Faculty Profiles - MORITA Mizuki

Papers - MORITA Mizuki

Division display 1 - 20 of about 50 ／ All the affair displays >>

Effects of Sampling Frequency on Human Activity Recognition with Machine Learning Aiming at Clinical Applications Reviewed International journal

Takahiro Yamane, Moeka Kimura, Mizuki Morita

Sensors 25 ( 12 ) 3780 - 3780 2025.6

Authorship：Last author,　Corresponding author Language：English Publishing type：Research paper (scientific journal) Publisher：MDPI AG

Human activity recognition using wearable accelerometer data can be a useful digital biomarker for severity assessment and the diagnosis of diseases, where the relationship between onset and patient activity is crucial. For long-term monitoring in clinical settings, the volume of data collected over time should be minimized to reduce power consumption, computational load, and communication volume. This study aimed to determine the lowest sampling frequency that maintains recognition accuracy for each activity. Thirty healthy participants wore nine-axis accelerometer sensors at five body locations and performed nine activities. Machine-learning-based activity recognition was conducted using data sampled at 100, 50, 25, 20, 10, and 1 Hz. Data from the non-dominant wrist and chest, which have previously shown high recognition accuracy, were used. Reducing the sampling frequency to 10 Hz did not significantly affect the recognition accuracy for either location. However, lowering the frequency to 1 Hz decreases the accuracy of many activities, particularly brushing teeth. Using data with a 10 Hz sampling frequency can maintain recognition accuracy while decreasing data volume, enabling long-term patient monitoring and device miniaturization for clinical applications.

DOI： 10.3390/s25123780

researchmap

DNA Degradation in FFPE Tissue Samples Caused by Air Transport: An Experimental Evaluation of Radiation Exposure Reviewed International journal

Rio Yamaguchi, Takahiro Yamane, Masahiro Oita, Hirofumi Inoue, Mizuki Morita

Pathology International 2025.6

Impact of Sensor-Axis Combinations on Machine Learning Accuracy for Human Activity Recognition Using Accelerometer Data in Clinical Settings Reviewed International journal

Takahiro Yamane, Moeka Kimura, Mizuki Morita

Physical Activity and Health 9 ( 1 ) 95 - 109 2025.5

Authorship：Last author,　Corresponding author Language：English Publishing type：Research paper (scientific journal) Publisher：Ubiquity Press, Ltd.

Background: Identifying patient activity during symptom onset is crucial in conditions such as chronic obstructive pulmonary disease (COPD) or arrhythmia. Accelerometer data can aid in this process; however, minimal data requirements are preferable. This study aimed to determine the minimum number of axes required to accurately recognize activities related to COPD or arrhythmia.Methods: Thirty healthy participants wore a 9-axis accelerometer in five positions and performed nine activities. Machine learning-based activity recognition was conducted using 9-, 6-, and 3-axis data from the nondominant wrist or chest, as these two positions demonstrated high recognition accuracy in our previous study.Results: For the nondominant wrist, the accuracy of recognizing activities such as lying in the supine position, standing, eating, and running was comparable for the 3-axis acceleration and 9-axis data. For the chest, the accuracy of recognizing activities such as lying in the supine position, standing, sitting, using the restroom, and ascending or descending stairs was comparable for 6-axis (combined acceleration and magnetometer) and 9-axis data.Conclusions: The findings suggest that 3-axis acceleration data for the nondominant wrist and 6-axis combined acceleration and magnetometer data for the chest lead to high activity recognition accuracy.

DOI： 10.5334/paah.441

researchmap

Clinical-level screening of sleep apnea syndrome with single-lead ECG alone is achievable using machine learning with appropriate time windows Reviewed International journal

Takahiro Yamane, Masanori Fujii, Mizuki Morita

Sleep and Breathing 29 ( 2 ) 156 2025.4

Authorship：Last author,　Corresponding author Language：English Publishing type：Research paper (scientific journal) Publisher：Springer Science and Business Media LLC

