arXiv subjects

Kyung Hwan Kim

Publications and source records attributed to Kyung Hwan Kim.

5 recordsLinked to original sources

arXiv2024

Improving Mortality Prediction After Radiotherapy with Large Language Model Structuring of Large-Scale Unstructured Electronic Health Records

Accurate survival prediction in radiotherapy (RT) is critical for optimizing treatment decisions. This study developed and validated the RT-Surv framework, which integrates general-domain, open-source large language models (LLMs) to structure unstructured electronic health records alongside structured clinical data. Using data from 34,276 patients and an external cohort of 852, the framework successfully transformed unstructured clinical information into structured formats. Incorporating LLM-structured clinical features improved the concordance index from 0.779 to 0.842 during external validation, demonstrating a significant performance enhancement. Key LLM-structured features, such as disease extent, general condition, and RT purpose, showed high predictive importance and aligned closely with statistically significant predictors identified through conventional statistical analyses, thereby improving model interpretability. Furthermore, the framework enhanced risk stratification, enabling more distinct differentiation among low-, intermediate-, and high-risk groups (p < 0.001) using LLM-structured clinical features. These findings highlight the potential of LLMs to convert unstructured data into actionable insights, improving predictive modeling and patient outcomes in clinics.

cs.CL↗

arXiv2024

Supercritical density fluctuations and structural heterogeneity in supercooled water-glycerol microdroplets

Recent experiments and theoretical studies strongly indicate that water exhibits a liquid-liquid phase transition (LLPT) in the supercooled domain. An open question is how the LLPT of water can affect the properties of aqueous solutions. Here, we study the structural and thermodynamic properties of supercooled glycerol-water microdroplets at dilute conditions ($χ_g=3.2~\%$ glycerol mole fraction). The combination of rapid evaporative cooling with ultrafast X-ray scattering allows us to outrun crystallization and gain access to the deeply supercooled regime down to $T=229.3$ K. We find that the density fluctuations of the glycerol-water solution or, equivalently, its isothermal compressibility, $κ_T$, increases upon cooling. This is confirmed by molecular dynamics simulations, which indicate that the presence of glycerol shifts the temperature of maximum $κ_T$ from $T=230$ K in pure water down to $T=223$ K in the solution. Our findings elucidate the interplay between the complex behavior of water, including its LLPT, and the properties of aqueous solutions at low temperatures, which can have practical consequences in cryogenic biological applications and cryopreservation techniques.

cond-mat.soft↗

arXiv2023

Melting Domain Size and Recrystallization Dynamics of Ice Revealed by Time-Resolved X-ray Scattering

The phase transition between water and ice is ubiquitous and one of the most important phenomena in nature. Here, we performed time-resolved x-ray scattering experiments capturing the melting and recrystallization dynamics of ice. The ultrafast heating of ice I is induced by an IR laser pulse and probed with an intense x-ray pulse, which provided us with direct structural information on different length scales. From the wide-angle x-ray scattering (WAXS) patterns, the molten fraction, as well as the corresponding temperature at each delay, were determined. The small-angle x-ray scattering (SAXS) patterns, together with the information extracted from the WAXS analysis, provided the time-dependent change of the size and the number of the liquid domains. The results show partial melting (~13 %) and superheating of ice occurring at around 20 ns. After 100 ns, the average size of the liquid domains grows from about 2.5 nm to 4.5 nm by the coalescence of approximately six adjacent domains. Subsequently, we capture the recrystallization of the liquid domains, which occurs on microsecond timescales due to the cooling by heat dissipation and results to a decrease of the average liquid domain size.

physics.chem-ph↗

arXiv2022

X-ray Free Electron Laser Studies of Electron and Phonon Dynamics of Graphene Adsorbed on Copper

We report optical pumping and X-ray absorption spectroscopy experiments at the PAL free electron laser that directly probe the electron dynamics of a graphene monolayer adsorbed on copper in the femtosecond regime. By analyzing the results with ab-initio theory we infer that the excitation of graphene is dominated by indirect excitation from hot electron-hole pairs created in the copper by the optical laser pulse. However, once the excitation is created in graphene, its decay follows a similar path as in many previous studies of graphene adsorbed on semiconductors, i e. rapid excitation of SCOPS (Strongly Coupled Optical Phonons) and eventual thermalization. It is likely that the lifetime of the hot electron-hole pairs in copper governs the lifetime of the electronic excitation of the graphene.

cond-mat.mes-hall↗

arXiv2021

An Interpretable Web-based Glioblastoma Multiforme Prognosis Prediction Tool using Random Forest Model

We propose predictive models that estimate GBM patients' health status of one-year after treatments (Classification task), predict the long-term prognosis of GBM patients at an individual level (Survival task). We used total of 467 GBM patients' clinical profile consists of 13 features and two follow-up dates. For baseline models of random forest classifier(RFC) and random survival forest model (RSF), we introduced generalized linear model (GLM), support vector machine (SVM) and Cox proportional hazardous model (COX), accelerated failure time model (AFT) respectively. After preprocessing and prefixing stratified 5-fold data set, we generated best performing models for model types using recursive feature elimination process. Total 10, 4, and 13 features were extracted for best performing one-year survival/progression status RFC models and RSF model via the recursive feature elimination process. In classification task, AUROC of best performing RFC recorded 0.6990 (for one-year survival status classification) and 0.7076 (for one-year progression classification) while that of second best baseline models (GLM in both cases) recorded 0.6691 and 0.6997 respectively. About survival task, the highest C-index of 0.7157 and the lowest IBS of 0.1038 came from the best performing RSF model while that of second best baseline models were 0.6556 and 0.1139 respectively. A simplified linear correlation (extracted from LIME and virtual patient group analysis) between each feature and prognosis of GBM patient were consistent with proven medical knowledge. Our machine learning models suggest that the top three prognostic factors for GBM patient survival were MGMT gene promoter, the extent of resection, and age. To the best of our knowledge, this study is the very first study introducing a interpretable and medical knowledge consistent GBM prognosis predictive models.

cs.LG↗