CIRCULATION CONTROL
Print ISSN : 0389-1844
Volume 39, Issue 3
Displaying 1-11 of 11 articles from this issue
  • Michihiro Sakai, Keita Saku
    Article type: Review
    2018 Volume 39 Issue 3 Pages 172-179
    Published: 2018
    Released on J-STAGE: February 02, 2019
    JOURNAL FREE ACCESS
    Medical artificial intelligence (Medical AI) is expected to produce great results in modern medicine. The strongest point of modern AI is a feature extraction technology that exceeds the recognition capacity of human in image, speech, motion capture, and big data. Deep machine learning brought about the great development of current AI since it has four unique features (multi task, multi modal, supervised/unsupervised/semi-supervised study modes, automatic acquisition of hierarchical features). It is unknown how to utilize medical AI in circulatory control medicine. There are several theories about deep machine learning (supervised, unsupervised, and semi-supervised), and each of which has its unique feature. In order to develop AI effectively in medicine, it is necessary to understand the basic theories and its advantage/disadvantages of deep learning methods.
    Download PDF (2540K)
  • Yukio Goto, Takashi Nakagawa, Kenji Shigemi
    2018 Volume 39 Issue 3 Pages 180-189
    Published: 2018
    Released on J-STAGE: February 02, 2019
    JOURNAL FREE ACCESS
    The last moment of the end-of-life in ICU is almost unconscious, thus any emotional discharge appearing or not in this time has not been proved. Then, using the non-linear heart rate variability that has made the brain-heart transmission, it focused on the occurrence or not of an emotional reaction in this moment contracting with a normal REM-sleep dream. By a small memory heart rate monitor and using 1/f-like spectrum analysis method by 1 ms based on ‘the theory of the comfort feeling by the 1/f sound fluctuation in the natural world widely’, and the new parameters of 4-balance indices, i.e. ‘As-Bal-I’, ‘SV-Bal-I’, ‘Hs-Bal-I’ and ‘Ls-Bal-I’ were calculated every 5 minutes interval using a MemCalc System. As the results, the patients immediately before cardiac arrest showed the rise-up of the ‘Hs-Bal-I’ as the cardiac activity struggling until then and also showed a sudden rise-up of ‘As-Bal-I’ as the emotional parameter and exceed over the ‘SV-Bal-I’. There was a little difference between the emotional dream reaction during the normal REM sleep and the end of life. That is, when the numerical level of ‘As-Bal-I’ was 0.5-1.5, it will be pleasant feeling, but this level was in upper than 2.0, it will be with painful. In conclusion, even if the patients were in unconscious, they might be visualized various emotional worlds like the dream phantasm immediately before death in the end-of-life. Like this, the Balance indices are useful parameters of fall down transmission system of information from brain center to cardiac.
    Download PDF (2590K)
Case Report
feedback
Top