Updated on 2025/06/30

Information

 

写真a

 
MATSUMOTO KOTARO
 
Organization
Faculty of Medical Sciences Department of Basic Medicine Assistant Professor
Graduate School of Medical Sciences Department of Health Care Administration and Management(Concurrent)
Title
Assistant Professor
Contact information
メールアドレス
Tel
0926426960

Research Areas

  • Life Science / Medical management and medical sociology

Degree

  • Doctor of Medicine

Research History

  • 済生会熊本病院   

    済生会熊本病院

  • 久留米大学 バイオ統計センター   

Research Interests・Research Keywords

  • Research theme: Research on the development and implementation of clinical prediction models using machine learning

    Keyword: machine learning, model agnostic interpretability method, clinical Prediction Model

    Research period: 2021.8

Awards

  • 2022 BEST PAPER AWARD

    2022.10   Asia Pacific Association for Medical Informatics  

  • 第41回医療情報学連合大会 最優秀学術論文賞

    2021.11   日本医療情報学会  

  • 第36回医療情報学連合大会 優秀口演賞

    2016.11   日本医療情報学会  

  • 第15回日本クリニカルパス学会学術集会 優秀賞

    2014.11   日本クリニカルパス学会  

Papers

  • Performance of multimodal prediction models for intracerebral hemorrhage outcomes using real-world data

    Matsumoto, K; Suzuki, M; Ishihara, K; Tokunaga, K; Matsuda, K; Chen, JH; Yamashiro, S; Soejima, H; Nakashima, N; Kamouchi, M

    INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS   202   105989   2025.10   ISSN:1386-5056 eISSN:1872-8243

     More details

    Language:English   Publisher:International Journal of Medical Informatics  

    Background: We aimed to develop and validate multimodal models integrating computed tomography (CT) images, text and tabular clinical data to predict poor functional outcomes and in-hospital mortality in patients with intracerebral hemorrhage (ICH). These models were designed to assist non-specialists in emergency settings with limited access to stroke specialists. Methods: A retrospective analysis of 527 patients with ICH admitted to a Japanese tertiary hospital between April 2019 and February 2022 was conducted. Deep learning techniques were used to extract features from three-dimensional CT images and unstructured data, which were then combined with tabular data to develop an L1-regularized logistic regression model to predict poor functional outcomes (modified Rankin scale score 3–6) and in-hospital mortality. The model's performance was evaluated by assessing discrimination metrics, calibration plots, and decision curve analysis (DCA) using temporal validation data. Results: The multimodal model utilizing both imaging and text data, such as medical interviews, exhibited the highest performance in predicting poor functional outcomes. In contrast, the model that combined imaging with tabular data, including physiological and laboratory results, demonstrated the best predictive performance for in-hospital mortality. These models exhibited high discriminative performance, with areas under the receiver operating curve (AUROCs) of 0.86 (95% CI: 0.79–0.92) and 0.91 (95% CI: 0.84–0.96) for poor functional outcomes and in-hospital mortality, respectively. Calibration was satisfactory for predicting poor functional outcomes, but requires refinement for mortality prediction. The models performed similar to or better than conventional risk scores, and DCA curves supported their clinical utility. Conclusion: Multimodal prediction models have the potential to aid non-specialists in making informed decisions regarding ICH cases in emergency departments as part of clinical decision support systems. Enhancing real-world data infrastructure and improving model calibration are essential for successful implementation in clinical practice.

    DOI: 10.1016/j.ijmedinf.2025.105989

    Web of Science

    Scopus

    PubMed

  • Comparative analysis of prognostic scores for functional outcome after ischemic stroke

    Irie, F; Matsumoto, K; Matsuo, R; Wakisaka, Y; Ago, T; Kitazono, T; Kamouchi, M

    JOURNAL OF THE NEUROLOGICAL SCIENCES   474   123539   2025.7   ISSN:0022-510X eISSN:1878-5883

     More details

    Language:English   Publisher:Journal of the Neurological Sciences  

    Background: Comparative data on the predictive performance of stroke prognostic scores in a real-world setting are sparse. Objective: We aimed to compare the performance of existing scores for acute stroke outcomes in an observational cohort. Methods: Using data from 12,486 patients with acute ischemic stroke (mean [SD] age, 72.5 [12.6] years; male, 59.4 %) prospectively registered in Fukuoka, Japan, between 2007 and 2017, we evaluated the predictive performance of six stroke prognostic scores, namely ASTRAL, iScore, PLAN, HIAT, SPAN-100, and THRIVE. The discriminative power of the scores was evaluated by the area under the receiver operating characteristic curve (AUROC). Calibration was evaluated using calibration plots. Overall performance, incorporating both discrimination and calibration, was assessed using Brier score. Results: In comparative analyses using un identical study population, AUROCs for predicting 3-month poor functional outcome were 0.87 for ASTRAL, 0.88 for iScore, and 0.89 for PLAN among the scores for all patients, and 0.74 for HIAT, 0.81 for SPAN-100, and 0.78 for THRIVE among the scores for patients receiving reperfusion therapy. The calibration plots showed fair agreement between the outcome predictions and the observed outcomes in all scores, and no substantial difference was found among the scores. The analysis of overall performance indicated that PLAN was better than ASTRAL, whereas no significant difference was found among HIAT, SPAN-100, and THRIVE. Conclusions: The predictive performance of all six scores was good, even in our observational cohort, reflecting the real-world setting. The prognostic scores could provide useful information for the management of acute stroke patients.

    DOI: 10.1016/j.jns.2025.123539

    Web of Science

    Scopus

    PubMed

  • Association between procedure volume and 30-day mortality in stroke patients treated with EVT or IV rt-PA during the introduction period of EVT in Japan

    Matsumoto, K; Maeda, M; Matsuo, R; Fukuda, H; Ago, T; Kitazono, T; Kamouchi, M; Irie, F

    GLOBAL HEALTH & MEDICINE   2025.6   ISSN:2434-9186 eISSN:2434-9194

  • Data-driven prediction of prolonged air leak after video-assisted thoracoscopic surgery for lung cancer: Development and validation of machine-learning-based models using real-world data through the ePath system

    Tou, S; Matsumoto, K; Hashinokuchi, A; Kinoshita, F; Nakaguma, H; Kozuma, Y; Sugeta, R; Nohara, Y; Yamashita, T; Wakata, Y; Takenaka, T; Iwatani, K; Soejima, H; Yoshizumi, T; Nakashima, N; Kamouchi, M

