Integration of National Health Insurance claims data and animal models reveals fexofenadine as a promising repurposed drug for Parkinson's disease.

BACKGROUND: Parkinson's disease (PD) is a common and costly progressive neurodegenerative disease of unclear etiology. A disease-modifying approach that can directly stop or slow its progression remains a major unmet need in the treatment of PD. A clinical pharmacology-based drug repositioning strategy is a useful approach for identifying new drugs for PD. METHODS: We analyzed claims data obtained from the National Health Insurance Service (NHIS), which covers a significant portion of the South Korean population, to investigate the association between antihistamines, a class of drugs commonly used to treat allergic symptoms by blocking H1 receptor, and PD in a real-world setting. Additionally, we validated this model using various animal models of PD such as the 6-hydroxydopmaine (6-OHDA), α-synuclein preformed fibrils (PFF) injection, and Caenorhabditis elegans (C. elegans) models. Finally, whole transcriptome data and Ingenuity Pathway Analysis (IPA) were used to elucidate drug mechanism pathways. RESULTS: We identified fexofenadine as the most promising candidate using National Health Insurance claims data in the real world. In several animal models, including the 6-OHDA, PFF injection, and C. elegans models, fexofenadine ameliorated PD-related pathologies. RNA-seq analysis and the subsequent experiments suggested that fexofenadine is effective in PD via inhibition of peripheral immune cell infiltration into the brain. CONCLUSION: Fexofenadine shows promise for the treatment of PD, identified through clinical data and validated in diverse animal models. This combined clinical and preclinical approach offers valuable insights for developing novel PD therapeutics.

Redefining Health Care Data Interoperability: Empirical Exploration of Large Language Models in Information Exchange.

BACKGROUND: Efficient data exchange and health care interoperability are impeded by medical records often being in nonstandardized or unstructured natural language format. Advanced language models, such as large language models (LLMs), may help overcome current challenges in information exchange. OBJECTIVE: This study aims to evaluate the capability of LLMs in transforming and transferring health care data to support interoperability. METHODS: Using data from the Medical Information Mart for Intensive Care III and UK Biobank, the study conducted 3 experiments. Experiment 1 assessed the accuracy of transforming structured laboratory results into unstructured format. Experiment 2 explored the conversion of diagnostic codes between the coding frameworks of the ICD-9-CM (International Classification of Diseases, Ninth Revision, Clinical Modification), and Systematized Nomenclature of Medicine Clinical Terms (SNOMED-CT) using a traditional mapping table and a text-based approach facilitated by the LLM ChatGPT. Experiment 3 focused on extracting targeted information from unstructured records that included comprehensive clinical information (discharge notes). RESULTS: The text-based approach showed a high conversion accuracy in transforming laboratory results (experiment 1) and an enhanced consistency in diagnostic code conversion, particularly for frequently used diagnostic names, compared with the traditional mapping approach (experiment 2). In experiment 3, the LLM showed a positive predictive value of 87.2% in extracting generic drug names. CONCLUSIONS: This study highlighted the potential role of LLMs in significantly improving health care data interoperability, demonstrated by their high accuracy and efficiency in data transformation and exchange. The LLMs hold vast potential for enhancing medical data exchange without complex standardization for medical terms and data structure.

Changes in the Circadian Rhythm of High-Frequency Heart Rate Variability Associated With Depression.

BACKGROUND: Heart rate variability (HRV) extracted from electrocardiogram measured for a short period during a resting state is clinically used as a bio-signal reflecting the emotional state. However, as interest in wearable devices increases, greater attention is being paid to HRV extracted from long-term electrocardiogram, which may contain additional clinical information. The purpose of this study was to examine the characteristics of HRV parameters extracted through long-term electrocardiogram and explore the differences between participants with and without depression and anxiety symptoms. METHODS: Long-term electrocardiogram was acquired from 354 adults with no psychiatric history who underwent Holter monitoring. Evening and nighttime HRV and the ratio of nighttime-to-evening HRV were compared between 127 participants with depressive symptoms and 227 participants without depressive symptoms. Comparisons were also made between participants with and without anxiety symptoms. RESULTS: Absolute values of HRV parameters did not differ between groups based on the presence of depressive or anxiety symptoms. Overall, HRV parameters increased at nighttime compared to evening. Participants with depressive symptoms showed a significantly higher nighttime-to-evening ratio of high-frequency HRV than participants without depressive symptoms. The nighttime-to-evening ratio of HRV parameters did not show a significant difference depending on the presence of anxiety symptoms. CONCLUSION: HRV extracted through long-term electrocardiogram showed circadian rhythm. Depression may be associated with changes in the circadian rhythm of parasympathetic tone.