Purpose: To establish a simple and noninvasive screening test for sleep apnea (SA) that imposes less burden on potential patients. The specific objective of this study was to verify the effectiveness of past and future single-lead electrocardiogram (ECG) data from SA occurrence sites in improving the estimation accuracy of SA and sleep apnea syndrome (SAS) using machine learning.
Methods: The Apnea-ECG dataset comprising 70 ECG recordings was used to construct various machine-learning models. The time window size was adjusted based on the accuracy of SA detection, and the performance of SA detection and SAS diagnosis (apnea‒hypopnea index ≥ 5 was considered SAS) was compared.
Results: Using ECG data from a few minutes before and after the occurrence of SAs improved the estimation accuracy of SA and SAS in all machine learning models. The optimal range of the time window and achieved accuracy for SAS varied by model; however, the sensitivity ranged from 95.7 to 100%, and the specificity ranged from 91.7 to 100%.
Conclusions: ECG data from a few minutes before and after SA occurrence were effective in SA detection and SAS diagnosis, confirming that SA is a continuous phenomenon and that SA affects heart function over a few minutes before and after SA occurrence. Screening tests for SAS, using data obtained from single-lead ECGs with appropriate past and future time windows, should be performed with clinical-level accuracy.

DOI： 10.1007/s11325-025-03316-0

researchmap

Other Link： https://link.springer.com/article/10.1007/s11325-025-03316-0/fulltext.html

Application of Nine-Axis Accelerometer-Based Recognition of Daily Activities in Clinical Examination Reviewed International journal

Takahiro Yamane, Moeka Kimura, Mizuki Morita

Physical Activity and Health 8 ( 1 ) 29 - 46 2024.3

Tri-Axial Accelerometer-Based Recognition of Daily Activities Causing Shortness of Breath in COPD Patients Reviewed International journal

Takahiro Yamane, Yuu Yamasaki, Wakana Nakashima, Mizuki Morita

Physical Activity and Health 7 ( 1 ) 64 - 75 2023.2

Trial of sportswear type ECG sensor device for cardiac safety management during marathon running Reviewed International journal

Takahiro Yamane, Kazuya Hirano, Kenta Hirai, Daiki Ousaka, Noriko Sakano, Mizuki Morita, Susumu Oozawa, Shingo Kasahara

Advanced Biomedical Engineering 11 151 - 161 2022.8

Initial evaluation of a novel electrocardiography sensor-embedded fabric wear during a full marathon Reviewed International journal

Daiki Ousaka, Kenta Hirai, Noriko Sakano, Mizuki Morita, Madoka Haruna, Kazuya Hirano, Takahiro Yamane, Akira Teraoka, Kazuo Sanou, Susumu Oozawa, Shingo Kasahara

Heart and Vessels 37 ( 3 ) 443 - 450 2022.3

Language：English Publishing type：Research paper (scientific journal)

Sudden cardiac accident (SCA) during a marathon is a concern due to the popularity of the sport. Preventive strategies, such as cardiac screening and deployment of automated external defibrillators have controversial cost-effectiveness. We investigated the feasibility of use of a new electrocardiography (ECG) sensor-embedded fabric wear (SFW) during a marathon as a novel preventive strategy against SCA. Twenty healthy volunteers participated in a full marathon race. They were equipped with a SFW hitoe® with a transmitter connected via Bluetooth to a standard smartphone for continuous ECG recording. All data were stored in a smartphone and used to analyze the data acquisition rate. The adequate data acquisition rate was > 90% in 13, 30-90% in 3, and < 10% in 4 runners. All of 4 runners with poorly recorded data were female. Inadequate data acquisition was significantly associated with the early phase of the race compared with the mid phase (P = 0.007). Except for 3 runners with poor heart rate data, automated software calculation was significantly associated with manual analysis for both the mean (P < 0.001) and maximum (P = 0.014) heart rate. We tested the feasibility of continuously recording cardiac data during a marathon using a new ECG sensor-embedded wearable device. Although data from 65% of runners were adequately recorded, female runners and the early phase of the race tended to have poor data acquisition. Further improvements in device ergonomics and software are necessary to improve ability to detect abnormal ECGs that may precede SCA.

