Updated on 2023/08/22

写真a

 
FURUKAWA Taiki
 
Organization
Nagoya University Hospital Medical IT Center Lecturer
Title
Lecturer

Degree 1

  1. 博士(医学) ( 2021.3   名古屋大学 ) 

Research Areas 2

  1. Life Science / Respiratory medicine

  2. Informatics / Life, health and medical informatics  / 医療情報学

Research History 2

  1. Nagoya University   Medical IT Center, Hospital   Designated assistant professor

    2021.4

  2. RIKEN

    2021.4

Professional Memberships 5

  1. 日本メディカルAI学会

    2023.6

  2. Japan Association for Medical Informatics

    2021.5

  3. The Japanese Society for Artificial Intelligence

    2021.4

  4. Japanese Respiratory Society

    2013.10

  5. Japanese Society of Allergology

Committee Memberships 2

  1. 厚生労働省難治性疾患等政策研究事業「びまん性肺疾患に関する調査研究」班   研究協力者  

    2023.4   

      More details

    Committee type:Other

  2. 日本呼吸器学会びまん性肺疾患MDD診断保険収載検討タスクフォース   幹事  

    2021.10   

      More details

    Committee type:Academic society

Awards 1

  1. Fukuchi Award

    2023.11   Asian Pacific Society of Respirology (APSR)   A comprehensible machine learning tool to differentially diagnose idiopathic pulmonary fibrosis from other chronic interstitial lung diseases

    Furukawa, T, Oyama, S, Yokota, H, Kondoh, Y, Kataoka, K, Johkoh, T, Fukuoka, J, Hashimoto, N, Sakamoto, K, Shiratori, Y, Hasegawa, Y

 

Papers 16

  1. A comprehensible machine learning tool to differentially diagnose idiopathic pulmonary fibrosis from other chronic interstitial lung diseases. Reviewed International journal

    Taiki Furukawa, Shintaro Oyama, Hideo Yokota, Yasuhiro Kondoh, Kensuke Kataoka, Takeshi Johkoh, Junya Fukuoka, Naozumi Hashimoto, Koji Sakamoto, Yoshimune Shiratori, Yoshinori Hasegawa

    Respirology (Carlton, Vic.)   Vol. 27 ( 9 ) page: 739 - 746   2022.9

     More details

    Authorship:Lead author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)  

    BACKGROUND AND OBJECTIVE: Idiopathic pulmonary fibrosis (IPF) has poor prognosis, and the multidisciplinary diagnostic agreement is low. Moreover, surgical lung biopsies pose comorbidity risks. Therefore, using data from non-invasive tests usually employed to assess interstitial lung diseases (ILDs), we aimed to develop an automated algorithm combining deep learning and machine learning that would be capable of detecting and differentiating IPF from other ILDs. METHODS: We retrospectively analysed consecutive patients presenting with ILD between April 2007 and July 2017. Deep learning was used for semantic image segmentation of HRCT based on the corresponding labelled images. A diagnostic algorithm was then trained using the semantic results and non-invasive findings. Diagnostic accuracy was assessed using five-fold cross-validation. RESULTS: In total, 646,800 HRCT images and the corresponding labelled images were acquired from 1068 patients with ILD, of whom 42.7% had IPF. The average segmentation accuracy was 96.1%. The machine learning algorithm had an average diagnostic accuracy of 83.6%, with high sensitivity, specificity and kappa coefficient values (80.7%, 85.8% and 0.665, respectively). Using Cox hazard analysis, IPF diagnosed using this algorithm was a significant prognostic factor (hazard ratio, 2.593; 95% CI, 2.069-3.250; p < 0.001). Diagnostic accuracy was good even in patients with usual interstitial pneumonia patterns on HRCT and those with surgical lung biopsies. CONCLUSION: Using data from non-invasive examinations, the combined deep learning and machine learning algorithm accurately, easily and quickly diagnosed IPF in a population with various ILDs.

    DOI: 10.1111/resp.14310

    Web of Science

    Scopus

    PubMed

  2. Serum mitochondrial DNA predicts the risk of acute exacerbation and progression of idiopathic pulmonary fibrosis. Reviewed International coauthorship International journal

    Koji Sakamoto, Taiki Furukawa, Yasuhiko Yamano, Kensuke Kataoka, Ryo Teramachi, Anjali Walia, Atsushi Suzuki, Masahide Inoue, Yoshio Nakahara, Changwan Ryu, Naozumi Hashimoto, Yasuhiro Kondoh

    The European respiratory journal   Vol. 57 ( 1 )   2021.1

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1183/13993003.01346-2020

    Web of Science

    Scopus

    PubMed

  3. Artificial intelligence in a prediction model for post-ERCP pancreatitis Reviewed International journal

    Takahashi Hidekazu, Eizaburo Ohno, Taiki Furukawa, Kentaro Yamao, Takuya Ishikawa, Yasuyuki Mizutani, Tadashi Iida, Yoshimune Shiratori, Shintaro Oyama, Junji Koyama, Kensaku Mori, Yuichiro Hayashi, Masahiro Oda, Takahisa Suzuki, Hiroki Kawashima

    Digestive Endoscopy     2023.7

     More details

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

    DOI: 10.1111/den.14622

    Web of Science

    Scopus

    PubMed

  4. Changes in patient-reported outcomes in patients with non-idiopathic pulmonary fibrosis fibrotic interstitial lung disease and progressive pulmonary fibrosis Reviewed International journal

    Reoto Takei, Toshiaki Matsuda, Jun Fukihara, Hajime Sasano, Yasuhiko Yamano, Toshiki Yokoyama, Kensuke Kataoka, Tomoki Kimura, Atsushi Suzuki, Taiki Furukawa, Junya Fukuoka, Takeshi Johkoh, Yasuhiro Kondoh

    Frontiers in Medicine   Vol. 10   page: 1067149   2023.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Frontiers Media SA  

    Background

    Health-related quality of life (HRQoL) captures different aspects of the fibrotic interstitial lung disease (FILD) evaluation from the patient’s perspective. However, little is known about how HRQoL changes in patients with non-idiopathic pulmonary fibrosis (IPF) FILD, especially in those with progressive pulmonary fibrosis (PPF). The aim of this study is to clarify whether HRQoL deteriorates in patients with non-IPF FILD and to evaluate the differences in the changes in HRQoL between those with and without PPF.

    Methods

    We collected data from consecutive patients with non-IPF FILD and compared annual changes in HRQoL over 2 years between patients with PPF and those without. The St George’s respiratory questionnaire (SGRQ) and COPD assessment test (CAT) were used to assess HRQoL. Changes in the SGRQ and CAT scores for 24 months from baseline were evaluated with a mixed-effect model for repeated measures.

