Development of non-bias phenotypic drug screening for cardiomyocyte hypertrophy by image segmentation using deep learning.

The number of patients with heart failure and related deaths is rapidly increasing worldwide, making it a major problem. Cardiac hypertrophy is a crucial preliminary step in heart failure, but its treatment has not yet been fully successful. In this study, we established a system to evaluate cardiomyocyte hypertrophy using a deep learning-based high-throughput screening system and identified drugs that inhibit it. First, primary cultured cardiomyocytes from neonatal rats were stimulated by both angiotensin II and endothelin-1, and cellular images were captured using a phase-contrast microscope. Subsequently, we used a deep learning model for instance segmentation and established a system to automatically and unbiasedly evaluate the cardiomyocyte size and perimeter. Using this system, we screened 100 FDA-approved drugs library and identified 12 drugs that inhibited cardiomyocyte hypertrophy. We focused on ezetimibe, a cholesterol absorption inhibitor, that inhibited cardiomyocyte hypertrophy in a dose-dependent manner in vitro. Additionally, ezetimibe improved the cardiac dysfunction induced by pressure overload in mice. These results suggest that the deep learning-based system is useful for the evaluation of cardiomyocyte hypertrophy and drug screening, leading to the development of new treatments for heart failure.

The Effectiveness of a Deep Learning Model to Detect Left Ventricular Systolic Dysfunction from Electrocardiograms.

Deep learning models can be applied to electrocardiograms (ECGs) to detect left ventricular (LV) dysfunction. We hypothesized that applying a deep learning model may improve the diagnostic accuracy of cardiologists in predicting LV dysfunction from ECGs. We acquired 37,103 paired ECG and echocardiography data records of patients who underwent echocardiography between January 2015 and December 2019. We trained a convolutional neural network to identify the data records of patients with LV dysfunction (ejection fraction < 40%) using a dataset of 23,801 ECGs. When tested on an independent set of 7,196 ECGs, we found the area under the receiver operating characteristic curve was 0.945 (95% confidence interval: 0.936-0.954). When 7 cardiologists interpreted 50 randomly selected ECGs from the test dataset of 7,196 ECGs, their accuracy for predicting LV dysfunction was 78.0% ± 6.0%. By referring to the model's output, the cardiologist accuracy improved to 88.0% ± 3.7%, which indicates that model support significantly improved the cardiologist diagnostic accuracy (P = 0.02). A sensitivity map demonstrated that the model focused on the QRS complex when detecting LV dysfunction on ECGs. We developed a deep learning model that can detect LV dysfunction on ECGs with high accuracy. Furthermore, we demonstrated that support from a deep learning model can help cardiologists to identify LV dysfunction on ECGs.

Selective elimination of undifferentiated human pluripotent stem cells using pluripotent state-specific immunogenic antigen Glypican-3.

Immunogenicity of immature pluripotent stem cells is a topic of intense debate. Immunogenic antigens, which are specific in pluripotent states, have not been described previously. In this study, we identified glypican-3 (GPC3), a known carcinoembryonic antigen, as a pluripotent state-specific immunogenic antigen. Additionally, we validated the applicability of human leukocyte antigen (HLA)-class I-restricted GPC3-reactive cytotoxic T lymphocytes (CTLs) in the removal of undifferentiated pluripotent stem cells (PSCs) from human induced pluripotent stem cell (hiPSC)-derivatives. HiPSCs uniquely express GPC3 in pluripotent states and were rejected by GPC3-reactive CTLs, which were sensitized with HLA-class I-restricted GPC3 peptides. Furthermore, GPC3-reactive CTLs selectively removed undifferentiated PSCs from hiPSC-derivatives in vitro and inhibited tumor formation in vivo. Our results demonstrate that GPC3 works as a pluripotent state-specific immunogenic antigen in hiPSCs and is applicable to regenerative medicine as a method of removing undifferentiated PSCs, which are the main cause of tumor formation.

Enhanced optineurin E50K-TBK1 interaction evokes protein insolubility and initiates familial primary open-angle glaucoma.

