Skip to content
お問い合わせ

    Letter 採択

     平均インパクトファクター「5」を超える学術誌に年間30編を超えるレターを掲載。 

    No. Title Authors Journal Year DOI
    32  Interpreting IDDSI-linked nutrient patterns: From correlations to compositional modules   Oka, Souichi; Yoshida, Kiyo; Takefuji, Yoshiyasu   Clinical Nutrition ESPEN   2,026   https://doi.org/10.1016/j.clnesp.2026.102982 
    31  Revisiting AI Interpretability in Precision Oncology: Why Predictive Accuracy Does Not Ensure Stable Feature Importance   Oka, Souichi; Takefuji, Yoshiyasu   Cancers   2,026   https://doi.org/10.3390/cancers18040593 
    30  Towards reliable feature interpretation in machine learning-based longevity prediction   Oka, Souichi; Takahashi, Yoshiki; Takefuji, Yoshiyasu   Annals of Epidemiology   2,026   https://doi.org/10.1016/j.annepidem.2026.01.005 

    29

    		  Beyond linear assumptions: Advancing lipidomic analysis in localized provoked vulvodynia   Oka, Souichi; Yoshida, Kiyo; Takefuji, Yoshiyasu   The Journal of Pain   2,026   https://doi.org/10.1016/j.jpain.2025.106179 
    28  From bias to reliable insight: Rethinking feature importance in microbiome analytics   Oka, Souichi; Yoshida, Kiyo; Takefuji, Yoshiyasu   Veterinary Microbiology   2,026   https://doi.org/10.1016/j.vetmic.2025.110838 
    27  Feature Importance Bias: Addressing Interpretability Issues in Tree-Based Acute Myocardial Infarction Risk Models   Oka, Souichi; Takemura, Kota; Takefuji, Yoshiyasu   Canadian Journal of Cardiology   2,025   https://doi.org/10.1016/j.cjca.2025.11.032 
    26  Beyond Parametric Boundaries: Rethinking the Distributed Lag Nonlinear Model in Meteorological Modelling for Oncology Emergencies   Oka, S.; Yoshida, K.; Takefuji, Y.   Clinical Oncology   2,026   https://doi.org/10.1016/j.clon.2025.103970 
    25  Beyond linear and parametric assumptions: A call for robust models in donor extracellular vesicles transcriptomics   Oka, Souichi; Yoshida, Kiyo; Takefuji, Yoshiyasu   The Journal of Thoracic and Cardiovascular Surgery   2,026   https://doi.org/10.1016/j.jtcvs.2025.09.041 
    24  Revisiting AI Model Interpretability in Lung Cancer Screening: Challenges in Balancing Predictive Performance and Reliability   Oka, Souichi; Takefuji, Yoshiyasu   Clinical Lung Cancer   2,025   https://doi.org/10.1016/j.cllc.2025.09.005 
    23  Beyond predictive accuracy: Statistical validation of feature importance in biomedical machine learning   Oka, Souichi; Inoue, Nobuko; Takefuji, Yoshiyasu   Computer Methods and Programs in Biomedicine   2,025   https://doi.org/10.1016/j.cmpb.2025.109085 
    22  Towards Reliable Feature Importance in Hashimoto's Thyroiditis Prediction: Reconstructing Machine Learning Frameworks   Oka, Souichi; Takefuji, Yoshiyasu   Ultrasound in Medicine & Biology   2,026   https://doi.org/10.1016/j.ultrasmedbio.2025.09.008 
    21  A call for more robust and interpretable models in predicting treatment-resistant depression   Oka, Souichi; Takemura, Kota; Takefuji, Yoshiyasu   European Neuropsychopharmacology   2,025   https://doi.org/10.1016/j.euroneuro.2025.09.012 
    20  Towards reliable feature interpretation in machine learning-based acute diarrhoea toxicity assessment   Oka, Souichi; Takahashi, Yoshiki; Takefuji, Yoshiyasu   Radiotherapy and Oncology   2,025   https://doi.org/10.1016/j.radonc.2025.111140 
    19  Reassessing PCA-based characterization of spiral ganglion neuron cell lines   Oka, Souichi; Ono, Ryota; Takefuji, Yoshiyasu   Neuroscience   2,025   https://doi.org/10.1016/j.neuroscience.2025.09.036 
    18  Pitfalls of XAI interpretation in environmental modeling: A warning on model bias in air quality data analysis   Oka, Souichi; Yamazaki, Takuma; Takefuji, Yoshiyasu   Environmental Modelling & Software   2,025   https://doi.org/10.1016/j.envsoft.2025.106700 
    17  Enhancing lipoprotein(a) association studies: A complementary approach to principal component analysis   Oka, Souichi; Inoue, Nobuko; Takefuji, Yoshiyasu   Journal of Clinical Lipidology   2,025   https://doi.org/10.1016/j.jacl.2025.08.021 
    16  Methodological Concerns in Radiomics: Addressing Bias in LASSO and SHAP for Thyroid Tumor Analysis   Iwata, Naoki; Oka, Souichi; Takefuji, Yoshiyasu   Ultrasound in Medicine & Biology   2,025   https://doi.org/10.1016/j.ultrasmedbio.2025.08.016 
