研究者詳細

顔写真

タカハシ ユウタ
高橋 雄太
Yuta Takahashi
所属
大学院医学系研究科 医科学専攻 神経・感覚器病態学講座(精神神経学分野)
職名
講師
学位
  • Ph.D

  • M.D.

プロフィール

精神保健指定医、精神科専門医・指導医。脳における情報処理を計算理論に基づき定式化する計算論的精神医学手法と、生物学的大規模データを用いたデータ駆動型機械学習手法の融合に取り組んでいます。これにより、生物学的妥当性が高く、治療法開発や個別化医療に応用しやすい病態脳のデジタルモデルの作成を目指しています。

経歴 5

  • 2025年4月 ~ 継続中
    東北大学 大学院医学系研究科 精神神経学分野 講師(クロスアポイントメント)

  • 2022年4月 ~ 継続中
    国立精神・神経医療研究センター 神経研究所疾病研究第七部 室長

  • 2020年8月 ~ 2022年3月
    東北大学病院 精神科 助教

  • 2015年4月 ~ 2020年7月
    東北大学病院 精神科 医員

  • 2013年4月 ~ 2015年3月
    独立行政法人国立国際医療研究センター 初期研修医

学歴 2

  • 東北大学 大学院医学系研究科 精神神経学分野

    2016年4月 ~ 2020年3月

  • 名古屋大学 医学部 医学科

    2007年4月 ~ 2013年3月

所属学協会 5

  • 日本メディカルAI学会

  • 日本神経科学会

  • 日本うつ病学会

  • 日本精神神経学会

  • 日本生物学的精神医学会

研究キーワード 12

  • データ同化

  • デジタルツイン

  • 予測処理理論

  • シミュレーション

  • 代謝物

  • 計算論的精神医学

  • 特徴量選択

  • 神経回路モデル

  • 機械学習

  • 人工知能

  • ゲノム

  • 精神医学

研究分野 4

  • 情報通信 / 生命、健康、医療情報学 /

  • ライフサイエンス / 認知脳科学 /

  • 情報通信 / ロボティクス、知能機械システム /

  • ライフサイエンス / 精神神経科学 /

受賞 7

  1. 東北医学会奨学賞(B)

    2021年1月

  2. 若手研究者育成プログラム奨励賞

    2019年6月 第41回日本生物学的精神医学会 機械学習を用いた因子間相互作用を考慮した精神疾患脆弱因子の探求

  3. 精神科専門医研修中の医師による演題の優秀発表賞

    2019年6月 第115回日本精神神経学会学術総会 メタボロームデータを用いた非線形変数選択機械学習によるうつ状態の予測

  4. 精神科専門医研修中の医師による演題の優秀発表賞

    2019年6月 第115回日本精神神経学会学術総会 ゲノムワイド遺伝子多型データを用いた機械学習によるうつ状態脆弱性の予測

  5. 若手道場口演優秀発表賞

    2018年9月 第40回日本生物学的精神医学会

  6. 精神科専門医研修中の医師による演題の優秀発表賞

    2017年6月 第113回日本精神神経学会学術総会 グリア線維酸性蛋白質遺伝子多型の脳構造への影響の検討

  7. 箱根山若手研究奨励賞

    2016年3月 国立研究開発法人国立国際医療研究センター病院

︎全件表示 ︎最初の5件までを表示

論文 38

  1. Digital Twin Brain: Generating Multitask Behavior from Connectomes for Personalized Therapy

    Yuta Takahashi, Takafumi Soda, Hiroaki Tomita, Yuichi Yamashita

    BME Frontiers 2026年1月

    DOI: 10.34133/bmef.0231  

  2. Digital twin brain simulator for real-time consciousness monitoring and virtual intervention using primate electrocorticogram data

    Yuta Takahashi, Hayato Idei, Misako Komatsu, Jun Tani, Hiroaki Tomita, Yuichi Yamashita

    npj Digital Medicine 8 (1) 2025年2月10日

    出版者・発行元: Springer Science and Business Media LLC

    DOI: 10.1038/s41746-025-01444-1  

    eISSN:2398-6352

    詳細を見る 詳細を閉じる

    Abstract At the forefront of bridging computational brain modeling with personalized medicine, this study introduces a novel, real-time, electrocorticogram (ECoG) simulator, based on the digital twin brain concept. Utilizing advanced data assimilation techniques, specifically a Variational Bayesian Recurrent Neural Network model with hierarchical latent units, the simulator dynamically predicts ECoG signals reflecting real-time brain latent states. By assimilating broad ECoG signals from macaque monkeys across awake and anesthetized conditions, the model successfully updated its latent states in real-time, enhancing precision of ECoG signal simulations. Behind successful data assimilation, self-organization of latent states in the model was observed, reflecting brain states and individuality. This self-organization facilitated simulation of virtual drug administration and uncovered functional networks underlying changes in brain function during anesthesia. These results show that the proposed model can simulate brain signals in real-time with high accuracy and is also useful for revealing underlying information processing dynamics.