DOI： 10.1007/s00380-021-01939-3

PubMed

researchmap

Multiple cancer type classification by small RNA expression profiles with plasma samples from multiple facilities Reviewed International journal

Kuno Suzuki, Hideyoshi Igata, Motoki Abe, Yusuke Yamamoto, small RNA based cancer classification project

Cancer Science 113 ( 6 ) 2144 - 2166 2022.2

Predicting Anesthetic Infusion Events Using Machine Learning Reviewed International journal

Naoki Miyaguchi, Koh Takeuchi, Hisashi Kashima, Mizuki Morita, Hiroshi Morimatsu

Scientific Reports 11 ( 1 ) 23648 - 23648 2021.11

Language：English Publishing type：Research paper (scientific journal)

Recently, research has been conducted to automatically control anesthesia using machine learning, with the aim of alleviating the shortage of anesthesiologists. In this study, we address the problem of predicting decisions made by anesthesiologists during surgery using machine learning; specifically, we formulate a decision making problem by increasing the flow rate at each time point in the continuous administration of analgesic remifentanil as a supervised binary classification problem. The experiments were conducted to evaluate the prediction performance using six machine learning models: logistic regression, support vector machine, random forest, LightGBM, artificial neural network, and long short-term memory (LSTM), using 210 case data collected during actual surgeries. The results demonstrated that when predicting the future increase in flow rate of remifentanil after 1 min, the model using LSTM was able to predict with scores of 0.659 for sensitivity, 0.732 for specificity, and 0.753 for ROC-AUC; this demonstrates the potential to predict the decisions made by anesthesiologists using machine learning. Furthermore, we examined the importance and contribution of the features of each model using Shapley additive explanations-a method for interpreting predictions made by machine learning models. The trends indicated by the results were partially consistent with known clinical findings.

DOI： 10.1038/s41598-021-03112-2

PubMed

researchmap

The Data Use Ontology to streamline responsible access to human biomedical datasets Reviewed International coauthorship International journal

Jonathan Lawson, Moran N. Cabili, Giselle Kerry, Tiffany Boughtwood, Adrian Thorogood, Pinar Alper, Sarion R. Bowers, Rebecca R. Boyles, Anthony J. Brookes, Matthew Brush, Tony Burdett, Hayley Clissold, Stacey Donnelly, Stephanie O.M. Dyke, Mallory A. Freeberg, Melissa A. Haendel, Chihiro Hata, Petr Holub, Francis Jeanson, Aina Jene, Minae Kawashima, Shuichi Kawashima, Melissa Konopko, Irene Kyomugisha, Haoyuan Li, Mikael Linden, Laura Lyman Rodriguez, Mizuki Morita, Nicola Mulder, Jean Muller, Satoshi Nagaie, Jamal Nasir, Soichi Ogishima, Vivian Ota Wang, Laura D. Paglione, Ravi N. Pandya, Helen Parkinson, Anthony A. Philippakis, Fabian Prasser, Jordi Rambla, Kathy Reinold, Gregory A. Rushton, Andrea Saltzman, Gary Saunders, Heidi J. Sofia, John D. Spalding, Morris A. Swertz, Ilia Tulchinsky, Esther J. van Enckevort, Susheel Varma, Craig Voisin, Natsuko Yamamoto, Chisato Yamasaki, Lyndon Zass, Jaime M. Guidry Auvil, Tommi H. Nyrönen, Mélanie Courtot

Cell Genomics 1 ( 2 ) 100028 - 100028 2021.11

Simple Wearable Device to Reduce Stress When Delivering a Speech without Pre-Training Reviewed International journal

Takahiro Yamane, Yuma Nakadoi, Mina Takagi, Mizuki Morita

Healthcare Informatics Research 27 ( 3 ) 231 - 240 2021.7

Rolling stockpile of medical supplies for pandemic preparedness: modeling and simulation Reviewed

Mizuki Morita

Interdisciplinary Science 1 17 - 20 2021.3

Authorship：Lead author,　Last author,　Corresponding author Language：Japanese Publishing type：Research paper (bulletin of university, research institution)

When a global pandemic of infectious diseases occurs, demand for medical supplies such as masks, disinfectants, and personal protective equipment will exceed the production capacity in normal times, consequently leading to serious shortages. Stockpiling is necessary to prepare for such situations. However, because pandemics are infrequent and might occur at any time, stockpile freshness is an important concern. As described in this paper, a “rolling stockpile” of medical supplies is proposed to prevent the medical supply stockpile from becoming too old. A formulation of a model and simulations based on it is presented. Results demonstrate that the method is applicable to the design of warehouses for rolling stockpiles, monitoring stockpile depletion during emergencies, and monitoring the process of recovery from emergencies.