    15  Clinical Machine Learning Pitfalls: Reliability of Feature Importance in Prediction of Continuous Renal   Oka, Souichi; Takefuji, Yoshiyasu   Journal of Cardiothoracic and Vascular Anesthesia   2,025   https://doi.org/10.1053/j.jvca.2025.08.035 
    14  Addressing Bias in machine learning feature importance for food quality assessment   Oka, Souichi; Yamazaki, Takuma; Takefuji, Yoshiyasu   Food Chemistry   2,025   https://doi.org/10.1016/j.foodchem.2025.146171 
    13  Beyond model-specific biases: An explainable multifaceted approach for robust PM10 source   Oka, Souichi; Yamazaki, Takuma; Takefuji, Yoshiyasu   Environmental Research   2,025   https://doi.org/10.1016/j.envres.2025.122656 
    12  Letter Re: Development of an artificial intelligence-generated, explainable treatment recommendation system for urothelial carcinoma and renal cell carcinoma to support multidisciplinary cancer conferences   Oka, Souichi; Yamazaki, Takuma; Takefuji, Yoshiyasu   European Journal of Cancer   2,025   https://doi.org/10.1016/j.ejca.2025.115733 
    11  Reassessing lipid-mood disorder associations: The limitations of PCA for nonlinear patterns   Ogawa, Soki; Oka, Souichi; Takefuji, Yoshiyasu   Journal of Affective Disorders   2,025   https://doi.org/10.1016/j.jad.2025.120024 
    10  Robust Feature Attribution in Radiomics: A Call for Multi-faceted Methodologies   Oka, Souichi; Takefuji, Yoshiyasu   Academic Radiology   2,025   https://doi.org/10.1016/j.acra.2025.07.048 
    9  Feature importance in building machine learning: Beyond model-dependent interpretations   Oka, Souichi; Yamazaki, Takuma; Takefuji, Yoshiyasu   Building and Environment   2,025   https://doi.org/10.1016/j.buildenv.2025.113493 
    8  Correspondence on “Large-scale analysis to identify risk factors for ovarian cancer” by Madakkatel et al   Oka, Souichi; Takefuji, Yoshiyasu   International Journal of Gynecological Cancer   2,025   https://doi.org/10.1016/j.ijgc.2025.102000 
    7  Complementing interpretable machine learning with synergistic analytical strategies for thyroid cancer recurrence prediction   Oka, Souichi; Takefuji, Yoshiyasu   European Journal of Radiology   2,025   https://doi.org/10.1016/j.ejrad.2025.112308 
    6  Re-evaluating structural equation modelling in nursing research: Insights from compassion fatigue and empowerment in Chinese intensive care units   Egawa, Mana; Oka, Souichi; Takefuji, Yoshiyasu   Australian Critical Care   2,025   https://doi.org/10.1016/j.aucc.2025.101292 
    5  Letter to the Editor: Complementary statistical approaches for interpreting machine learning feature importance in osteoporosis risk   Oka, Souichi; Yamazaki, Takuma; Takefuji, Yoshiyasu   Computers in Biology and Medicine   2,025   https://doi.org/10.1016/j.compbiomed.2025.110710 
    4  Comments on "Toward prediction and insight of porosity formation in laser welding: A physics-informed deep learning framework"   Oka, Souichi; Takefuji, Yoshiyasu   Scripta Materialia   2,025   https://doi.org/10.1016/j.scriptamat.2025.116857 
    3  Letter to the Editor regarding “Prediction of PFAS bioaccumulation in different plant tissues with machine learning models based on molecular fingerprints” by Song et al. (2024), Sci. Total Environ. 950 175091   Oka, Souichi; Takefuji, Yoshiyasu   Science of The Total Environment   2,025   https://doi.org/10.1016/j.scitotenv.2025.179714 
    2  Comments on "Dialogue between algorithms and soil: Machine learning unravels the mystery of phthalates pollution in soil" by Pan et al. (2025)   Oka, Souichi; Takefuji, Yoshiyasu   Journal of Hazardous Materials   2,025   https://doi.org/10.1016/j.jhazmat.2025.138366 
    1  Comment on "Optimized machine learning model for predicting unplanned reoperation after rectal cancer anterior resection"   Oka, Souichi; Takefuji, Yoshiyasu   European Journal of Surgical Oncology   2,025   https://doi.org/10.1016/j.ejso.2025.110025 

     


    Coming Soon.
    2026.4.1

    好奇心は、止まらない。

    AI研究所は、今のAIが抱える矛盾に真正面から向き合い、ビジネスの力に変える。

    © 2026 サイエンスパーク株式会社 AI研究所（仮称）　|　設立予定日：2026年4月1日