Reclassification of moderate aortic stenosis based on data-driven phenotyping of hemodynamic progression.

The management and follow-up of moderate aortic stenosis (AS) lacks consensus as the progression patterns are not well understood. This study aimed to identify the hemodynamic progression of AS, and associated risk factors and outcomes. We included patients with moderate AS with at least three transthoracic echocardiography (TTE) studies performed between 2010 and 2021. Latent class trajectory modeling was used to classify AS groups with distinctive hemodynamic trajectories, which were determined by serial systolic mean pressure gradient (MPG) measurements. Outcomes were defined as all-cause mortality and aortic valve replacement (AVR). A total of 686 patients with 3093 TTE studies were included in the analysis. Latent class model identified two distinct AS trajectory groups based on their MPG: a slow progression group (44.6%) and a rapid progression group (55.4%). Initial MPG was significantly higher in the rapid progression group (28.2 ± 5.6 mmHg vs. 22.9 ± 2.8 mmHg, P < 0.001). The prevalence of atrial fibrillation was higher in the slow progression group; there was no significant between-group difference in the prevalence of other comorbidities. The rapid progression group had a significantly higher AVR rate (HR 3.4 [2.4-4.8], P < 0.001); there was no between-group difference in mortality (HR 0.7 [0.5-1.0]; P = 0.079). Leveraging longitudinal echocardiographic data, we identified two distinct groups of patients with moderate AS: slow and rapid progression. A higher initial MPG (≥ 24 mmHg) was associated with more rapid progression of AS and higher rates of AVR, thus indicating the predictive value of MPG in management of the disease.

Machine Learning-Based Mortality Prediction Model for Critically Ill Cancer Patients Admitted to the Intensive Care Unit (CanICU).

BACKGROUND: Although cancer patients are increasingly admitted to the intensive care unit (ICU) for cancer- or treatment-related complications, improved mortality prediction remains a big challenge. This study describes a new ML-based mortality prediction model for critically ill cancer patients admitted to ICU. PATIENTS AND METHODS: We developed CanICU, a machine learning-based 28-day mortality prediction model for adult cancer patients admitted to ICU from Medical Information Mart for Intensive Care (MIMIC) database in the USA (n = 766), Yonsei Cancer Center (YCC, n = 3571), and Samsung Medical Center in Korea (SMC, n = 2563) from 2 January 2008 to 31 December 2017. The accuracy of CanICU was measured using sensitivity, specificity, and area under the receiver operating curve (AUROC). RESULTS: A total of 6900 patients were included, with a 28-day mortality of 10.2%/12.7%/36.6% and a 1-year mortality of 30.0%/36.6%/58.5% in the YCC, SMC, and MIMIC-III cohort. Nine clinical and laboratory factors were used to construct the classifier using a random forest machine-learning algorithm. CanICU had 96% sensitivity/73% specificity with the area under the receiver operating characteristic (AUROC) of 0.94 for 28-day, showing better performance than current prognostic models, including the Acute Physiology and Chronic Health Evaluation (APACHE) or Sequential Organ Failure Assessment (SOFA) score. Application of CanICU in two external data sets across the countries yielded 79-89% sensitivity, 58-59% specificity, and 0.75-0.78 AUROC for 28-day mortality. The CanICU score was also correlated with one-year mortality with 88-93% specificity. CONCLUSION: CanICU offers improved performance for predicting mortality in critically ill cancer patients admitted to ICU. A user-friendly online implementation is available and should be valuable for better mortality risk stratification to allocate ICU care for cancer patients.

Identification of Distinct Subgroups in Moderately Severe Rheumatic Mitral Stenosis Using Data-Driven Phenotyping of Longitudinal Hemodynamic Progression.

Background Rheumatic mitral stenosis is a significant cause of valvular heart disease. Pulmonary arterial systolic pressure (PASP) reflects the hemodynamic consequences of mitral stenosis and is used to determine treatment strategies. However, PASP progression and expected outcomes based on PASP changes in patients with moderately severe mitral stenosis remain unclear. Methods and Results A total of 436 patients with moderately severe rheumatic mitral stenosis (valve area 1.0-1.5 cm2) were enrolled. Composite outcomes included all-cause mortality and hospitalization for heart failure. Data-driven phenotyping identified 2 distinct trajectory groups based on PASP progression: rapid (8.7%) and slow (91.3%). Patients in the rapid progression group were older and had more diabetes and atrial fibrillation than those in the slow progression group (all P<0.05). The initial mean diastolic pressure gradient and PASP were higher in the rapid progression group than in the slow progression group (6.2±2.4 mm Hg versus 5.1±2.0 mm Hg [P=0.001] and 42.3±13.3 mm Hg versus 33.0±9.2 mm Hg [P<0.001], respectively). The rapid progression group had a poorer event-free survival rate than the slow progression group (log-rank P<0.001). Rapid PASP progression was a significant risk factor for composite outcomes even after adjusting for comorbidities (hazard ratio, 3.08 [95% CI, 1.68-5.64]; P<0.001). Multivariate regression analysis revealed that PASP >40 mm Hg was independently associated with allocation to the rapid progression group (odds ratio, 4.95 [95% CI, 2.08-11.99]; P<0.001). Conclusions Rapid PASP progression was associated with a higher risk of the composite outcomes. The main independent predictor for rapid progression group allocation was initial PASP >40 mm Hg.

Incorporation of Korean Electronic Data Interchange Vocabulary into Observational Medical Outcomes Partnership Vocabulary.

OBJECTIVES: We incorporated the Korean Electronic Data Interchange (EDI) vocabulary into Observational Medical Outcomes Partnership (OMOP) vocabulary using a semi-automated process. The goal of this study was to improve the Korean EDI as a standard medical ontology in Korea. METHODS: We incorporated the EDI vocabulary into OMOP vocabulary through four main steps. First, we improved the current classification of EDI domains and separated medical services into procedures and measurements. Second, each EDI concept was assigned a unique identifier and validity dates. Third, we built a vertical hierarchy between EDI concepts, fully describing child concepts through relationships and attributes and linking them to parent terms. Finally, we added an English definition for each EDI concept. We translated the Korean definitions of EDI concepts using Google.Cloud.Translation.V3, using a client library and manual translation. We evaluated the EDI using 11 auditing criteria for controlled vocabularies. RESULTS: We incorporated 313,431 concepts from the EDI to the OMOP Standardized Vocabularies. For 10 of the 11 auditing criteria, EDI showed a better quality index within the OMOP vocabulary than in the original EDI vocabulary. CONCLUSIONS: The incorporation of the EDI vocabulary into the OMOP Standardized Vocabularies allows better standardization to facilitate network research. Our research provides a promising model for mapping Korean medical information into a global standard terminology system, although a comprehensive mapping of official vocabulary remains to be done in the future.