign sensing, remote health monitoring

Related publications

Kosuke Oiwa, Mayuko Nakagawa, Yasushi Nanai, Kent Nagumo, Akio Nozawa, “Optimal Wavelength Bands for Remote Blood Glucose Estimation Using Facial NIR Spectroscopic Images Measured at 800–1650 nm,” IEEE Transactions on Biomedical Engineering, 2026.

Masahito Takano, Kent Nagumo, Yasushi Nanai, Kosuke Oiwa, Akio Nozawa, “Remote blood pressure measurement from near-infrared face images: A comparison of the accuracy by the use of first and second biological optical window,” Biomedical Signal Processing and Control, 2024.

Mayuko Nakagawa, Kosuke Oiwa, Yasushi Nanai, Kent Nagumo, Akio Nozawa, “Feature Extraction for Estimating Acute Blood Glucose Level Variation from Multi-wavelength Facial Images,” IEEE Sensors Journal, 2023.

Kosuke Oiwa, Yusuke Ozawa, Kent Nagumo, Seiya Nishimura, Yasushi Nanai, Akio Nozawa, “Remote Blood Pressure Sensing Using Near-infrared Wideband LEDs,” IEEE Sensors Journal, 2021.

Estimation of Physiological and Psychological States Using Ear-Canal Pressure Pulse Waves

Our laboratory focuses on ear-canal pressure pulse waves that can be measured using ordinary earphones or headphones, and studies technologies for unobtrusive assessment of physiological states in daily-life and learning environments. Ear-canal pressure pulse waves may contain information related to hemodynamics, stress, psychological states, and learning engagement.

Because earphones and headphones are widely used in daily life, ear-canal pressure pulse sensing may enable continuous monitoring of health status, concentration, and stress without placing a large burden on users. We analyze waveform features and time-series changes in ear-canal pressure pulse waves and aim to apply this technology to medical, educational, and daily-life support.

Keywords: ear-canal pressure pulse wave, earphone-based sensing, headphone-based sensing, psychophysiological state estimation, learning engagement assessment, wearable and hearable sensing

Related publication

Kosuke Oiwa, Airi Mori, Hiroshi Ogawa, Shusaku Nomura, “Morphological changes in ear canal pulse waves, detected via consumer headphones, under acute stress conditions,” AHFE International Conference & Expo Hawaii Edition 2025, 2025.

Analysis of ICU and Clinical Time-Series Data

In ICUs and other medical settings, various types of clinical time-series data, such as vital signs, laboratory values, treatment records, and nursing records, are continuously recorded. In our laboratory, we analyze these data using AI and machine learning to develop technologies for predicting changes in patient states and future risks.

In clinical practice, patient conditions change over time; therefore, it is important to capture not only single-point values but also the temporal flow of changes from the past to the present. We aim to extract temporal patterns from clinical time-series data and develop predictive models that contribute to early warning, risk detection, and medical safety support.

Keywords: ICU data analysis, clinical time-series prediction, patient state changes, risk prediction, medical AI, medical safety support

Related Research: Human Behavior Recognition and Remote Communication Support

In addition to our main research themes, we also conduct research on human support technologies using image and time-series information. Specifically, we are working on applied AI sensing technologies for medical, educational, and daily-life support, including sign language recognition, human behavior recognition, and psychophysiological state estimation in educational and living environments.

These studies are consistent with our laboratory’s research concept in that they aim to understand changes in human states from images, signals, and time-series data and connect such understanding to human support.

Keywords: sign language recognition, human behavior recognition, image recognition, psychophysiological state estimation, educational support, daily-life support

Related publication

Keiji Osumi, Koya Hiraishi, Shu Kobayashi, Nagul Cooharojananone, Hirokazu Doi, Kosuke Oiwa, “Effects of Air Environment on Students’ Behavior and Psychophysiological States,” 31st International Symposium on Artificial Life and Robotics, 2026.