    LEARNING HEALTH SYSTEMS   9 ( 2 )   e10469   2025.4   ISSN:2379-6146

     More details

    Language:English   Publisher:Learning Health Systems  

    Introduction: The reliability of data-driven predictions in real-world scenarios remains uncertain. This study aimed to develop and validate a machine-learning-based model for predicting clinical outcomes using real-world data from an electronic clinical pathway (ePath) system. Methods: All available data were collected from patients with lung cancer who underwent video-assisted thoracoscopic surgery at two independent hospitals utilizing the ePath system. The primary clinical outcome of interest was prolonged air leak (PAL), defined as drainage removal more than 2 days post-surgery. Data-driven prediction models were developed in a cohort of 314 patients from a university hospital applying sparse linear regression models (least absolute shrinkage and selection operator, ridge, and elastic net) and decision tree ensemble models (random forest and extreme gradient boosting). Model performance was then validated in a cohort of 154 patients from a tertiary hospital using the area under the receiver operating characteristic curve (AUROC) and calibration plots. Results: To mitigate bias, variables with missing data related to PAL or those with high rates of missing data were excluded from the dataset. Fivefold cross-validation indicated improved AUROCs when utilizing key variables, even post-imputation of missing data. Dichotomizing continuous variables enhanced performance, particularly when fewer variables were employed in the decision tree ensemble models. Consequently, regression models incorporating seven key variables in complete case analysis demonstrated superior discriminatory ability for both internal (AUROCs: 0.77–0.84) and external cohorts (AUROCs: 0.75–0.84). These models exhibited satisfactory calibration in both cohorts. Conclusions: The data-driven prediction model implementing the ePath system exhibited adequate performance in predicting PAL post-video-assisted thoracoscopic surgery, optimizing variables and considering population characteristics in a real-world setting.

    DOI: 10.1002/lrh2.10469

    Web of Science

    Scopus

    PubMed

  • Machine Learning-Based Prediction for In-Hospital Mortality After Acute Intracerebral Hemorrhage Using Real-World Clinical and Image Data

    Matsumoto, K; Ishihara, K; Matsuda, K; Tokunaga, K; Yamashiro, S; Soejima, H; Nakashima, N; Kamouchi, M

    JOURNAL OF THE AMERICAN HEART ASSOCIATION   13 ( 24 )   e036447   2024.12   eISSN:2047-9980

     More details

    Language:English   Publisher:Journal of the American Heart Association  

    BACKGROUND: Machine learning (ML) techniques are widely employed across various domains to achieve accurate predictions. This study assessed the effectiveness of ML in predicting early mortality risk among patients with acute intracerebral hemorrhage (ICH) in real-world settings. METHODS AND RESULTS: ML-based models were developed to predict in-hospital mortality in 527 patients with ICH using raw brain imaging data from brain computed tomography and clinical data. The models’ performances were evaluated using the area under the receiver operating characteristic curves and calibration plots, comparing them with traditional risk scores such as the ICH score and ICH grading scale. Kaplan–Meier curves were used to examine the post-ICH survival rates, stratified by ML-based risk assessment. The net benefit of ML-based models was evaluated using decision curve analysis. The area under the receiver operating characteristic curves were 0.91 (95% CI, 0.86–0.95) for the ICH score, 0.93 (95% CI, 0.89–0.97) for the ICH grading scale, 0.83 (95% CI, 0.71–0.91) for the ML-based model fitted with raw image data only, and 0.87 (95% CI, 0.76–0.93) for the ML-based model fitted using clinical data without specialist expertise. The area under the receiver operating characteristic curve increased significantly to 0.97 (95% CI, 0.94–0.99) when the ML model was fitted using clinical and image data assessed by specialists. All ML-based models demonstrated good calibration, and the survival rates showed significant differences between risk groups. Decision curve analysis indicated the highest net benefit when utilizing the findings assessed by specialists. CONCLUSIONS: ML-based prediction models exhibit satisfactory performance in predicting post-ICH in-hospital mortality when utilizing raw imaging data or nonspecialist input. Nevertheless, incorporating specialist expertise notably improves performance.

    DOI: 10.1161/JAHA.124.036447

    Web of Science

    Scopus

    PubMed

  • g.ridge: An R Package for Generalized Ridge Regression for Sparse and High-Dimensional Linear Models Reviewed International journal

    @Takeshi Emura, @Koutarou Matsumoto, @Ryuji Uozumi, @Hirofumi Michimae

    Symmetry   2024.2

     More details

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

    DOI: 10.3390/sym16020223

  • Predictive performance of machine learning-based models for post-stroke clinical outcomes in comparison with conventional prognostic scores: a multicenter hospital-based observational study Invited Reviewed International journal

    @Fumi Irie, @Koutarou Matsumoto, @Ryu Matsuo, @Yasunobu Nohara, @Yoshinobu Wakisaka, @Tetsuro Ago, @Naoki Nakashima, @Takanari Kitazono, @Masahiro Kamouchi

    JMIR AI   3   e46840   2024.1   eISSN:2817-1705

     More details

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

    Background: Although machine learning is a promising tool for making prognoses, the performance of machine learning in predicting outcomes after stroke remains to be examined. Objective: This study aims to examine how much data-driven models with machine learning improve predictive performance for poststroke outcomes compared with conventional stroke prognostic scores and to elucidate how explanatory variables in machine learning–based models differ from the items of the stroke prognostic scores. Methods: We used data from 10,513 patients who were registered in a multicenter prospective stroke registry in Japan between 2007 and 2017. The outcomes were poor functional outcome (modified Rankin Scale score >2) and death at 3 months after stroke. Machine learning–based models were developed using all variables with regularization methods, random forests, or boosted trees. We selected 3 stroke prognostic scores, namely, ASTRAL (Acute Stroke Registry and Analysis of Lausanne), PLAN (preadmission comorbidities, level of consciousness, age, neurologic deficit), and iScore (Ischemic Stroke Predictive Risk Score) for comparison. Item-based regression models were developed using the items of these 3 scores. The model performance was assessed in terms of discrimination and calibration. To compare the predictive performance of the data-driven model with that of the item-based model, we performed internal validation after random splits of identical populations into 80% of patients as a training set and 20% of patients as a test set; the models were developed in the training set and were validated in the test set. We evaluated the contribution of each variable to the models and compared the predictors used in the machine learning–based models with the items of the stroke prognostic scores. Results: The mean age of the study patients was 73.0 (SD 12.5) years, and 59.1% (6209/10,513) of them were men. The area under the receiver operating characteristic curves and the area under the precision-recall curves for predicting poststroke outcomes were higher for machine learning–based models than for item-based models in identical populations after random splits. Machine learning–based models also performed better than item-based models in terms of the Brier score. Machine learning–based models used different explanatory variables, such as laboratory data, from the items of the conventional stroke prognostic scores. Including these data in the machine learning–based models as explanatory variables improved performance in predicting outcomes after stroke, especially poststroke death. Conclusions: Machine learning–based models performed better in predicting poststroke outcomes than regression models using the items of conventional stroke prognostic scores, although they required additional variables, such as laboratory data, to attain improved performance. Further studies are warranted to validate the usefulness of machine learning in clinical settings.

