Takeshi Tohyama
Research Interests
Make your next move.
Prepare your application
Review drafts before you send them.
Explore related searches
Articles (9)
Year:
2026
BACKGROUND: Risk-prediction models are widely used for quality of care evaluations, resource management, and patient stratification in research. While established models have long been used for risk prediction, healthcare has evolved significantly, and the optimal model must be selected for evaluation in line with contemporary healthcare settings and regional considerations. OBJECTIVES: To evaluate the geographic and temporal generalizability of the models for mortality prediction in ICUs through external validation in Japan. DERIVATION COHORT: Not applicable. VALIDATION COHORT: The care Japanese Intensive care PAtient Database from 2015 to 2022. PREDICTION MODEL: The Global Open-Source Severity of Illness Score (GOSSIS-1), a modern risk model utilizing machine learning approaches, was compared with conventional models—the Acute Physiology and Chronic Health Evaluation (APACHE-II and APACHE-III)—and a locally calibrated model, the Japan Risk of Death (JROD). RESULTS: Despite the demographic and clinical differences of the validation cohort, GOSSIS-1 maintained strong discrimination, achieving an area under the curve of 0.908, comparable to APACHE-III (0.908) and JROD (0.910). It also exhibited superior calibration, achieving a standardized mortality ratio (SMR) of 0.89 (95% CI, 0.88–0.90), significantly outperforming APACHE-II (SMR, 0.39; 95% CI, 0.39–0.40) and APACHE-III (SMR, 0.46; 95% CI, 0.46–0.47), and demonstrating a performance close to that of JROD (SMR, 0.97; 95% CI, 0.96–0.99). However, performance varied significantly across disease categories, with suboptimal calibration for neurologic conditions and trauma. While the model showed temporal stability from 2015 to 2019, performance deteriorated during the COVID-19 pandemic, broadly reducing performance across disease categories in 2020. This trend was particularly pronounced in GOSSIS compared with APACHE-III. CONCLUSIONS: GOSSIS-1 demonstrates robust discrimination despite substantial geographic dataset shift but shows important calibration variations across disease categories. In particular, in a complex model like GOSSIS-1, stresses on the health system, such as a pandemic, can manifest changes in model calibration.
Year:
2025
Background and Aims Echocardiography serves as a cornerstone of cardiovascular diagnostics through multiple standardized imaging views. While recent AI foundation models demonstrate superior capabilities across cardiac imaging tasks, their massive computational requirements and reliance on large-scale datasets create accessibility barriers, limiting AI development to well-resourced institutions. Vector embedding approaches offer promising solutions by leveraging compact representations from original medical images for downstream applications. Furthermore, demographic fairness remains critical, as AI models may incorporate biases that confound clinically relevant features. We developed a multi-view encoder framework to address computational accessibility while investigating demographic fairness challenges. Methods We utilized the MIMIC-IV-ECHO dataset (7,169 echocardiographic studies) to develop a transformer-based multi-view encoder that aggregates view-level representations into study-level embeddings. The framework incorporated adversarial learning to suppress demographic information while maintaining clinical performance. We evaluated performance across 21 binary classification tasks encompassing echocardiographic measurements and clinical diagnoses, comparing against foundation model baselines with varying adversarial weights. Results The multi-view encoder achieved a mean improvement of 9.0 AUC points (12.0% relative improvement) across clinical tasks compared to foundation model embeddings. Performance remained robust with limited echocardiographic views compared to the conventional approach. However, adversarial learning showed limited effectiveness in reducing demographic shortcuts, with stronger weighting substantially compromising diagnostic performance. Conclusions Our framework democratizes advanced cardiac AI capabilities, enabling substantial diagnostic improvements without massive computational infrastructure. While algorithmic approaches to demographic fairness showed limitations, the multi-view encoder provides a practical pathway for broader AI adoption in cardiovascular medicine with enhanced efficiency in real-world clinical settings. Structured graphical abstract or graphical abstract Key Question Can multi-view encoder frameworks achieve superior diagnostic performance compared to foundation model embeddings while reducing computational requirements and maintaining robust performance with fewer echocardiographic views for cardiac AI applications? Key Finding Multi-view encoder achieved 12.0% relative improvement (9.0 AUC points) across 21 cardiac tasks compared to foundation model baselines, with efficient 512-dimensional vector embeddings and robust performance using fewer echocardiographic views. Take-home Message Vector embedding approaches with attention-based multi-view integration significantly improve cardiac diagnostic performance while reducing computational requirements, offering a pathway toward more efficient AI implementation in clinical settings. Translational Perspective Our proposed multi-view encoder framework overcomes critical barriers to the widespread adoption of artificial intelligence in echocardiography. By dramatically reducing computational requirements, the multi-view encoder approach allows smaller healthcare institutions to develop sophisticated AI models locally. The framework maintains robust performance with fewer echocardiographic examinations, which addresses real-world clinical constraints where comprehensive imaging is not feasible due to patient factors or time limitations. This technology provides a practical way to democratize advanced cardiac AI capabilities, which could improve access to cardiovascular care across diverse healthcare settings while reducing dependence on proprietary datasets and massive computational resources.
Year:
2025
Year:
2024
Background Although a tool for sharing patient prognosis among all medical staff is desirable in heart failure (HF) cases, only a few simple HF prognostic scores are available. We previously presented the A 2 B score, a simple user‐friendly HF risk score, and validated it in a small single‐center cohort. In the present study, we validated it in a larger nationwide cohort. Methods and Results We examined the 2‐year mortality in relation to the A 2 B scores in 3483 patients from a Japanese nationwide cohort and attempted to stratify their prognoses according to the scores. The A 2 B score was determined by assigning points for age, anemia, and brain natriuretic peptide (BNP) level at discharge: age (<65 years, 0; 65–74 years, 1; ≥75 years, 2), anemia (hemoglobin ≥12 g/dL, 0; 10–11.9 g/dL, 1; <10 g/dL, 2), and BNP (<200 pg/mL, 0; 200–499 pg/mL, 1; ≥500 pg/mL, 2). Hemoglobin and BNP levels were applied to the data at discharge. The 2‐year survival rates for A 2 B scores 1, 2, 3, 4, 5, and 6 were 94.1%, 83.2%, 74.1%, 63.5%, 51.6%, and 41.5%, respectively; the mortality rate increased by ≈10% for each point increase (c‐index, 0.702). The A 2 B score was applicable in HF cases with reduced or preserved ejection fraction and remained useful when BNP was substituted with N‐terminal proBNP (c‐index, 0.749, 0.676, and 0.682, respectively). Conclusions The A 2 B score showed a good prognostic value for HF in a large population even when BNP was replaced with N‐terminal proBNP.
Year:
2024
Year:
2023
Year:
2023
Year:
2023
Year:
2021
Collaborators (2)
Shouji Matsushima
Assistant professor
Kyushu University Hospital
Takuya Nagata
Kyushu University
Make your next move.
Prepare your application
Review drafts before you send them.