Automated Detection of Acute Myocardial Infarction Using Asynchronous Electrocardiogram Signals-Preview of Implementing Artificial Intelligence With Multichannel Electrocardiographs Obtained From Smartwatches: Retrospective Study.

BACKGROUND: When using a smartwatch to obtain electrocardiogram (ECG) signals from multiple leads, the device has to be placed on different parts of the body sequentially. The ECG signals measured from different leads are asynchronous. Artificial intelligence (AI) models for asynchronous ECG signals have barely been explored. OBJECTIVE: We aimed to develop an AI model for detecting acute myocardial infarction using asynchronous ECGs and compare its performance with that of the automatic ECG interpretations provided by a commercial ECG analysis software. We sought to evaluate the feasibility of implementing multiple lead-based AI-enabled ECG algorithms on smartwatches. Moreover, we aimed to determine the optimal number of leads for sufficient diagnostic power. METHODS: We extracted ECGs recorded within 24 hours from each visit to the emergency room of Ajou University Medical Center between June 1994 and January 2018 from patients aged 20 years or older. The ECGs were labeled on the basis of whether a diagnostic code corresponding to acute myocardial infarction was entered. We derived asynchronous ECG lead sets from standard 12-lead ECG reports and simulated a situation similar to the sequential recording of ECG leads via smartwatches. We constructed an AI model based on residual networks and self-attention mechanisms by randomly masking each lead channel during the training phase and then testing the model using various targeting lead sets with the remaining lead channels masked. RESULTS: The performance of lead sets with 3 or more leads compared favorably with that of the automatic ECG interpretations provided by a commercial ECG analysis software, with 8.1%-13.9% gain in sensitivity when the specificity was matched. Our results indicate that multiple lead-based AI-enabled ECG algorithms can be implemented on smartwatches. Model performance generally increased as the number of leads increased (12-lead sets: area under the receiver operating characteristic curve [AUROC] 0.880; 4-lead sets: AUROC 0.858, SD 0.008; 3-lead sets: AUROC 0.845, SD 0.011; 2-lead sets: AUROC 0.813, SD 0.018; single-lead sets: AUROC 0.768, SD 0.001). Considering the short amount of time needed to measure additional leads, measuring at least 3 leads-ideally more than 4 leads-is necessary for minimizing the risk of failing to detect acute myocardial infarction occurring in a certain spatial location or direction. CONCLUSIONS: By developing an AI model for detecting acute myocardial infarction with asynchronous ECG lead sets, we demonstrated the feasibility of multiple lead-based AI-enabled ECG algorithms on smartwatches for automated diagnosis of cardiac disorders. We also demonstrated the necessity of measuring at least 3 leads for accurate detection. Our results can be used as reference for the development of other AI models using sequentially measured asynchronous ECG leads via smartwatches for detecting various cardiac disorders.

Machine Learning Approach for Active Vaccine Safety Monitoring.

BACKGROUND: Vaccine safety surveillance is important because it is related to vaccine hesitancy, which affects vaccination rate. To increase confidence in vaccination, the active monitoring of vaccine adverse events is important. For effective active surveillance, we developed and verified a machine learning-based active surveillance system using national claim data. METHODS: We used two databases, one from the Korea Disease Control and Prevention Agency, which contains flu vaccination records for the elderly, and another from the National Health Insurance Service, which contains the claim data of vaccinated people. We developed a case-crossover design based machine learning model to predict the health outcome of interest events (anaphylaxis and agranulocytosis) using a random forest. Feature importance values were evaluated to determine candidate associations with each outcome. We investigated the relationship of the features to each event via a literature review, comparison with the Side Effect Resource, and using the Local Interpretable Model-agnostic Explanation method. RESULTS: The trained model predicted each health outcome of interest with a high accuracy (approximately 70%). We found literature supporting our results, and most of the important drug-related features were listed in the Side Effect Resource database as inducing the health outcome of interest. For anaphylaxis, flu vaccination ranked high in our feature importance analysis and had a positive association in Local Interpretable Model-Agnostic Explanation analysis. Although the feature importance of vaccination was lower for agranulocytosis, it also had a positive relationship in the Local Interpretable Model-Agnostic Explanation analysis. CONCLUSION: We developed a machine learning-based active surveillance system for detecting possible factors that can induce adverse events using health claim and vaccination databases. The results of the study demonstrated a potentially useful application of two linked national health record databases. Our model can contribute to the establishment of a system for conducting active surveillance on vaccination.

