Optimizing machine learning (ML) model performance relies heavily on appropriate data preprocessing techniques. Despite the widespread use of standardization and normalization, empirical comparisons across different models, dataset sizes, and domains remain sparse. This study bridges this gap by evaluating five machine learning algorithms- Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost)-on datasets of varying sizes from the business, health, and agriculture domains. This study assessed the models without scaling, with standardized data, and with normalized data. The comparative analysis reveals that while standardization consistently improves the performance of linear models like SVM and LR for large and medium datasets, normalization enhances the performance of linear models for small datasets. Moreover, this study employs SHapley Additive exPlanations (SHAP) summary plots to understand how each feature contributes to the model’s performance interpretability with unscaled and scaled datasets. This study provides practical guidelines for selecting appropriate scaling techniques based on the characteristics of datasets and compatibility with various algorithms. Finally, this investigation laid the foundation for data preprocessing and feature engineering across diverse models and domains which offers actionable insights for practitioners.

The study utilizes osteosarcoma hematoxylin and the Eosin-stained image dataset, which is unevenly dispersed, and it raises concerns about the potential impact on the overall performance and reliability of any analyses or models derived from the dataset. In this study, a deep-learning-based convolution neural network (CNN) and adapted heterogeneous ensemble-learning-based voting classifier have been proposed to classify osteosarcoma. The proposed methods can also resolve the issue and develop unbiased learning models by introducing an evenly distributed training dataset. Data augmentation is employed to boost the generalization abilities. Six different pre-trained CNN models, namely MobileNetV1, Mo-bileNetV2, ResNetV250, InceptionV2, EfficientNetV2B0, and NasNetMobile, are applied and evaluated in frozen and fine-tuned-based phases. In addition, a novel CNN model and adapted heterogeneous ensemble-learning-based voting classifier developed from the proposed CNN model, fine-tuned NasNetMobile model, and fine-tuned Efficient-NetV2B0 model are also introduced to classify osteosarcoma. The proposed CNN model outperforms other pre-trained models. The Kappa score obtained from the proposed CNN model is 93.09%. Notably, the proposed voting classifier attains the highest Kappa score of 96.50% and outperforms all other models. The findings of this study have practical implications in telemedicine, mobile healthcare systems, and as a supportive tool for medical professionals.

Administration of erythropoietin (EPO) is neuroprotective against a variety of experimentally-induced neurological disorders. The aim was to determine if EPO protects against hippocampal neurodegeneration as well as impairment of cognition and motor performance, associated with long-term diabetes. BALB/c mice were randomly allocated between control, diabetic and EPO-treated diabetic groups. EPO-treated diabetic mice were administered EPO 0.05 U/kg/day i.p. three times/week for 10 weeks. Cognition was assessed by Morris water maze. Brain samples were processed for light microscopic evaluation of hippocampus. Controls showed gradual improvement of cognitive performance in water maze when comparing latency (p < 0.01) and distance swum to reach the platform (p = 0.001). There was a similar trend for improvement in EPO-treated diabetics (p < 0.001). Latency did not improve in diabetic animals indicating lack of learning (p = 0.79). In probe trials, controls and EPO-treated diabetics spent more time in the training quadrant than expected by chance (p < 0.001). Diabetics did not show memory recall behavior; performance was significantly worse than expected by chance (p = 0.023). In diabetics, there was neurodegeneration in hippocampus and reduction in number of granule cells (p < 0.01) in the dentate gyrus. EPO treatment improved these neurodegenerative changes and preserved numbers of granule cells (p < 0.1, compared to controls). Erythropoietin treatment is protective against cognitive deficits and hippocampal neurodegeneration in diabetic mice.

Background: Formative assessment with feedback is part of the assessment program in medical education to improve students’ learning. Limited research has focused on its application and impact on practical anatomy education. Methods: This study aimed to examine medical students’ perceptions of formative assessment in practical anatomy sessions of body systems-based educational units and explore its influence on final practical exam performance. A descriptive, cross-sectional study was conducted. Data was collected from 173 Year 2 medical students through a survey that addressed their perception of process and importance of formative assessment and feedback. The survey employed a 5-point Likert scale. Two open-ended questions were appended at the end of the survey. Students’ performance in Unit 3 (where formative assessment was conducted) was compared to their performance in Unit 2 (where no formative assessment was conducted) and with the performance of the previous academic year’s students in Unit 3 (where no formative assessment was conducted). Descriptive statistics were used. The level of statistical significance was set at p-value < 0.05. Responses to open-ended questions (qualitative data) were counted, categorized as themes, and presented as frequencies and percentages. Results: The survey showed high internal consistency, and its validity was established through exploratory factor analysis. Results showed that the mean mark for the unit with formative assessment and feedback was significantly higher than for the units without formative assessment and feedback. Students showed positive perception of formative assessment and feedback conducted after practical anatomy sessions. They reported useful insights regarding the benefits they gained from formative assessment and feedback as well as constructive suggestions for future improvements. Conclusion: The study indicates that students positively perceived formative assessment and feedback sessions after practical anatomy sessions. Findings also refer to a positive effect of formative assessment on students’ performance in summative practical assessment in anatomy.

Background: Inflammatory bowel disease (IBD) comprises a group of disorders that manifest through chronic inflammation of the colon and small intestine. Although the exact cause of IBD is still unclear, dysfunctional immunoregulation involving overproduction of inflammatory cytokines such as TNF‐α, and IL‐6 have been implicated in pathogenesis. Current therapy relies on immunosuppression, cytotoxic drugs, and monoclonal antibodies against TNF‐α. These classes of drugs have severe side‐effects, especially when used for long duration. Our previous work with raloxifene, a selective estrogen receptor modulator, has shown that the drug, and to a greater extent its micellar formulation, has a significant suppressive effect on NF‐κB, an essential immune‐regulator. This finding directed the current work towards testing the anti‐inflammatory and immunomodulatory effects of raloxifene using cell lines, as well as testing the potential use of the styrene maleic acid (SMA) micelles loaded with raloxifene (SMA‐Ral) against dextran sulfate sodium (DSS) induced colitis in an in vivo model of IBD.Results: Treatment of MCF‐7 cells with TNF‐α was shown to protect the cells from the cytotoxic effect of raloxifene (42 vs. 10% cell death, with TNF‐α. Treating CaCo‐2 cells with both free and SMA‐Ral improved cell survival after exposure to 2% DDS with significantly higher protection with SMA‐Ral. Treatment of U‐937 with SMA‐Ral and free‐Ral resulted in down‐regulation of TNF‐α, IL‐1β, IL‐6, and MIP1α, with greater inhibition of the SMA‐Ral, compared to free Ral. Balb/c mice treated with raloxifene and SMA‐Ral showed weight gain at 14 days, compared to the control group (122, and 115% respectively). Treatment with raloxifene prevented DSS‐induced diarrhea in 6/6 of free raloxifene treated mice and in 5/6 mice treated with SMA‐Ral. Control group of DSS‐treated mice showed average colon length of 7.4 cm compared to 13 cm in the control group. The average colon length was 12.3 and 11.5 cm for raloxifene and SMA‐Ral treated groups, respectively. Furthermore, inflammatory cytokines such as IL‐6 and TNF‐α were reduced in serum of animals treated with free‐Ral and SMA‐Ral.Conclusions: Raloxifene and its micellar formulation warrants further studies to understand their effect on the treatment of colitis.