    Results

    A total of 396 patients with non-IPF FILD were reviewed. The median age was 65 years and 202 were male (51.0%). The median SGRQ and CAT scores were 29.6 and 11, respectively. Eighty-six (21.7%) showed PPF. Both SGRQ and CAT scores were significantly deteriorated in patients with PPF compared to those without PPF (p &amp;lt; 0.01 for both). Clinically important deterioration in the SGRQ and CAT scores were observed in 40.0 and 35.7% of patients with PPF and 11.7 and 16.7% of those without, respectively. PPF was significantly associated with clinically important deterioration in the SGRQ score (odds ratio 5.04; 95%CI, 2.61–9.76, p &amp;lt; 0.01) and CAT score (odds ratio 2.78; 95%CI, 1.27–6.06, p = 0.02).

    Conclusion

    The SGRQ and CAT scores were significantly deteriorated in patients with non-IPF FILD and PPF. Considering an evaluation of HRQoL would be needed when assessing PPF.

    DOI: 10.3389/fmed.2023.1067149

    Web of Science

    Scopus

    PubMed

  5. DEVELOPMENT OF A MACHINE-LEARNING MODEL FOR PREDICTING POST-ERCP PANCREATITIS Reviewed International journal

    Takahashi Hidekazu, Eizaburo Ohno, Taiki Furukawa, Kentaro Yamao, Takuya Ishikawa, Yasuyuki Mizutani, Tadashi Iida, Yoshimune Shiratori, Shintaro Oyama, Junji Koyama, Kensaku Mori, Yuichiro Hayashi, Masahiro Oda, Takahisa Suzuki, Hiroki Kawashima

    Gastrointestinal Endoscopy   Vol. 97 ( 6 ) page: AB656 - AB656   2023.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Elsevier BV  

    DOI: 10.1016/j.gie.2023.04.1087

  6. In-Hospital Cancer Mortality Prediction by Multimodal Learning of Non-English Clinical Texts International journal

    Oyama S., Furukawa T., Misawa S., Kano R., Yarimizu H., Taniguchi T., Onoda K., Sato K., Shiratori Y.

    Studies in Health Technology and Informatics   Vol. 302   page: 821 - 822   2023.5

     More details

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

    Predicting important outcomes in patients with complex medical conditions using multimodal electronic medical records remains challenge. We trained a machine learning model to predict the inpatient prognosis of cancer patients using EMR data with Japanese clinical text records, which has been considered difficult due to its high context. We confirmed high accuracy of the mortality prediction model using clinical text in addition to other clinical data, suggesting applicability of this method to cancer.

    DOI: 10.3233/SHTI230276

    Scopus

    PubMed

  7. Interstitial pneumonia with autoimmune features and histologic usual interstitial pneumonia treated with anti-fibrotic versus immunosuppressive therapy Reviewed International journal

    Yasuhiko Yamano, Kensuke Kataoka, Reoto Takei, Hajime Sasano, Toshiki Yokoyama, Toshiaki Matsuda, Tomoki Kimura, Yuta Mori, Taiki Furukawa, Junya Fukuoka, Takeshi Johko, Yasuhiro Kondoh

    Respiratory Investigation   Vol. 61 ( 3 ) page: 297 - 305   2023.5

     More details

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

    Background: Therapeutic strategies in patients with interstitial pneumonia with autoimmune features (IPAF) and histological usual interstitial pneumonia (UIP) pattern (IPAF-UIP) have not been thoroughly evaluated. We compared the therapeutic efficacy of anti-fibrotic therapy with that of immunosuppressive treatment for patients with IPAF-UIP. Methods: In this retrospective case series, we identified consecutive IPAF-UIP patients treated with anti-fibrotic therapy or immunosuppressive therapy. Clinical characteristics, one-year treatment response, acute exacerbation, and survival were studied. We performed a stratified analysis by the pathological presence or absence of inflammatory cell infiltration. Results: Twenty-seven patients with anti-fibrotic therapy and 29 with immunosuppressive treatment were included. There was a significant difference in one-year forced vital capacity (FVC) change between patients with anti-fibrotic treatment (4 in 27 improved, 12 stable, and 11 worsened) and those with immunosuppressive treatment (16 in 29 improved, eight stable, and five worsened) (p = 0.006). There was also a significant difference in one-year St George's Respiratory Questionnaire (SGRQ) change between patients with anti-fibrotic therapy (2 in 27 improved, ten stable, and 15 worsened) and those with immunosuppressive treatment (14 in 29 improved, 12 stable, and worsened) (p < 0.001). There was no significant difference in survival between the groups (p = 0.32). However, in the subgroup with histological inflammatory cell infiltration, survival was significantly better with immunosuppressive therapy (p = 0.02). Conclusion: In IPAF-UIP, immunosuppressive therapy seemed to be superior to anti-fibrotic treatment in terms of therapeutic response, and provided better outcomes in the histological inflammatory subgroup. Further prospective studies are needed to clarify the therapeutic strategy in IPAF-UIP.

    DOI: 10.1016/j.resinv.2023.01.007

    Web of Science

    Scopus

    PubMed

  8. Prevalence and prognosis of chronic fibrosing interstitial lung diseases with a progressive phenotype. Reviewed International journal

    Reoto Takei, Kevin K Brown, Yasuhiko Yamano, Kensuke Kataoka, Toshiki Yokoyama, Toshiaki Matsuda, Tomoki Kimura, Atsushi Suzuki, Taiki Furukawa, Junya Fukuoka, Takeshi Johkoh, Yoshihito Goto, Yasuhiro Kondoh

    Respirology (Carlton, Vic.)   Vol. 27 ( 5 ) page: 333 - 340   2022.5

     More details

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

    BACKGROUND AND OBJECTIVE: The development of clinically progressive fibrosis complicates a wide array of interstitial lung diseases (ILDs). However, there are limited data regarding its prevalence and prognosis. METHODS: We analysed consecutive patients seen for initial evaluation of a fibrosing form of ILD (FILD). Patients were evaluated for evidence of progressive fibrosis over the first 24 months of follow-up. We defined a progressive phenotype as the presence of at least one of the following: a relative decline in forced vital capacity (FVC) of ≥10%; a relative decline in FVC of ≥5%-<10% with a relative decline in diffusing capacity of the lung for carbon monoxide of ≥15%, increased fibrosis on HRCT or progressive symptoms. RESULTS: Eight hundred and forty-four patients (397 with idiopathic pulmonary fibrosis [IPF] and 447 non-IPF FILD) made up the final analysis cohort. Three hundred and fifty-five patients (42.1%) met the progressive phenotype criteria (59.4% of IPF patients and 26.6% of non-IPF FILD patients, p <0.01). In both IPF and non-IPF FILD, transplantation-free survival differed between patients with a progressive phenotype and those without (p <0.01). Multivariable analysis showed that a progressive phenotype was an independent predictor of transplantation-free survival (hazard ratio [HR]: 3.36, 95% CI: 2.68-4.23, p <0.01). Transplantation-free survival did not differ between non-IPF FILD with a progressive phenotype and IPF (HR: 1.12, 95% CI: 0.85-1.48, p = 0.42). CONCLUSION: Over one-fourth of non-IPF FILD patients develop a progressive phenotype compared to approximately 60% of IPF patients. The survival of non-IPF FILD patients with a progressive phenotype is similar to IPF.

