Kyushu University · Medicine
Professor Koutarou Matsumoto's research lab specializes in developing and validating data-driven predictive models for neurological emergencies, with a focus on acute ischemic stroke and intracerebral hemorrhage. The lab integrates real-world clinical data, medical imaging, and machine learning to enhance clinical decision support systems, particularly for non-specialists in emergency settings. Key research directions include multimodal risk prediction, model calibration, and leveraging learning health systems to optimize patient outcomes.
Figures are computed from collected data and may differ slightly.
Background and Purpose- Several stroke prognostic scores have been developed to predict clinical outcomes after stroke. This study aimed to develop and validate novel data-driven predictive models for clinical outcomes by referring to previous prognostic scores in patients with acute ischemic stroke in a real-world setting. Methods- We used retrospective data of 4237 patients with acute ischemic stroke who were hospitalized in a single stroke center in Japan between January 2012 and August 2017.
ML-based prediction models exhibit satisfactory performance in predicting post-ICH in-hospital mortality when utilizing raw imaging data or nonspecialist input. Nevertheless, incorporating specialist expertise notably improves performance.
The XGBoost model did not significantly outperform the LASSO model in predicting postoperative delirium. Furthermore, a parsimonious logistic model with a few important predictors achieved comparable performance to machine learning models in predicting postoperative delirium.
Risk-appropriate care informed by the use of learning health system data could improve care and potentially reduce the risk of SAP in patients with intracerebral hemorrhage in the acute stage.
The data-driven prediction model implementing the ePath system exhibited adequate performance in predicting PAL post-video-assisted thoracoscopic surgery, optimizing variables and considering population characteristics in a real-world setting.
Multimodal prediction models have the potential to aid non-specialists in making informed decisions regarding ICH cases in emergency departments as part of clinical decision support systems. Enhancing real-world data infrastructure and improving model calibration are essential for successful implementation in clinical practice.
Swin-Transformer consistently demonstrated superior discrimination compared to ResNet. This trend persisted even under unique distribution shifts in the fundus images.
Delirium in hospitalized patients is a worldwide problem, causing a burden on healthcare professionals and impacting patient prognosis. A machine learning interpretation method (ML interpretation method) presents the results of machine learning predictions and promotes guided decisions. This study focuses on visualizing the predictors of delirium using a ML interpretation method and implementing the analysis results in clinical practice. Retrospective data of 55,389 patients hospitalized in a si
The purpose of this study is investigation of transmitting phased array antennas for a future wireless power transfer (WPT) demonstration satellite experiment. A sequential array was used to construct an array antenna to improve the overall axial ratio of the transmitting array antenna. We evaluate the characteristics based on simulations for three types of arrays. We conduct experiments using the model determined in the simulations to validate the reliability of the simulations.
Delirium is common in the emergency department, and once it develops, there is a risk of self-extubation of drains and tubes, so it is critical to predict delirium before it occurs. Machine learning was used to create two prediction models in this study: one for predicting the occurrence of delirium and one for predicting self-extubation after delirium. Each model showed high discriminative performance, indicating the possibility of selecting high-risk cases. Visualization of predictors using Sh
<sec> <title>BACKGROUND</title> Although machine learning models demonstrate significant potential in predicting postoperative delirium, the advantages of their implementation in real-world settings remain unclear and require a comparison with conventional models in practical applications. </sec> <sec> <title>OBJECTIVE</title> The objective of this study was to validate the temporal generalizability of decision tree ensemble and sparse linear regression models for predicting delirium after surge
In wireless power transfer, it is crucial to deliver a power transmission beam efficiently to a precise direction. This paper examines methods to reduce the direction error of the main lobe and the deviation of the main lobe amplitude from their design values in a phased array antenna for wireless power transfer.
Open papers in the app to read, cite, and organize with AI.