    DOI: 10.2196/46840

    Web of Science

    Scopus

    PubMed

  • Development of Machine Learning Prediction Models for Self-Extubation After Delirium Using Emergency Department Data Reviewed

    @Koutarou Matsumoto, @Yasunobu Nohara, @ Mikako Sakaguchi, @Yohei Takayama,@Takanori Yamashita,@Hidehisa Soejima, @Naoki Nakashima

    Studies in Health Technology and Informatics   25 ( 310 )   1001 - 1005   2024.1   ISSN:0926-9630 ISBN:978-1-64368-456-7 eISSN:1879-8365

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Studies in Health Technology and Informatics  

    Delirium is common in the emergency department, and once it develops, there is a risk of self-extubation of drains and tubes, so it is critical to predict delirium before it occurs. Machine learning was used to create two prediction models in this study: one for predicting the occurrence of delirium and one for predicting self-extubation after delirium. Each model showed high discriminative performance, indicating the possibility of selecting high-risk cases. Visualization of predictors using Shapley additive explanation (SHAP), a machine learning interpretability method, showed that the predictors of delirium were different from those of self-extubation after delirium. Data-driven decisions, rather than empirical decisions, on whether or not to use physical restraints or other actions that cause patient suffering will result in improved value in medical care.

    DOI: 10.3233/SHTI231115

    Web of Science

    Scopus

    PubMed

  • Comparing the robustness of resnet, swin-transformer, and mlp-mixer under unique distribution shifts in fundus images Reviewed International journal

    @Kazuaki Ishihara, @Koutarou Matsumoto

    Bioengineering (Basel)   2023.10

     More details

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

    DOI: 10.3390/bioengineering10121383

  • Temporal generalizability of machine learning models for predicting postoperative delirium using electronic health record data: Model development and validation study Reviewed International journal

    @Koutarou Matsumoto, @Yasunobu Nohara, @ Mikako Sakaguchi, @Yohei Takayama, @Syota Fukushige, @Hidehisa Soejima, @Naoki Nakashima, @Masahiro Kamouchi

    JMIR PERIOPERATIVE MEDICINE   6 ( 1 )   e50895   2023.10   ISSN:2561-9128

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Jmir Perioperative Medicine  

    Background: Although machine learning models demonstrate significant potential in predicting postoperative delirium, the advantages of their implementation in real-world settings remain unclear and require a comparison with conventional models in practical applications. Objective: The objective of this study was to validate the temporal generalizability of decision tree ensemble and sparse linear regression models for predicting delirium after surgery compared with that of the traditional logistic regression model. Methods: The health record data of patients hospitalized at an advanced emergency and critical care medical center in Kumamoto, Japan, were collected electronically. We developed a decision tree ensemble model using extreme gradient boosting (XGBoost) and a sparse linear regression model using least absolute shrinkage and selection operator (LASSO) regression. To evaluate the predictive performance of the model, we used the area under the receiver operating characteristic curve (AUROC) and the Matthews correlation coefficient (MCC) to measure discrimination and the slope and intercept of the regression between predicted and observed probabilities to measure calibration. The Brier score was evaluated as an overall performance metric. We included 11,863 consecutive patients who underwent surgery with general anesthesia between December 2017 and February 2022. The patients were divided into a derivation cohort before the COVID-19 pandemic and a validation cohort during the COVID-19 pandemic. Postoperative delirium was diagnosed according to the confusion assessment method. Results: A total of 6497 patients (68.5, SD 14.4 years, women n=2627, 40.4%) were included in the derivation cohort, and 5366 patients (67.8, SD 14.6 years, women n=2105, 39.2%) were included in the validation cohort. Regarding discrimination, the XGBoost model (AUROC 0.87-0.90 and MCC 0.34-0.44) did not significantly outperform the LASSO model (AUROC 0.86-0.89 and MCC 0.34-0.41). The logistic regression model (AUROC 0.84-0.88, MCC 0.33-0.40, slope 1.01-1.19, intercept –0.16 to 0.06, and Brier score 0.06-0.07), with 8 predictors (age, intensive care unit, neurosurgery, emergency admission, anesthesia time, BMI, blood loss during surgery, and use of an ambulance) achieved good predictive performance. Conclusions: The XGBoost model did not significantly outperform the LASSO model in predicting postoperative delirium. Furthermore, a parsimonious logistic model with a few important predictors achieved comparable performance to machine learning models in predicting postoperative delirium.

    DOI: 10.2196/50895

    Web of Science

    Scopus

    PubMed

  • Development of artificial intelligence prognostic model for surgically resected non-small cell lung cancer Reviewed International journal

    @Fumihiko Kinoshita, @Tomoyoshi Takenaka, @Takanori Yamashita, @Koutarou Matsumoto, @Yuka Oku, @Yuki Ono, @Sho Wakasu, @Naoki Haratake, @Tetsuzo Tagawa, @Naoki Nakashima, @Masaki Mori

    Scientific Reports   13 ( 1 )   15683   2023.9   ISSN:2045-2322

     More details

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

    There are great expectations for artificial intelligence (AI) in medicine. We aimed to develop an AI prognostic model for surgically resected non-small cell lung cancer (NSCLC). This study enrolled 1049 patients with pathological stage I–IIIA surgically resected NSCLC at Kyushu University. We set 17 clinicopathological factors and 30 preoperative and 22 postoperative blood test results as explanatory variables. Disease-free survival (DFS), overall survival (OS), and cancer-specific survival (CSS) were set as objective variables. The eXtreme Gradient Boosting (XGBoost) was used as the machine learning algorithm. The median age was 69 (23–89) years, and 605 patients (57.7%) were male. The numbers of patients with pathological stage IA, IB, IIA, IIB, and IIIA were 553 (52.7%), 223 (21.4%), 100 (9.5%), 55 (5.3%), and 118 (11.2%), respectively. The 5-year DFS, OS, and CSS rates were 71.0%, 82.8%, and 88.7%, respectively. Our AI prognostic model showed that the areas under the curve of the receiver operating characteristic curves of DFS, OS, and CSS at 5 years were 0.890, 0.926, and 0.960, respectively. The AI prognostic model using XGBoost showed good prediction accuracy and provided accurate predictive probability of postoperative prognosis of NSCLC.

    DOI: 10.1038/s41598-023-42964-8

    Web of Science

    Scopus

    PubMed

  • Non-linear association between body weight and functional outcome after acute ischemic stroke Reviewed International journal

    @Kayo Wakisaka, @Ryu Matsuo, @Koutarou Matsumoto, @Yasunobu Nohara, @Fumi Irie, @Yoshinobu Wakisaka, @Tetsuro Ago, @Naoki Nakashima, @Masahiro Kamouchi, @Takanari Kitazono

    Scientific Reports   13 ( 1 )   8697   2023.3   ISSN:2045-2322

     More details

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

    This study aimed to determine whether body weight is associated with functional outcome after acute ischemic stroke. We measured the body mass index (BMI) and assessed clinical outcomes in patients with acute ischemic stroke. The BMI was categorized into underweight (< 18.5 kg/m<sup>2</sup>), normal weight (18.5–22.9 kg/m<sup>2</sup>), overweight (23.0–24.9 kg/m<sup>2</sup>), and obesity (≥ 25.0 kg/m<sup>2</sup>). The association between BMI and a poor functional outcome (modified Rankin Scale [mRS] score: 3–6) was evaluated. We included 11,749 patients with acute ischemic stroke (70.3 ± 12.2 years, 36.1% women). The risk of a 3-month poor functional outcome was higher for underweight, lower for overweight, and did not change for obesity in reference to a normal weight even after adjusting for covariates by logistic regression analysis. Restricted cubic splines and SHapley Additive exPlanation values in eXtreme Gradient Boosting model also showed non-linear relationships. Associations between BMI and a poor functional outcome were maintained even after excluding death (mRS score: 3–5) or including mild disability (mRS score: 2–6) as the outcome. The associations were strong in older patients, non-diabetic patients, and patients with mild stroke. Body weight has a non-linear relationship with the risk of a poor functional outcome after acute ischemic stroke.