    DOI: 10.1111/resp.14245

    Web of Science

    Scopus

    PubMed

  9. The prognostic value of the COPD Assessment Test in fibrotic interstitial lung disease. Reviewed International journal

    Toshiaki Matsuda, Yasuhiro Kondoh, Taiki Furukawa, Atsushi Suzuki, Reoto Takei, Hajime Sasano, Yasuhiko Yamano, Toshiki Yokoyama, Kensuke Kataoka, Tomoki Kimura

    Respiratory investigation   Vol. 60 ( 1 ) page: 99 - 107   2022.1

     More details

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

    BACKGROUND: The COPD Assessment Test (CAT) has been studied as a measure of health status in idiopathic pulmonary fibrosis (IPF) and interstitial lung disease associated with connective tissue disease. However, its prognostic value is unknown. The present study explored the association between CAT score and mortality in fibrotic interstitial lung disease (FILD), including IPF and other forms of ILD. METHODS: We retrospectively analyzed 501 consecutive patients with FILD who underwent clinical assessment, including pulmonary function test and CAT. The association between CAT score and 3-year mortality was assessed using Cox proportional hazard analysis, Kaplan-Meier plots, and the log-rank test for trend. To handle missing data, the imputed method was used. RESULTS: The patients' median age was 68 years, and 320 were male (63.9%). Regarding CAT severity, 203 patients had a low impact level (score <10), 195 had a medium level (10-20), 80 had a high level (21-30), and 23 had a very high level (31-40). During the 3-year study period, 118 patients died. After adjusting for age, sex, forced vital capacity, diffusion capacity for carbon monoxide, IPF diagnosis, and usual interstitial pneumonia pattern on high-resolution computed tomography, the CAT score was significantly associated with 3-year mortality (hazard ratio in increments of 10 points: 1.458, 95% confidence interval 1.161-1.830; p < 0.001). In addition, patients with high and very high impact levels had twofold and threefold higher mortality risk than those with low levels, respectively. CONCLUSION: The CAT has prognostic value in FILD.

    DOI: 10.1016/j.resinv.2021.07.007

    Web of Science

    Scopus

    PubMed

  10. 新型コロナウイルス感染症(COVID-19)拡大におけるDPCデータを用いた受療状況分析 Reviewed

    佐藤 菊枝, 小林 大介, 山下 暁士, 大山 慎太郎, 古川 大記, 白鳥 義宗

    医療情報学連合大会論文集   Vol. 41回   page: 570 - 572   2021.11

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)   Publisher:(一社)日本医療情報学会  

  11. 東海国立大学機構が実現しようとしているSociety5.0 Invited Reviewed

    白鳥 義宗, 大山 慎太郎, 山下 暁士, 佐藤 菊枝, 小林 大介, 舩田 千秋, 古川 大記, 菅野 亜紀, 森 龍太郎, 矢部 大介

    医療情報学連合大会論文集   Vol. 41回   page: 113 - 115   2021.11

     More details

    Language:Japanese   Publishing type:Research paper (international conference proceedings)   Publisher:(一社)日本医療情報学会  

  12. The current issues and future perspective of artificial intelligence for developing new treatment strategy in non-small cell lung cancer: harmonization of molecular cancer biology and artificial intelligence. Reviewed International journal

    Ichidai Tanaka, Taiki Furukawa, Masahiro Morise

    Cancer cell international   Vol. 21 ( 1 ) page: 454 - 454   2021.8

     More details

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

    Comprehensive analysis of omics data, such as genome, transcriptome, proteome, metabolome, and interactome, is a crucial technique for elucidating the complex mechanism of cancer onset and progression. Recently, a variety of new findings have been reported based on multi-omics analysis in combination with various clinical information. However, integrated analysis of multi-omics data is extremely labor intensive, making the development of new analysis technology indispensable. Artificial intelligence (AI), which has been under development in recent years, is quickly becoming an effective approach to reduce the labor involved in analyzing large amounts of complex data and to obtain valuable information that is often overlooked in manual analysis and experiments. The use of AI, such as machine learning approaches and deep learning systems, allows for the efficient analysis of massive omics data combined with accurate clinical information and can lead to comprehensive predictive models that will be desirable for further developing individual treatment strategies of immunotherapy and molecular target therapy. Here, we aim to review the potential of AI in the integrated analysis of omics data and clinical information with a special focus on recent advances in the discovery of new biomarkers and the future direction of personalized medicine in non-small lung cancer.

    DOI: 10.1186/s12935-021-02165-7

    Web of Science

    Scopus

    PubMed

  13. Prognosis in Non-IPF with Progressive Fibrotic Phenotype Results in Similar Prognosis in IPF Reviewed International journal

    Ito T., Takei R., Sasano H., Yamano Y., Yokoyama T., Matsuda T., Kimura T., Furukawa T., Johkoh T., Fukuoka J., Kondoh Y.

    AMERICAN JOURNAL OF RESPIRATORY AND CRITICAL CARE MEDICINE   Vol. 203 ( 9 )   2021.5

     More details

    Language:Japanese   Publishing type:Research paper (international conference proceedings)  

    Web of Science

  14. Impact of post-capillary pulmonary hypertension on mortality in interstitial lung disease. Reviewed International journal

    Ryo Teramachi, Hiroyuki Taniguchi, Yasuhiro Kondoh, Tomoki Kimura, Kensuke Kataoka, Toshiki Yokoyama, Taiki Furukawa, Mitsuaki Yagi, Koji Sakamoto, Naozumi Hashimoto, Yoshinori Hasegawa