  3. Interaction between Functional Connectivity and Neural Excitability in Autism: A Novel Framework for Computational Modeling and Application to Biological Data 査読有り

    Yuta Takahashi, Shingo Murata, Masao Ueki, Hiroaki Tomita, Yuichi Yamashita

    Computational Psychiatry 2023年1月20日

    DOI: 10.5334/cpsy.93  

  4. Neural network modeling of altered facial expression recognition in autism spectrum disorders based on predictive processing framework 査読有り

    Yuta Takahashi, Shingo Murata, Hayato Idei, Hiroaki Tomita, Yuichi Yamashita

    Scientific Reports 11 (1) 2021年12月

    出版者・発行元: Springer Science and Business Media LLC

    DOI: 10.1038/s41598-021-94067-x  

    eISSN:2045-2322

    詳細を見る 詳細を閉じる

    The mechanism underlying the emergence of emotional categories from visual facial expression information during the developmental process is largely unknown. Therefore, this study proposes a system-level explanation for understanding the facial emotion recognition process and its alteration in autism spectrum disorder (ASD) from the perspective of predictive processing theory. Predictive processing for facial emotion recognition was implemented as a hierarchical recurrent neural network (RNN). The RNNs were trained to predict the dynamic changes of facial expression movies for six basic emotions without explicit emotion labels as a developmental learning process, and were evaluated by the performance of recognizing unseen facial expressions for the test phase. In addition, the causal relationship between the network characteristics assumed in ASD and ASD-like cognition was investigated. After the developmental learning process, emotional clusters emerged in the natural course of self-organization in higher-level neurons, even though emotional labels were not explicitly instructed. In addition, the network successfully recognized unseen test facial sequences by adjusting higher-level activity through the process of minimizing precision-weighted prediction error. In contrast, the network simulating altered intrinsic neural excitability demonstrated reduced generalization capability and impaired emotional clustering in higher-level neurons. Consistent with previous findings from human behavioral studies, an excessive precision estimation of noisy details underlies this ASD-like cognition. These results support the idea that impaired facial emotion recognition in ASD can be explained by altered predictive processing, and provide possible insight for investigating the neurophysiological basis of affective contact.

  5. Machine learning to reveal hidden risk combinations for the trajectory of posttraumatic stress disorder symptoms 国際誌 査読有り

    Yuta Takahashi, Kazuki Yoshizoe, Masao Ueki, Gen Tamiya, Yu Zhiqian, Yusuke Utsumi, Atsushi Sakuma, Koji Tsuda, Atsushi Hozawa, Ichiro Tsuji, Hiroaki Tomita

    Scientific Reports 10 (1) 21726-21726 2020年12月

    出版者・発行元: Springer Science and Business Media LLC

    DOI: 10.1038/s41598-020-78966-z  

    eISSN:2045-2322

    詳細を見る 詳細を閉じる

    <title>Abstract</title>The nature of the recovery process of posttraumatic stress disorder (PTSD) symptoms is multifactorial. The Massive Parallel Limitless-Arity Multiple-testing Procedure (MP-LAMP), which was developed to detect significant combinational risk factors comprehensively, was utilized to reveal hidden combinational risk factors to explain the long-term trajectory of the PTSD symptoms. In 624 population-based subjects severely affected by the Great East Japan Earthquake, 61 potential risk factors encompassing sociodemographics, lifestyle, and traumatic experiences were analyzed by MP-LAMP regarding combinational associations with the trajectory of PTSD symptoms, as evaluated by the Impact of Event Scale-Revised score after eight years adjusted by the baseline score. The comprehensive combinational analysis detected 56 significant combinational risk factors, including 15 independent variables, although the conventional bivariate analysis between single risk factors and the trajectory detected no significant risk factors. The strongest association was observed with the combination of short resting time, short walking time, unemployment, and evacuation without preparation (adjusted <italic>P</italic> value = 2.2 × 10−4, and raw <italic>P</italic> value = 3.1 × 10−9). Although short resting time had no association with the poor trajectory, it had a significant interaction with short walking time (<italic>P</italic> value = 1.2 × 10−3), which was further strengthened by the other two components (<italic>P</italic> value = 9.7 × 10−5). Likewise, components that were not associated with a poor trajectory in bivariate analysis were included in every observed significant risk combination due to their interactions with other components. Comprehensive combination detection by MP-LAMP is essential for explaining multifactorial psychiatric symptoms by revealing the hidden combinations of risk factors.

  6. Machine learning for effectively avoiding overfitting is a crucial strategy for the genetic prediction of polygenic psychiatric phenotypes 査読有り

    Yuta Takahashi, Masao Ueki, Gen Tamiya, Soichi Ogishima, Kengo Kinoshita, Atsushi Hozawa, Naoko Minegishi, Fuji Nagami, Kentaro Fukumoto, Kotaro Otsuka, Kozo Tanno, Kiyomi Sakata, Atsushi Shimizu, Makoto Sasaki, Kenji Sobue, Shigeo Kure, Masayuki Yamamoto, Hiroaki Tomita

    Translational Psychiatry 10 (1) 2020年12月

    出版者・発行元: Springer Science and Business Media LLC

    DOI: 10.1038/s41398-020-00957-5  

    eISSN:2158-3188

  7. Improved metabolomic data-based prediction of depressive symptoms using nonlinear machine learning with feature selection 査読有り

    Yuta Takahashi, Masao Ueki, Makoto Yamada, Gen Tamiya, Ikuko N. Motoike, Daisuke Saigusa, Miyuki Sakurai, Fuji Nagami, Soichi Ogishima, Seizo Koshiba, Kengo Kinoshita, Masayuki Yamamoto, Hiroaki Tomita