Stroke Incidence in Survivors of Carbon Monoxide Poisoning in South Korea: A Population-Based Longitudinal Study.

BACKGROUND Carbon monoxide (CO) poisoning is a suspected risk factor for stroke. However, the association between stroke occurrence and carbon monoxide poisoning remains unclear. This nationwide study in Korea analyzed the incidence of stroke in survivors of CO poisoning. MATERIAL AND METHODS In this nationwide, population-based longitudinal study, the database of the Health Insurance Review and Assessment Service was searched to identify patients diagnosed with CO poisoning from 2012 to 2018. Their incidence of ischemic and hemorrhagic strokes, the patterns of stroke incidences, the annual incidence rates in sequential time, the standardized incidence ratio (SIR), and the effects of hyperbaric oxygen therapy (HBOT) were analyzed. RESULTS Of the 29 301 patients diagnosed with CO poisoning during the study period, 984 (3.36%) were diagnosed with stroke after CO poisoning, with approximately 50% occurring within 1 year after CO poisoning. The overall SIR for stroke was 19.49 (95% confidence interval [CI], 17.92-21.12) during the first year, decreasing to 5.64 (95% CI, 4.75-6.66) during the second year. Overall stroke hazard ratio (HR) in the patients admitted to the ICU for CO poisoning was 2.28 (95% CI, 1.19-2.27), compared with 2.35 (95% CI, 1.94-2.84) for ischemic stroke and 1.76 (95% CI, 1.11-2.78) for hemorrhagic stroke. Cumulative HRs did not differ between patients who were and were not treated with HBOT for stroke. CONCLUSIONS CO poisoning is a high-risk factor for the development of stroke, evidenced by high incidences of stroke after CO poisoning. Practical strategies for preventing stroke after CO poisoning are needed, because stroke after CO poisoning affects adults of almost all ages, significantly increasing their socioeconomic burden.

Does Exposure to Computed Tomography Contrast Media Increase Risk of End-Stage Renal Disease?

BACKGROUND There are many studies on acute kidney injury (AKI) after exposure to contrast media in patients with chronic kidney disease (CKD). However, whether the risk of end-stage renal disease (ESRD) increases after exposure to contrast media in the long term, regardless of development of AKI after such exposure, has not been studied. MATERIAL AND METHODS The electronic health records of patients diagnosed with CKD and followed up from 2014 to 2018 at a tertiary university hospital were retrospectively collected. Patients were divided into patients who progressed to ESRD (ESRD group) and those who did not (non-ESRD group). Patients in the non-ESRD group were matched 1: 1 to those in the ESRD group by using disease risk score generation and matching. Multivariate logistic regression analysis was performed to assess the effect of contrast media exposure on progression to ESRD. RESULTS In total, 179 patients were enrolled per group; 178 (99.4%) were in CKD stage 3 or above in both groups. Average serum creatinine was 4.31±3.02 mg/dl and 3.64±2.55 mg/dl in the ESRD and non-ESRD groups, respectively (p=0.242). Other baseline characteristics were not statistically significant, except for the number of times contrast-enhanced computed tomography (CECT) was performed (0.00 [Interquartile range (IQR) 0.00-2.00] in the ESRD group and 0.00 [IQR 0.00-1.00] in the non-ESRD group [p=0.006]); in multivariate logistic regression, this number (OR=1.24, 95% CI=1.08-1.47, p=0.006) was significantly related to progression to ESRD. CONCLUSIONS The use of CECT increased the risk of ESRD 1.2-fold in advanced and stable CKD outpatients after 5-year follow-up.

Real-life effectiveness of inhaler device switch from dry powder inhalers to pressurized metred-dose inhalers in patients with asthma treated with ICS/LABA.