DOI： 10.18926/interdisciplinary/61886

researchmap

Information and communication technology equipment and services for remote monitoring and health management: Survey of services and their classification for use in home care nursing Reviewed

Toshio Sakamoto, Akina Hirata, Mizuki Morita

Interdisciplinary Science 1 47 - 63 2021.3

De-identifying free text of Japanese electronic health records Reviewed International journal

Kohei Kajiyama, Hiromasa Horiguchi, Takashi Okumura, Mizuki Morita, Yoshinobu Kano

Journal of Biomedical Semantics 11 ( 1 ) 11 - 11 2020.9

Language：English Publishing type：Research paper (scientific journal)

BACKGROUND: Recently, more electronic data sources are becoming available in the healthcare domain. Electronic health records (EHRs), with their vast amounts of potentially available data, can greatly improve healthcare. Although EHR de-identification is necessary to protect personal information, automatic de-identification of Japanese language EHRs has not been studied sufficiently. This study was conducted to raise de-identification performance for Japanese EHRs through classic machine learning, deep learning, and rule-based methods, depending on the dataset. RESULTS: Using three datasets, we implemented de-identification systems for Japanese EHRs and compared the de-identification performances found for rule-based, Conditional Random Fields (CRF), and Long-Short Term Memory (LSTM)-based methods. Gold standard tags for de-identification are annotated manually for age, hospital, person, sex, and time. We used different combinations of our datasets to train and evaluate our three methods. Our best F1-scores were 84.23, 68.19, and 81.67 points, respectively, for evaluations of the MedNLP dataset, a dummy EHR dataset that was virtually written by a medical doctor, and a Pathology Report dataset. Our LSTM-based method was the best performing, except for the MedNLP dataset. The rule-based method was best for the MedNLP dataset. The LSTM-based method achieved a good score of 83.07 points for this MedNLP dataset, which differs by 1.16 points from the best score obtained using the rule-based method. Results suggest that LSTM adapted well to different characteristics of our datasets. Our LSTM-based method performed better than our CRF-based method, yielding a 7.41 point F1-score, when applied to our Pathology Report dataset. This report is the first of study applying this LSTM-based method to any de-identification task of a Japanese EHR. CONCLUSIONS: Our LSTM-based machine learning method was able to extract named entities to be de-identified with better performance, in general, than that of our rule-based methods. However, machine learning methods are inadequate for processing expressions with low occurrence. Our future work will specifically examine the combination of LSTM and rule-based methods to achieve better performance. Our currently achieved level of performance is sufficiently higher than that of publicly available Japanese de-identification tools. Therefore, our system will be applied to actual de-identification tasks in hospitals.

DOI： 10.1186/s13326-020-00227-9

PubMed

researchmap

DV200 index for assessing RNA integrity in next-generation sequencing Reviewed International journal

Takehiro Matsubara, Junichi Soh, Mizuki Morita, Takahiro Uwabo, Shuta Tomida, Toshiyoshi Fujiwara, Susumu Kanazawa, Shinichi Toyooka, Akira Hirasawa

BioMed Research International 2020 9349132 2020.2

Language：English Publishing type：Research paper (scientific journal) Publisher：Hindawi

