Details of the Researcher

PHOTO

Shinya Sonobe
Section
Tohoku University Hospital
Job title
Assistant Professor
Degree
Profile
茨城県水戸市出身。
東京学芸大学教育学部附属高等学校卒業。
東北大学医学部医学科卒業。

Research History 17

  • 2022/04 - Present
    Tohoku University Graduate School of Medicine　Department of Neurosurgical Engineering and Translational Neuroscience　Assistant Professor

  • 2019/10 - 2022/03
    東北大学病院　脳神経外科　助教

  • 2017/04 - 2019/09
    大崎市民病院　脳神経外科　副科長

  • 2016/04 - 2017/03
    気仙沼市立病院　脳神経外科　医長

  • 2015/04 - 2016/03
    National Hospital Organization

  • 2014/10 - 2015/03
    財団法人広南会 広南病院　脳神経外科　医員

  • 2014/04 - 2014/09
    National Hospital Organization

  • 2013/11 - 2014/03
    財団法人広南会 広南病院　脳神経外科　医員

  • 2013/04 - 2013/10
    いわき市立総合磐城共立病院　脳神経外科　医長

  • 2011/10 - 2013/03
    東北大学病院　脳神経外科　医員

  • 2011/04 - 2011/09
    米沢市立病院　脳神経外科　医員

  • 2010/11 - 2011/03
    さいたま赤十字病院　脳神経外科　医員

  • 2010/04 - 2010/10
    青森県立中央病院　脳神経外科　医員

  • 2009/12 - 2010/03
    財団法人広南会 広南病院　脳神経外科　医員

  • 2009/08 - 2009/11
    東北大学病院　脳神経外科　医員

  • 2009/04 - 2009/07
    National Hospital Organization

  • 2007/04 - 2009/03
    東北大学病院　初期臨床研修

Show all Show first 5

Professional Memberships 9

  • ヘルスデータサイエンス学会

  • 医療の質・安全学会

  • 日本医療情報学会

  • メディカルAI学会

  • 日本脳神経外科コングレス

  • THE JAPANESE SOCIETY ON SURGERY FOR CEREBRAL STROKE

  • THE JAPAN STROKE SOCIETY

  • The Japanese Society for Neuroendovascular Therapy

  • THE JAPAN NEUROSURGICAL SOCIETY

︎Show all ︎Show first 5

Research Interests 6

  • 産学連携

  • 脳神経外科

  • 働き方改革

  • 人工知能

  • 脳血管内治療

  • 脳卒中

Research Areas 2

  • Informatics / Biological, health, and medical informatics /

  • Life sciences / Neurosurgery /

Awards 1

  1. Best Practices Award - Grand Prize

    2020/11　The 15th Annual Congress Of Japanese Society for Quality and Safety in Healthcare

Papers 40

  1. Development and validation of a machine learning model for predicting positive blood cultures using vital signs in ICU patients. International-journal

    Issei Seike, Hiroaki Baba, Shinya Sonobe, Junya Iwazaki, Makoto Miyauchi, Tomoya Kobayashi, Eichi Takaya, Saori Ikumi, Taro Miyamoto, Shota Kawamoto, Shintaro Oyama, Takahiro Imaizumi, Akemi Morohashi, Kengo Oshima, Asami Nakayama, Tetsuji Aoyagi

    Scientific reports　2026/04/24

    DOI： 10.1038/s41598-026-50400-w 　

    More details Close

    Bloodstream infections require timely and appropriate diagnosis and treatment, as inadequate management is associated with higher mortality. Previous predictive models for bloodstream infection have generally incorporated laboratory test results in addition to vital signs, although laboratory results are not always immediately available in clinical practice. This study aimed to develop and validate a machine learning model to predict positive blood cultures using only vital signs in febrile intensive care unit (ICU) patients (maximum BT ≥ 38 °C). Clinical data from ICU patients at two university hospitals were included, with 597 blood cultures used for model development and 366 for external validation. Six explanatory variables derived from body temperature, heart rate, and mean arterial pressure measured over three days were used to construct a Balanced Random Forest model. The area under the receiver operating characteristic curve was 0.700 ± 0.072 for internal validation and 0.679 ± 0.010 for external validation. SHapley Additive exPlanations value analysis indicated that a larger temperature range contributed to positive predictions, while no increase in temperature, increases in blood pressure, and a decrease in heart rate contributed to negative predictions. The model demonstrates moderate predictive performance and shows comparable results across different datasets. It can continuously monitor the need for blood cultures, thereby serving as an adjunctive tool to support clinical decision-making.

  2. Corrigendum to 'Osteoporosis prediction from frontal lumbar spine X-rays' [Journal of clinical densitometry, volume 29 (2026), 101666]. International-journal

    Ryusei Inamori, Tomoya Kobayashi, Eichi Takaya, Junya Iwazaki, Carlos Makoto Miyauchi, Saori Ikumi, Yoshikazu Okamoto, Cheng Wei Lin, Sheng Che Hsiao, Qingzong Tseng, Shinya Sonobe

    Journal of clinical densitometry : the official journal of the International Society for Clinical Densitometry　101671-101671　2026/01/31

    DOI： 10.1016/j.jocd.2026.101671 　

  3. Osteoporosis prediction from Frontal Lumbar Spine X-rays. International-journal

    Ryusei Inamori, Tomoya Kobayashi, Eichi Takaya, Junya Iwazaki, Carlos Makoto Miyauchi, Saori Ikumi, Yoshikazu Okamoto, Cheng Wei Lin, Sheng Che Hsiao, Qingzong Tseng, Shinya Sonobe

    Journal of clinical densitometry : the official journal of the International Society for Clinical Densitometry　29　(1)　101666-101666　2026