BACKGROUND AND OBJECTIVE: Mixed inhaler device use for asthma is associated with worse inhaler technique and outcomes. Given that relievers are commonly prescribed as pressurized metred-dose inhalers (pMDI), changing preventers from dry powder inhalers (DPI) to pMDI may improve asthma outcomes. This study aimed to assess the persistence and effectiveness of switching from DPI to pMDI for inhaled corticosteroid and long-acting ß2 -agonist combination therapy (ICS/LABA). METHODS: This was a historical cohort study using Ajou University Hospital (Korea) patient records. Persistence of switch was defined as receiving ≥1 pMDI and no DPI after the switch. Effectiveness of switch was assessed as the proportion without severe asthma exacerbation and the proportion achieving risk domain asthma control (RDAC; no asthma-related hospitalization, antibiotics without upper respiratory diagnosis or acute course of oral corticosteroids) and overall asthma control (OAC; RDAC and ≤ 200 µg salbutamol/≤500 µg terbutaline average daily dose) comparing 1 year after and before the switch. RESULTS: Within 85 patients who switched from DPI to pMDI and persisted for a year, higher proportion were free from asthma exacerbation after the switch (mean difference in proportion = 0.129, 95% CI: 0.038-0.220). Switching to pMDI was also associated with better RDAC (75.3% vs 57.7%, P = 0.001) and OAC (57.7% vs 45.9%, P = 0.021). From the entire 117 patients who switched to fixed-dose combination (FDC)/ICS LABA pMDI, 76.1% (95% CI: 69.0-100.0%) patients persisted in the following 6 months. CONCLUSION: Switching to and persisting with pMDI was associated with decreased asthma exacerbations and improved asthma control. The majority of patients persisted with the switch to pMDI for ICS/LABA treatment.

Application and optimisation of the Comparison on Extreme Laboratory Tests (CERT) algorithm for detection of adverse drug reactions: Transferability across national boundaries.

PURPOSE: The Singapore regulatory agency for health products (Health Sciences Authority), in performing active surveillance of medicines and their potential harms, is open to new methods to achieve this goal. Laboratory tests are a potential source of data for this purpose. We have examined the performance of the Comparison on Extreme Laboratory Tests (CERT) algorithm, developed by Ajou University, Korea, as a potential tool for adverse drug reaction detection based on the electronic medical records of the Singapore health care system. METHODS: We implemented the original CERT algorithm, comparing extreme laboratory results pre- and post-drug exposure, and 5 variations thereof using 4.5 years of National University Hospital (NUH) electronic medical record data (31 869 588 laboratory tests, 6 699 591 drug dispensings from 272 328 hospitalizations). We investigated 6 drugs from the original CERT paper and an additional 47 drugs. We benchmarked results against a reference standard that we created from UpToDate 2015. RESULTS: The original CERT algorithm applied to all 53 drugs and 44 laboratory abnormalities yielded a positive predictive value (PPV) and sensitivity of 50.3% and 54.1%, respectively. By raising the minimum number of cases for each drug-laboratory abnormality pair from 2 to 400, the PPV and sensitivity increased to 53.9% and 67.2%, respectively. This post hoc variation, named CERT400, performed particularly well for drug-induced hepatic and renal toxicities. DISCUSSION: We have demonstrated that the CERT algorithm can be applied across national boundaries. One modification (CERT400) was able to identify adverse drug reaction signals from laboratory data with reasonable PPV and sensitivity, which indicates potential utility as a supplementary pharmacovigilance tool.

Provider risk factors for medication administration error alerts: analyses of a large-scale closed-loop medication administration system using RFID and barcode.