    Respiratory investigation   Vol. 59 ( 3 ) page: 342 - 349   2021.5

     More details

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

    BACKGROUND: Pulmonary hypertension (PH) influences mortality in patients with interstitial lung disease (ILD). Almost all studies on patients with ILD, have focused on the clinical impact of pre-capillary PH on survival. Therefore, little is known about the influence of post-capillary PH. We aimed to assess the prevalence of post-capillary PH and its clinical impact on survival in patients with ILD, followed by comparison with pre-capillary PH. METHODS: This retrospective study enrolled 1152 patients with ILD who were diagnosed with PH using right heart catheterization between May 2007 and December 2015. We analyzed the demographics and composite outcomes (defined as death from any cause or lung transplantation) of patients with post-capillary PH and compared them with patients with pre-capillary PH. RESULTS: Thirty-two (20%) of the 157 patients with ILD-PH were diagnosed with post-capillary PH. Patients with post-capillary PH had significantly lower modified Medical Research Council scores, higher diffusion capacity for carbon monoxide, higher resting PaO2, lower pulmonary vascular resistance (PVR), and higher lowest oxygen saturation during the 6-min walk test compared to those with pre-capillary PH. Cardiovascular diseases were associated with a higher risk of mortality in patients with post-capillary PH. Multivariate Cox proportional hazards analysis demonstrated no significant difference between the composite outcomes in pre-capillary and post-capillary PH, while PVR and the ILD Gender-Age-Physiology Index were significantly associated with the composite outcome. CONCLUSIONS: We found that approximately one-fifth of patients with ILD-PH were diagnosed with post-capillary PH, and that PVR and not post-capillary PH was associated with mortality.

    DOI: 10.1016/j.resinv.2020.12.010

    Web of Science

    Scopus

    PubMed

  15. Smart hospital infrastructure: geomagnetic in-hospital medical worker tracking. Reviewed International journal

    Keiko Yamashita, Shintaro Oyama, Tomohiro Otani, Satoshi Yamashita, Taiki Furukawa, Daisuke Kobayashi, Kikue Sato, Aki Sugano, Chiaki Funada, Kensaku Mori, Naoki Ishiguro, Yoshimune Shiratori

    Journal of the American Medical Informatics Association : JAMIA   Vol. 28 ( 3 ) page: 477 - 486   2021.3

     More details

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

    PURPOSE: Location visualization is essential for locating people/objects, improving efficiency, and preventing accidents. In hospitals, Wi-Fi, Bluetooth low energy (BLE) Beacon, indoor messaging system, and similar methods have generally been used for tracking, with Wi-Fi and BLE being the most common. Recently, nurses are increasingly using mobile devices, such as smartphones and tablets, while shifting. The accuracy when using Wi-Fi or BLE may be affected by interference or multipath propagation. In this research, we evaluated the positioning accuracy of geomagnetic indoor positioning in hospitals. MATERIALS AND METHODS: We compared the position measurement accuracy of a geomagnetic method alone, Wi-Fi alone, BLE beacons alone, geomagnetic plus Wi-Fi, and geomagnetic plus BLE in a general inpatient ward, using a geomagnetic positioning algorithm by GiPStech. The existing Wi-Fi infrastructure was used, and 20 additional BLE beacons were installed. Our first experiment compared these methods' accuracy for 8 test routes, while the second experiment verified a combined geomagnetic/BLE beacon method using 3 routes based on actual daily activities. RESULTS: The experimental results demonstrated that the most accurate method was geomagnetic/BLE, followed by geomagnetic/Wi-Fi, and then geomagnetic alone. DISCUSSION: The geomagnetic method's positioning accuracy varied widely, but combining it with BLE beacons reduced the average position error to approximately 1.2 m, and the positioning accuracy could be improved further. We believe this could effectively target humans (patients) where errors of up to 3 m can generally be tolerated. CONCLUSION: In conjunction with BLE beacons, geomagnetic positioning could be sufficiently effective for many in-hospital localization tasks.

    DOI: 10.1093/jamia/ocaa204

    Web of Science

    Scopus

    PubMed

  16. Hand hygiene monitoring by positioning technology utilizing IoT devices. Reviewed International journal

    Keiko Yamashita, Shintaro Oyama, Satoshi Yamashita, Chiaki Funada, Kikue Sato, Taiki Furukawa, Aki Sugano, Daisuke Kobayashi, Hiroshi Tomozawa, Yuji Sakamoto, Yoshinori Ideno, Kensaku Mori, Yoshimune Shiratori

    AMIA     2021

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Other Link: https://dblp.uni-trier.de/rec/conf/amia/2021

▼display all

Books 2

  1. 間質性肺炎診療と新テクノロジー

    古川大記( Role: Sole author)

    呼吸器内科学レビュー 2022-’23  2021.12 

     More details

    Language:Japanese Book type:Scholarly book

  2. 間質性肺炎のAI診断

    古川大記, 大山慎太郎( Role: Joint author)

    呼吸器ジャーナル  2021.8 

     More details

    Language:Japanese Book type:Scholarly book

MISC 15

  1. In-Hospital Cancer Mortality Prediction by Multimodal Learning of Non-English Clinical Texts Reviewed International journal

    Oyama S., Furukawa T., Misawa S., Kano R., Yarimizu H., Taniguchi T., Onoda K., Sato K., Shiratori Y.

    Studies in Health Technology and Informatics   Vol. 302   page: 821 - 822   2023.5

     More details

    Language:English   Publishing type:Article, review, commentary, editorial, etc. (international conference proceedings)   Publisher:Studies in Health Technology and Informatics  

    Predicting important outcomes in patients with complex medical conditions using multimodal electronic medical records remains challenge. We trained a machine learning model to predict the inpatient prognosis of cancer patients using EMR data with Japanese clinical text records, which has been considered difficult due to its high context. We confirmed high accuracy of the mortality prediction model using clinical text in addition to other clinical data, suggesting applicability of this method to cancer.

    DOI: 10.3233/SHTI230276

    Scopus

    PubMed

  2. Sentence Extraction using Outcome Prediction Model Trained from Clinical Data Reviewed

    MISAWA Shotaro, FURUKAWA Taiki, OYAMA Shintaro, KANO Ryuji, YARIMIZU Hirokazu, TANIGUCHI Tomoki, ONODA Kohei, SATO Kikue, SHIRATORI Yoshimune

    Proceedings of the Annual Conference of JSAI   Vol. JSAI2023 ( 0 ) page: 3Xin404 - 3Xin404   2023

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)   Publisher:The Japanese Society for Artificial Intelligence  

    <p>This study aims to extract clinically important sentences from accumulated medical documents to assist medical workers to search documents. Unsupervised document summarization methods such as LexRank are commonly used in situations where it is difficult to prepare training data. However, these methods are based on a hypothesis that important topics are frequently referred which does not match the medical document. Many previous studies have predicted the length of hospital stay and mortality using clinical data, and we propose these outcomes can be distant labels of clinical importance. Namely, an output from the outcome prediction model becomes high when an input sentence is clinically important. Therefore, in this study, we propose a model to extract clinically important sentences using an outcome prediction model. Experimental results show our text extraction model with an outcome prediction model can summarize more accurately than the conventional models.</p>