    DOI： 10.1016/j.jocd.2025.101666 　

    More details Close

    BACKGROUND: This study aimed to evaluate the performance of DeepXray™ Spina, a software that estimates bone mineral density (BMD) and T-scores from frontal lumbar spine X-ray (FLS-X), in predicting osteoporosis. METHODOLOGY: Patients from a Japanese cohort who underwent both FLS-X and dual-energy X-ray absorptiometry (DXA) using Hologic systems within 30 days at Tohoku University Hospital (May 2014-April 2024) were included. BMD was estimated from FLS-X using DeepXray™ Spina, which was developed using dataset from a Taiwanese Cohort. BMD assessed by DXA (observed BMD) and BMD estimated from FLS-X by DeepXray™ Spina (estimated BMD) were compared using Pearson's correlation coefficient (PCC) and normalized root mean square error (NRMSE). T-scores were converted to osteoporosis classifications as normal, osteopenia, or osteoporosis following the World Health Organization criteria. Classification performance was evaluated by accuracy, sensitivity, specificity, Cohen's kappa, and quadratic-weighted Cohen's kappa. RESULTS: The correlation between estimated and observed BMD was strong, with a PCC of 0.901 and an NRMSE of 0.070. For osteoporosis classification, the accuracy, sensitivity, specificity, and Cohen's kappa were as follows: 0.902, 1.000, 0.842, and 0.803 for normal; 0.854, 0.729, 0.924, and 0.673 for osteopenia; 0.951, 0.810, 1.000, and 0.863 for osteoporosis. The quadratic-weighted Cohen's kappa was 0.884. CONCLUSION: This study evaluated the performance of Deep Xray™ Spina in predicting osteoporosis from FLS-X. The software is a practical and reliable tool for predicting osteoporosis, with high performance and robustness.

  4. Multifactorial Biomarkers for "Talk and Deteriorate" after Head Trauma Identified Using Machine Learning.

    Youhei Takeuchi, Shinya Sonobe, Kuniyasu Niizuma, Arata Nagai, Ayumi Narisawa, Atsuhiro Nakagawa, Motonobu Kameyama, Hiroshi Karibe, Hidenori Endo, Teiji Tominaga

    Neurologia medico-chirurgica　65　(12)　568-575　2025/12/15

    DOI： 10.2176/jns-nmc.2025-0166 　

    More details Close

    Talk and Deteriorate refers to a clinical course where a patient is able to speak immediately after a traumatic brain injury but subsequently deteriorates in consciousness. Talk and Deteriorate outcomes are poor, and reliable prediction may help improve them. We searched for multifactorial biomarkers-combinations of multiple risk factors-assuming they would predict Talk and Deteriorate more reliably than single factors. A total of 680 consecutive patients aged ≥16 years with intracranial traumatic lesions and a Glasgow Coma Scale of 13-15 upon admission were included. Information on 27 factors at admission and whether Talk and Deteriorate developed was collected. The correlation between Talk and Deteriorate incidence and each factor was evaluated using univariate analysis. Multifactorial biomarkers associated with a high Talk and Deteriorate incidence were identified using a brute force method combined with clustering based on combinations of factors and various thresholds for each. Among the 680 patients, 89 (13.1%) developed Talk and Deteriorate. A total of 94 multifactorial biomarkers with a Talk and Deteriorate incidence rate of ≥50.0% were identified. These multifactorial biomarkers, which included factors previously suspected to be related to Talk and Deteriorate, were associated with a higher Talk and Deteriorate incidence than each factor alone. Thus, this study indicates that predicting Talk and Deteriorate is more reliable when based on multifactorial biomarkers than on single factors. Factors not previously reported as independent biomarkers contributed as components of multifactorial biomarkers, while previously reported factors played more important roles within them. Thus, this study revealed multifactorial contributions of factors related to Talk and Deteriorate. Future studies focusing on these biomarkers, incorporating pathophysiologic insights, will improve Talk and Deteriorate outcomes.

  5. Operative Time Prediction by Machine Learning for Robot-Assisted Laparoscopic Radical Prostatectomy. International-journal

    Yu Suzuki, Shinya Sonobe, Yoshihide Kawasaki, Saori Ikumi, Eichi Takaya, Carlos Makoto Miyauchi, Tomoya Kobayashi, Junya Iwazaki, Hisanobu Adachi, Naoki Kawamorita, Akihiro Ito

    International journal of urology : official journal of the Japanese Urological Association　2025/11/30

    DOI： 10.1111/iju.70292 　

    More details Close

    OBJECTIVES: Operative time prediction is crucial for efficient operating room scheduling. This study developed and validated an operative time prediction system for robot-assisted laparoscopic radical prostatectomy using data from two institutions. METHODS: Retrospectively identified 557 and 150 patients who underwent RARP at Tohoku University Hospital and Miyagi Cancer Center were analyzed. The following variables were collected as explanatory variables for the prediction system: Age, height, body mass index, comorbidities, performance status, prostate volume, tumor extent of local invasion, grade group, prostatitis, preoperative treatment, history of intraperitoneal surgery, lymphadenectomy, and nerve-sparing. In addition, the observed operative time was collected as a source variable for the objective variable. The observed operative time was calculated as the sum of components related to institutional, operator, and patient factors. Approximation curves were applied to the first two components, while a random forest-based machine learning model was applied to the latter, resulting in the development of an integrated prediction system. RESULTS: The normalized root mean square error between the observed and predicted operative times was 0.107 in internal validation and 0.148 in external validation, demonstrating greater reliability than the expected operative time by operators in advance. Factors that are known to impact operative time, such as lymphadenectomy, grade group, prostate volume, and body mass index, were identified as contributing variables. CONCLUSIONS: The system provides a reliable and robust prediction focusing on factors known to impact operative time. It has the potential to improve the efficiency of operating room scheduling.