    Translational Psychiatry 10 (1) 2020年12月

    出版者・発行元: Springer Science and Business Media LLC

    DOI: 10.1038/s41398-020-0831-9  

    eISSN:2158-3188

    詳細を見る 詳細を閉じる

    <title>Abstract</title>To solve major limitations in algorithms for the metabolite-based prediction of psychiatric phenotypes, a novel prediction model for depressive symptoms based on nonlinear feature selection machine learning, the Hilbert–Schmidt independence criterion least absolute shrinkage and selection operator (HSIC Lasso) algorithm, was developed and applied to a metabolomic dataset with the largest sample size to date. In total, 897 population-based subjects were recruited from the communities affected by the Great East Japan Earthquake; 306 metabolite features (37 metabolites identified by nuclear magnetic resonance measurements and 269 characterized metabolites based on the intensities from mass spectrometry) were utilized to build prediction models for depressive symptoms as evaluated by the Center for Epidemiologic Studies-Depression Scale (CES-D). The nested fivefold cross-validation was used for developing and evaluating the prediction models. The HSIC Lasso-based prediction model showed better predictive power than the other prediction models, including Lasso, support vector machine, partial least squares, random forest, and neural network. <sc>l</sc>-leucine, 3-hydroxyisobutyrate, and gamma-linolenyl carnitine frequently contributed to the prediction. We have demonstrated that the HSIC Lasso-based prediction model integrating nonlinear feature selection showed improved predictive power for depressive symptoms based on metabolome data as well as on risk metabolites based on nonlinear statistics in the Japanese population. Further studies should use HSIC Lasso-based prediction models with different ethnicities to investigate the generality of each risk metabolite for predicting depressive symptoms.

  8. A single nucleotide polymorphism (−250 A/C) of the GFAP gene is associated with brain structures and cerebral blood flow 査読有り

    Yuta Takahashi, Hikaru Takeuchi, Mai Sakai, Zhiqian Yu, Yoshie Kikuchi, Fumiaki Ito, Hiroo Matsuoka, Osamu Tanabe, Jun Yasuda, Yasuyuki Taki, Ryuta Kawashima, Hiroaki Tomita

    Psychiatry and Clinical Neurosciences 74 (1) 49-55 2020年1月

    出版者・発行元: Wiley

    DOI: 10.1111/pcn.12932  

    ISSN:1323-1316

    eISSN:1440-1819

  9. Linking Activation of Microglia and Peripheral Monocytic Cells to the Pathophysiology of Psychiatric Disorders 査読有り

    Yuta Takahashi, Zhiqian Yu, Mai Sakai, Hiroaki Tomita

    Frontiers in Cellular Neuroscience 10 (JUN) 2016年6月3日

    出版者・発行元: Frontiers Media S.A.

    DOI: 10.3389/fncel.2016.00144  

    ISSN:1662-5102

  10. Upper gastrointestinal symptoms predictive of candida esophagitis and erosive esophagitis in HIV and non-HIV patients: An endoscopy-based cross-sectional study of 6011 patients 査読有り

    Yuta Takahashi, Naoyoshi Nagata, Takuro Shimbo, Takeshi Nishijima, Koji Watanabe, Tomonori Aoki, Katsunori Sekine, Hidetaka Okubo, Kazuhiro Watanabe, Toshiyuki Sakurai, Chizu Yokoi, Akio Mimori, Shinichi Oka, Naomi Uemura, Junichi Akiyama

    Medicine (United States) 94 (47) e2138 2015年11月1日

    出版者・発行元: Lippincott Williams and Wilkins

    DOI: 10.1097/MD.0000000000002138  

    ISSN:1536-5964 0025-7974

  11. Long-term trends in esophageal candidiasis prevalence and associated risk factors with or without HIV infection: Lessons from an endoscopic study of 80,219 patients 査読有り

    Yuta Takahashi, Naoyoshi Nagata, Takuro Shimbo, Takeshi Nishijima, Koji Watanabe, Tomonori Aoki, Katsunori Sekine, Hidetaka Okubo, Kazuhiro Watanabe, Toshiyuki Sakurai, Chizu Yokoi, Masao Kobayakawa, Hirohisa Yazaki, Katsuji Teruya, Hiroyuki Gatanaga, Yoshimi Kikuchi, Sohtaro Mine, Toru Igari, Yuko Takahashi, Akio Mimori, Shinichi Oka, Junichi Akiyama, Naomi Uemura

    PLoS ONE 10 (7) 2015年7月24日

    出版者・発行元: Public Library of Science

    DOI: 10.1371/journal.pone.0133589  

    ISSN:1932-6203

  12. Calculation of approximate heart rate variability indicators based on low-resolution heart rate data provided by widely used commercially available wearable devices

    Xue Li, Goh Onoguchi, Hiroshi Komatsu, Chiaki Ono, Noriko Warita, Zhiqian Yu, Atsuko Nagaoka, Sho Horikoshi, Kenji Iwabuchi, Kohei Fuji, Mizuki Hino, Yuta Takahashi, Hisashi Ohseto, Natsuko Kobayashi, Saya Kikuchi, Yasuto Kunii, Taku Obara, Shinichi Kuriyama, Noriyasu Homma, Parashkev Nachev, Akinori Ito, Hiroaki Tomita