    DOI: 10.11517/pjsai.jsai2023.0_3xin404

    CiNii Research

  3. 呼吸器内科 間質性肺疾患のAI画像診断の開発状況と今後の展望について 実臨床で使用できるようにAI開発とシステム構築が進められている

    古川 大記, 伊藤 健太郎

    日本医事新報   ( 5136 ) page: 48 - 49   2022.10

     More details

    Authorship:Lead author, Corresponding author   Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (trade magazine, newspaper, online media)   Publisher:(株)日本医事新報社  

  4. 【びまん性肺疾患における多職種合議(MDD)診断とAI支援の現在と未来】MDD診断へのAI「画像診断」支援の現状と可能性について

    古川 大記, 寺町 涼

    呼吸器内科   Vol. 41 ( 2 ) page: 180 - 184   2022.2

     More details

    Authorship:Lead author, Last author, Corresponding author   Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (scientific journal)   Publisher:(有)科学評論社  

  5. 肺線維症の病態に関連する2つの新規マーカー分子:メフリンとミトコンドリアDNA

    阪本 考司, 橋本 直純, 中原 義夫, 古川 大記

    呼吸器内科   Vol. 41 ( 2 ) page: 197 - 201   2022.2

     More details

    Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (scientific journal)   Publisher:(有)科学評論社  

  6. MDD診断へのAI「画像診断」支援の現状と可能性について. Invited

    古川 大記

    呼吸器内科   Vol. 41(2)   page: 180 - 184   2022

     More details

    Authorship:Lead author, Last author, Corresponding author   Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (scientific journal)  

    CiNii Research

  7. 【最新主要文献とガイドラインでみる呼吸器内科学レビュー 2022-'23】(XIV章)新テクノロジーと肺疾患 間質性肺炎診療と新テクノロジー

    古川 大記

    呼吸器内科学レビュー   Vol. 2022-'23   page: 327 - 332   2021.12

     More details

    Authorship:Lead author, Last author, Corresponding author   Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (scientific journal)   Publisher:(株)総合医学社  

    間質性肺炎(ILD)の正確な診断には、呼吸器内科医、放射線科医、病理医の集学的議論(MDD)、外科的肺生検やクライオバイオプシーが重要であるが、近年、新しいテクノロジーを用いた診療が広がりつつある。機械学習と深層学習を用いたILDの画像所見の抽出、ゲノム評価、診断と治療効果予測について概説した。また、間質性肺炎のAI(人工知能)創薬、遠隔診療(オンラインMDD診断)、在宅モニタリングと呼吸器リハビリテーションについて述べた。

  8. 特集 間質性肺炎 徹底討論!-鳥からは逃げられない過敏性肺炎,放置してよいのかILA Ⅳ.最近の話題 間質性肺炎のAI診断

    古川 大記, 大山 慎太郎

    呼吸器ジャーナル   Vol. 69 ( 3 ) page: 450 - 457   2021.8

     More details

    Authorship:Lead author, Corresponding author   Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (trade magazine, newspaper, online media)   Publisher:株式会社 医学書院  

    DOI: 10.11477/mf.1437200484

    CiNii Research

  9. Prognosis in Non-IPF with Progressive Fibrotic Phenotype Results in Similar Prognosis in IPF Reviewed International journal

    Ito T., Takei R., Sasano H., Yamano Y., Yokoyama T., Matsuda T., Kimura T., Furukawa T., Johkoh T., Fukuoka J., Kondoh Y.

    AMERICAN JOURNAL OF RESPIRATORY AND CRITICAL CARE MEDICINE   Vol. 203 ( 9 )   2021.5

     More details

    Language:English   Publishing type:Research paper, summary (international conference)  

    Web of Science

  10. 間質性肺疾患における肺高血圧予測モデルの構築 Reviewed

    佐藤 智則, 古川 大記, 寺町 涼, 山野 泰彦, 横山 俊樹, 松田 俊明, 片岡 健介, 木村 智樹, 近藤 康博

    日本呼吸器学会誌   Vol. 10 ( 増刊 ) page: 225 - 225   2021.4

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)   Publisher:(一社)日本呼吸器学会  

  11. Construction of a data collection platform based on the regional medical care data infrastructure Reviewed

    佐藤菊枝, 小林大介, 小林大介, 山下暁士, 大山慎太郎, 古川大記, 白鳥義宗

    日本医療情報学会春季学術大会プログラム・抄録集   Vol. 25th   2021

     More details

  12. スマートホスピタル構想~医療Society5.0におけるDx研究~ Reviewed

    大山慎太郎, 大山慎太郎, 古川大記, 古川大記, 山下暁士, 山下暁士, 原武史, 原武史

    医療情報学連合大会論文集(CD-ROM)   Vol. 41st   2021

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

  13. Outcome prediction using Integrated Clinical Database toward Automatic Generation of Clinical Summaries Reviewed

    古川大記, 三沢翔太郎, 大山慎太郎, 佐藤菊枝, 狩野竜示, 鑓水大和, 白鳥義宗

    医療情報学連合大会論文集(CD-ROM)   Vol. 41st   2021

     More details

    Authorship:Lead author, Corresponding author   Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

  14. Patient access analysis in COVID-19 Pandemic using DPC data Reviewed

    佐藤菊枝, 小林大介, 小林大介, 山下暁士, 大山慎太郎, 古川大記, 白鳥義宗

    医療情報学連合大会論文集(CD-ROM)   Vol. 41st   2021

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

  15. 間質性肺炎診療と新テクノロジー Invited

    古川 大記

    最新主要文献とガイドラインでみる 呼吸器内科学レビュー 2022-’23   Vol. -   page: 327 - 332   2021

     More details

    Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (trade magazine, newspaper, online media)  

    CiNii Research

▼display all

Presentations 21

  1. 機械学習による院内死亡予測モデルの特性分析

    古川大記, 三沢翔太郎, 大山慎太郎, 狩野竜示, 鑓水大和, 谷口友紀, 小野田浩平, 佐藤菊枝, 白鳥義宗

    第27回 日本医療情報学会春季学術大会  2023.7.1 

     More details

    Event date: 2023.6 - 2023.7

    Language:Japanese   Presentation type:Oral presentation (general)  

  2. 診療データを用いた予測モデルによる文抽出

    三沢翔太郎, 古川大記, 大山慎太郎, 狩野竜示, 鑓水大和, 谷口友紀, 小野田浩平, 佐藤菊枝, 白鳥義宗

    第37回人工知能学会全国大会  2023.6.9 

     More details

    Event date: 2023.6

    Language:Japanese   Presentation type:Poster presentation  

  3. Prognostic factors for Covid-19 on admission profile and air pollutants International conference

    Kikue Sato, Taiki Furukawa, Satoshi Yamashita, Daisuke Kobayashi, Shintaro Oyama, Yoshimune Shiratori