  6. 医療データ利活用における制度・倫理的課題とその対応 東北大学病院MDUCの実践から(Addressing Regulatory and Ethical Issues in Medical Data Utilization: Insights from MDUC at Tohoku University Hospital)

    藤井 進, 野中 小百合, 川本 章大, 中村 直毅, 横田 崇, 園部 真也

    医療情報学連合大会論文集　45回　812-813　2025/11

    Publisher: (一社)日本医療情報学会

    ISSN： 1347-8508

    eISSN： 2433-698X

  7. 【実践】診療録自動生成ソフトウェアAIVOの導入初期における知見

    井汲 沙織, 園部 真也, 中村 直毅, 藤井 進

    医療情報学連合大会論文集　45回　1174-1177　2025/11

    Publisher: (一社)日本医療情報学会

    ISSN： 1347-8508

    eISSN： 2433-698X

  8. 【学術】次世代医療基盤法に基づく匿名加工データの母集団代表性と研究利用の妥当性に関する検証(Evaluation of Population Representativeness and Research Validity of Anonymized Data under the Next-Generation Medical Infrastructure Act)

    藤井 進, 野中 小百合, 川本 章太, 中村 直毅, 横田 崇, 園部 真也

    医療情報学連合大会論文集　45回　1451-1453　2025/11

    Publisher: (一社)日本医療情報学会

    ISSN： 1347-8508

    eISSN： 2433-698X

  9. 【学術】臨床研究の対象となる候補患者を医療記録に基づいて抽出するシステムの構築(Development of a System for Identifying Candidate Patients for Clinical Research Based on Electronic Medical Records)

    園部 真也, 宮本 太郎, 川本 章太, 井汲 沙織, 中村 直毅, 藤井 進

    医療情報学連合大会論文集　45回　1460-1461　2025/11

    Publisher: (一社)日本医療情報学会

    ISSN： 1347-8508

    eISSN： 2433-698X

  10. Machine learning using serial changes in proteinuria during initial steroid therapy to predict treatment response and immunosuppressant use in pediatric idiopathic nephrotic syndrome.

    Takaya Iida, Kenichiro Miura, Takayuki Okamoto, Shuichiro Fujinaga, Yuko Akioka, Yasuhiro Takeshima, Maki Urushihara, Masataka Hisano, Yoshimitsu Gotoh, Toshiyuki Ohta, Eichi Takaya, Carlos Makoto Miyauchi, Shinya Sonobe, Tadashi Kaname, Motoshi Hattori

    Clinical and experimental nephrology　29　(11)　1618-1626　2025/11

    DOI： 10.1007/s10157-025-02714-8 　

    More details Close

    BACKGROUND: Epidemiological studies on idiopathic nephrotic syndrome (INS) in children have identified no definitive factors predicting steroid-resistant nephrotic syndrome (SRNS) or frequent relapsing nephrotic syndrome. Research using machine learning (ML) has been conducted to predict INS prognosis; however, no studies have evaluated serial changes in proteinuria during initial steroid therapy. METHODS: INS patient data were collected from 23 medical centers. ML using clinical and laboratory data at first presentation and time-series features generated using serial changes in urine protein to creatinine ratio (UPCR) during initial steroid therapy were performed to predict SRNS and immunosuppressant use in 329 and 190 patients, respectively. ML models were run to calculate the area under the curve (AUC) and to identify variables contributing to predicted outcomes using the backward stepwise method. RESULTS: In the SRNS prediction model, UPCR at the final analysis point (i.e., the last sequential day of UPCR input included for model analysis) and several preceding days substantially contributed to the prediction, with UPCR at the final analysis point being the most significant contributor. The immunosuppressant prediction model achieved an AUC ranging from 0.715 to 0.759 and showed that age, serum albumin, serum total cholesterol, and time-series features (approximate entropy, mean UPCR value between the 20th to 80th percentiles, and 70th percentile UPCR value) were significant contributors. CONCLUSIONS: Our ML suggested that UPCR at the final analysis point was an important predictor of SRNS. Age, serum albumin, serum total cholesterol and serial changes in proteinuria contributed to immunosuppressant use.

  11. Prediction of financial deficits of postoperative patients in the intensive care unit using machine learning. International-journal

    Saori Ikumi, Takuya Shiga, Eichi Takaya, Shinya Sonobe, Yu Kaiho, Yukiko Ito, Masanori Yamauchi

    JA clinical reports　11　(1)　57-57　2025/10/21

    DOI： 10.1186/s40981-025-00819-3 　

    More details Close

    BACKGROUND: Operational loss, defined as unanticipated financial deficits in intensive care unit (ICU) management, is challenging to predict yet critical for hospital sustainability. This study aimed to evaluate whether machine-learning models can predict financial loss events in postoperative ICU patients. METHODS: We conducted a retrospective analysis of postoperative patients admitted to the ICU at Tohoku University Hospital between April 2017 and March 2021. A total of 22 clinical and administrative variables collected within 24 h of ICU admission were used to develop machine-learning models. The outcome was defined as financial loss events, determined by a negative contribution margin below the break-even threshold of - 909 USD. The dataset was randomly split into training (70%) and test (30%) sets. Predictive performance was assessed using the area under the receiver operating characteristic curve (AUC) and accuracy. RESULTS: Among 6743 postoperative ICU patients, 425 (6.3%) experienced financial loss events. The random forest classifier demonstrated high predictive performance, with an AUC of 0.859 and accuracy of 0.785. CONCLUSIONS: Machine-learning models may accurately predict financial loss events in postoperative ICU patients, potentially supporting efficient resource allocation and hospital financial planning.

