MACHINE LEARNING FOR PREDICTING HEMODYNAMIC DETERIORATION OF PATIENTS WITH INTERMEDIATE-RISK PULMONARY EMBOLISM IN INTENSIVE CARE UNIT.

ABSTRACT: Background: Intermediate-risk pulmonary embolism (PE) patients in the intensive care unit (ICU) are at a higher risk of hemodynamic deterioration than those in the general ward. This study aimed to construct a machine learning (ML) model to accurately identify the tendency for hemodynamic deterioration in the ICU patients with intermediate-risk PE. Method: A total of 704 intermediate-risk PE patients from the MIMIC-IV database were retrospectively collected. The primary outcome was defined as hemodynamic deterioration occurring within 30 days after admission to ICU. Four ML algorithms were used to construct models on the basis of all variables from MIMIC IV database with missing values less than 20%. The extreme gradient boosting (XGBoost) model was further simplified for clinical application. The performance of the ML models was evaluated by using the receiver operating characteristic curve, calibration plots, and decision curve analysis. Predictive performance of simplified XGBoost was compared with the simplified Pulmonary Embolism Severity Index score. SHapley Additive explanation (SHAP) was performed on a simplified XGBoost model to calculate the contribution and impact of each feature on the predicted outcome and presents it visually. Results: Among the 704 intermediate-risk PE patients included in this study, 120 patients experienced hemodynamic deterioration within 30 days after admission to the ICU. Simplified XGBoost model demonstrated the best predictive performance with an area under the curve of 0.866 (95% confidence interval, 0.800-0.925), and after recalibrated by isotonic regression, the area under the curve improved to 0.885 (95% confidence interval, 0.822-0.935). Based on the simplified XGBoost model, a web app was developed to identify the tendency for hemodynamic deterioration in ICU patients with intermediate-risk PE. Conclusion: A simplified XGBoost model can accurately predict the occurrence of hemodynamic deterioration for intermediate-risk PE patients in the ICU, assisting clinical workers in providing more personalized management for PE patients in the ICU.

Comparison of day surgery between varicose veins with and without superficial venous thrombosis below knee: a propensity score-matched analysis.

OBJECTIVES: Development of endovenous treatment and sclerotherapy technology makes it feasible for clinicians to treat varicose veins (VV) through day surgery (DS). Superficial venous thrombosis (SVT) of lower extremities is a common complication of VV. This study aimed to investigate whether the existence of SVT below knee affect the safety and efficacy of DS for VV patients. METHODS: This is a single-center retrospective study. Clinical data of 593 VV patients was retrospectively analyzed. Raw data were matched by the using of propensity score matching model. Operation time, technical failure, postoperative DVT, skin burns, saphenous nerve injury, subcutaneous induration, and bleeding were compared between the groups. Also, we compared VV recurrence, SVT formation, DVT events and the change of VCSS score with 12 months. RESULTS: Fifty-nine patients complicated with SVT below knee were matched with 118 patients had VV only. Perioperative and follow-up outcomes were similar in both groups except for the number of incisions (median = 6 [5, 7] VS median = 4 [4, 5], P < 0.001). Both groups experienced a great decrease in VCSS score. CONCLUSION: We systematically compared the clinical outcomes of DS in VV patients. Our results indicate DS is safe and effective for patients with VV, whether accompanied by SVT below the knee. TRIAL REGISTRATION: The ClinicalTrials.gov identifier for this trial is NCT05380895 (retrospectively registered).

Machine learning-based models for predicting mortality and acute kidney injury in critical pulmonary embolism.

OBJECTIVES: We aimed to use machine learning (ML) algorithms to risk stratify the prognosis of critical pulmonary embolism (PE). MATERIAL AND METHODS: In total, 1229 patients were obtained from MIMIC-IV database. Main outcomes were set as all-cause mortality within 30 days. Logistic regression (LR) and simplified eXtreme gradient boosting (XGBoost) were applied for model constructions. We chose the final models based on their matching degree with data. To simplify the model and increase its usefulness, finally simplified models were built based on the most important 8 variables. Discrimination and calibration were exploited to evaluate the prediction ability. We stratified the risk groups based on risk estimate deciles. RESULTS: The simplified XGB model performed better in model discrimination, which AUC were 0.82 (95% CI: 0.78-0.87) in the validation cohort, compared with the AUC of simplified LR model (0.75 [95% CI: 0.69-0.80]). And XGB performed better than sPESI in the validation cohort. A new risk-classification based on XGB could accurately predict low-risk of mortality, and had high consistency with acknowledged risk scores. CONCLUSIONS: ML models can accurately predict the 30-day mortality of critical PE patients, which could further be used to reduce the burden of ICU stay, decrease the mortality and improve the quality of life for critical PE patients.

Machine learning-based prediction of the post-thrombotic syndrome: Model development and validation study.

Background: Prevention is highly involved in reducing the incidence of post-thrombotic syndrome (PTS). We aimed to develop accurate models with machine learning (ML) algorithms to predict whether PTS would occur within 24 months. Materials and methods: The clinical data used for model building were obtained from the Acute Venous Thrombosis: Thrombus Removal with Adjunctive Catheter-Directed Thrombolysis study and the external validation cohort was acquired from the Sun Yat-sen Memorial Hospital in China. The main outcome was defined as the occurrence of PTS events (Villalta score ≥5). Twenty-three clinical variables were included, and four ML algorithms were applied to build the models. For discrimination and calibration, F scores were used to evaluate the prediction ability of the models. The external validation cohort was divided into ten groups based on the risk estimate deciles to identify the hazard threshold. Results: In total, 555 patients with deep vein thrombosis (DVT) were included to build models using ML algorithms, and the models were further validated in a Chinese cohort comprising 117 patients. When predicting PTS within 2 years after acute DVT, logistic regression based on gradient descent and L1 regularization got the highest area under the curve (AUC) of 0.83 (95% CI:0.76-0.89) in external validation. When considering model performance in both the derivation and external validation cohorts, the eXtreme gradient boosting and gradient boosting decision tree models had similar results and presented better stability and generalization. The external validation cohort was divided into low, intermediate, and high-risk groups with the prediction probability of 0.3 and 0.4 as critical points. Conclusion: Machine learning models built for PTS had accurate prediction ability and stable generalization, which can further facilitate clinical decision-making, with potentially important implications for selecting patients who will benefit from endovascular surgery.

Tripartite motif containing 35 contributes to the proliferation, migration, and invasion of lung cancer cells in vitro and in vivo.

The tripartite motif (TRIM) family is a family of proteins with highly conserved domains. Previous researches have suggested that the members of TRIM family proteins played a crucial role in cancer development and progression. Our study explored the relationship between TRIM35 and non-small cell lung cancer (NSCLC). The study showed that the expression of TRIM35 was increased in NSCLC samples, and patients with high expression of TRIM35 had a poor clinical prognosis. Overexpression of TRIM35 in NSCLC cell line H460 promoted cell proliferation, migration, and invasion, knockdown of TRIM35 produced an opposite result in A549 and H1299 cell lines. In vivo study further confirmed that overexpression of TRIM35 promoted tumor formation. The RNA-seq analysis suggested that TRIM35 might promote lung cancer proliferation, migration, and invasion by regulating cancer-associated functions and signaling pathways. Hence, we identified TRIM35 played a significant role in tumoral growth and was a potential diagnosis and prognosis target for lung cancer.

Identification of hub driving genes and regulators of lung adenocarcinoma based on the gene Co-expression network.

Lung adenocarcinoma (LUAD) remains the leading cause of cancer-related deaths worldwide. Increasing evidence suggests that circular RNAs (circRNAs) and long non-coding RNAs (lncRNAs) can regulate target gene expression and participate in tumor genesis and progression. However, hub driving genes and regulators playing a potential role in LUAD progression have not been fully elucidated yet. Based on data from The Cancer Genome Atlas database, 2837 differentially expressed genes, 741 DE-regulators were screened by comparing cancer tissues with paracancerous tissues. Then, 651 hub driving genes were selected by the topological relation of the protein-protein interaction network. Also, the target genes of DE-regulators were identified. Moreover, a key gene set containing 65 genes was obtained from the hub driving genes and target genes intersection. Subsequently, 183 hub regulators were selected based on the analysis of node degree in the ceRNA network. Next, a comprehensive analysis of the subgroups and Wnt, mTOR, and MAPK signaling pathways was conducted to understand enrichment of the subgroups. Survival analysis and a receiver operating characteristic curve analysis were further used to screen for the key genes and regulators. Furthermore, we verified key molecules based on external database, LRRK2, PECAM1, EPAS1, LDB2, and HOXA11-AS showed good results. LRRK2 was further identified as promising biomarker associated with CNV alteration and various immune cells' infiltration levels in LUAD. Overall, the present study provided a novel perspective and insight into hub driving genes and regulators in LUAD, suggesting that the identified signature could serve as an independent prognostic biomarker.