    Medical Informatics Europe 2023  2023.5.22 

     More details

    Event date: 2023.5

    Language:English   Presentation type:Poster presentation  

  4. In-Hospital Mortality Prediction by Multimodal Learning of non-English Clinical Texts

    Shintaro Oyama, Taiki Furukawa, Shotaro Misawa, Ryuji Kano, Hirokazu Yarimizu, Tomoki Taniguchi, Kohei Onoda, Kikue Sato, Yoshimune Shiratori

    Medical Informatics Europe 2023  2023.5.22 

     More details

    Event date: 2023.5

    Language:English   Presentation type:Poster presentation  

  5. 機械学習を活用した抗PD-1/PD-L1抗体治療の生存予測バイオマーカー構築

    神山 潤二, 森瀬 昌宏, 古川 大記, 阪本 考司, 松下 明弘, 松尾 正樹, 浅野 周一, 田中 太郎, 島 浩一郎, 木村 智樹, 近藤 康博, 石井 誠

    第63回日本呼吸器学会学術集会  2023.4.28 

     More details

    Event date: 2023.4

    Language:Japanese   Presentation type:Oral presentation (general)  

  6. 進行非小細胞肺癌における臨床および画像特徴量を用いた機械学習による個別化生存予測モデルの構築

    神山潤二, 森瀬昌宏, 古川大記, 松澤令子, 田中一大, 横田秀夫, 木村智樹, 近藤康博, 橋本直純

    第63回日本肺癌学会学術集会  2022.12.3 

     More details

    Event date: 2022.12

    Language:Japanese   Presentation type:Oral presentation (general)  

  7. Artificial intelligence-based personalized survival prediction using clinical and radiomics features in patients with advanced non-small cell lung cancer International conference

    Junji Koyama, Masahiro Morise, Taiki Furukawa, Shintaro Oyama, Reiko Matsuzawa, Ichidai Tanaka, Keiko Wakahara, Hideo Yokota, Tomoki Kimura, Yoshimune Shiratori, Yasuhiro Kondoh, Naozumi Hashimoto

    The 26th Congress of the Asian Pacific Society of Respirology  2022.11.18 

     More details

    Event date: 2022.11

    Language:English   Presentation type:Oral presentation (general)  

  8. 機械学習を用いたERCP後膵炎リスク予測モデルの構築

    高橋秀和, 古川大記, 大野栄三郎, 石川卓哉, 水谷泰之, 飯田忠, 鈴木貴久, 川嶋啓揮

    Japan Digestive Disease Week 2022  2022.10.28 

     More details

    Event date: 2022.10

    Language:Japanese   Presentation type:Poster presentation  

  9. 間質性肺炎MDD 診断と予後予測の立場から Invited

    古川大記

    第2回日本びまん性肺疾患研究会  2022.10.2 

     More details

    Event date: 2022.10

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

  10. 間質性肺炎の診断・予後予測アルゴリズム構築と社会実装に向けて Invited

    古川大記

    ARO協議会 第9回学術集会  2022.9.16 

     More details

    Event date: 2022.9

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

  11. Development of AI models to predict mortality and long-term hospitalization in pneumonia International conference

    Taiki Furukawa, Shintaro Oyama, Kikue Sato, Shotaro Misawa, Ryuji Kano, Hirokazu Yarimizu, Yoshimmune Shiratori

    ERS International Congress 2022  2022.9.6 

     More details

    Event date: 2022.9

    Language:English   Presentation type:Oral presentation (general)  

  12. 医療用AIとアルゴリズムの構築 Invited

    古川大記

    第7回日本肺高血圧・肺循環学会学術集会  2022.7.3 

     More details

    Event date: 2022.7

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

  13. 時系列情報から間質性肺炎急性増悪発症及び予後を予測する深層学習モデルの構築

    寺町 涼, 古川大記, 大山慎太郎, 近藤康博, 烏山昌幸, 片岡健介, 白鳥義宗

    第4回日本メディカルAI学会学術集会  2022.6.10 

     More details

    Event date: 2022.6

    Language:Japanese   Presentation type:Oral presentation (general)  

  14. 進行非小細胞肺癌に対する薬物療法後の個別化生存予測における機械学習の活用

    神山潤二, 森瀬昌宏, 古川大記, 大山慎太郎, 松澤令子, 田中一大, 若原恵子, 横田秀夫, 木村智樹, 白鳥義宗, 近藤康博, 橋本直純

    第4回日本メディカルAI学会学術集会  2022.6.10 

     More details

    Event date: 2022.6

    Language:Japanese   Presentation type:Oral presentation (general)  

  15. IPFのAI診断の現状と問題点 Invited

    古川大記

    第62回日本呼吸器学会学術集会  2022.4.24 

     More details

    Event date: 2022.4

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

  16. びまん性肺疾患MDD診断の為の 双方向性Webプラットフォーム構築と 人工知能診断の社会実装に関する前向き研究 Invited

    古川大記

    第62回日本呼吸器学会学術集会  2022.4.23 

     More details

    Event date: 2022.4

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

  17. 統合診療データを用いたAIによるアウトカム予測と 診療サマリ生成に向けた検討

    古川 大記, 三沢 翔太郎, 大山 慎太郎, 佐藤 菊枝, 狩野 竜示, 鑓水 大和, 白鳥 義宗

    第41回医療情報学連合大会  2021.11.20 

     More details

    Event date: 2021.11

    Presentation type:Oral presentation (general)  

  18. Interstitial lung disease and BIG-DATA / AI Invited

    Taiki Furukawa

    The 61st Annual Meeting of The Japanese Respiratory Society  2021.4.24 

     More details

    Event date: 2021.4

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

  19. Expanding Features of Outcome Prediction using Estimated Hospitalization Progress.

    MISAWA Shotaro, FURUKAWA Taiki, OYAMA Shintaro, SATO Kikue, KANO Ryuji, YARIMIZU Hirokazu, TANIGUCHI Tomoki, ONODA Kohei, OHKUMA Tomoko, SHIRATORI Yoshimune

    Proceedings of the Annual Conference of JSAI  2022  The Japanese Society for Artificial Intelligence

     More details

    Language:Japanese   Presentation type:Poster presentation  

    <p>Outcome prediction using clinical data such as mortality prediction, length-of-stay prediction is applicable to acute change prediction, early treatment, and prediction of treatment effects. However, it is difficult to predict the long-term future status of patients. To improve the performance of the prediction model, we first estimate the short-term future and leverage the estimated value to predict the long-term future status of patients. Such hospitalization progress in the short-term future can be estimated by constructing another estimation model. In this study, we propose the feature expansion using estimated hospitalization progress for the outcome prediction model. We conduct experiments on clinical data of pneumonia cases aggregated in "CITA Clinical Finder", the integrated medical support platform. The result shows our model can predict more accurately than the model without feature expansion.</p>

    DOI: 10.11517/pjsai.jsai2022.0_3yin228

    CiNii Research

  20. Development of AI models to predict mortality and long-term hospitalization in pneumonia International conference

    Furukawa T., Oyama S., Sato K., Misawa S., Kano R., Yarimizu H., Shiratori Y.