  12. 術前の臨床データから骨盤リンパ節転移を予測する機械学習モデルの構築

    久木元 詩央香, 重田 昌吾, 村川 東, 萩原 達也, 高屋 英知, 小林 智哉, 宮内 誠, 岩崎 淳也, 園部 真也, 渡邉 善, 石橋 ますみ, 島田 宗昭, 齋藤 昌利

    日本婦人科腫瘍学会学術講演会プログラム・抄録集　67回　221-221　2025/07

    Publisher: (公社)日本婦人科腫瘍学会

  13. Artificial Intelligence in Neuroendovascular Therapy: Current Applications and Future Directions.

    Shinya Sonobe, Kuniyasu Niizuma, Hidenori Endo

    Journal of neuroendovascular therapy　19　(1)　2025

    DOI： 10.5797/jnet.ra.2025-0073 　

    More details Close

    In recent years, artificial intelligence (AI) has made remarkable progress. In the near future, AI will become an indispensable technology in daily clinical practice in the field of neuroendovascular therapy. Clinicians who understand the information processing and limitations of AI will create new and comfortable working styles. This article introduces current applications of AI in the field of neuroendovascular therapy and presents a vision for its future directions.

  14. Multifactorial Assessment of Complication Risks in Embolization for Ruptured Cerebral Aneurysm

    Arata Nagai, Shinya Sonobe, Kuniyasu Niizuma, Tetsuo Ishikawa, Eiryo Kawakami, Yasushi Matsumoto, Hirotoshi Imamura, Tetsu Satow, Koji Iihara, Chiaki Sakai, Nobuyuki Sakai, Shigeru Miyachi, Hidenori Endo, Teiji Tominaga

    Journal of Neuroendovascular Therapy　19　(1)　n/a-n/a　2025

    Publisher: The Japanese Society for Neuroendovascular Therapy

    DOI： 10.5797/jnet.oa.2024-0095 　

    ISSN： 1882-4072

    eISSN： 2186-2494

  15. 救急集中治療領域におけるAIとDX～工学・医学・産業の融合を果たすには～ 医療AIの研究と開発、社会実装を大学と企業の立場で考える

    藤井 進, 中村 直毅, 野中 小百合, 園部 真也

    日本救急医学会雑誌　35　(11)　582-582　2024/11

    Publisher: (一社)日本救急医学会

    ISSN： 0915-924X

    eISSN： 1883-3772

  16. 次世代医療基盤法を活用した医療データの利活用の促進と現状、その課題 医学研究における匿名加工医療情報と源データと比較 研究結果への影響

    藤井 進, 野中 小百合, 園部 真也, 横田 崇, 中村 直毅

    医療情報学連合大会論文集　44回　431-433　2024/11

    Publisher: (一社)日本医療情報学会

    ISSN： 1347-8508

    eISSN： 2433-698X

  17. 臨床医がAI技術を理解する意義

    園部 真也, 新妻 邦泰, 永井 新, 竹内 洋平, 田宮 元, 岩崎 淳也, 宮内 誠, 小林 智哉, 高屋 英知, 川上 英良, 石川 哲朗, 遠藤 英徳

    日本脳神経血管内治療学会学術集会抄録集　40回　1064-1064　2024/11

    Publisher: (一社)日本脳神経血管内治療学会

    eISSN： 2759-6907

  18. 脳神経血管内治療とAI:診断～治療まで JR-NET3のAI解析

    園部 真也, 永井 新, 新妻 邦泰, 坂井 信幸, 坂井 千秋, 飯原 弘二, 佐藤 徹, 今村 博敏, 石川 哲朗, 川上 英良, 植田 琢也, 遠藤 英徳

    脳血管内治療　8　(Suppl.)　S65-S65　2023/11

    Publisher: (NPO)日本脳神経血管内治療学会

    ISSN： 2423-9119

    eISSN： 2424-1709

  19. 東北大学病院における匿名加工医療情報および仮名加工情報の利活用と産学連携へ向けた取り組み Peer-reviewed

    園部 真也, 藤井 進, 中村 直毅, 横田 崇, 志村 浩孝, 小林 智哉, 志賀 卓弥, 大田 英輝, 荻島 創一, 田宮 元, 植田 琢也, 冨永 悌二

    日本医療情報学会春季学術大会プログラム・抄録集　27回　128-129　2023/06

    Publisher: (一社)日本医療情報学会

  20. Development and validation of machine learning prediction model for post-rehabilitation functional outcome after intracerebral hemorrhage

    Shinya Sonobe, Tetsuo Ishikawa, Kuniyasu Niizuma, Eiryo Kawakami, Takuya Ueda, Eichi Takaya, Carlos Makoto Miyauchi, Junya Iwazaki, Ryuzaburo Kochi, Toshiki Endo, Arun Shastry, Vijayananda Jagannatha, Ajay Seth, Atsuhiro Nakagawa, Masahiro Yoshida, Teiji Tominaga

    Interdisciplinary Neurosurgery: Advanced Techniques and Case Management　29　2022/09

    DOI： 10.1016/j.inat.2022.101560 　

    eISSN： 2214-7519

  21. 外来での照射中問診のためのタブレットアプリケーションの開発

    武田 一也, 神宮 啓一, 園部 真也, 植田 琢也

    Japanese Journal of Radiology　40　(Suppl.)　6-6　2022/02

    Publisher: (公社)日本医学放射線学会

    ISSN： 1867-1071

    eISSN： 1867-108X

  22. Case Report: Vertebro-vertebral arteriovenous fistula showing symptoms mimicking ALS: Diagnostic imaging supports accurate differentiation between ALS and mimicking conditions. International-journal

    Hinako Kirikae, Ryuhei Harada, Tatsuhiko Hosaka, Tatsuro Misu, Daisuke Ando, Hitoshi Warita, Toshiki Endo, Shinya Sonobe, Kuniyasu Niizuma, Masashi Aoki

    F1000Research　11　546-546　2022

    DOI： 10.12688/f1000research.121554.3 　

    More details Close

    We report a rare case of a vertebro-vertebral arteriovenous fistula (VVAVF) manifesting as amyotrophic lateral sclerosis (ALS). A 76-year-old female patient presented with progressive weakness, muscle atrophy, fasciculation, and preserved deep tendon reflexes in the right upper limb. Electrophysiological testing showed lower motor neuron dysfunction. The patient was suspected to have ALS, but cervical magnetic resonance imaging (MRI) revealed enlarged blood vessels in the spinal canal, which compressed the cervical spinal cord and nerve roots. Angiography showed a shunt from the right vertebral artery to the right intervertebral vein and the vertebral venous plexus; therefore, the patient was diagnosed with VVAVF. Transarterial embolization was performed to obliterate the shunt, and weakness in the patient's right upper limb subsequently improved. It is worth considering VVAVF as a differential diagnosis of ALS-like diseases.