    DOI: 10.1038/s41598-023-35894-y

    Web of Science

    Scopus

    PubMed

  • Diagnostic model for preschool workers' unwillingness to continue working: Developed using machine-learning techniques Reviewed International journal

    @Moemi Matsuo, @Koutarou Matsumoto, @Misako Higashijima, @Susumu Shirabe, @Goro Tanaka, @Yuri Yoshida, @Toshio Higashi, @Hiroya Miyabara, @Youhei Komatsu, @Ryoichiro Iwanaga

    Medicine (Baltimore)   102 ( 2 )   e32630   2023.1   ISSN:00257974

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Medicine United States  

    The turnover of kindergarten teachers has drastically increased in the past 10 years. Reducing the turnover rates among preschool workers has become an important issue worldwide. Parents have avoided enrolling children in preschools due to insufficient care, which affects their ability to work. Therefore, this study developed a diagnostic model to understand preschool workers' unwillingness to continue working. A total of 1002 full-time preschool workers were divided into 2 groups. Predictors were drawn from general questionnaires, including those for mental health. We compared 3 algorithms: the least absolute shrinkage and selection operator, eXtreme Gradient Boosting, and logistic regression. Additionally, the SHapley Additive exPlanation was used to visualize the relationship between years of work experience and intention to continue working. The logistic regression model was adopted as the diagnostic model, and the predictors were "not living with children," "human relation problems with boss," "high risk of mental distress," and "work experience." The developed risk score and the optimal cutoff value were 14 points. By using the diagnostic model to determine workers' unwillingness to continue working, supervisors can intervene with workers who are experiencing difficulties at work and can help resolve their problems.

    DOI: 10.1097/MD.0000000000032630

    Scopus

    PubMed

  • Delirium Prediction Using Machine Learning Interpretation Method and Its Incorporation into a Clinical Workflow Invited Reviewed International journal

    @Koutarou Matsumoto, @Yasunobu Nohara, @Mikako Sakaguchi, @Yohei Takayama, @Shota Fukushige, @Hidehisa Soejima, @Naoki Nakashima

    Applied Sciences (Switzerland)   13 ( 3 )   2023.1   eISSN:2076-3417

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Applied Sciences Switzerland  

    Delirium in hospitalized patients is a worldwide problem, causing a burden on healthcare professionals and impacting patient prognosis. A machine learning interpretation method (ML interpretation method) presents the results of machine learning predictions and promotes guided decisions. This study focuses on visualizing the predictors of delirium using a ML interpretation method and implementing the analysis results in clinical practice. Retrospective data of 55,389 patients hospitalized in a single acute care center in Japan between December 2017 and February 2022 were collected. Patients were categorized into three analysis populations, according to inclusion and exclusion criteria, to develop delirium prediction models. The predictors were then visualized using Shapley additive explanation (SHAP) and fed back to clinical practice. The machine learning-based prediction of delirium in each population exhibited excellent predictive performance. SHAP was used to visualize the body mass index and albumin levels as critical contributors to delirium prediction. In addition, the cutoff value for age, which was previously unknown, was visualized, and the risk threshold for age was raised. By using the SHAP method, we demonstrated that data-driven decision support is possible using electronic medical record data.

    DOI: 10.3390/app13031564

    Web of Science

    Scopus

  • Explanation of machine learning models using shapley additive explanation and application for real data in hospital Invited Reviewed International journal

    @Yasunobu Nohara, @Koutarou Matsumoto, @Hidehisa Soejima, @Naoki Nakashima

    Computer Methods and Programs in Biomedicine   214   106584   2021.12   ISSN:0169-2607 eISSN:1872-7565

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Computer Methods and Programs in Biomedicine  

    Background and Objective: When using machine learning techniques in decision-making processes, the interpretability of the models is important. In the present paper, we adopted the Shapley additive explanation (SHAP), which is based on fair profit allocation among many stakeholders depending on their contribution, for interpreting a gradient-boosting decision tree model using hospital data. Methods: For better interpretability, we propose two novel techniques as follows: (1) a new metric of feature importance using SHAP and (2) a technique termed feature packing, which packs multiple similar features into one grouped feature to allow an easier understanding of the model without reconstruction of the model. We then compared the explanation results between the SHAP framework and existing methods using cerebral infarction data from our hospital. Results: The interpretation by SHAP was mostly consistent with that by the existing methods. We showed how the A/G ratio works as an important prognostic factor for cerebral infarction using proposed techniques. Conclusion: Our techniques are useful for interpreting machine learning models and can uncover the underlying relationships between features and outcome.

    DOI: 10.1016/j.cmpb.2021.106584

    Web of Science

    Scopus

    PubMed

  • Impact of a learning health system on acute care and medical complications after intracerebral hemorrhage Reviewed International journal

    @Koutarou Matsumoto, @ Yasunobu Nohara, @Yoshifumi Wakata, @Takanori Yamashita, @Yukio Kozuma, @Rui Sugeta, @Miki Yamakawa, @Fumiko Yamauchi, @ Eri Miyashita, @Tatsuya Takezaki, @Shigeo Yamashiro, @Toru Nishi, @Jiro Machida, @Hidehisa Soejima, @Masahiro Kamouchi, @Naoki Nakashima

    Learning Health Systems   2021.4

     More details

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

    DOI: 10.1002/lrh2.10223

  • A functional learning health system in japan: Experience with processes and information infrastructure toward continuous health improvement Reviewed International journal

    @Soejima Hidehisa, @Matsumoto Koutarou, @Nakashima Naoki, @Nohara Yasunobu, @Yamashita Takanori, @Machida Jiro

    Learning Health Systems   2020.11

     More details

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

    DOI: 10.1002/lrh2.10252

  • Stroke prognostic scores and data-driven prediction of clinical outcomes after acute ischemic stroke Reviewed International journal

    @Koutarou Matsumoto, @Yasunobu, Nohara, @Toshiro Yonehara, @Naoki Nakashima, @Masahiro Kamouchi

    stroke   2020.5

     More details

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

    DOI: 10.1161/STROKEAHA.119.027300

▼display all

Books

  • 医療者とAIの相互連携システムの構築

    @松本晃太郎, 野原 康伸, 副島 秀久(Role:Joint author)