    EUROPEAN RESPIRATORY JOURNAL  2022.9.4 

     More details

    Language:English   Presentation type:Oral presentation (general)  

    DOI: 10.1183/13993003.congress-2022.342

  21. Artificial intelligence-based personalized survival prediction using clinical and radiomics features in patients with advanced non-small cell lung cancer International conference

    Koyama Junji, Morise Masahiro, Furukawa Taiki, Oyama Shintaro, Matsuzawa Reiko, Tanaka Ichidai, Wakahara Keiko, Yokota Hideo, Kimura Tomoki, Shiratori Yoshimune, Kondoh Yasuhiro, Hashimoto Naozumi

    RESPIROLOGY  2023.2 

     More details

    Language:English   Presentation type:Oral presentation (general)  

▼display all

Research Project for Joint Research, Competitive Funding, etc. 7

  1. All Japan大規模レジストリデータを背景とした間質性肺炎の治療プログラム及びデバイスの開発

    2022.4 - 2026.3

    医療機器等研究成果展開事業 

    中澤 公貴, 五十嵐亮レオナルド, 大山慎太郎

      More details

    Authorship:Principal investigator  Grant type:Competitive

  2. 間質性肺炎に対する多施設共同前向き観察研究

    2020.3 - 2025.12

      More details

    Authorship:Coinvestigator(s)  Grant type:Collaborative (industry/university)

  3. All Japan大規模レジストリデータを背景とした間質性肺炎の遠隔診断と、治療プログラム及びデバイスの事業化検証

    2022.8 - 2023.3

    大学発新産業創出プログラム(START)大学エコシステム推進型GAPファンドプログラム 

    古川大記, 大山慎太郎, 五十嵐亮レオナルド

      More details

    Authorship:Principal investigator  Grant type:Competitive

  4. 医師の業務効率化を支援するアルゴリズムの機械学習

    2021.11 - 2023.10

    白鳥義宗, 佐藤菊枝, 大山慎太郎, 古川大記

      More details

    Authorship:Coinvestigator(s)  Grant type:Collaborative (industry/university)

  5. 特発性間質性肺炎の前向きレジストリの構築とインタラクティブMDD診断システムを用いた診断標準化に基づく疫学データの創出―人工知能(AI)診断システムと新規バイオマーカーの開発―

    2020.4 - 2022.3

    難治性疾患等実用化研究事業 

    須田 隆文, 井上 義一, 横田 秀夫, 宮崎 泰成, 近藤 康博, 古川 大記, 坂東 政司, 小倉 高志, 上甲 剛, 長谷川 好規, 白鳥 義宗, 福岡 順也, 本間 栄

      More details

    Authorship:Coinvestigator(s)  Grant type:Competitive

  6. びまん性肺疾患MDD診断のための双方向性Webプラットフォーム構築と人工知能診断の社会実装に関する前向き研究

    2019.4 - 2022.3

      More details

    Authorship:Principal investigator  Grant type:Competitive

  7. びまん性肺疾患診断の臨床画像クラウド型統合データベースの基盤構築と機械学習による診断・予後予測アルゴリズム構築に関する研究

    2019.4 - 2022.3

      More details

    Authorship:Principal investigator  Grant type:Competitive

▼display all

KAKENHI (Grants-in-Aid for Scientific Research) 6

  1. 人工衛星による大気汚染情報を活用した間質性肺炎プレシジョンメディシンの実現

    Grant number:23H02919  2023.4 - 2026.3

    日本学術振興会  科学研究費助成事業 基盤研究(B)  基盤研究(B)

    古川 大記, 大山 慎太郎, 横田 秀夫, 横田 秀夫, 大山 慎太郎

      More details

    Authorship:Principal investigator  Grant type:Competitive

    Grant amount:\19370000 ( Direct Cost: \14900000 、 Indirect Cost:\4470000 )

    間質性肺炎は、肺の間質が侵される肺疾患の総称で、多数の診断群と多様な経過をたどる。中でも最も予後不良である特発性肺線維症(IPF)は、正確に診断できる専門医が少ない。同様に予後不良である進行性線維性間質性肺炎(PF-ILD)は、病状が悪化した後にPF-ILD と判断されるため治療導入が遅れてしまうが、診断は困難である。
    このため、本研究では前向き・後ろ向きリアルワールド疾患データと大気汚染情報を統合し、データ駆動型研究により疾患の本質を導き出す。

  2. Development of a quantitative evaluation method for medical resource optimization and construction of a regional medical data platform

    Grant number:23K09547  2023.4 - 2026.3

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

      More details

    Authorship:Coinvestigator(s)  Grant type:Competitive

  3. Immune-pathological diagnostic artificial intelligence development research for pulmonary fibrosis using fibrotic foci-specific enhanced micro-CT

    Grant number:20K21599  2020.7 - 2023.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research Grant-in-Aid for Challenging Research (Exploratory)  Grant-in-Aid for Challenging Research (Exploratory)

      More details

    Authorship:Coinvestigator(s)  Grant type:Competitive

  4. 特発性間質性肺炎の前向きレジストリの構築とインタラクティブMDD診断システムを用いた診断標準化に基づく疫学データの創出―人工知能(AI)診断システムと新規バイオマーカーの開発―

    2020.4 - 2022.3

    日本医療研究開発機構(AMED)  難治性疾患等実用化研究事業 

    須田 隆文, 井上 義一, 横田 秀夫, 宮崎 泰成, 近藤 康博, 古川 大記, 坂東 政司, 小倉 高志, 上甲 剛, 長谷川 好規, 白鳥 義宗, 福岡 順也, 本間 栄

      More details

    Authorship:Coinvestigator(s) 

  5. Orality and Narrative Technique in Pain Clinic

    Grant number:19KT0027  2019.7 - 2022.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)  Grant-in-Aid for Scientific Research (C)

    OYAMA Shintaro

      More details

    Authorship:Coinvestigator(s)  Grant type:Competitive

    The goal of this study was to develop a medical care learning tool to systematize orality techniques for physicians in the treatment of chronic pain patients. The latter was possible to implement using existing libraries, but the accuracy of facial expressions could not be improved due to the principle of wearing a mask in the examination room. Based on the existing machine learning model, we conducted a dialogue (clinical) test, conducted reinforcement learning with the data, and constructed a model that adapted the Softmax function to the five classes of emotional parameter outputs. The results were reported at a conference.