Poor quality of biological samples will result in an inaccurate analysis of next-generation sequencing (NGS). Therefore, methods to accurately evaluate sample integrity are needed. Among methods for evaluating RNA quality, the RNA integrity number equivalent (RINe) is widely used, whereas the DV200, which evaluates the percentage of fragments of >200 nucleotides, is also used as a quality assessment standard. In this study, we compared the RINe and DV200 RNA quality indexes to determine the most suitable RNA index for the NGS analysis. Seventy-one RNA samples were extracted from formalin-fixed paraffin-embedded tissue samples (n = 30), fresh-frozen samples (n = 25), or cell lines (n = 16). After assessing RNA quality using the RINe and DV200, we prepared two kinds of stranded mRNA sequencing libraries. Finally, we calculated the correlation between each RNA quality index and the amount of library product (1st PCR product per input RNA). The DV200 measure showed stronger correlation with the amount of library product than the RINe (R 2 = 0.8208 for the DV200 versus 0.6927 for the RINe). Receiver operating characteristic curve analyses revealed that the DV200 was the better marker for predicting efficient library production than the RINe using a threshold of >10 ng/ng for the amount of the 1st PCR product per input RNA (cutoff value for the RINe and DV200, 2.3 and 66.1%; area under the curve, 0.99 and 0.91; sensitivity, 82% and 92%; and specificity, 93% and 100%, respectively). Our results indicate that NGS libraries prepared using RNA samples with the DV200 value > 66.1% exhibit greater sensitivity and specificity than those prepared with the RINe values > 2.3. These findings suggest that the DV200 is superior to the RINe, especially for low-quality RNA, because it is a more consistent assessment of the amount of the 1st NGS library product per input.

DOI： 10.1155/2020/9349132

PubMed

researchmap

Search for Therapeutic Agents for Cardiac Arrest Using a Drug Discovery Tool and Large-Scale Medical Information Database Reviewed International journal

Yoshito Zamami, Takahiro Niimura, Toshihiro Koyama, Yuta Shigemi, Yuki Izawa-Ishizawa, Mizuki Morita, Ayako Ohshima, Keisaku Harada, Toru Imai, Hiromi Hagiwara, Naoto Okada, Mitsuhiro Goda, Kenshi Takechi, Masayuki Chuma, Yutaka Kondo, Koichiro Tsuchiya, Shiro Hinotsu, Mitsunobu R Kano, Keisuke Ishizawa

Frontiers in pharmacology 10 1257 - 1257 2019.11

Language：English Publishing type：Research paper (scientific journal)

The survival rate of cardiac arrest patients is less than 10%; therefore, development of a therapeutic strategy that improves their prognosis is necessary. Herein, we searched data collected from medical facilities throughout Japan for drugs that improve the survival rate of cardiac arrest patients. Candidate drugs, which could improve the prognosis of cardiac arrest patients, were extracted using "TargetMine," a drug discovery tool. We investigated whether the candidate drugs were among the drugs administered within 1 month after cardiac arrest in data of cardiac arrest cases obtained from the Japan Medical Data Center. Logistic regression analysis was performed, with the explanatory variables being the presence or absence of the administration of those candidate drugs that were administered to ≥10 patients and the objective variable being the "survival discharge." Adjusted odds ratios for survival discharge were calculated using propensity scores for drugs that significantly improved the proportion of survival discharge; the influence of covariates, such as patient background, medical history, and treatment factors, was excluded by the inverse probability-of-treatment weighted method. Using the search strategy, we extracted 165 drugs with vasodilator activity as candidate drugs. Drugs not approved in Japan, oral medicines, and external medicines were excluded. Then, we investigated whether the candidate drugs were administered to the 2,227 cardiac arrest patients included in this study. The results of the logistic regression analysis showed that three (isosorbide dinitrate, nitroglycerin, and nicardipine) of seven drugs that were administered to ≥10 patients showed significant association with improvement in the proportion of survival discharge. Further analyses using propensity scores revealed that the adjusted odds ratios for survival discharge for patients administered isosorbide dinitrate, nitroglycerin, and nicardipine were 3.35, 5.44, and 4.58, respectively. Thus, it can be suggested that isosorbide dinitrate, nitroglycerin, and nicardipine could be novel therapeutic agents for improving the prognosis of cardiac arrest patients.

