Decision Support System for Predicting Survivability of Hepatitis Patients

Unveiling the potential of artificial intelligence in revolutionizing disease diagnosis and prediction: a comprehensive review of machine learning and deep learning approaches

The rapid advancement of Machine Learning (ML) and Deep Learning (DL) technologies has revolutionized healthcare, particularly in the domains of disease prediction and diagnosis. This study provides a comprehensive review of ML and DL applications across sixteen diverse diseases, synthesizing findings from research conducted between 2015 and 2024. We explore these technologies' methodologies, effectiveness, and clinical outcomes, highlighting their transformative potential in healthcare settings. Although ML and DL demonstrate remarkable accuracy and efficiency in disease prediction and diagnosis, challenges including quality of data, interpretability of models, and their integration into clinical workflows remain significant barriers. By evaluating advanced approaches and their outcomes, this review not only underscores the current capabilities of ML and DL but also identifies key areas for future research. Ultimately, this work aims to serve as a roadmap for advancing healthcare practices, enhancing clinical decision making, and strengthening patient outcomes through the effective and responsible implementation of AI-driven technologies.

A deep convolutional neural network for efficient microglia detection

Microglial cells are a type of glial cells that make up 10-15% of all brain cells, and they play a significant role in neurodegenerative disorders and cardiovascular diseases. Despite their vital role in these diseases, developing fully automated microglia counting methods from immunohistological images is challenging. Current image analysis methods are inefficient and lack accuracy in detecting microglia due to their morphological heterogeneity. This study presents development and validation of a fully automated and efficient microglia detection method using the YOLOv3 deep learning-based algorithm. We applied this method to analyse the number of microglia in different spinal cord and brain regions of rats exposed to opioid-induced hyperalgesia/tolerance. Our numerical tests showed that the proposed method outperforms existing computational and manual methods with high accuracy, achieving 94% precision, 91% recall, and 92% F1-score. Furthermore, our tool is freely available and adds value to exploring different disease models. Our findings demonstrate the effectiveness and efficiency of our new tool in automated microglia detection, providing a valuable asset for researchers in neuroscience.

Analysis of Diabetes Clinical Data Based on Recurrent Neural Networks

At present, diabetes is one of the most important chronic noncommunicable diseases, that have threatened human health. By 2020, the number of diabetic patients worldwide has reached 425 million. This amazing number has attracted the great attention of various countries. With the progress of computing technology, many mathematical models and intelligent algorithms have been applied in different fields of health care. 822 subjects were selected in this paper. They were divided into 389 diabetic patients and 423 nondiabetic patients. Each of the subjects included 41 indicators. Too many indicator variables would increase the computational effort and there could be a strong correlation and data redundancy between the data. Therefore, the sample features were first dimensionally reduced to generate seven new features in the new space, retaining up to 99.9% of the valid information from the original data. A diagnostic and classification model for diabetes clinical data based on recurrent neural networks were constructed, and particle swarm optimization (PSO) was introduced to optimise recurrent neural network's hyperparameters to achieve effective diagnosis and classification of diabetes.

Application Effect of Somatostatin Combined with Transnasal Ileus Catheterization in Patients with Acute Intestinal Obstruction and Advanced Gastric Cancer

Objective: To explore the application of somatostatin combined with nasal plug catheterization in patients with advanced gastric cancer and acute intestinal obstruction. Methods. This study included 94 cases of patients with acute intestinal obstruction and advanced gastric cancer, and according to the length of hospital stay, the patients were randomly divided into two groups: the control group and the study group, with 47 cases in each group. Based on the observations made by the team in the control group given somatostatin combined treatment, we observed two groups of patients with gastrointestinal function, serum index, quality of life, therapeutic effect, and adverse reactions. Results. Abdominal distention, abdominal pain duration, and normal exhaust time were significantly shorter in the study group than in the control group. The study group was higher than the control group in terms of gastrointestinal decompression volume, drainage volume, and abdominal circumference reduction within 24 hours (P < 0.05). After treatment, the levels of CRP, IgA, LPS, and FABP were lower than before, and the levels of CRP, IgA, LPS, and FABP in the former group were much lower than those in the latter group (P < 0.05). Compared with before treatment, the former GIQLI scale score was significantly higher than the latter (P < 0.05). After treatment, the efficiency is much higher than the latter (P < 0.05). After treatment, the former significantly lowers the incidence of postoperative complications of the latter (P < 0.05). