Identification of distinct clinical phenotypes of cardiogenic shock using machine learning consensus clustering approach.

BACKGROUND: Cardiogenic shock (CS) is a complex state with many underlying causes and associated outcomes. It is still difficult to differentiate between various CS phenotypes. We investigated if the CS phenotypes with distinctive clinical profiles and prognoses might be found using the machine learning (ML) consensus clustering approach. METHODS: The current study included patients who were diagnosed with CS at the time of admission from the electronic ICU (eICU) Collaborative Research Database. Among 21,925 patients with CS, an unsupervised ML consensus clustering analysis was conducted. The optimal number of clusters was identified by means of the consensus matrix (CM) heat map, cumulative distribution function (CDF), cluster-consensus plots, and the proportion of ambiguously clustered pairs (PAC) analysis. We calculated the standardized mean difference (SMD) of each variable and used the cutoff of ± 0.3 to identify each cluster's key features. We examined the relationship between the phenotypes and several clinical endpoints utilizing logistic regression (LR) analysis. RESULTS: The consensus cluster analysis identified two clusters (Cluster 1: n = 9,848; Cluster 2: n = 12,077). The key features of patients in Cluster 1, compared with Cluster 2, included: lower blood pressure, lower eGFR (estimated glomerular filtration rate), higher BUN (blood urea nitrogen), higher creatinine, lower albumin, higher potassium, lower bicarbonate, lower red blood cell (RBC), higher red blood cell distribution width (RDW), higher SOFA score, higher APS III score, and higher APACHE IV score on admission. The results of LR analysis showed that the Cluster 2 was associated with lower in-hospital mortality (odds ratio [OR]: 0.374; 95% confidence interval [CI]: 0.347-0.402; P < 0.001), ICU mortality (OR: 0.349; 95% CI: 0.318-0.382; P < 0.001), and the incidence of acute kidney injury (AKI) after admission (OR: 0.478; 95% CI: 0.452-0.505; P < 0.001). CONCLUSIONS: ML consensus clustering analysis synthesized the pattern of clinical and laboratory data to reveal distinct CS phenotypes with different clinical outcomes.

Phenotyping cardiogenic shock that showed different clinical outcomes and responses to vasopressor use: a latent profile analysis from MIMIC-IV database.

Background: Cardiogenic shock (CS) is increasingly recognized as heterogeneous in its severity and response to therapies. This study aimed to identify CS phenotypes and their responses to the use of vasopressors. Method: The current study included patients with CS complicating acute myocardial infarction (AMI) at the time of admission from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Laboratory and clinical variables were collected and used to conduct latent profile (LPA) analysis. Furthermore, we used a multivariable logistic regression (LR) model to explore the independent association between the use of vasopressors and endpoints. Result: A total of 630 eligible patients with CS after AMI were enrolled in the study. The LPA identified three profiles of CS: profile 1 (n = 259, 37.5%) was considered as the baseline group; profile 2 (n = 261, 37.8%) was characterized by advanced age, more comorbidities, and worse renal function; and profile 3 (n = 170, 24.6%) was characterized by systemic inflammatory response syndrome (SIRS)-related indexes and acid-base balance disturbance. Profile 3 showed the highest all-cause in-hospital mortality rate (45.9%), followed by profile 2 (43.3%), and profile 1 (16.6%). The LR analyses showed that the phenotype of CS was an independent prognostic factor for outcomes, and profiles 2 and 3 were significantly associated with a higher risk of in-hospital mortality (profile 2: odds ratio [OR] 3.95, 95% confidence interval [CI] 2.61-5.97, p < 0.001; profile 3: OR 3.90, 95%CI 2.48-6.13, p < 0.001) compared with profile 1. Vasopressor use was associated with an improved risk of in-hospital mortality for profile 2 (OR: 2.03, 95% CI: 1.15-3.60, p = 0.015) and profile 3 (OR: 2.91, 95% CI: 1.02-8.32, p = 0.047), respectively. The results of vasopressor use showed no significance for profile 1. Conclusion: Three phenotypes of CS were identified, which showed different outcomes and responses to vasopressor use.

Construction and validation of nomograms based on the log odds of positive lymph nodes to predict the prognosis of lung neuroendocrine tumors.

Background: This research aimed to investigate the predictive performance of log odds of positive lymph nodes (LODDS) for the long-term prognosis of patients with node-positive lung neuroendocrine tumors (LNETs). Methods: We collected 506 eligible patients with resected N1/N2 classification LNETs from the Surveillance, Epidemiology, and End Results (SEER) database between 2004 and 2015. The study cohort was split into derivation cohort (n=300) and external validation cohort (n=206) based on different geographic regions. Nomograms were constructed based on the derivation cohort and validated using the external validation cohort to predict the 1-, 3-, and 5-year cancer-specific survival (CSS) and overall survival (OS) of patients with LNETs. The accuracy and clinical practicability of nomograms were tested by Harrell's concordance index (C-index), integrated discrimination improvement (IDI), net reclassification improvement (NRI), calibration plots, and decision curve analyses. Results: The Cox proportional-hazards model showed the high LODDS group (-0.79≤LODDS) had significantly higher mortality compared to those in the low LODDS group (LODDS<-0.79) for both CSS and OS. In addition, age at diagnosis, sex, histotype, type of surgery, radiotherapy, and chemotherapy were also chosen as predictors in Cox regression analyses using stepwise Akaike information criterion method and included in the nomograms. The values of C-index, NRI, and IDI proved that the established nomograms were better than the conventional eighth edition of the TNM staging system. The calibration plots for predictions of the 1-, 3-, and 5-year CSS/OS were in excellent agreement. Decision curve analyses showed that the nomograms had value in terms of clinical application. Conclusions: We created visualized nomograms for CSS and OS of LNET patients, facilitating clinicians to bring individually tailored risk assessment and therapy.

Predictive value of lymphocyte-to-monocyte ratio in critically Ill patients with atrial fibrillation: A propensity score matching analysis.

BACKGROUND: Inflammation plays a key role in the initiation and progression of atrial fibrillation (AF). Lymphocyte-to-monocyte ratio (LMR) has been proved to be a reliable predictor of many inflammation-associated diseases, but little data are available on the relationship between LMR and AF. We aimed to evaluate the predictive value of LMR in predicting all-cause mortality among AF patients. METHODS: Data of patients diagnosed with AF were retrieved from the Medical Information Mart for Intensive Care-III (MIMIC-III) database. X-tile analysis was used to calculate the optimal cutoff value for LMR. The Cox regression model was used to assess the association of LMR and 28-day, 90-day, and 1-year mortality. Additionally, a propensity score matching (PSM) method was performed to minimize the impact of potential confounders. RESULTS: A total of 3567 patients hospitalized with AF were enrolled in this study. The X-tile software indicated that the optimal cutoff value of LMR was 2.67. A total of 1127 pairs were generated, and all the covariates were well balanced after PSM. The Cox proportional-hazards model showed that patients with the low LMR (≤2.67) had a higher 1-year all-cause mortality than those with the high LMR (>2.67) in the study cohort before PSM (HR = 1.640, 95% CI: 1.437-1.872, p < 0.001) and after PSM (HR = 1.279, 95% CI: 1.094-1.495, p = 0.002). The multivariable Cox regression analysis for 28-day and 90-day mortality yielded similar results. CONCLUSIONS: The lower LMR (≤2.67) was associated with a higher risk of 28-day, 90-day, and 1-year all-cause mortality, which might serve as an independent predictor in AF patients.