  6. びまん性肺疾患の診断と予後予測における機械学習アルゴリズム構築に関する研究

    Grant number:19K17633  2019.4 - 2022.3

    日本学術振興会  科学研究費助成事業 若手研究  若手研究

    古川 大記

      More details

    Authorship:Principal investigator  Grant type:Competitive

    Grant amount:\4290000 ( Direct Cost: \3300000 、 Indirect Cost:\990000 )

    びまん性肺疾患は一般の呼吸器科医には診断が困難な上に予後不良な群が含まれる一方、精度の高い診断を行える専門医が少ないため、人工知能(AI)による精度の高い診断システムと予後予測システムの開発、及び開発に必要な大規模なデータベースが望まれてきた。このため、びまん性肺疾患の臨床情報・画像データのデータベース構築と、精度の高いびまん性肺疾患診断・予後予測AI開発を行い、一般に利用できる形を検討する。
    びまん性肺疾患は一般の呼吸器科医には診断が困難なことが多い上に予後不良な群が含まれる一方,精度の高い診断を行える専門医が少ないため,人工知能(AI)による精度の高い診断システムと予後予測システムの開発,及び開発に必要な大規模なデータベースが望まれてきた.本研究の全体計画における目標は「びまん性肺疾患の臨床情報・画像データのデータベース構築と,精度の高いびまん性肺疾患診断・予後予測人工知能(AI)開発」である.具体的には(A)医療用データベースの構築,(B)臨床情報・画像データと医療知識のマッピング,(C)ディープラーニングを含めた機械学習による医療画像・臨床情報からの自動所見抽出,(D)びまん性肺疾患診断・予後予測人工知能(AI)を開発することである.
    本研究では令和元年度と2年度に,全国のびまん性肺疾患の系統だった疾患データを蓄積してデータベースを構築し,AI診断に適したデータ変換を行った.さらに,びまん性肺疾患の診断予測AIを構築し,単施設データで作成された診断AIモデルと同等の精度を達成した.加えて、予後情報に対してディープラーニングと機械学習を組み合わせ,精度の高い予後予測AIを構築した.構築した予後予測AIを応用し,個々人での治療効果予測を可能とするアルゴリズム構築を達成した.このアルゴリズムにより,臨床情報からの個別化医療への道筋を示した.
    当該年度(令和3年度)では、作成したびまん性肺疾患診断・予後予測AIを広く前向きに使用するための汎化性能向上を目指し、解析を行なった.非専門施設でも収集可能なデータをインプットとして診断、予後予測を行う必要性が出たため、アルゴリズムの再構築を行なった.
    本研究は,当該年度(令和3年度)に作成したびまん性肺疾患診断・予後予測AIをCT機器やウェブ上に組み込んで、広く一般に利用できるプラットフォームを構築する事を目的とし,目的達成のために以下の課題を遂行することを掲げてきた.
    1. 診断AIと予後予測AIを組み込むプラットフォームの構築
    令和3年度には,開発済みのびまん性肺疾患AI診断システムをブラッシュアップし,より汎化性能の高いAI診断、予後予測AIを構築した.また、当初計画には無かった非専門施設でも使用可能なインプットデータに対応する必要性が出たため,構築済みの診断AIと予後予測AIの再構築のためのワークステーションを購入し、再構築を行なった.また、ウェブ上で利用可能なプラットフォームを構築するために、アプリケーションプログラムインターフェイスの仕様を検討した.
    当初計画になかった項目の検討を行なったため、プラットフォームの構築が遅れている.来年度にプラットフォームの構築を進める.
    本研究の解析によって,非専門施設データに対する適切な前処理方法,解析の高速化方法がわかっている.また,高精度予後予測AIを応用した個々人への治療効果予測アルゴリズムを構築した.
    令和4年度には,令和2年度で構築し令和3年度で汎化性能を向上した予後予測AIは個別化医療への道を開くものであるため,本領域に与える影響が大きく,より多くの施設で精度が落ちないように汎化性能を高めるためのアルゴリズムブラッシュアップを行っていく.令和3年度には当初計画に無かった非専門施設データへの対応により全体計画の進捗が遅れたが、対応が完了したため,令和4年度に診断AIと予後予測AIを組み込むプラットフォームの構築を進めていく.プラットフォーム構築に必要なワークステーションの購入等による環境整備を行う.
    研究発表は,コロナ禍でオンラインによる発表に変更になったため旅費使用額が減少したが,令和4年度には,これまでの研究成果を国内外で積極的に発表するとともに,全ての結果をまとめたジャーナル投稿を予定している.また,作成したびまん性肺疾患診断AIと予後予測AIをウェブ上に組み込んで,広く一般に利用できるプラットフォームを構築する.
    現在,大規模前向き全国レジストリを開始しており,この中で前向きに人の診断とAIの診断を施設に提示するプラットフォーム構築に取り掛かっており,臨床現場における洗練化と精度向上,新規知見の創出を行いたい.

▼display all

Industrial property rights 7

  1. 情報処理装置、情報処理方法、および、コンピュータプログラム

    寺町涼, 古川大記, 烏山昌幸, 横田秀夫

     More details

    Applicant:国立大学法人東海国立大学機構

    Application no:特願2022-175512  Date applied:2022.11

  2. Identifying device, learning device, method, and storage medium

    Taiki FURUKAWA, Hideo Yokota, Shintaro OYAMA, Yoshinori Hasegawa, Yoshimune SHIRATORI

     More details

    Application no:特願US20200372650  Date applied:2020.5

    Date announced:2020.11

    Patent/Registration no:特許US11,361,443 B2  Date registered:2022.6 

  3. Identifying device, learning device, method, and storage medium

     More details

    Applicant:国立研究開発法人理化学研究所

    Application no:特願2023-109008  Date applied:2023.7

  4. Identifying device, learning device, method, and storage medium

     More details

    Applicant:国立研究開発法人理化学研究所

    Application no:特願2023-109002  Date applied:2023.7

  5. 情報処理装置

    古川大記

     More details

    Applicant:国立大学法人東海国立大学機構名古屋大学

    Application no:特願2022-1388807  Date applied:2022.8

  6. 情報処理装置

    古川大記

     More details

    Applicant:国立大学法人東海国立大学機構名古屋大学

    Application no:特願2022-1388808  Date applied:2022.8

  7. 情報処理装置、情報処理方法、および、コンピュータプログラム

    神山 潤二, 古川 大記, 森瀬 昌宏, 横田 秀夫

     More details

    Application no:特願2022-043291  Date applied:2022.3

▼display all

 

Teaching Experience (Off-campus) 1

  1. 医療情報学

    2021.4