PURPOSE: To determine the risk factors and rate of medication administration error (MAE) alerts by analyzing large-scale medication administration data and related error logs automatically recorded in a closed-loop medication administration system using radio-frequency identification and barcodes. METHODS: The subject hospital adopted a closed-loop medication administration system. All medication administrations in the general wards were automatically recorded in real-time using radio-frequency identification, barcodes, and hand-held point-of-care devices. MAE alert logs recorded during a full 1 year of 2012. We evaluated risk factors for MAE alerts including administration time, order type, medication route, the number of medication doses administered, and factors associated with nurse practices by logistic regression analysis. RESULTS: A total of 2 874 539 medication dose records from 30 232 patients (882.6 patient-years) were included in 2012. We identified 35 082 MAE alerts (1.22% of total medication doses). The MAE alerts were significantly related to administration at non-standard time [odds ratio (OR) 1.559, 95% confidence interval (CI) 1.515-1.604], emergency order (OR 1.527, 95%CI 1.464-1.594), and the number of medication doses administered (OR 0.993, 95%CI 0.992-0.993). Medication route, nurse's employment duration, and working schedule were also significantly related. CONCLUSION: The MAE alert rate was 1.22% over the 1-year observation period in the hospital examined in this study. The MAE alerts were significantly related to administration time, order type, medication route, the number of medication doses administered, nurse's employment duration, and working schedule. The real-time closed-loop medication administration system contributed to improving patient safety by preventing potential MAEs. Copyright © 2016 John Wiley & Sons, Ltd.

A normalization method for combination of laboratory test results from different electronic healthcare databases in a distributed research network.

PURPOSE: Distributed research networks (DRNs) afford statistical power by integrating observational data from multiple partners for retrospective studies. However, laboratory test results across care sites are derived using different assays from varying patient populations, making it difficult to simply combine data for analysis. Additionally, existing normalization methods are not suitable for retrospective studies. We normalized laboratory results from different data sources by adjusting for heterogeneous clinico-epidemiologic characteristics of the data and called this the subgroup-adjusted normalization (SAN) method. METHODS: Subgroup-adjusted normalization renders the means and standard deviations of distributions identical under population structure-adjusted conditions. To evaluate its performance, we compared SAN with existing methods for simulated and real datasets consisting of blood urea nitrogen, serum creatinine, hematocrit, hemoglobin, serum potassium, and total bilirubin. Various clinico-epidemiologic characteristics can be applied together in SAN. For simplicity of comparison, age and gender were used to adjust population heterogeneity in this study. RESULTS: In simulations, SAN had the lowest standardized difference in means (SDM) and Kolmogorov-Smirnov values for all tests (p < 0.05). In a real dataset, SAN had the lowest SDM and Kolmogorov-Smirnov values for blood urea nitrogen, hematocrit, hemoglobin, and serum potassium, and the lowest SDM for serum creatinine (p < 0.05). CONCLUSION: Subgroup-adjusted normalization performed better than normalization using other methods. The SAN method is applicable in a DRN environment and should facilitate analysis of data integrated across DRN partners for retrospective observational studies.

Is there any correlation between model-based perfusion parameters and model-free parameters of time-signal intensity curve on dynamic contrast enhanced MRI in breast cancer patients?

OBJECTIVE: To find out any correlation between dynamic contrast-enhanced (DCE) model-based parameters and model-free parameters, and evaluate correlations between perfusion parameters with histologic prognostic factors. METHODS: Model-based parameters (Ktrans, Kep and Ve) of 102 invasive ductal carcinomas were obtained using DCE-MRI and post-processing software. Correlations between model-based and model-free parameters and between perfusion parameters and histologic prognostic factors were analysed. RESULTS: Mean Kep was significantly higher in cancers showing initial rapid enhancement (P = 0.002) and a delayed washout pattern (P = 0.001). Ve was significantly lower in cancers showing a delayed washout pattern (P = 0.015). Kep significantly correlated with time to peak enhancement (TTP) (ρ = -0.33, P < 0.001) and washout slope (ρ = 0.39, P = 0.002). Ve was significantly correlated with TTP (ρ = 0.33, P = 0.002). Mean Kep was higher in tumours with high nuclear grade (P = 0.017). Mean Ve was lower in tumours with high histologic grade (P = 0.005) and in tumours with negative oestrogen receptor status (P = 0.047). TTP was shorter in tumours with negative oestrogen receptor status (P = 0.037). CONCLUSIONS: We could acquire general information about the tumour vascular physiology, interstitial space volume and pathologic prognostic factors by analyzing time-signal intensity curve without a complicated acquisition process for the model-based parameters. KEY POINTS: • Kep mainly affected the initial and delayed curve pattern in time-signal intensity curve. • There is significant correlation between model-based and model-free parameters. • We acquired information about tumour vascular physiology, interstitial space volume and prognostic factors.