  23. Digital intravascular pressure wave recording during endovascular treatment reveals abnormal shunting flow in vertebral venous fistula of the vertebral artery: illustrative case. International-journal

    Yoshiteru Shimoda, Shinya Sonobe, Kuniyasu Niizuma, Toshiki Endo, Hidenori Endo, Mayuko Otomo, Teiji Tominaga

    Journal of neurosurgery. Case lessons　2　(2)　CASE21172　2021/07/12

    DOI： 10.3171/CASE21172 　

    More details Close

    BACKGROUND: An arteriovenous fistula is an abnormal arteriovenous shunt between an artery and a vein, which often leads to venous congestion in the central nervous system. The blood flow near the fistula is different from normal artery flow. A novel method to detect the abnormal shunting flow or pressure near the fistula is needed. OBSERVATIONS: A 76-year-old woman presented to the authors' institute with progressive right upper limb weakness. Right vertebral angiography showed a fistula between the right extracranial vertebral artery (VA) and the right vertebral venous plexus at the C7 level. The patient underwent endovascular treatment for shunt flow reduction. Before the procedure, blood pressures were measured at the proximal VA, distal VA near the fistula, and just at the fistula and drainer using a microcatheter. The blood pressure waveforms were characteristically different in terms of resistance index, half-decay time, and appearance of dicrotic notch. The fistula was embolized with coils and N-butyl cyanoacrylate solution. LESSONS: During endovascular treatment, the authors were able to digitally record the vascular pressure waveform from the tip of the microcatheter and succeeded in calculating several parameters that characterize the shunting flow. Furthermore, these parameters could help recognize the abnormal blood flow, allowing a safer endovascular surgery.

  24. Trans-Cell Technique through Mesh of Pipeline Embolization Device: A Case Report Peer-reviewed

    Shinya Sonobe, Masayuki Ezura, Ayumi Narisawa, Naoto Kimura, Hiroshi Uenohara, Teiji Tominaga

    Journal of Neuroendovascular Therapy　15　(1)　46-51　2021

    Publisher: The Japanese Society for Neuroendovascular Therapy

    DOI： 10.5797/jnet.cr.2020-0047 　

    ISSN： 1882-4072

    eISSN： 2186-2494

  25. Ruptured Basilar Artery Dissection Diagnosed Using Magnetic Resonance Vessel Wall Imaging and Treated with Coil Embolization with Overlapping LVIS Stents: A Case Report Peer-reviewed

    Sonobe S, Yoshida M, Niizuma K, Tominaga T

    NMC Case Report Journal　7　(2)　75-79　2020/03

  26. A case of cavernous sinus dural arteriovenous fistula presenting with medulla oblongata dysfunction in parallel to thrombosis of a varix on a drainage route after transvenous embolization. Peer-reviewed

    Sonobe S, Ezura M, Sato K, Uenohara H, Tominaga T

    Journal of Neuroendovascular Therapy　13　(5)　228-232　2019/02

  27. Application of neuro-endoscopic target aspiration of the necrotic core for cerebral contusion with delayed progression: technical note. Peer-reviewed

    Mino M, Fujimura M, Yoshida M, Sonobe S, Tominaga T

    Acta Neurochirurgica　161　(2)　225-230　2019/02

  28. Usefulness of enhanced three-dimensional T1 fast spin-echo in the treatment of subarachnoid hemorrhage with multiple intracerebral aneurysms in elderly patients: a report of two cases. Peer-reviewed

    Osada Y, Sonobe S, Mino M, Yoshida M, Tominaga T

    Surgery for Cerebral Stroke　47　(3)　196-201　2019/01

  29. Mechanical thrombectomy for acute ischemic stroke arising from thrombus of the left superior pulmonary vein stump after left pneumonectomy: a case report. Peer-reviewed

    Sonobe S, Yoshida M, Niizuma K, Tominaga T

    NMC Case Report Journal　6　(1)　17-20　2018/12

  30. Spontaneous Development of Encapsulated Subdural Hematoma in the Posterior Cranial Fossa after Cardiac Surgery: A Case Report. Peer-reviewed

    Kochi R, Mino M, Sonobe S, Yoshida M, Tominaga T

    NMC Case Report Journal　5　(4)　87-90　2018/09

  31. コイル塞栓術後再開通により破裂した脳動脈瘤に関する数値流体力学的解析 Peer-reviewed

    園部 真也, 杉山 慎一郎, 松本 康史, 遠藤 英徳, 新妻 邦泰, 冨永 悌二

    脳血管内治療　1　(Suppl.)　S248-S248　2016/11

    Publisher: (NPO)日本脳神経血管内治療学会

    ISSN： 2423-9119

    eISSN： 2424-1709

  32. 解離性頸部内頸動脈瘤に対して人工血管置換術を施行した一例

    園部 真也, 井上 敬, 柴原 一陽, 江面 正幸, 上之原 広司, 冨永 悌二

    東北脳血管障害研究会学術集会記録集　37回　283-298　2015/12

    Publisher: サノフィ(株)仙台オフィス

    ISSN： 1880-9278

  33. Increased vascular MMP-9 in mice lacking RNF213: moyamoya disease susceptibility gene Peer-reviewed

    Shinya Sonobe, Miki Fujimura, Kuniyasu Niizuma, Taku Fujimura, Sadanori Furudate, Yasuo Nishijima, Shigeo Kure, Teiji Tominaga