    Biomedical Signal Processing and Control 112 108579-108579 2026年2月

    出版者・発行元: Elsevier BV

    DOI: 10.1016/j.bspc.2025.108579  

    ISSN:1746-8094

  13. Digital Twin Brain Generating Multitask Behavior from Individual Connectome for Psychiatric Treatment Simulation

    Yuta Takahashi, Takafumi Soda, Hiroaki Tomita, Yuichi Yamashita

    PsyArXiv 2025年8月19日

    出版者・発行元: Center for Open Science

    DOI: 10.31234/osf.io/4uqta_v1  

    詳細を見る 詳細を閉じる

    <p>Personalized psychiatry demands digital twins that translate individual brain connectomes into predictions of multidomain functions (e.g., emotion, cognition) and treatment responses. We present a digital twin brain framework where a Hypernetwork, using resting-state connectomes, generates parameters for a Main recurrent network. This enables the Main network to jointly simulate behavioral and blood-oxygen-level-dependent (BOLD) time series across multiple tasks. Validated in a transdiagnostic cohort (n=228), our model demonstrated high-fidelity prediction of behavioral choices (&amp;gt;90% accuracy), reaction times (r&amp;gt;0.85), and distributed BOLD activation (r=0.84) during affective and cognitive tasks, capturing individual neurobehavioral dynamics. Leveraging the model's differentiability, we identified gradient-based connectome manipulation targets (e.g., limbic, parietal, prefrontal) to selectively modulate affective or cognitive functions. Crucially, in-silico trials simulating these manipulations reproduced realistic inter-individual variability in treatment effects (effect size range &amp;gt;2 SD). This establishes our digital twin brain as a quantitative, mechanistic platform for simulating and designing personalized psychiatric interventions.</p>

  14. CPMSイエロー基準による頻回の血液検査が続き効果的だったクロザピンの中止を希望した治療抵抗性統合失調症の1例

    佐久間 篤, 五十嵐 江美, 内海 裕介, 菊地 佑樹, 畠山 拓志, 高橋 雄太, 小松 浩, 菊地 紗耶, 富田 博秋

    総合病院精神医学 36 (3) 241-247 2024年7月

    出版者・発行元: (一社)日本総合病院精神医学会

    ISSN:0915-5872

  15. Digital Twin Brain Simulator: Harnessing Primate ECoG Data for Real-Time Consciousness Monitoring and Virtual Intervention

    Yuta Takahashi, Hayato Idei, Misako Komatsu, Jun Tani, Hiroaki Tomita, Yuichi Yamashita

    2024年5月19日

    出版者・発行元: Cold Spring Harbor Laboratory

    DOI: 10.1101/2024.05.17.594789  

    詳細を見る 詳細を閉じる

    ABSTRACT At the forefront of bridging computational brain modeling with personalized medicine, this study introduces a novel, real-time, electrocorticogram (ECoG) simulator based on the digital twin brain concept. Utilizing advanced data assimilation techniques, specifically a Variational Bayesian Recurrent Neural Network model with hierarchical latent units, the simulator dynamically predicts ECoG signals reflecting real-time brain latent states. By assimilating broad ECoG signals from Macaque monkeys across awake and anesthetized conditions, the model successfully updated its latent states in real-time, enhancing the precision of ECoG signal simulations. Behind the successful data assimilation, a self-organization of latent states in the model was observed, reflecting brain states and individuality. This self-organization facilitated simulation of virtual drug administration and uncovered functional networks underlying changes in brain function during anesthesia. These results show that the proposed model is not only capable of simulating brain signals in real-time with high accuracy, but is also useful for revealing underlying information processing dynamics.

  16. Comprehensive evaluation of machine learning algorithms for predicting sleep–wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability

    Xue Li, Chiaki Ono, Noriko Warita, Tomoka Shoji, Takashi Nakagawa, Hitomi Usukura, Zhiqian Yu, Yuta Takahashi, Kei Ichiji, Norihiro Sugita, Natsuko Kobayashi, Saya Kikuchi, Ryoko Kimura, Yumiko Hamaie, Mizuki Hino, Yasuto Kunii, Keiko Murakami, Mami Ishikuro, Taku Obara, Tomohiro Nakamura, Fuji Nagami, Takako Takai, Soichi Ogishima, Junichi Sugawara, Tetsuro Hoshiai, Masatoshi Saito, Gen Tamiya, Nobuo Fuse, Susumu Fujii, Masaharu Nakayama, Shinichi Kuriyama, Masayuki Yamamoto, Nobuo Yaegashi, Noriyasu Homma, Hiroaki Tomita

    Frontiers in Psychiatry 14 2023年6月6日

    出版者・発行元: Frontiers Media SA

    DOI: 10.3389/fpsyt.2023.1104222  

    eISSN:1664-0640

    詳細を見る 詳細を閉じる

    Introduction Perinatal women tend to have difficulties with sleep along with autonomic characteristics. This study aimed to identify a machine learning algorithm capable of achieving high accuracy in predicting sleep–wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability (HRV). Methods Nine HRV indicators (features) and sleep–wake conditions of 154 pregnant women were measured for 1 week, from the 23rd to the 32nd weeks of pregnancy. Ten machine learning and three deep learning methods were applied to predict three types of sleep–wake conditions (wake, shallow sleep, and deep sleep). In addition, the prediction of four conditions, in which the wake conditions before and after sleep were differentiated—shallow sleep, deep sleep, and the two types of wake conditions—was also tested. Results and Discussion In the test for predicting three types of sleep–wake conditions, most of the algorithms, except for Naïve Bayes, showed higher areas under the curve (AUCs; 0.82–0.88) and accuracy (0.78–0.81). The test using four types of sleep–wake conditions with differentiation between the wake conditions before and after sleep also resulted in successful prediction by the gated recurrent unit with the highest AUC (0.86) and accuracy (0.79). Among the nine features, seven made major contributions to predicting sleep–wake conditions. Among the seven features, “the number of interval differences of successive RR intervals greater than 50 ms (NN50)” and “the proportion dividing NN50 by the total number of RR intervals (pNN50)” were useful to predict sleep–wake conditions unique to pregnancy. These findings suggest alterations in the vagal tone system specific to pregnancy.