Non-linear association of serum 25-hydroxyvitamin D with urinary albumin excretion rate in normoalbuminuric subjects.

BACKGROUND: Vitamin D deficiencies and increases in urinary albumin excretion (UAE) are both important and potentially related health problems; however, the nature of their relationship has not been established in normoalbuminuric subjects. METHODS: We obtained data from 14,594 normoalbuminuric Korean adults who underwent voluntary health screenings. We used a generalized additive model to examine the threshold level for relationship between serum 25-hydroxyvitamin D [25(OH)D] and urinary-albumin creatinine ratio (UACR) levels. We conducted multivariate logistic regression for high-normal UAE (UACR, 10-29 mg/g), according to various categories of vitamin D status. RESULTS: The generalized additive model confirmed a non-linear relationship between serum 25(OH)D and UACR levels, and the threshold concentration of 25(OH)D was 8.0 ng/mL after multivariate adjustment. Comparing subjects who fell into the lowest category of serum 25(OH)D levels with subjects who were in the reference range (the highest category), we observed that the multivariate adjusted odds ratio (OR) for high-normal UAE was significantly increased, regardless of the criteria used to categorize vitamin D levels: OR of the 1st quartile over the 4th quartile, 1.20 (95% CI, 1.04-1.39); OR of the 1.0-4.9th percentile over the 50-100th percentile, 1.56 (95% CI, 1.25-1.93); and OR of vitamin D deficiency group over vitamin D sufficiency group, 1.28 (95% CI, 1.08-1.52). CONCLUSIONS: We demonstrated that there was an inverse relationship between serum 25(OH)D less than 8.0 ng/mL and UACR in normoalbuminuric subjects, suggesting that severe vitamin D deficiency could cause an increase in UAE in subjects with normoalbuminuria.

An Explainable Artificial Intelligence-enabled ECG Framework for the Prediction of Subclinical Coronary Atherosclerosis.

Coronary artery calcium (CAC) as assessed by computed tomography (CT) is a marker of subclinical coronary atherosclerosis. However, routine application of CAC scoring via CT is limited by high costs and accessibility. An electrocardiogram (ECG) is a widely-used, sensitive, cost-effective, non-invasive, and radiation-free diagnostic tool. Considering this, if artificial intelligence (AI)-enabled electrocardiograms (ECGs) could opportunistically detect CAC, it would be particularly beneficial for the asymptomatic or subclinical populations, acting as an initial screening measure, paving the way for further confirmatory tests and preventive strategies, a step ahead of conventional practices. With this aim, we developed an AI-enabled ECG framework that not only predicts a CAC score ≥400 but also offers a visual explanation of the associated potential morphological ECG changes, and tested its efficacy on individuals undergoing health checkups, a group primarily comprising healthy or subclinical individuals. To ensure broader applicability, we performed external validation at a separate institution.

Prediction of Antibiotic Resistance in Patients With a Urinary Tract Infection: Algorithm Development and Validation.

BACKGROUND: The early prediction of antibiotic resistance in patients with a urinary tract infection (UTI) is important to guide appropriate antibiotic therapy selection. OBJECTIVE: In this study, we aimed to predict antibiotic resistance in patients with a UTI. Additionally, we aimed to interpret the machine learning models we developed. METHODS: The electronic medical records of patients who were admitted to Yongin Severance Hospital, South Korea were used. A total of 71 features extracted from patients' admission, diagnosis, prescription, and microbiology records were used for classification. UTI pathogens were classified as either sensitive or resistant to cephalosporin, piperacillin-tazobactam (TZP), carbapenem, trimethoprim-sulfamethoxazole (TMP-SMX), and fluoroquinolone. To analyze how each variable contributed to the machine learning model's predictions of antibiotic resistance, we used the Shapley Additive Explanations method. Finally, a prototype machine learning-based clinical decision support system was proposed to provide clinicians the resistance probabilities for each antibiotic. RESULTS: The data set included 3535, 737, 708, 1582, and 1365 samples for cephalosporin, TZP, TMP-SMX, fluoroquinolone, and carbapenem resistance prediction models, respectively. The area under the receiver operating characteristic curve values of the random forest models were 0.777 (95% CI 0.775-0.779), 0.864 (95% CI 0.862-0.867), 0.877 (95% CI 0.874-0.880), 0.881 (95% CI 0.879-0.882), and 0.884 (95% CI 0.884-0.885) in the training set and 0.638 (95% CI 0.635-0.642), 0.630 (95% CI 0.626-0.634), 0.665 (95% CI 0.659-0.671), 0.670 (95% CI 0.666-0.673), and 0.721 (95% CI 0.718-0.724) in the test set for predicting resistance to cephalosporin, TZP, carbapenem, TMP-SMX, and fluoroquinolone, respectively. The number of previous visits, first culture after admission, chronic lower respiratory diseases, administration of drugs before infection, and exposure time to these drugs were found to be important variables for predicting antibiotic resistance. CONCLUSIONS: The study results demonstrated the potential of machine learning to predict antibiotic resistance in patients with a UTI. Machine learning can assist clinicians in making decisions regarding the selection of appropriate antibiotic therapy in patients with a UTI.