    NEUROREPORT　25　(18)　1442-1446　2014/12

    DOI： 10.1097/WNR.0000000000000289 　

    ISSN： 0959-4965

    eISSN： 1473-558X

  34. Genetics and Biomarkers of Moyamoya Disease: Significance of RNF213 as a Susceptibility Gene Peer-reviewed

    Miki Fujimura, Shinya Sonobe, Yasuo Nishijima, Kuniyasu Niizuma, Hiroyuki Sakata, Shigeo Kure, Teiji Tominaga

    JOURNAL OF STROKE　16　(2)　65-72　2014/05

    DOI： 10.5853/jos.2014.16.2.65 　

    ISSN： 2287-6391

    eISSN： 2287-6405

  35. Temporal profile of the vascular anatomy evaluated by 9.4-T magnetic resonance angiography and histopathological analysis in mice lacking RNF213: A susceptibility gene for moyamoya disease Peer-reviewed

    Shinya Sonobe, Miki Fujimura, Kuniyasu Niizuma, Yasuo Nishijima, Akira Ito, Hiroaki Shimizu, Atsuo Kikuchi, Natsuko Arai-Ichinoi, Shigeo Kure, Teiji Tominaga

    BRAIN RESEARCH　1552　64-71　2014/03

    DOI： 10.1016/j.brainres.2014.01.011 　

    ISSN： 0006-8993

    eISSN： 1872-6240

  36. Characteristics of distal middle cerebral artery aneurysm Peer-reviewed

    Narisawa Ayumi, Kon Hiroyuki, Kawaguchi Tomohiro, Takazawa Hiroki, Morita Takahiro, Sonobe Shinya, Ohtani Keisuke, Sasaki Tatsuya, Nishijima Michiharu

    Jpn. J. Stroke　34　(5)　304-309　2012

    Publisher: 一般社団法人 日本脳卒中学会

    DOI： 10.3995/jstroke.34.304 　

    ISSN： 0912-0726

    More details Close

    Objective: Distal middle cerebral artery (MCA) aneurysm is rare among intracranial aneurysms. In diagnosing and treating distal MCA aneurysms, it is important to note that it differs significantly from other aneurysms located around the circle of Willis. The purpose of this study is to identify the clinical characteristics of distal MCA aneurysms.Method: We encountered 12 patients with distal MCA aneurysms at our institution from January 2000 to March 2011. They correspond to 0.7% of all patients with cerebral aneurysms over the same period. We retrospectively reviewed the records of patients with distal MCA aneurysms which include important parameters such as onset type (ruptured/unruptured), presence or absence of intracerebral hematoma, size of the aneurysm, treatment, and outcome.Result: Nine patients had multiple aneurysms. Eight patients had aneurysmal subarachnoid hemorrhage (SAH). Among the eight, 4 patients had a ruptured distal MCA aneurysm whereas the other 4 patients had ruptured non-distal MCA aneurysm and unruptured distal MCA aneurysm. Two patients with aneurysmal SAH had intracerebral hematoma. Eleven patients underwent clipping of distal MCA aneurysms.Conclusion: Distal MCA aneurysms differ from typical saccular aneurysms on major branch points of the circle of Willis and they need unique considerations in diagnosis and treatment.

  37. Subarachnoid Hemorrhage Due to Ruptured Posterior Cerebral Artery Aneurysm Simultaneously Associated With Multiple Remote Intracerebral Hemorrhages-Case Report Peer-reviewed

    Shinya Sonobe, Miki Fujimura, Hidenori Endo, Takashi Inoue, Hiroaki Shimizu, Teiji Tominaga

    NEUROLOGIA MEDICO-CHIRURGICA　51　(12)　836-838　2011/12

    ISSN： 0470-8105

  38. 急性期塞栓術を施行した多発性脳動脈瘤の検討

    園部 真也, 高沢 弘樹, 川口 奉洋, 金森 政之, 対馬 史泰, 場崎 潔, 緑川 宏, 佐々木 達也, 西嶌 美知春

    JNET: Journal of Neuroendovascular Therapy　4　(4)　190-190　2010/11

    Publisher: (NPO)日本脳神経血管内治療学会

    ISSN： 1882-4072

    eISSN： 2186-2494

  39. C2 Neurinoma with Intracranial Extension: A Case Report Peer-reviewed

    Shinya Sonobe, Kensuke Murakami, Misaki Kohama, Mika Watanabe, Toshihiro Kumabe, Teiji Tominaga

