Background: Trauma is one of the most critical public health issues worldwide, leading to death and disability and influencing all age groups. Therefore, there is great interest in models for predicting mortality in trauma patients admitted to the ICU. The main objective of the present study is to develop and evaluate SMOTE-based machine-learning tools for predicting hospital mortality in trauma patients with imbalanced data. Methods: This retrospective cohort study was conducted on 126 trauma patients admitted to an intensive care unit at Besat hospital in Hamadan Province, western Iran, from March 2020 to March 2021. Data were extracted from the medical information records of patients. According to the imbalanced property of the data, SMOTE techniques, namely SMOTE, Borderline-SMOTE1, Borderline-SMOTE2, SMOTE-NC, and SVM-SMOTE, were used for primary preprocessing. Then, the Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost) methods were used to predict patients' hospital mortality with traumatic injuries. The performance of the methods used was evaluated by sensitivity, specificity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), accuracy, Area Under the Curve (AUC), Geometric Mean (G-means), F1 score, and P-value of McNemar's test. Results: Of the 126 patients admitted to an ICU, 117 (92.9%) survived and 9 (7.1%) died. The mean follow-up time from the date of trauma to the date of outcome was 3.98 ± 4.65 days. The performance of ML algorithms is not good with imbalanced data, whereas the performance of SMOTE-based ML algorithms is significantly improved. The mean area under the ROC curve (AUC) of all SMOTE-based models was more than 91%. F1-score and G-means before balancing the dataset were below 70% for all ML models except ANN. In contrast, F1-score and G-means for the balanced datasets reached more than 90% for all SMOTE-based models. Among all SMOTE-based ML methods, RF and ANN based on SMOTE and XGBoost based on SMOTE-NC achieved the highest value for all evaluation criteria. Conclusions: This study has shown that SMOTE-based ML algorithms better predict outcomes in traumatic injuries than ML algorithms. They have the potential to assist ICU physicians in making clinical decisions.

Bone marrow (BM) niche is a specific microenvironment for hematopoietic stem cells (HSCs) as well as non-hematopoietic cells. Evidence shows that chemo/radiotherapy can lead to the disruption of different properties of HSCs such as proliferation, differentiation, localization, self-renewal steady-state of cell populations. Investigations have shown that the deregulation of balance within the marrow cavity due to chemo/radiotherapy could lead to bone loss, abnormal hematopoiesis, and enhanced differentiation potential of mesenchymal stem cells towards the adipogenic lineage. Therefore, understanding the underlying mechanisms of chemo/radiotherapy induced BM niche changes may lead to the application of appropriate therapeutic agents to prevent BM niche defects.

Although the efficacy of MSCs on the liver fibrosis is investigated, it is not exactly clear whether released molecules by MSCs are sufficient to mediate the anti-fibrotic effects or not. In this study, the possible hepatoprotective effects of human umbilical cord MSCs derived conditioned medium (UC-CM) was investigated. 30 male rats were divided into 3 groups (n = 10): C: control; F: fibrosis were intraperitoneally injected with CCl₄ (1 ml/kg, i.p); F/UC-CM: fibrosis rats that received UC-CM (100 µg/kg, i.v). At the end of the 12th week, serum and liver samples were collected to analyze biochemical, molecular, and histopathological parameters. In comparison with CCl₄ intoxicated animals, the results showed a significant amelioration of weight loss, histological changes as well as attenuation of serum activity of ALT, AST, and ALP in F/UC-CM. The liver hydroxyproline content was significantly reduced by UC-CM treatment. Accordingly, improvement in oxidative parameters such as MDA, TAC, and TOS was also observed in the F/UC-CM group. UC-CM administration down-regulated gene expression of TGF-β1, TNF-α, TβRII, MMP-2, and MMP-9 as well as the protein level in TGF-β1 and TNF-α. Immunohistochemical analysis showed a notable lower hepatic α-SMA expression in the F/UC-CM group. In conclusion, these findings revealed that the remarkable hepatoprotective property of UC-CM could lend support to its anti-inflammatory and antioxidative and anti-fibrotic effects.

Umbilical cord blood-derived mesenchymal stromal cells (UCB-MSCs) are ideally suited for use in various cell-based therapies. We investigated a novel induction protocol (NIP) to improve the neuronal differentiation of human UCB-MSCs under appropriate conditions. This experimental study was performed in Iranian Blood Transfusion Organization (IBTO), Tehran, Iran. UCB-MSCs were cultured in DMEM medium supplemented with 10% FBS in a humidified incubator in equilibration with 5% CO2 at 37°C. For neuronal differentiation of UCB-MSCs, DMEM was removed and replaced with pre-induction medium containing RA, bFGF, EGF, and basal medium for two days. Then, NGF, IBMX, AsA, and Neurobasal medium were used for six days for this purpose. Real-time PCR was performed to analyze the neuronal differentiation of UCB-MSCs for the first time in Iran. We found that the maximum and minimum levels of gene expression were related to GFAP and nestin, respectively. In addition, our study showed that compared to other neuronal inducers, RA might play the main role in neuronal differentiation and fate of MSCs compared to other neuronal inducers. Our data showed that the combination of chemical (RA, IBMX, AsA) and growth factors (NGF, EGF, bFGF) in NIP may improve the efficiency of neuronal differentiation of UCB-MSCs and may provide a new method for easy and quick application of UCB-MSCs in regenerative medicine in the future. However, the functionality of neuron-like cells must be carefully assessed in animal experiments prior to use in clinical applications.