Evaluation of GPT-4 for 10-year cardiovascular risk prediction: Insights from the UK Biobank and KoGES data.

Cardiovascular disease (CVD) remains a pressing global health concern. While traditional risk prediction methods such as the Framingham and American College of Cardiology/American Heart Association (ACC/AHA) risk scores have been widely used in the practice, artificial intelligence (AI), especially GPT-4, offers new opportunities. Utilizing large scale of multi-center data from 47,468 UK Biobank participants and 5,718 KoGES participants, this study quantitatively evaluated the predictive capabilities of GPT-4 in comparison with traditional models. Our results suggest that the GPT-based score showed commendably comparable performance in CVD prediction when compared to traditional models (AUROC on UKB: 0.725 for GPT-4, 0.733 for ACC/AHA, 0.728 for Framingham; KoGES: 0.664 for GPT-4, 0.674 for ACC/AHA, 0.675 for Framingham). Even with omission of certain variables, GPT-4's performance was robust, demonstrating its adaptability to data-scarce situations. In conclusion, this study emphasizes the promising role of GPT-4 in predicting CVD risks across varied ethnic datasets, pointing toward its expansive future applications in the medical practice.

Machine learning with clinical and intraoperative biosignal data for predicting postoperative delirium after cardiac surgery.

Early identification of patients at high risk of delirium is crucial for its prevention. Our study aimed to develop machine learning models to predict delirium after cardiac surgery using intraoperative biosignals and clinical data. We introduced a novel approach to extract relevant features from continuously measured intraoperative biosignals. These features reflect the patient's overall or baseline status, the extent of unfavorable conditions encountered intraoperatively, and beat-to-beat variability within the data. We developed a soft voting ensemble machine learning model using retrospective data from 1,912 patients. The model was then prospectively validated with data from 202 additional patients, achieving a high performance with an area under the receiver operating characteristic curve of 0.887 and an accuracy of 0.881. According to the SHapley Additive exPlanation method, several intraoperative biosignal features had high feature importance, suggesting that intraoperative patient management plays a crucial role in preventing delirium after cardiac surgery.

Evaluation of rosuvastatin-induced QT prolongation risk using real-world data, in vitro cardiomyocyte studies, and mortality assessment.

Drug-induced QT prolongation is attributed to several mechanisms, including hERG channel blockage. However, the risks, mechanisms, and the effects of rosuvastatin-induced QT prolongation remain unclear. Therefore, this study assessed the risk of rosuvastatin-induced QT prolongation using (1) real-world data with two different settings, namely case-control and retrospective cohort study designs; (2) laboratory experiments using human-induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CM); (3) nationwide claim data for mortality risk evaluation. Real-world data showed an association between QT prolongation and the use of rosuvastatin (OR [95% CI], 1.30 [1.21-1.39]) but not for atorvastatin (OR [95% CI], 0.98 [0.89-1.07]). Rosuvastatin also affected the sodium and calcium channel activities of cardiomyocytes in vitro. However, rosuvastatin exposure was not associated with a high risk of all-cause mortality (HR [95% CI], 0.95 [0.89-1.01]). Overall, these results suggest that rosuvastatin use increased the risk of QT prolongation in real-world settings, significantly affecting the action potential of hiPSC-CMs in laboratory settings. Long-term rosuvastatin treatment was not associated with mortality. In conclusion, while our study links rosuvastatin use to potential QT prolongation and possible influence on the action potential of hiPSC-CMs, long-term use does not show increased mortality, necessitating further research for conclusive real-world applications.