    NEUROLOGICAL SURGERY　37　(9)　893-897　2009/09

    ISSN： 0301-2603

  40. Evoked magnetic fields in recognition memory task for auditory presented Japanese words. Peer-reviewed

    Sonobe S, Tanji K, Kanno A, Nakasato N

    The Journal of Japan Biomagnetism and Bioelectromagnetics Society　17　98-99　2004

Show all ︎Show first 5

Misc. 12

  1. 文章埋め込みモデルを用いた診療録検索の検証

    田中翔, 高屋英知, 高屋英知, 小林智哉, 小林智哉, 宮内誠カルロス, 岩崎淳也, 園部真也, 園部真也, 園部真也

    日本メディカルAI学会学術集会プログラム・抄録集　7th　2025

  2. 診療録のテキスト類似性計算手法の探索:電子カルテデータの横断的利用に向けた研究

    宮内誠カルロス, 岩崎淳也, 高屋英知, 小林智哉, 園部真也

    日本メディカルAI学会学術集会プログラム・抄録集　6th　2024

  3. マンモグラフィ画像の階調数がAIモデルの精度に及ぼす影響-CNNにおける乳腺濃度分類の精度検証-

    小林智哉, 小林智哉, 稲森瑠星, 高屋英知, 高屋英知, 宮内誠カルロス, 岩崎淳也, 園部真也, 園部真也, 園部真也, 植田琢也, 植田琢也

    日本メディカルAI学会学術集会プログラム・抄録集　6th　2024

  4. 集中治療室退室後患者がハイケアユニットを経由することの費用対効果分析-日本全国DPCデータを用いた後方視的解析-

    井汲沙織, 井汲沙織, 志賀卓弥, 高屋英知, 高屋英知, 岩崎淳也, 宮内誠カルロス, 小林智哉, 園部真也, 園部真也, 園部真也, 園部真也, 山内正憲

    日本メディカルAI学会学術集会プログラム・抄録集　6th　2024

  5. 脳血管内治療における手技合併症率算出モデルのAIを用いた構築

    永井新, 永井新, 高屋英知, 高屋英知, 小林智哉, 小林智哉, 宮内誠カルロス, 岩崎淳也, 園部真也, 園部真也, 園部真也, 園部真也

    日本メディカルAI学会学術集会プログラム・抄録集　6th　2024

  6. 自然言語処理に基づく診療録仮名化データセットの構築

    高屋英知, 宮内誠カルロス, 岩崎淳也, 小林智哉, 園部真也

    日本メディカルAI学会学術集会プログラム・抄録集　6th　2024

  7. 同じ条件で一回前後のみ観測される二値従属変数のそれぞれの条件における確率分布推定

    園部真也, 園部真也, 園部真也, 永井新, 永井新, 高屋英知, 小林智哉, 宮内誠カルロス, 岩崎淳也

    日本メディカルAI学会学術集会プログラム・抄録集　6th　2024

  8. 24万人分の診療録を用いた日本語版医療用大規模言語モデル構築の試み

    岩崎淳也, 高屋英知, 宮内誠カルロス, 小林智哉, 園部真也

    日本メディカルAI学会学術集会プログラム・抄録集　6th　2024

  9. JR-NET3のAI解析

    園部真也, 園部真也, 園部真也, 園部真也, 永井新, 永井新, 新妻邦泰, 新妻邦泰, 新妻邦泰, 新妻邦泰, 坂井信幸, 坂井千秋, 飯原弘二, 佐藤徹, 今村博敏, 石川哲朗, 川上英良, 植田琢也, 遠藤英徳

    脳血管内治療(Web)　8　(Supplement)　2023

    ISSN： 2424-1709

  10. 外来放射線治療におけるタブレット問診票の導入

    園部 真也, 武田 一也, 佐々木 恵利奈, 中村 直毅, 植田 琢也, 神宮 啓一, 中山 雅晴

    医療情報学連合大会論文集　40回　855-856　2020/11

    Publisher: (一社)日本医療情報学会

    ISSN： 1347-8508

    eISSN： 2433-698X

  11. 外来放射線治療でのタブレット問診システム

    園部 真也, 武田 一也, 佐々木 恵利奈, 中村 直毅, 植田 琢也, 神宮 啓一, 中山 雅晴

    医療の質・安全学会誌　15　(Suppl.)　237-237　2020/11

    Publisher: (一社)医療の質・安全学会

    ISSN： 1881-3658

    eISSN： 1882-3254

  12. ステント型血栓回収デバイスの臨床効果の検討 単施設における無作為割り付けによる比較

    園部 真也, 江面 正幸, 石田 朋久, 面高 俊介, 柴原 一陽, 倉前 卓実, 井上 敬, 上之原 広司

    JNET: Journal of Neuroendovascular Therapy　9　(6)　S340-S340　2015/11

    Publisher: (一社)日本脳神経血管内治療学会

    ISSN： 1882-4072

    eISSN： 2186-2494

Show all ︎Show first 5

Research Projects 10

  1. 全国の電子カルテ情報の統合データベース作成を可能にする自然言語処理技術の開発

    岩崎 淳也, 園部 真也, 高屋 英知, 宮内 誠

    Offer Organization: 日本学術振興会

    System: 科学研究費助成事業

    Category: 基盤研究(C)

    Institution: 国立研究開発法人理化学研究所

    2025/04/01 - 2028/03/31

  2. もやもや病感受性遺伝子ＲＮＦ２１３多型保持健常者における潜在的画像所見のＡＩ解析

    園部 真也, 新妻 邦泰, 麦倉 俊司

    Offer Organization: 日本学術振興会

    System: 科学研究費助成事業

    Category: 基盤研究(C)

    Institution: 東北大学

    2025/04/01 - 2028/03/31

  3. Secure Computation-Based Framework for Developing Medical AI with Distributed Personal Information Analysis.

    Offer Organization: Japan Society for the Promotion of Science

    System: Grants-in-Aid for Scientific Research

    Category: Grant-in-Aid for Scientific Research (C)

    Institution: Nagoya University

    2025/04/01 - 2028/03/31

  4. 血管壁MRイメージングと数値流体解析を駆使した脳動脈瘤増大予測モデルの開発

    面高 俊介, 中川 敦寛, 新妻 邦泰, 杉山 慎一郎, 園部 真也, 遠藤 英徳, 船本 健一

    Offer Organization: 日本学術振興会

    System: 科学研究費助成事業

    Category: 基盤研究(C)

    Institution: 東北大学

    2024/04/01 - 2027/03/31

  5. 爆風損傷の初期診療におけるトリアージ法に関する基礎研究

    中川 敦寛, 大谷 清伸, 大沢 伸一郎, 園部 真也, 下田 由輝, 辻田 哲平, 近野 敦, 佐瀬 一弥

    Offer Organization: 日本学術振興会

    System: 科学研究費助成事業

    Category: 基盤研究(B)