    Medical Science Digest  2022.8 

     More details

    Language:Japanese   Book type:Scholarly book

Presentations

  • クリティカルインディケーターの客観的評価

    @松本 晃太郎, @加島 史, @米原 敏郎, @町田 二郎, @森崎 真美, @中熊 英貴

    第15回日本クリニカルパス学会学術集会  2014.11 

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  • 脳梗塞軽症パスと重症パスの予後予測因子の比較

    @松本 晃太郎, @中島 直樹, @若田 好史, @野原 康伸, @山下 貴範, @副島 秀久, @町田 二郎, @甲斐 聖人, @小妻 幸男, @中熊 英貴

    第16回日本クリニカルパス学会学術大会  2015.11 

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  • 脳梗塞重症パスにおける肺炎発症の予測因子の抽出

    @松本 晃太郎, @中島 直樹, @若田 好史, @野原 康伸, @山下 貴範, @副島 秀久, @町田 二郎, @米原 敏郎, @甲斐 聖人, @小妻 幸男

    第16回日本クリニカルパス学会学術大会  2015.11 

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  • 機械学習を用いた探索的なクリニカルパス分析

    @松本 晃太郎, @野原 康伸, @若田 好史, @山下 貴範, @牟田 大輔, @西 徹, @中熊 英貴, @小妻 幸男, @甲斐 聖人, @町田 二郎, @副島 秀久, @中島 直樹

    第36回医療情報学連合大会  2016.11 

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  • Exploratory data analysis of clinical pathway for brain hemorrhage using machine learning technique International conference

    @Koutarou Matsumoto, @Yasunobu Nohara, @Yoshifumi Wakata, @Takanori Yamashita, @Naoki Nakashima

    China-Japan-Korea Joint Symposium on Medical Informatics(CJKMI)  2016.11 

     More details

    Language:English  

    Country:Japan  

  • クリニカルパスを用いたLearning Health System構築

    @松本 晃太郎, @野原 康伸, @若田 好史, @山下 貴範, @鴨打 正浩, @中島 直樹

    第21回日本医療情報学会春季学術大会  2017.6 

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  • 機械学習による脳梗塞患者の予後予測と因果効果推定への応用

    @野原 康伸, @松本 晃太郎, @鴨打 正浩,@ 飯原 弘二, @中島 直樹

    第21回日本医療情報学会春季学術大会  2017.6 

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  • Extracting Predictive Indicator for Prognosis of Cerebral Infarction Using Machine Learning Techniques International conference

    @Yasunobu Nohara, @Koutarou Matsumoto, @Naoki Nakashima

    Medical and Health Informatics (MedInfo)  2017.8 

     More details

    Language:English   Presentation type:Oral presentation (general)  

    Country:China  

  • クリニカルパスを用いたLearning Health System構築

    @松本 晃太郎, @野原 康伸, @若田 好史, @山下 貴範, @鴨打 正浩, @中島 直樹

    第22回日本医療情報学会春季学術大会  2018.6 

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  • Shapley Additive Explanationを用いた機械学習モデルの解釈と医療実データへの応用

    @野原 康伸, @松本 晃太郎, @副島 秀久, @中島 直樹

    第23回日本医療情報学会春季学術大会  2019.6 

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  • クリニカルパスを用いたLearning Health Systemの効果

    @松本 晃太郎, @野原 康伸, @若田 好史, @山下 貴範, @鴨打 正浩, @中島 直樹

    第23回日本医療情報学会春季学術大会  2019.6 

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  • Explanation of Machine Learning Models Using Improved Shapley Additive Explanation International conference

    @Yasunobu Nohara, @Koutarou Matsumoto, @Hidehisa Soejima, @Naoki Nakashima

    Bioinformatics, Computational Biology and Health Informatics(BCB)  2019.9 

     More details

    Language:English   Presentation type:Oral presentation (general)  

    Country:United States  

  • 腹腔鏡下胆嚢摘出術における手術時間予測モデルの作成

    @松本 晃太郎, @田﨑年晃, @新田英利, @増田稔郎, @生田義明, @髙森 啓二

    第55回日本胆道学会学術集会  2019.10 

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  • Developing a Learning Health System for Delirium Using XAI International conference

    @Koutarou Matsumoto, @Yasunobu Nohara, @Mikako Sakaguchi, @Yohei Takayama, @Hidehisa Soejima, @Naoki Nakashima

    Asia Pacific Association for Medical Informatics(APAMI)  2022.10 

     More details

    Language:English   Presentation type:Oral presentation (general)  

    Country:Taiwan, Province of China  

  • Development of Machine Learning Prediction Models for Self-Extubation After Delirium Using Emergency Department Data International conference

    @Koutarou Matsumoto, @Yasunobu Nohara, @Mikako Sakaguchi, @Yohei Takayama, @Takanori Yamashita, @Hidehisa Soejima, @Naoki Nakashima

    Medical and Health Informatics (MedInfo)  2023.7 

     More details

    Language:English   Presentation type:Oral presentation (general)  

    Country:Australia  

  • 医師の働き方改革を目的としたLearning Health System 構築- ePath データの活用事例 -

    @松本 晃太郎, @若田 好史, @野原 康伸, @中熊 英貴, @小妻 幸男, 管田 塁, @山下 貴範, @的場 哲哉, @坂本 和生, @橋之口 朝仁, @木下 郁彦, @竹中 朋祐, @荒木 千恵子, @劔 卓夫, @堀尾 英治, @岩谷 和法, @羽藤 慎二, @重松 久之, @山下 素弘, @村岡 修子, @杉田 匡聡, @副島 秀久, @中島 直樹

    第43回医療情報学連合大会  2023.11 

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  • 腹腔鏡下膵頭十二指腸切除術の保険償還価格及び費用的側面から見た現状 Invited

    @松本 晃太郎, @岩下 明日香, @小妻 幸男, @田﨑 年晃, @富安 真二朗, @副島 秀久, @里井 壯平, @本田 五郎

    第36回日本内視鏡外科学会総会  2023.12 

     More details

    Language:Japanese   Presentation type:Symposium, workshop panel (public)  

    Country:Japan  

  • 人工知能CT histogram解析 間質性肺炎患者の放射線学的UIPとNSIPパターンの鑑別と予後との相関(Artificial-Intelligence-Based CT Histogram Analysis: Differentiation of Radiologic UIP and NSIP Patterns and Correlation with Prognosis in Patients with Interstitial Pneumonia)

    Chikasue Tomonori, Sumi Akiko, Sumikawa Hiromitsu, Matsumoto Kotaro, Murotani Kenta, Zaizen Yoshiaki, Tominaga Masaki, Okamoto Masaki, Tanoue Shuichi, Fujimoto Kiminori

    日本医学放射線学会学術集会抄録集  2024.3  (公社)日本医学放射線学会

     More details

    Language:English  

  • 人工知能(AI)を用いた肺癌術後合併症予測ツールの開発

    木下 郁彦, 松本 晃太郎, 山下 貴範, 朝日 達也, 溝田 和弘, 徳永 貴之, バッシィ・ジャコモ , 橋之口 朝仁, 松堂 響人, 赤嶺 貴紀, 河野 幹寛, 大薗 慶吾, 中島 直樹, 竹中 朋祐, 吉住 朋晴