Machine Learning Algorithms Predict Successful Weaning From Mechanical Ventilation Before Intubation: Retrospective Analysis From the Medical Information Mart for Intensive Care IV Database.

BACKGROUND: The prediction of successful weaning from mechanical ventilation (MV) in advance of intubation can facilitate discussions regarding end-of-life care before unnecessary intubation. OBJECTIVE: We aimed to develop a machine learning-based model that predicts successful weaning from ventilator support based on routine clinical and laboratory data taken before or immediately after intubation. METHODS: We used the Medical Information Mart for Intensive Care IV database, which is an open-access database covering 524,740 admissions of 382,278 patients in Beth Israel Deaconess Medical Center, United States, from 2008 to 2019. We selected adult patients who underwent MV in the intensive care unit (ICU). Clinical and laboratory variables that are considered relevant to the prognosis of the patient in the ICU were selected. Data collected before or within 24 hours of intubation were used to develop machine learning models that predict the probability of successful weaning within 14 days of ventilator support. Developed models were integrated into an ensemble model. Performance metrics were calculated by 5-fold cross-validation for each model, and a permutation feature importance and Shapley additive explanations analysis was conducted to better understand the impacts of individual variables on outcome prediction. RESULTS: Of the 23,242 patients, 19,025 (81.9%) patients were successfully weaned from MV within 14 days. Using the preselected 46 clinical and laboratory variables, the area under the receiver operating characteristic curve of CatBoost classifier, random forest classifier, and regularized logistic regression classifier models were 0.860 (95% CI 0.852-0.868), 0.855 (95% CI 0.848-0.863), and 0.823 (95% CI 0.813-0.832), respectively. Using the ensemble voting classifier using the 3 models above, the final model revealed the area under the receiver operating characteristic curve of 0.861 (95% CI 0.853-0.869), which was significantly better than that of Simplified Acute Physiology Score II (0.749, 95% CI 0.742-0.756) and Sequential Organ Failure Assessment (0.588, 95% CI 0.566-0.609). The top features included lactate and anion gap. The model's performance achieved a plateau with approximately the top 21 variables. CONCLUSIONS: We developed machine learning algorithms that can predict successful weaning from MV in advance to intubation in the ICU. Our models can aid the appropriate management for patients who hesitate to decide on ventilator support or meaningless end-of-life care.

Machine learning-based 2-year risk prediction tool in immunoglobulin A nephropathy.

Background: This study aimed to develop a machine learning-based 2-year risk prediction model for early identification of patients with rapid progressive immunoglobulin A nephropathy (IgAN). We also assessed the model's performance to predict the long-term kidney-related outcome of patients. Methods: A retrospective cohort of 1,301 patients with biopsy-proven IgAN from two tertiary hospitals was used to derive and externally validate a random forest-based prediction model predicting primary outcome (30% decline in estimated glomerular filtration rate from baseline or end-stage kidney disease requiring renal replacement therapy) and secondary outcome (improvement of proteinuria) within 2 years after kidney biopsy. Results: For the 2-year prediction of primary outcomes, precision, recall, area-under-the-curve, precision-recall-curve, F1, and Brier score were 0.259, 0.875, 0.771, 0.242, 0.400, and 0.309, respectively. The values for the secondary outcome were 0.904, 0.971, 0.694, 0.903, 0.955, and 0.113, respectively. From Shapley Additive exPlanations analysis, the most informative feature identifying both outcomes was baseline proteinuria. When Kaplan-Meier analysis for 10-year kidney outcome risk was performed with three groups by predicting probabilities derived from the 2-year primary outcome prediction model (low, moderate, and high), high (hazard ratio [HR], 13.00; 95% confidence interval [CI], 9.52-17.77) and moderate (HR, 12.90; 95% CI, 9.92-16.76) groups showed higher risks compared with the low group. From the 2-year secondary outcome prediction model, low (HR, 1.66; 95% CI, 1.42-1.95) and moderate (HR, 1.42; 95% CI, 0.99-2.03) groups were at greater risk for 10-year prognosis than the high group. Conclusion: Our machine learning-based 2-year risk prediction models for the progression of IgAN showed reliable performance and effectively predicted long-term kidney outcome.