    Institution: 東北大学

    2023/04/01 - 2026/03/31

  6. 爆風損傷の初期診療におけるトリアージ法に関する基礎研究

    中川 敦寛, 大谷 清伸, 大沢 伸一郎, 園部 真也, 下田 由輝, 辻田 哲平, 近野 敦, 佐瀬 一弥

    Offer Organization: 日本学術振興会

    System: 科学研究費助成事業

    Category: 基盤研究(B)

    Institution: 東北大学

    2023/04/01 - 2026/03/31

  7. 人工知能を用いたもやもや病における病期進行予測モデルの開発

    遠藤 英徳, 中川 敦寛, 新妻 邦泰, 麦倉 俊司, 杉山 慎一郎, 園部 真也, 植田 琢也, 面高 俊介

    Offer Organization: 日本学術振興会

    System: 科学研究費助成事業

    Category: 基盤研究(C)

    Institution: 東北大学

    2023/04/01 - 2026/03/31

  8. MRI・バイオマーカーによる脳循環自動調節能メカニズム解明及びAIによるその評価

    井上 敬, 冨永 悌二, 新妻 邦泰, 園部 真也

    Offer Organization: 日本学術振興会

    System: 科学研究費助成事業 基盤研究(C)

    Category: 基盤研究(C)

    Institution: 東北大学

    2021/04/01 - 2026/03/31

    More details Close

    今年度は、まずバイオマーカーによる神経損傷程度推定法を検討した。脳主幹動脈閉塞例に対し、急性期血行再建術を施行した症例を対象とした。神経損傷バイオマーカーとしては、研究者らがこれまで報告してきたtRNA由来物を測定した。脳神経損傷程度はこれまでMRI拡散強調像で評価されることが一般的であった。しかし、MRI拡散強調像では、すでに非可逆的な損傷を受けていても、所見として捉えることができない偽陰性症例や、その逆に可逆的損傷にもかかわらず、所見が出現する偽陽性の症例が存在する。本研究では、拡散強調画像を取得するタイミングで採血した血漿からtRNA由来物を定量的に測定した。神経損傷は３ヶ月後の神経学的検査で判定することとした。その結果、tRNA由来物はMRI拡散強調像よりも鋭敏に神経損傷を評価できることが判明した。この結果は現在英文誌に投稿中である。 さらに、AIによる神経機能評価法の基礎的な検討も始めた。AIによるdeep learning はこれまでの統計学的手法では抽出困難な危険因子を同定できる可能性がある。しかし、deep learningでは古典的統計学的手法に比べ、必要症例数が飛躍的に増加する。脳循環予備能推定が本研究の最終目標であるが、本年度はまずは十分な症例数のある疾患でAIによる神経機能評価法を確認した。対象としては慢性硬膜下血腫手術例約200例を対象とした。統計学的手法では術後神経機能回復が遅れる危険因子として、年齢・術前意識レベルなどが抽出された。AIを用いた検討では、これら以外にリハビリテーションの有無が、術後神経機能回復と関係があることが示唆された。統計学的手法ではリハビリテーションの有無は交絡因子とされたが、AIでの検討では独立因子と判定された。今後はさらに症例数を増やすことにより、どちらがより臨床的に有効か研究を続けたい。

  9. 血管壁イメージングMRIと瘤内血流のAI解析による脳動脈瘤破裂点の推定

    面高 俊介, 中川 敦寛, 新妻 邦泰, 杉山 慎一郎, 園部 真也, 遠藤 英徳, 船本 健一

    Offer Organization: 日本学術振興会

    System: 科学研究費助成事業 基盤研究(C)

    Category: 基盤研究(C)

    Institution: 東北大学

    2021/04/01 - 2024/03/31

    More details Close

    本研究では近年明らかになったMRIにおける脳動脈瘤壁の造影効果を破裂点の予測に応用し、さらにCFD (数値流体解析: computational fluid dynamics) 解析及びAI (人工知能: artificial intelligence) 解析を組み合わせることで、従来は主に形態学的特徴から予測していた破裂点をより高い精度で予測する手法を確立する。初年度である当該当年度は後ろ向き研究として主に患者データの収集を行った。画像データ（MRI及び脳血管撮影の3次元データ）を院内放射線サーバーからPCへ移す作業を行った。予定していた約400例分のうち2/3程終了した。移行した画像データを用いて画像解析ソフトを用いた瘤壁造影効果の評価、流体解析ソフトを用いたCFD解析を同時に進めているところである。現在のところ中間結果の段階であるが破裂点の予測にはMRIにおける瘤壁造影効果は非常に有用であるとの結果が得られつつある。すなわちくも膜下血種の患者さんで術前に造影MRIを行うことで事前に破裂点を予測しうるとの結果が得られており今後解析が進むにつれて根拠が増すものと予想される。現在移行している画像データはAI解析にも活用でき、将来的にはAI解析も進めることを視野に入れている。関連する検討として同データベースを用いて切迫破裂例における瘤壁臓絵効果に関する検討を行い論文化（Omodaka S et al. J Neurosurg. 2022）、学会発表 (脳神経外科総会2021, Stroke 2022)を行い、瘤壁造影効果の臨床的意義を示すことができており本研究成果の一部であるとともに本研究を後押しする成果が得られている。

  10. Analysis of latent imaging findings in healthy subjects with moyamoya disease susceptibility gene RNF213 polymorphism using artificial intelligence

    Offer Organization: Japan Society for the Promotion of Science

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

    Category: Grant-in-Aid for Scientific Research (C)

    Institution: Tohoku University

    2020/04/01 - 2023/03/31

Show all Show first 5