  17. 白血球数4000/μL未満による頻回の血液検査が続きクロザピン中止を希望した治療抵抗性統合失調症の一例

    佐久間 篤, 五十嵐 江美, 内海 裕介, 菊地 佑樹, 畠山 拓志, 高橋 雄太, 小松 浩, 菊地 紗耶, 富田 博秋

    精神神経学雑誌 (2023特別号) S695-S695 2023年6月

    出版者・発行元: (公社)日本精神神経学会

    ISSN:0033-2658

  18. 白血球数4000/μL未満による頻回の血液検査が続きクロザピン中止を希望した治療抵抗性統合失調症の一例

    佐久間 篤, 五十嵐 江美, 内海 裕介, 菊地 佑樹, 畠山 拓志, 高橋 雄太, 小松 浩, 菊地 紗耶, 富田 博秋

    精神神経学雑誌 (2023特別号) S695-S695 2023年6月

    出版者・発行元: (公社)日本精神神経学会

    ISSN:0033-2658

  19. AIを用いたうつ病の病態解明と個別化精神医療に向けた展望

    富田博秋, 兪志前, 李雪, 高橋雄太

    臨床精神薬理特集「AI(人工知能)を用いた精神科薬物療法の近未来を問う」 26 (3) 2023年

  20. Plasma metabolic disturbances during pregnancy and postpartum in women with depression. 国際誌 査読有り

    Zhiqian Yu, Naomi Matsukawa, Daisuke Saigusa, Ikuko N Motoike, Chiaki Ono, Yasunobu Okamura, Tomomi Onuma, Yuta Takahashi, Mai Sakai, Hisaaki Kudo, Taku Obara, Keiko Murakami, Matusyuki Shirota, Saya Kikuchi, Natsuko Kobayashi, Yoshie Kikuchi, Junichi Sugawara, Naoko Minegishi, Soichi Ogishima, Kengo Kinoshita, Masayuki Yamamoto, Nobuo Yaegashi, Shinichi Kuriyama, Seizo Koshiba, Hiroaki Tomita

    iScience 25 (12) 105666-105666 2022年12月22日

    DOI: 10.1016/j.isci.2022.105666  

    詳細を見る 詳細を閉じる

    Examining plasma metabolic profiling during pregnancy and postpartum could help clinicians understand the risk factors for postpartum depression (PPD) development. This analysis targeted paired plasma metabolites in mid-late gestational and 1 month postpartum periods in women with (n = 209) or without (n = 222) PPD. Gas chromatogram-mass spectrometry was used to analyze plasma metabolites at these two time points. Among the 170 objected plasma metabolites, principal component analysis distinguished pregnancy and postpartum metabolites but failed to discriminate women with and without PPD. Compared to women without PPD, those with PPD exhibited 37 metabolites with disparate changes during pregnancy and the 1-month postpartum period and an enriched citrate cycle. Machine learning and multivariate statistical analysis identified two or three compounds that could be potential biomarkers for PPD prediction during pregnancy. Our findings suggest metabolic disturbances in women with depression and may help to elucidate metabolic processes associated with PPD development.

  21. Publisher Correction: Neural network modeling of altered facial expression recognition in autism spectrum disorders based on predictive processing framework (Scientific Reports, (2021), 11, 1, (14684), 10.1038/s41598-021-94067-x)

    Yuta Takahashi, Shingo Murata, Hayato Idei, Hiroaki Tomita, Yuichi Yamashita

    Scientific Reports 11 (1) 2021年12月1日

    出版者・発行元: Nature Research

    DOI: 10.1038/s41598-021-97145-2  

    ISSN:2045-2322

  22. Heart Rate Information-Based Machine Learning Prediction of Emotions Among Pregnant Women. 国際誌 査読有り

    Xue Li, Chiaki Ono, Noriko Warita, Tomoka Shoji, Takashi Nakagawa, Hitomi Usukura, Zhiqian Yu, Yuta Takahashi, Kei Ichiji, Norihiro Sugita, Natsuko Kobayashi, Saya Kikuchi, Yasuto Kunii, Keiko Murakami, Mami Ishikuro, Taku Obara, Tomohiro Nakamura, Fuji Nagami, Takako Takai, Soichi Ogishima, Junichi Sugawara, Tetsuro Hoshiai, Masatoshi Saito, Gen Tamiya, Nobuo Fuse, Shinichi Kuriyama, Masayuki Yamamoto, Nobuo Yaegashi, Noriyasu Homma, Hiroaki Tomita