Glaucoma is the leading cause for blindness affecting 60 million people worldwide. The optineurin (OPTN) E50K mutation was first identified in familial primary open-angle glaucoma (POAG), the onset of which is not associated with intraocular pressure (IOP) elevation, and is classified as normal-tension glaucoma (NTG). Optineurin (OPTN) is a multifunctional protein and its mutations are associated with neurodegenerative diseases such as POAG and amyotrophic lateral sclerosis (ALS). We have previously described an E50K mutation-carrying transgenic (E50K-tg) mouse that exhibited glaucomatous phenotypes of decreased retinal ganglion cells (RGCs) and surrounding cell death at normal IOP. Further phenotypic analysis of these mice revealed persistent reactive gliosis and E50K mutant protein deposits in the outer plexiform layer (OPL). Over-expression of E50K in HEK293 cells indicated accumulation of insoluble OPTN in the endoplasmic reticulum (ER). This phenomenon was consistent with the results seen in neurons derived from induced pluripotent stem cells (iPSCs) from E50K mutation-carrying NTG patients. The E50K mutant strongly interacted with TANK-binding kinase 1 (TBK1), which prohibited the proper oligomerization and solubility of OPTN, both of which are important for OPTN intracellular transition. Treatment with a TBK1 inhibitor, BX795, abrogated the aberrant insolubility of the E50K mutant. Here, we delineated the intracellular dynamics of the endogenous E50K mutant protein for the first time and demonstrated how this mutation causes OPTN insolubility, in association with TBK1, to evoke POAG.

Analysis of cardiomyocyte movement in the developing murine heart.

The precise assemblage of several types of cardiac precursors controls heart organogenesis. The cardiac precursors show dynamic movement during early development and then form the complicated heart structure. However, cardiomyocyte movements inside the newly organized mammalian heart remain unclear. We previously established the method of ex vivo time-lapse imaging of the murine heart to study cardiomyocyte behavior by using the Fucci (fluorescent ubiquitination-based cell cycle indicator) system, which can effectively label individual G1, S/G2/M, and G1/S-transition phase nuclei in living cardiomyocytes as red, green, and yellow, respectively. Global analysis of gene expression in Fucci green positive ventricular cardiomyocytes confirmed that cell cycle regulatory genes expressed in G1/S, S, G2/M, and M phase transitions were upregulated. Interestingly, pathway analysis revealed that many genes related to the cell cycle were significantly upregulated in the Fucci green positive ventricular cardiomyocytes, while only a small number of genes related to cell motility were upregulated. Time-lapse imaging showed that murine proliferating cardiomyocytes did not exhibit dynamic movement inside the heart, but stayed on site after entering the cell cycle.

Time-lapse imaging of cell cycle dynamics during development in living cardiomyocyte.

Mammalian cardiomyocytes withdraw from the cell cycle shortly after birth, although it remains unclear how cardiomyocyte cell cycles behave during development. Compared to conventional immunohistochemistry in static observation, time-lapse imaging can reveal comprehensive data in hard-to-understand biological phenomenon. However, there are no reports of an established protocol of successful time-lapse imaging in mammalian heart. Thus, it is valuable to establish a time-lapse imaging system to enable the observation of cell cycle dynamics in living murine cardiomyocytes. This study sought to establish time-lapse imaging of murine heart to study cardiomyocyte cell cycle behavior. The Fucci (fluorescent ubiquitination-based cell cycle indicator) system can effectively label individual G1, S/G2/M, and G1/S-transition phase nuclei red, green and yellow, respectively, in living mammalian cells, and could therefore be useful to visualize the real-time cell cycle transitions in living murine heart. To establish a similar system for time-lapse imaging of murine heart, we first developed an ex vivo culture system, with the culture conditions determined in terms of sample state, serum concentration, and oxygen concentration. The optimal condition (slice culture, oxygen concentration 20%, serum concentration 10%) successfully mimicked physiological cardiomyocyte proliferation in vivo. Time-lapse imaging of cardiac slices from E11.5, E14.5, E18.5, and P1 Fucci-expressing transgenic mice revealed an elongated S/G2/M phase in cardiomyocytes during development. Our time-lapse imaging of murine heart revealed a gradual elongation of the S/G2/M phase during development in living cardiomyocytes.