DOI： 10.3389/fphar.2019.01257

PubMed

researchmap

Challenges in Building and Maintaining Rare Disease Patient Registries: Results of a Questionnaire Survey in Japan at 2012

Mizuki Morita, Soichi Ogishima

medRxiv 19004770 2019.8

A new approach to prevent critical cardiac accidents in athletes by real-time electrocardiographic tele-monitoring system: Initial trial in full marathon Reviewed International journal

Daiki Ousaka, Noriko Sakano, Mizuki Morita, Takayuki Shuku, Kazuo Sanou, Shingo Kasahara, Susumu Oozawa

Journal of Cardiology Cases 20 ( 1 ) 35 - 38 2019.5

Language：English Publishing type：Research paper (scientific journal)

The majority of marathon deaths are caused by sudden cardiac arrest (SCA), which occur in approximately 1 in 57,000 runners. Such deaths are more common among older males and usually occur in the last 4 miles of the racecourse. Although prompt resuscitation, including early use of an automated external defibrillator (AED), improves survival, the deployment of enough trained medical staff and AEDs is difficult due to increased cost. Moreover, most victims of exercise-related SCA have no premonitory symptoms. Therefore, we tried to use a novel approach to prevent sudden cardiac deaths (SCD) related to SCA using real-time electrocardiographic tele-monitoring system, as an initial trial to assess operative possibility in a full marathon. As a result, 3 out of 5 runners had reasonable measurement results and sufficient tele-monitoring without complications related to this trial was possible. However, many investigations and improvements, such as improving cost-effectiveness, reducing noise, and automating the monitoring system, are needed for practical application of these devices for athletes. As a next step, we would establish a novel strategy to reduce SCDs in athletes using next-generation devices, which include an alarm system associated with early application of AED. <Learning objectives: Sudden cardiac arrest (SCA) is a major problem in sports cardiology. Here we investigated a novel approach using a real-time tele-monitoring system of electrocardiogram (ECG) to prevent sudden cardiac deaths by making use of an advanced alarm system which responds to SCA risk. Three out of five cases we monitored showed reasonable measurement of ECG with centralized observation in full marathon. This is the first report of this method, which may lead to the effective application of automated external defibrillator in athletes.>.

DOI： 10.1016/j.jccase.2019.03.008

PubMed

researchmap

Tweet Classification Toward Twitter-Based Disease Surveillance: New Data, Methods, and Evaluations Reviewed International journal

Shoko Wakamiya, Mizuki Morita, Yoshinobu Kano, Tomoko Ohkuma, Eiji Aramaki

Journal of Medical Internet Research 21 ( 2 ) e12783 2019.2

Language：English Publishing type：Research paper (scientific journal)

BACKGROUND: The amount of medical and clinical-related information on the Web is increasing. Among the different types of information available, social media-based data obtained directly from people are particularly valuable and are attracting significant attention. To encourage medical natural language processing (NLP) research exploiting social media data, the 13th NII Testbeds and Community for Information access Research (NTCIR-13) Medical natural language processing for Web document (MedWeb) provides pseudo-Twitter messages in a cross-language and multi-label corpus, covering 3 languages (Japanese, English, and Chinese) and annotated with 8 symptom labels (such as cold, fever, and flu). Then, participants classify each tweet into 1 of the 2 categories: those containing a patient's symptom and those that do not. OBJECTIVE: This study aimed to present the results of groups participating in a Japanese subtask, English subtask, and Chinese subtask along with discussions, to clarify the issues that need to be resolved in the field of medical NLP. METHODS: In summary, 8 groups (19 systems) participated in the Japanese subtask, 4 groups (12 systems) participated in the English subtask, and 2 groups (6 systems) participated in the Chinese subtask. In total, 2 baseline systems were constructed for each subtask. The performance of the participant and baseline systems was assessed using the exact match accuracy, F-measure based on precision and recall, and Hamming loss. RESULTS: The best system achieved exactly 0.880 match accuracy, 0.920 F-measure, and 0.019 Hamming loss. The averages of match accuracy, F-measure, and Hamming loss for the Japanese subtask were 0.720, 0.820, and 0.051; those for the English subtask were 0.770, 0.850, and 0.037; and those for the Chinese subtask were 0.810, 0.880, and 0.032, respectively. CONCLUSIONS: This paper presented and discussed the performance of systems participating in the NTCIR-13 MedWeb task. As the MedWeb task settings can be formalized as the factualization of text, the achievement of this task could be directly applied to practical clinical applications.

DOI： 10.2196/12783

PubMed

researchmap

　 PREV - NEXT 　

< MORITA Mizuki >

Papers - MORITA Mizuki