Predicting the complexity and mortality of polytrauma patients with machine learning models.

We aim to develop machine learning (ML) models for predicting the complexity and mortality of polytrauma patients using clinical features, including physician diagnoses and physiological data. We conducted a retrospective analysis of a cohort comprising 756 polytrauma patients admitted to the intensive care unit (ICU) at Pizhou People's Hospital Trauma Center, Jiangsu, China between 2020 and 2022. Clinical parameters encompassed demographics, vital signs, laboratory values, clinical scores and physician diagnoses. The two primary outcomes considered were mortality and complexity. We developed ML models to predict polytrauma mortality or complexity using four ML algorithms, including Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN) and eXtreme Gradient Boosting (XGBoost). We assessed the models' performance and compared the optimal ML model against three existing trauma evaluation scores, including Injury Severity Score (ISS), Trauma Index (TI) and Glasgow Coma Scale (GCS). In addition, we identified several important clinical predictors that made contributions to the prognostic models. The XGBoost-based polytrauma mortality prediction model demonstrated a predictive ability with an accuracy of 90% and an F-score of 88%, outperforming SVM, RF and ANN models. In comparison to conventional scoring systems, the XGBoost model had substantial improvements in predicting the mortality of polytrauma patients. External validation yielded strong stability and generalization with an accuracy of up to 91% and an AUC of 82%. To predict polytrauma complexity, the XGBoost model maintained its performance over other models and scoring systems with good calibration and discrimination abilities. Feature importance analysis highlighted several clinical predictors of polytrauma complexity and mortality, such as Intracranial hematoma (ICH). Leveraging ML algorithms in polytrauma care can enhance the prognostic estimation of polytrauma patients. This approach may have potential value in the management of polytrauma patients.

Transcriptomic Analysis of the Rat Dorsal Root Ganglion After Fracture.

In fractures, pain signals are transmitted from the dorsal root ganglion (DRG) to the brain, and the DRG generates efferent signals to the injured bone to participate in the injury response. However, little is known about how this process occurs. We analyzed DRG transcriptome at 3, 7, 14, and 28 days after fracture. We identified the key pathways through KEGG and GO enrichment analysis. We then used IPA analysis to obtain upstream regulators and disease pathways. Finally, we compared the sequencing results with those of nerve injury to identify the unique transcriptome changes in DRG after fracture. We found that the first 14 days after fracture were the main repair response period, the 3rd day was the peak of repair activity, the 14th day was dominated by the stimulus response, and on the 28th day, the repair response had reached a plateau. ECM-receptor interaction, protein digestion and absorption, and the PI3K-Akt signaling pathway were most significantly enriched, which may be involved in repair regeneration, injury response, and pain transmission. Compared with the nerve injury model, DRG after fracture produced specific alterations related to bone repair, and the bone density function was the most widely activated bone-related function. Our results obtained some important genes and pathways in DRG after fracture, and we also summarized the main features of transcriptome function at each time point through functional annotation clustering of GO pathway, which gave us a deeper understanding of the role played by DRG in fracture.