    日本外科学会定期学術集会抄録集  2025.4  (一社)日本外科学会

     More details

    Language:Japanese  

  • レセプトデータを用いた気象要因と建造環境が熱中症による受診に与える影響の評価

    西 巧, 前田 俊樹, 今任 拓也, 松本 晃太郎

    日本衛生学雑誌  2024.3  (一社)日本衛生学会

     More details

    Language:Japanese  

  • ePathを活用した業務削減および治験、外来の基盤について

    中熊 英貴, 管田 塁, 小妻 幸男, 藤 沙織, 松本 晃太郎, 山下 貴範, 若田 好史, 的場 哲哉, 松木 絵里, 船越 公太, 戸高 浩司, 佐藤 直市, 仁科 智裕, 羽藤 慎二, 中島 直樹, 岡田 美保子, 副島 秀久

    医療情報学連合大会論文集  2024.11  (一社)日本医療情報学会

     More details

    Language:Japanese  

  • ePathを活用したアウトカム予測モデルの開発 胸腔鏡視下肺切除術(VATS)パス症例を対象として

    藤 沙織, 松本 晃太郎, 山下 貴範, 若田 好史, 中熊 英貴, 橋之口 朝仁, 木下 郁彦, 竹中 朋祐, 岩谷 和法, 副島 秀久, 中島 直樹, 鴨打 正浩

    医療情報学連合大会論文集  2024.11  (一社)日本医療情報学会

     More details

    Language:Japanese  

  • ePathの概要とその活用、効果について

    中熊 英貴, 管田 塁, 小妻 幸男, 藤 沙織, 松本 晃太郎, 山下 貴範, 若田 好史, 的場 哲哉, 松木 絵里, 船越 公太, 戸高 浩司, 佐藤 直市, 仁科 智裕, 羽藤 慎二, 中島 直樹, 岡田 美保子, 副島 秀久

    医療情報学連合大会論文集  2024.11  (一社)日本医療情報学会

     More details

    Language:Japanese  

  • AIを用いた非小細胞肺癌術後予後予測モデルの開発

    木下 郁彦, 山下 貴範, 松本 晃太郎, 中西 芳之, 斎藤 駿一, 橋之口 朝仁, 松堂 響人, 長野 太智, 赤嶺 貴紀, 河野 幹寛, 大薗 慶吾, 山口 正史, 竹中 朋祐

    日本呼吸器外科学会雑誌  2024.4  (一社)日本呼吸器外科学会

     More details

    Language:Japanese  

  • AIを用いた早期肺癌の予後予測モデル

    木下 郁彦, 山下 貴範, 松本 晃太郎, 奥 結華, 藤下 卓才, 伊藤 謙作, 庄司 文裕, 岡本 龍郎

    日本呼吸器外科学会雑誌  2023.6  (一社)日本呼吸器外科学会

     More details

    Language:Japanese  

  • Learning Health Systemの事例 ePathデータ解析から派生したリスクスコア開発

    松本 晃太郎, 藤 沙織, 徳永 晃己, 高宗 伸次, 管田 塁, 中熊 英貴, 小妻 幸男, 野原 康伸, 山下 貴範, 若田 好史, 岩谷 和法, 副島 秀久, 中島 直樹, 鴨打 正浩

    医療情報学連合大会論文集  2024.11  (一社)日本医療情報学会

     More details

    Language:Japanese  

  • 高難度の肝胆膵内視鏡外科手術は本当に患者のためになっているか 腹腔鏡下膵頭十二指腸切除術(ロボット支援手術を含む)の保険償還価格及び費用的側面から見た現状

    松本 晃太郎, 岩下 明日香, 小妻 幸男, 田崎 年晃, 富安 真二朗, 副島 秀久

    日本内視鏡外科学会雑誌  2023.12  (一社)日本内視鏡外科学会

     More details

    Language:Japanese  

  • 虚血性心疾患・脳血管疾患入院患者の特定健診受診・外来受療行動と医療費の関連

    西 巧, 前田 俊樹, 松本 晃太郎

    日本医療・病院管理学会誌  2023.11  (一社)日本医療・病院管理学会

     More details

    Language:Japanese  

  • 糖尿病未治療者における定期受診開始に与える要因と予測精度の検証

    西 巧, 前田 俊樹, 松本 晃太郎

    日本医療・病院管理学会誌  2022.9  (一社)日本医療・病院管理学会

     More details

    Language:Japanese  

  • 画像診断・気管支鏡における新技術 LASSOによる機械学習を用いた肺癌術後予後予測モデルの相互検証

    木下 郁彦, 松本 晃太郎, 山下 貴範, 赤嶺 貴紀, 河野 幹寛, 大薗 慶吾, 山口 正史, 竹中 朋祐

    肺癌  2024.10  (NPO)日本肺癌学会

     More details

    Language:Japanese  

  • 機械学習を用いた早期肺癌術後予後予測モデルの構築と検証

    木下 郁彦, 山下 貴範, 松本 晃太郎, 中西 芳之, 斎藤 駿一, 橋之口 朝仁, 松堂 響人, 長野 太智, 赤嶺 貴紀, 河野 幹寛, 大薗 慶吾, 山口 正史, 竹中 朋祐

    肺癌  2023.10  (NPO)日本肺癌学会

     More details

    Language:Japanese  

  • 機械学習を用いた早期肺癌の術後予後予測モデル構築

    木下 郁彦, 山下 貴範, 松本 晃太郎, 奥 結華, 高森 信吉, 藤下 卓才, 河野 幹寛, 伊藤 謙作, 三浦 奈央子, 竹中 朋祐, 庄司 文裕, 岡本 龍郎, 中島 直樹, 吉住 朋晴

    日本外科学会定期学術集会抄録集  2023.4  (一社)日本外科学会

     More details

    Language:Japanese  

  • 標準化クリニカルパス「ePath」を基盤とした予測モデルの開発

    藤 沙織, 松本 晃太郎, 橋之口 朝仁, 山下 貴範, 若田 好史, 中熊 英貴, 岩谷 和法, 副島 秀久, 中島 直樹, 鴨打 正浩

    日本クリニカルパス学会誌  2024.9  (一社)日本クリニカルパス学会

     More details

    Language:Japanese  

  • 標準化クリニカルパス「ePath」を基盤としたアウトカム予測とクリティカルインディケータ探索手法

    藤 沙織, 松本 晃太郎, 山下 貴範, 若田 好史, 野原 康伸, 橋之口 朝仁, 木下 郁彦, 竹中 朋祐, 鴨打 正浩, 中島 直樹

    医療情報学連合大会論文集  2023.11  (一社)日本医療情報学会

     More details

    Language:Japanese  

  • 大規模言語モデルを活用したローカル環境における医療文章作成支援システムの開発

    宮川 悠月, 松本 晃太郎, 野原 康伸

    医療情報学連合大会論文集  2024.11  (一社)日本医療情報学会

     More details

    Language:Japanese  

  • 多施設、多ベンダーのデータ統合におけるデータマネジャーの役割 ePathプロジェクトでの経験から

    中熊 英貴, 古山 千春, 管田 塁, 松本 晃太郎, 小妻 幸男, 山下 貴範, 若田 好史, 岡田 美保子, 中島 直樹, 副島 秀久

    日本医療・病院管理学会誌  2022.9  (一社)日本医療・病院管理学会

     More details

    Language:Japanese  

  • 呼吸器外科における新規テクノロジー AIを用いた肺癌術後予後予測モデル 汎用性の高い予後予測モデル構築を目指して

    木下 郁彦, 山下 貴範, 松本 晃太郎, 中西 芳之, 斎藤 駿一, 橋之口 朝仁, 松堂 響人, 長野 太智, 赤嶺 貴紀, 河野 幹寛, 大薗 慶吾, 山口 正史, 竹中 朋祐, 吉住 朋晴

