Kensaku Takahashi

Dr. Kensaku Takahashi


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 July 2020 in Diagnostics
Verified
Journal Article
Open access
PDF file
SKShinji Kitamura
Shinji Kitamura
KTKensaku Takahashi
Kensaku Takahashi
YSYizhen Sang
Yizhen Sang
KFKazuhiko FUKUSHIMA
Kazuhiko FUKUSHIMA
Kenji TsujiKenji Tsuji
Kenji Tsuji
JWJun Wada
Jun Wada
Artificial Intelligence (AI) imaging diagnosis is developing, making enormous steps forward in medical fields. Regarding diabetic nephropathy (DN), medical doctors diagnose them with clinical course, clinical laboratory data and renal pathology, mainly evaluate with light microscopy images rather than immunofluorescent images because there are no characteristic findings in immunofluorescent images for DN diagnosis. Here, we examined the possibility of whether AI could diagnose DN from immunofluorescent images. We collected renal immunofluorescent images from 885 renal biopsy patients in our hospital, and we created a dataset that contains six types of immunofluorescent images of IgG, IgA, IgM, C3, C1q and Fibrinogen for each patient. Using the dataset, 39 programs worked without errors (Area under the curve (AUC): 0.93). Five programs diagnosed DN completely with immunofluorescent images (AUC: 1.00). By analyzing with Local interpretable model-agnostic explanations (Lime), the AI focused on the peripheral lesion of DN glomeruli. On the other hand, the nephrologist diagnostic ratio (AUC: 0.75833) was slightly inferior to AI diagnosis. These findings suggest that DN could be diagnosed only by immunofluorescent images by deep learning. AI could diagnose DN and identify classified unknown parts with the immunofluorescent images that nephrologists usually do not use for DN diagnosis.

10 February 2023 in Diagnostics
Verified
Journal Article
Open access
PDF file
NMNatsumi Matsuoka-Uchiyama
Natsumi Matsuoka-Uchiyama
Kenji TsujiKenji Tsuji
Kenji Tsuji
KTKensaku Takahashi
Kensaku Takahashi
KFKazuhiko Fukushima
Kazuhiko Fukushima
HTHidemi Takeuchi
Hidemi Takeuchi
JWJun Wada
Jun Wada
While hypothyroidism increases serum creatinine (Cr) levels, it is uncertain whether the elevation is mediated via a decline in the glomerular filtration rate (GFR) or the reflection of enhanced Cr production from the muscles or both. In the present study, we explored an association between urinary Cr excretion rate (CER) and hypothyroidism. A total of 553 patients with chronic kidney disease were enrolled in a cross-sectional study. Multiple linear regression analysis was performed to explore the association between hypothyroidism and urinary CER. The mean urinary CER was 1.01 ± 0.38 g/day and 121 patients (22%) had hypothyroidism. The multiple linear regression analysis revealed explanatory variables with urinary CER, including age, sex, body mass index, 24 h Cr clearance (24hrCcr), and albumin while hypothyroidism was not considered an independent explanatory variable. In addition, scatter plot analysis with regression fit line representing the association between estimated GFR calculated using s-Cr (eGFRcre) and 24hrCcr revealed that eGFRcre and 24hrCcr had strong correlations with each other in hypothyroid patients as well as euthyroid patients. Collectively, hypothyroidism was not considered an independent explanatory variable for urinary CER in the present study and eGFRcre is a useful marker to evaluate kidney function regardless of the presence of hypothyroidism.