A Comparative Study of Access Analysis Service Utilization on Japanese Medical Institutions' Websites with GDPR-Compliant Cases.

The browsing history of a medical institution's website can potentially reveal or identify information about the health condition of the website visitor through browser cookies and fingerprints. In Japan, although the Personal Information Protection Law was revised in April 2022, the use of access analysis services to collect browsing history on medical institution websites has not been investigated. Therefore, this study investigates the actual usage of access analysis services on Japanese medical institution websites and compares it with the current situation in France, which follows the General Data Protection Regulation. The results revealed that the larger the size of the hospital, the higher the percentage of adoption of access analytics services in Japan. However, the implementation of a system for obtaining consent for the use of access analysis in Japan was found to be poor compared to that of French medical institutions. While access analysis tools are used in the websites of several medical institutions in Japan, the implementation of the process of obtaining consent to acquire browsing history is poor.

Graph Representation Learning-Based Fixed-Length Clinical Feature Vector Generation from Heterogeneous Medical Records.

Transformation of patient data extracted from a database into fixed-length numerical vectors requires expertise in topical medical knowledge as well as data manipulation-thus, manual feature design is labor-intensive. In this study, we propose a machine learning-based method to for this purpose applicable to electronic medical data recorded during hospitalization, which utilizes unsupervised feature extraction based on graph embedding. Unsupervised learning is performed on a heterogeneous graph using Graph2Vec, and the inclusion of clinically useful data in the obtained embedding representation is evaluated by predicting readmission within 30 days of discharge based on it. The embedded representations are observed to improve predictive performance significantly as the information contained in the graph increases, indicating the suitability of the proposed method for feature design corresponding to clinical information.

Providing Practical Knowledge and Skills to Handle Real-World Data? Lessons Learned from Med RWD Program.

Both lectures and hands-on education are essential for the development of human resources that can use real-world data (RWD). The University of Tokyo has launched a new hybrid-style RWD educational program entitled "Medical Real World Data Utilization Human Resource Development Project" from FY2019 onwards. We present an overview of the overall picture of the project, including the development process of the educational program and the challenges associated with it.

Immediate postnatal prediction of death or bronchopulmonary dysplasia among very preterm and very low birth weight infants based on gradient boosting decision trees algorithm: A nationwide database study in Japan.

INTRODUCTION: Bronchopulmonary dysplasia (BPD) poses a substantial global health burden. Individualized treatment strategies based on early prediction of the development of BPD can mitigate preterm birth complications; however, previously suggested predictive models lack early postnatal applicability. We aimed to develop predictive models for BPD and mortality based on immediate postnatal clinical data. METHODS: Clinical information on very preterm and very low birth weight infants born between 2008 and 2018 was extracted from a nationwide Japanese database. The gradient boosting decision trees (GBDT) algorithm was adopted to predict BPD and mortality, using predictors within the first 6 h postpartum. We assessed the temporal validity and evaluated model adequacy using Shapley additive explanations (SHAP) values. RESULTS: We developed three predictive models using data from 39,488, 39,096, and 40,291 infants to predict "death or BPD," "death or severe BPD," and "death before discharge," respectively. These well-calibrated models achieved areas under the receiver operating characteristic curve of 0.828 (95% CI: 0.828-0.828), 0.873 (0.873-0.873), and 0.887 (0.887-0.888), respectively, outperforming the multivariable logistic regression models. SHAP value analysis identified predictors of BPD, including gestational age, size at birth, male sex, and persistent pulmonary hypertension. In SHAP value-based case clustering, the "death or BPD" prediction model stratified infants by gestational age and persistent pulmonary hypertension, whereas the other models for "death or severe BPD" and "death before discharge" commonly formed clusters of low mortality, extreme prematurity, low Apgar scores, and persistent pulmonary hypertension of the newborn. CONCLUSIONS: GBDT models for predicting BPD and mortality, designed for use within 6 h postpartum, demonstrated superior prognostic performance. SHAP value-based clustering, a data-driven approach, formed clusters of clinical relevance. These findings suggest the efficacy of a GBDT algorithm for the early postnatal prediction of BPD.