    Frontiers in psychiatry 12 799029-799029 2021年

    DOI: 10.3389/fpsyt.2021.799029  

    詳細を見る 詳細を閉じる

    In this study, the extent to which different emotions of pregnant women can be predicted based on heart rate-relevant information as indicators of autonomic nervous system functioning was explored using various machine learning algorithms. Nine heart rate-relevant autonomic system indicators, including the coefficient of variation R-R interval (CVRR), standard deviation of all NN intervals (SDNN), and square root of the mean squared differences of successive NN intervals (RMSSD), were measured using a heart rate monitor (MyBeat) and four different emotions including "happy," as a positive emotion and "anxiety," "sad," "frustrated," as negative emotions were self-recorded on a smartphone application, during 1 week starting from 23rd to 32nd weeks of pregnancy from 85 pregnant women. The k-nearest neighbor (k-NN), support vector machine (SVM), logistic regression (LR), random forest (RF), naïve bayes (NB), decision tree (DT), gradient boosting trees (GBT), stochastic gradient descent (SGD), extreme gradient boosting (XGBoost), and artificial neural network (ANN) machine learning methods were applied to predict the four different emotions based on the heart rate-relevant information. To predict four different emotions, RF also showed a modest area under the receiver operating characteristic curve (AUC-ROC) of 0.70. CVRR, RMSSD, SDNN, high frequency (HF), and low frequency (LF) mostly contributed to the predictions. GBT displayed the second highest AUC (0.69). Comprehensive analyses revealed the benefits of the prediction accuracy of the RF and GBT methods and were beneficial to establish models to predict emotions based on autonomic nervous system indicators. The results implicated SDNN, RMSSD, CVRR, LF, and HF as important parameters for the predictions.

  23. 数理モデルと情報科学技術を用いた生物学的知見と精神症状の橋渡し研究

    高橋 雄太

    日本生物学的精神医学会誌 31 (4) 188-188 2020年12月

    出版者・発行元: 日本生物学的精神医学会

    ISSN:2186-6619

    eISSN:2186-6465

  24. 最近の多様化する災害と総合病院精神医学の対応について 災害医療に従事した病院職員に対するメンタルヘルス支援 縦断調査からみえてきた課題

    佐久間 篤, 内海 裕介, 臼倉 瞳, 五十嵐 江美, 田坂 有香, 高橋 雄太, 菊地 紗耶, 本多 奈美, 國井 泰人, 富田 博秋

    総合病院精神医学 32 (Suppl.) S-68 2020年11月

    出版者・発行元: (一社)日本総合病院精神医学会

    ISSN:0915-5872

  25. 個別化精神医療確立に向けたバイオバンク整備の展望 バイオバンク情報への機械学習の導入

    高橋 雄太, 植木 優夫, 田宮 元, 富田 博秋

    精神神経学雑誌 (2020特別号) S247-S247 2020年9月

    出版者・発行元: (公社)日本精神神経学会

    ISSN:0033-2658

  26. 予測符号化理論に基づくニューラルネットワークを用いた自閉スペクトラム症における表情認知特性に関する検討

    高橋 雄太, 村田 真悟, 出井 勇人, 富田 博秋, 山下 祐一

    日本神経精神薬理学会年会・日本生物学的精神医学会年会・日本精神薬学会総会・学術集会合同年会プログラム 50回・42回・4回 183-183 2020年8月

    出版者・発行元: 日本神経精神薬理学会・日本生物学的精神医学会・日本精神薬学会

  27. The Impact of Health Consciousness on the Association Between Walking Durations and Mental Health Conditions After a Disaster: a Cross-Sectional Study. 国際誌 査読有り

    Yusuke Utsumi, Harumi Nemoto, Naoki Nakaya, Tomohiro Nakamura, Naho Tsuchiya, Akira Narita, Mana Kogure, Tomomi Suzuki, Moe Seto, Mitsuaki Katayanagi, Junko Okuyama, Atsushi Sakuma, Nami Honda, Yumi Sugawara, Halley Kaye-Kauderer, Yuta Takahashi, Akemi Kayama, Yoshihisa Kakuto, Masahiro Kohzuki, Atsushi Hozawa, Ichiro Tsuji, Hiroaki Tomita

    Sports medicine - open 6 (1) 30-30 2020年7月16日

    DOI: 10.1186/s40798-020-00259-6  

    詳細を見る 詳細を閉じる

    BACKGROUND: In communities affected by a disaster, walking can be a feasible form of physical exercise to improve physical and mental health conditions. However, there is limited evidence to support relationships between walking habits and mental health conditions in post-disaster settings. Cross-sectional epidemiological data obtained from a questionnaire survey (conducted in October 2017) of a community affected by the 2011 Great East Japan Earthquake (GEJE) was analyzed to evaluate the relationships. METHODS: Participants included individuals over 20 years of age (N = 718) from Shichigahama town in Miyagi prefecture, whose houses were significantly damaged by the GEJE. Their mental health conditions were assessed by the Kessler Psychological Distress Scale (K6), the Center for Epidemiologic Studies Depression Scale (CES-D), and the Impact of Event Scale-Revised (IES-R). Additionally, the questionnaire asked the participants spent duration walking on average and their walking purpose by the following items: (1) longer than 60 min per day, (2) between 30 and 60 min per day, or (3) less than 30 min per day, and whether they walked to maintain healthy living habits (health-conscious walkers) or merely for transportation without considering health consequences (non-health-conscious walkers). These information and mental health indicators were analyzed using analysis of covariance (ANCOVA). RESULTS: Among the three walking duration groups of health-conscious walkers, there were significant differences in CES-D and K6 scores (p = 0.01 and p = 0.04), but not in IES-R scores, considering age, gender, and alcohol drinking habits as covariates. CES-D score was significantly higher among short walkers (p = 0.004). Among the three walking duration groups of non-health-conscious walkers, there were significant differences in avoidance symptoms, the subdomain of IES-R (p = 0.01), but not in CES-D, K6, and total IES-R scores, considering the variants. CONCLUSION: Our study suggests that walking durations may positively affect mood, but not PTSR, only when walking is performed with the purpose of maintaining healthy living habits. Walking durations were negatively associated with avoidance symptoms among non-health-conscious walkers in the community affected by the GEJE, indicating that the disaster may have had a long-lasting impact on walking habits.