    日本外科学会定期学術集会抄録集  2024.4  (一社)日本外科学会

     More details

    Language:Japanese  

  • 医師の働き方改革を目的としたLearning Health System構築 ePathデータの活用事例

    松本 晃太郎, 若田 好史, 野原 康伸, 中熊 英貴, 小妻 幸男, 管田 塁, 山下 貴範, 的場 哲哉, 坂本 和生, 橋之口 朝仁, 木下 郁彦, 竹中 朋祐, 荒木 千恵子, 劔 卓夫, 堀尾 英治, 岩谷 和法, 羽藤 慎二, 重松 久之, 山下 素弘, 村岡 修子, 杉田 匡聡, 副島 秀久, 中島 直樹

    医療情報学連合大会論文集  2023.11  (一社)日本医療情報学会

     More details

    Language:Japanese  

▼display all

MISC

  • 最先端医療の今 医療者とAIの相互連携システムの構築

    松本 晃太郎, 副島 秀久, 野原 康伸

    Medical Science Digest   48 ( 8 )   378 - 379   2022.8   ISSN:1347-4340

     More details

    Language:Japanese   Publisher:(株)ニュー・サイエンス社  

    医療分野では機械学習を駆使した診断支援システムが急速に開発されつつあるが、未だに診療意思決定支援ツールとして実装・普及するまでには至っていない。医療診断という行為の説明責任の重大性に加えて、これまでの機械学習予測モデルでは予測性能が高い一方で、どのような変数がどのように予測に寄与しているのか解釈が困難であるというブラックボックス性が実装の障壁となっている。本研究では、機械学習予測モデルに対してモデル非依存的な解釈手法であるSHapley Additive exPlanationsを併用し、医療従事者が解釈可能な予測モデルを開発することを目的としている。さらに、多くの病院で電子カルテに実装されつつある電子クリニカルパス(標準療養計画書)に着目し、上記の機械学習予測モデルを電子クリニカルパスに実装することで、医療従事者との相互連携性を生み出す仕組みの構築を目指す。(著者抄録)

Professional Memberships

  • 日本医療情報学会

  • 人工知能学会

Committee Memberships

  • Japanese Journal of Statistics and Data Science   associate editor   Foreign country

    2023.4 - 2025.3   

  • 日本計量生物学会   学会誌編集委員   Domestic

    2023.4 - 2025.3   

Academic Activities

  • Screening of academic papers

    Role(s): Peer review

    2024

     More details

    Type:Peer review 

    Number of peer-reviewed articles in foreign language journals:15

    Number of peer-reviewed articles in Japanese journals:1

  • Japanese Journal of Statistics and Data Science International contribution

    2023.4 - 2025.3

     More details

    Type:Academic society, research group, etc. 

  • 計量生物学

    2023.4 - 2025.3

     More details

    Type:Academic society, research group, etc. 

Research Projects

  • 脳卒中後QOLと効用値に基づく費用対効果分析の基盤構築

    Grant number:25H01083  2025.4 - 2029.3

    Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (A)

    鴨打 正浩, 秦 淳, 吾郷 哲朗, 入江 芙美, 松尾 龍, 松本 晃太郎

      More details

    Grant type:Scientific research funding

    脳卒中患者を対象に、費用対効果分析で推奨されているEQ-5Dを用いて、患者がとらえるQOLとそれに対する医療の効果を評価する。地域脳卒中疾患コホート研究、National Database等のレセプトデータを用いて我が国における脳卒中患者のQOL効用値、質調整生存年(quality-adjusted life year: QALY)とそれらに脳卒中医療が及ぼす効果を、予測モデルを用いて推定する。各診療行為がQOLに及ぼす効果を、傾向スコアや機械学習モデルによる因果推論、意思決定曲線分析等を用いて推定し、医師・患者の選好を考慮した比較を行う。

  • 成人T細胞性白血病の病態解明のための腸内細菌の解析

    Grant number:25K13597  2025.4 - 2029.3

    Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C)

    前田 俊樹, 尾鶴 亮, 有馬 久富, 石田 晋太郎, 石津 昌直, 西 巧, 松本 晃太郎

      More details

    Grant type:Scientific research funding

    本研究では福岡県在住一般住民の前向きコホート研究にて得られた約1000 名をhealthy controlとしHTLV-1キャリア、成人T細胞性白血病患者から採取した便検体を次世代シークエンス解析にて解析し、ケース・コホート研究の疫学的手法を用いて比較検討する。そして腸内細菌叢の違いがHTLV-1ウイルスへの感染や成人T細胞性白血病の発症に及ぼす影響を明らかにすることで、将来的にHTLV-1ウイルス感染の予防もしくは成人T細胞性白血病の発症予防に寄与することを目的とする

  • 医療と介護レセプト連結データを用いた脳卒中の疾病負荷に関する研究

    Grant number:24K02669  2024.4 - 2028.3

    Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)

    松尾 龍, 入江 芙美, 松本 晃太郎

      More details

    Grant type:Scientific research funding

    脳卒中はひとたび発症すると、その後遺症により容易に要介護状態となり、健康寿命が損なわれる。そのため、医療と介護が緊密に連携し、医療と介護の効率的かつ効果的な提供が求められる。しかしながら脳卒中患者の経時的な長期予後は明らかではなく、最適な医療と介護提供のためのエビデンスもみられない。我が国には匿名レセプト情報等および介護保険による匿名介護情報等が存在し、これらのデータを連結することで医療と介護の可視化が可能である。本研究では、医療と介護の連結データベースを用いて、脳卒中患者における医療と介護の実態を可視化し、長期予後を含む疾病負荷を明らかにすることをめざす。

    CiNii Research

  • Verification and improvement of Large Language Models utilizing structured medical data, and development of a method for explaining model outputs

    Grant number:24K15166  2024.4 - 2028.3

    Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C)

    野原 康伸, 松本 晃太郎

      More details

    Grant type:Scientific research funding

    大規模言語モデル(LLM)は、読解や文章生成などの自然言語処理で優れた能力を有しており、医療分野でも活躍が期待されるが、信頼性等の面で課題を抱えている。LLMの学習や検証には、大量の正解ラベルデータが必要であるが、医療データでは専門家の人手が必要であり、その収集には特段の労力を要する。本研究では、電子クリニカルパスという我々が保有する質の高い構造化医療データ基盤を活用することで、効率よく大量の正解ラベルを収集し、LLMの検証と改良を継続的に行うとともに、そのオープンデータ化を目指す。

