Development and validation of novel simple prognostic model for predicting mortality in Korean intensive care units using national insurance claims data.

BACKGROUND/AIMS: Intensive care unit (ICU) quality is largely determined by the mortality rate. Therefore, we aimed to develop and validate a novel prognostic model for predicting mortality in Korean ICUs, using national insurance claims data. METHODS: Data were obtained from the health insurance claims database maintained by the Health Insurance Review and Assessment Service of South Korea. From patients who underwent the third ICU adequacy evaluation, 42,489 cases were enrolled and randomly divided into the derivation and validation cohorts. Using the models derived from the derivation cohort, we analyzed whether they accurately predicted death in the validation cohort. The models were verified using data from one general and two tertiary hospitals. RESULTS: Two severity correction models were created from the derivation cohort data, by applying variables selected through statistical analysis, through clinical consensus, and from performing multiple logistic regression analysis. Model 1 included six categorical variables (age, sex, Charlson comorbidity index, ventilator use, hemodialysis or continuous renal replacement therapy, and vasopressor use). Model 2 additionally included presence/absence of ICU specialists and nursing grades. In external validation, the performance of models 1 and 2 for predicting in-hospital and ICU mortality was not inferior to that of pre-existing scoring systems. CONCLUSION: The novel and simple models could predict in-hospital and ICU mortality and were not inferior compared to the pre-existing scoring systems.

Mastering data visualization with Python: practical tips for researchers.

Big data have revolutionized the way data are processed and used across all fields. In the past, research was primarily conducted with a focus on hypothesis confirmation using sample data. However, in the era of big data, this has shifted to gaining insights from the collected data. Visualizing vast amounts of data to derive insights is crucial. For instance, leveraging big data for visualization can help identify and predict characteristics and patterns related to various infectious diseases. When data are presented in a visual format, patterns within the data become clear, making it easier to comprehend and provide deeper insights. This study aimed to comprehensively discuss data visualization and the various techniques used in the process. It also sought to enable researchers to directly use Python programs for data visualization. By providing practical visualization exercises on GitHub, this study aimed to facilitate their application in research endeavors.

MCHeart: Multi-Channel-Based Heart Signal Processing Scheme for Heart Noise Detection Using Deep Learning.

In this study, we constructed a model to predict abnormal cardiac sounds using a diverse set of auscultation data collected from various auscultation positions. Abnormal heart sounds were identified by extracting features such as peak intervals and noise characteristics during systole and diastole. Instead of using raw signal data, we transformed them into log-mel 2D spectrograms, which were employed as input variables for the CNN model. The advancement of our model involves integrating a deep learning architecture with feature extraction techniques based on existing knowledge of cardiac data. Specifically, we propose a multi-channel-based heart signal processing (MCHeart) scheme, which incorporates our proposed features into the deep learning model. Additionally, we introduce the ReLCNN model by applying residual blocks and MHA mechanisms to the LCNN architecture. By adding murmur features with a smoothing function and training the ReLCNN model, the weighted accuracy of the model increased from 79.6% to 83.6%, showing a performance improvement of approximately 4% point compared to the LCNN baseline model.

Laboratory information management system for COVID-19 non-clinical efficacy trial data.

BACKGROUND: As the number of large-scale studies involving multiple organizations producing data has steadily increased, an integrated system for a common interoperable format is needed. In response to the coronavirus disease 2019 (COVID-19) pandemic, a number of global efforts are underway to develop vaccines and therapeutics. We are therefore observing an explosion in the proliferation of COVID-19 data, and interoperability is highly requested in multiple institutions participating simultaneously in COVID-19 pandemic research. RESULTS: In this study, a laboratory information management system (LIMS) approach has been adopted to systemically manage various COVID-19 non-clinical trial data, including mortality, clinical signs, body weight, body temperature, organ weights, viral titer (viral replication and viral RNA), and multiorgan histopathology, from multiple institutions based on a web interface. The main aim of the implemented system is to integrate, standardize, and organize data collected from laboratories in multiple institutes for COVID-19 non-clinical efficacy testings. Six animal biosafety level 3 institutions proved the feasibility of our system. Substantial benefits were shown by maximizing collaborative high-quality non-clinical research. CONCLUSIONS: This LIMS platform can be used for future outbreaks, leading to accelerated medical product development through the systematic management of extensive data from non-clinical animal studies.