  28. ゲノムワイド遺伝子多型データを用いた機械学習によるうつ状態脆弱性の予測

    高橋 雄太, 植木 優夫, 田宮 元, 荻島 創一, 長神 風二, 福本 健太郎, 大塚 耕太郎, 山本 雅之, 富田 博秋

    精神神経学雑誌 (2019特別号) S609-S609 2019年6月

    出版者・発行元: (公社)日本精神神経学会

    ISSN:0033-2658

  29. メタボロームデータを用いた非線形変数選択機械学習によるうつ状態の予測

    高橋 雄太, 植木 優夫, 山田 誠, 田宮 元, 元池 育子, 三枝 大輔, 櫻井 美由紀, 長神 風二, 小柴 生造, 木下 賢吾, 山本 雅之, 富田 博秋

    精神神経学雑誌 (2019特別号) S609-S609 2019年6月

    出版者・発行元: (公社)日本精神神経学会

    ISSN:0033-2658

  30. 東日本大震災被災者における外傷後ストレス障害症状の変化を予測する因子に関する,機械学習を用いた組み合わせの検討

    高橋雄太, 高橋雄太, 高橋雄太, 美添一樹, 植木優夫, 植木優夫, 田宮元, 田宮元, 富田博秋, 富田博秋, 富田博秋

    日本生物学的精神医学会(Web) 41st 2019年

  31. Polymorphisms in the microglial marker molecule CX3CR1 affect the blood volume of the human brain 査読有り

    Mai Sakai, Hikaru Takeuchi, Zhiqian Yu, Yoshie Kikuchi, Chiaki Ono, Yuta Takahashi, Fumiaki Ito, Hiroo Matsuoka, Osamu Tanabe, Jun Yasuda, Yasuyuki Taki, Ryuta Kawashima, Hiroaki Tomita

    Psychiatry and Clinical Neurosciences 72 (6) 409-422 2018年6月1日

    出版者・発行元: Blackwell Publishing

    DOI: 10.1111/pcn.12649  

    ISSN:1323-1316

    eISSN:1440-1819

  32. グリア線維酸性蛋白質遺伝子多型の脳構造への影響の検討 精神疾患感受性メカニズムの理解に向けて

    高橋 雄太, 伊藤 文晃, 竹内 光, 坂井 舞, 兪 志前, 松岡 洋夫, 瀧 靖之, 川島 隆太, 富田 博秋

    精神神経学雑誌 (2017特別号) S622-S622 2017年6月

    出版者・発行元: (公社)日本精神神経学会

    ISSN:0033-2658

  33. Microglial production of TNF-alpha is a key element of sustained fear memory 査読有り

    Zhiqian Yu, Hotaka Fukushima, Chiaki Ono, Mai Sakai, Yoshiyuki Kasahara, Yoshie Kikuchi, Nicole Gunawansa, Yuta Takahashi, Hiroo Matsuoka, Satoshi Kida, Hiroaki Tomita

    Brain, Behavior, and Immunity 59 313-321 2017年1月

    出版者・発行元: Elsevier BV

    DOI: 10.1016/j.bbi.2016.08.011  

    ISSN:0889-1591

  34. リチウム投与下でのマウスミクログリアと末梢単球の遺伝子発現プロフィール変化の検討

    高橋 雄太, 兪 志前, 坂井 舞, 富田 博秋

    日本神経精神薬理学会年会プログラム 46回 218-218 2016年7月

    出版者・発行元: (一社)日本神経精神薬理学会

  35. 恐怖記憶の持続におけるミクログリア由来TNF-αの発現(Role of microglial TNF-alpha in fear memory formation)

    兪 志前, 福島 穂高, 小野 千晶, 坂井 舞, 笠原 好之, 菊地 淑恵, Gunawansa Nicole, 高橋 雄太, 松岡 洋夫, 喜田 聡, 富田 博秋

    日本神経精神薬理学会年会プログラム 46回 238-238 2016年7月

    出版者・発行元: (一社)日本神経精神薬理学会

  36. OLIG2遺伝子多型(rs1059004)が脳白質の神経線維束の拡散異方性及び安静時脳灌流量に及ぼす効果の検討

    小松 浩, 竹内 光, 菊地 淑恵, 小野 千晶, 坂井 舞, 小高 晃, 舩越 俊一, 大野 高志, 角藤 芳久, 高橋 雄太, 松岡 洋夫, 瀧 靖之, 川島 隆太, 富田 博秋