    CiNii Research

  • 集積嚥下波形データの活用による誤嚥検出のための自動解析システムの開発と臨床応用

    Grant number:24K15875  2024.4 - 2027.3

    Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C)

    東嶋 美佐子, 松本 晃太郎, 植田 友貴

      More details

    Grant type:Scientific research funding

    食物の取り込みから飲み込みまでの摂食嚥下運動を波形と画像で可視化し、誤嚥を非侵襲的に捉える摂食嚥下機能評価システムを構築して、10年間そのデータを集積してきた。今までの研究成果を踏まえて二つの課題解決を目的としている。一つ目は個々人で異なる食形態の食べ始めから食べ終わりまでの、摂食嚥下運動を自動抽出する課題、二つ目は摂食嚥下運動障害の起因対応を行うことで嚥下問題の回避効果について検証する課題である。これらの課題解決によって、パンデミック後は主流になりつつある遠隔支援にも貢献できると思われる。

    CiNii Research

  • 緩和的放射線治療の有効性を予測する機械学習モデルの開発

    Grant number:24K10764  2024.4 - 2027.3

    Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C)

    斉藤 哲雄, 松本 晃太郎, 大屋 夏生

      More details

    Grant type:Scientific research funding

    緩和的放射線治療は局所的な疼痛奏効(疼痛の緩和)を目的とするが、全身的な疼痛コントロールも患者のQOL向上に重要である。他の疼痛の優勢(照射対象腫瘍の疼痛を上回る強さの疼痛が他に存在)は、全身的な疼痛の進行を評価するアウトカムである。さらに、最終的に疼痛による生活の支障の改善の有無が問題となる。本課題では、これらのアウトカムの予測モデルを開発することで、各患者に適した緩和ケア戦略の開発の一端としたい。

    CiNii Research

  • 医療と介護レセプト連結データを用いた脳卒中の疾病負荷に関する研究

    2024.4

      More details

    Authorship:Coinvestigator(s) 

  • 構造化医療データを活用した大規模言語モデルの検証改良とモデル出力根拠説明法の開発

    2024.4

      More details

    Authorship:Coinvestigator(s) 

  • 緩和的放射線治療の有効性を予測する機械学習モデルの開発

    2024.4

      More details

    Authorship:Coinvestigator(s) 

  • 集積嚥下波形データの活用による誤嚥検出のための自動解析システムの開発と臨床応用

    2024.4

      More details

    Authorship:Coinvestigator(s) 

  • Establishment of Personalized Nutritional Therapy for Prevention of Geriatric Syndrome through Community Cohort and Deep Learning

    Grant number:23K28017  2023.4 - 2028.3

    Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)

    矢部 大介, 堀川 幸男, 室谷 健太, 飯塚 勝美, 松本 晃太郎, 矢部 富雄, 高橋 佳大

      More details

    Grant type:Scientific research funding

    本研究では、食習慣ならびに運動習慣、ゲノムや腸内細菌叢等の情報、糖尿病や肥満症などの基礎疾患の有無とこれら疾患の病態を評価するバイオマーカーの統合情報が、サルコペニアや認知症、フレイルの発症・進展に与える影響を、岐阜県に在住の75歳以上の高齢者を対象としたコホートからデータ収集、深層学習を行うことで明確化し、食習慣、ゲノム情報、腸内細菌叢、基礎疾患の有無によりサルコペニア、認知症、フレイルの発症・進展を予測するリスク・エンジンを作出し、個別化栄養療法支援アプリを開発する。

    CiNii Research

  • 地域コホートと深層学習による老年症候群予防に資する個別化栄養療法の確立

    2023.4

      More details

    Authorship:Coinvestigator(s) 

  • 気象・周辺環境情報を統合した保健医療情報基盤構築と個人・環境要因の複合的影響評価

    Grant number:23K24586  2022.4 - 2026.3

    Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)

    西 巧, 前田 俊樹, 今任 拓也, 松本 晃太郎

      More details

    Grant type:Scientific research funding

    超高齢化社会の到来による社会保障制度の持続可能性に対する脅威のみならず、気候変動による暑熱・異常気象等の問題によって、経済・社会活動の持続可能性が大きな脅威に晒されている。これらの両者に対応するためには、保健医療情報と気象情報等の収集と分析が必要不可欠である。しかしながら、小地域レベルでこれらの情報を統合した利活用可能な情報基盤は存在しない。
    そこで、本研究は保健医療介護縦断データベースとGISの連携により、気象要因と居住地周辺の建造環境を統合した保健医療介護情報基盤を構築し、統計的機械学習の手法を用いることで、個人要因と環境要因が疾患の発症・予後に与える複合的な影響を明らかにする。

    CiNii Research

  • 医療者とAIの相互連携システム構築を目的とした解釈可能な機械学習予測モデルの開発

    2022.4 - 2025.3

    九州大学・医学研究院 

      More details

    Authorship:Principal investigator 

    解釈可能な機械学習予測モデルの開発と運用を目指す.

  • 気象・周辺環境情報を統合した保健医療情報基盤構築と個人・環境要因の複合的影響評価

    2022.4

      More details

    Authorship:Coinvestigator(s) 

  • 医療者とAIの相互連携システム構築を目的とした解釈可能な機械学習予測モデルの開発

    2022 - 2024

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Early-Career Scientists

      More details

    Grant type:Scientific research funding

  • Data-driven high-performance medicine for stroke

    Grant number:23K21506  2021.4 - 2025.3

    Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)

    鴨打 正浩, 福田 治久, 松尾 龍, 北園 孝成, 松本 晃太郎

      More details

    Grant type:Scientific research funding

    大規模脳卒中患者登録データに対して、正則化線形回帰や決定木アンサンブル学習などの機械学習手法を用いて、網羅的な変数による機能予後、生命予後の予測モデルを開発する。交差検証、時間的検証、外部検証により、予測モデルの妥当性を検証する。リスク調整を行った上で、標準偏回帰係数や変数重要度から短期及び長期機能予後、生命予後、ADL×生存年等のアウトカムの予測確率に対して大きな影響を及ぼす診療行為を抽出する。シミュレーションを行い、各診療行為の変数の実測値と仮想値における推定予後確率の変化を検討する。診療点数あたりの効果に変換し費用対効果を推定する。

    CiNii Research

  • 脳卒中疾病負荷軽減のためのデータ駆動型最適化医療の構築

      More details

    Authorship:Coinvestigator(s) 

▼display all

Educational Activities

  • 主に社会人大学院生を対象に医学統計学及びデータサイエンス全般の指導を行っている.

Class subject

  • データサイエンス概論

    2024.10 - 2025.3   Second semester

  • 医学統計学

    2024.4 - 2024.9   First semester

Visiting, concurrent, or part-time lecturers at other universities, institutions, etc.

  • 2024  久留米大学 バイオ統計センター  Classification:Part-time lecturer  Domestic/International Classification:Japan 

  • 2024  済生会熊本病院 医療情報調査研究所  Classification:Part-time lecturer  Domestic/International Classification:Japan