    精神神経学雑誌 (2016特別号) S367-S367 2016年6月

    出版者・発行元: (公社)日本精神神経学会

    ISSN:0033-2658

  37. リチウム投与下でのミクログリアと単球の遺伝子発現プロフィールの検討

    高橋 雄太, 兪 志前, 坂井 舞, 小松 浩, 伊藤 文晃, 松岡 洋夫, 富田 博秋

    精神神経学雑誌 (2016特別号) S481-S481 2016年6月

    出版者・発行元: (公社)日本精神神経学会

    ISSN:0033-2658

  38. Microglial Gene Expression Alterations in the Brains of Patients with Psychiatric Disorders 査読有り

    Mai Sakai, Yuta Takahashi, Zhiqian Yu, Hiroaki Tomita

    Advances in Neuroimmune Biology 6 (2) 83-93 2016年

    出版者・発行元: IOS Press

    DOI: 10.3233/NIB-160110  

    ISSN:1878-948X

    eISSN:1878-9498

︎全件表示 ︎最初の5件までを表示

MISC 2

  1. 健常成人1212人におけるGFAP多型と脳機能画像との相関の検討

    高橋雄太, 高橋雄太, 坂井舞, 兪志前, 富田博秋

    日本生物学的精神医学会(Web) 38th 2016年

  2. 恐怖記憶の持続におけるミクログリア由来TNF-αの発現

    兪志前, 兪志前, 福島穂高, 小野千晶, 坂井舞, 笠原好之, 高橋雄太, 松岡洋夫, 喜田聡, 富田博秋, 富田博秋

    日本生物学的精神医学会(Web) 38th 2016年

講演・口頭発表等 10

  1. 精神医学データに対する機械学習的アプローチ 招待有り

    高橋雄太

    科研費シンポジウム「データサイエンス・統計学における方法論と応用の新展開」 2021年12月

  2. Prediction of depressive state based on metabolome data of 897 subjects utilizing a non-linear machine learning model with feature selection

    WFSBP 2018 KOBE 2018年9月

  3. Machine-learning prediction of psychiatric diseases based on genomic/metabolomic data

    WFSBP 2018 KOBE 2018年9月

  4. バイオバンク情報への機械学習の導入

    第116回日本精神神経学会学術総会シンポジウム「個別化精神医療確立に向けたバイオバンク整備の展望」

  5. 脳内領域間機能的結合性の変調が自閉症症状を出現させるメカニズムについての計算論的精神医学研究

    高橋雄太

    第43回日本生物学的精神医学会年会 2021年7月

  6. メタボロームデータを用いた非線形変数選択機械学習によるうつ状態の予測

    第115回日本精神神経学会学術総会 2019年6月

  7. ゲノムワイド遺伝子多型データを用いた機械学習によるうつ状態脆弱性の予測

    第115回日本精神神経学会学術総会 2019年6月

  8. 東日本大震災被災者における外傷後ストレス障害症状の変化を予測する因子に関する、機械学習を用いた組み合わせの検討

    2019年6月

  9. Prediction of susceptibility to depression utilizing a machine learning model based on genome wide single nucleotide polymorphism data

    第40回日本生物学的精神医学会・第61回日本神経化学会大会 合同年会 2018年9月

  10. 予測符号化理論に基づくニューラルネットワークを用いた自閉スペクトラム症における表情認知特性に関する検討

    第42回日本生物学的精神医学会年会

︎全件表示 ︎最初の5件までを表示

共同研究・競争的資金等の研究課題 4

  1. デジタルツイン脳で可能になる精神医学研究

    2025年4月 ~ 2030年3月

  2. データ駆動特徴量抽出と脳計算理論の融合による精神疾患個別化治療シミュレーション

    2024年4月 ~ 2028年3月

  3. 個人の脳領域間の結合性を反映したニューラルネットワークによる自閉症認知特性の再現

    高橋 雄太

    2021年4月1日 ~ 2024年3月31日

    詳細を見る 詳細を閉じる

    本研究課題では、頭部MRIデータベースを用いて、各被験者の脳領域間の結合性パターンを一対一対応させた人工ニューラルネットワークを用意する。そして、オリジナルの被験者の自閉症的な認知特性と、対応する人工ニューラルネットワークにおける認知特性が類似することを確認する。さらに、人工ニューラルネットワークにおける神経活動を調べることで、脳領域間の結合性変化が自閉症症状を引き起こすメカニズムを検討する。 初年度は、頭部MRIデータベースとして、Autism Brain Imaging Data Exchange (ABIDE)データを入手した。脳領域間の結合性については、このデータベースにおける機能的結合性指標を用いることとした。被験者の機能的結合性の分布に人工ニューラルネットワークのパラメータを対応させる方法について検討した。そして、人工ニューラルネットワークに表情から感情を認識する課題のシミュレーションを行い、感情という高次情報を抽出する能力、感情認識を汎化させる能力について評価した。人工ニューラルネットワークで観察される自閉症的な認知特性の背景には、機能的結合性に対応するパラメータ間の相互作用が関わっていることがわかった。人工ニューラルネットワークの神経活動を観察することで、このパラメータの相互作用を引き起こすメカニズムとして、内部モデルと知覚情報への依存度のバランスと、知覚情報の予測の汎化能が複雑に影響しあっていることがわかった。そして、人工ニューラルネットワークで自閉症的な認知傾向を示す場合には、対応する被験者でも自閉スぺクラム障害の診断がなされている傾向が示された。これにより、人工ニューラルネットワークで観察されたパラメータ間の相互作用や自閉症的な認知傾向は、頭部MRIデータベースによって生物学的な妥当性が検証された。

  4. 自由エネルギー原理にもとづく多感覚・行動・脳波信号の統合的シミュレーションによる精神疾患病態解明

    2023年4月 ~ 2024年3月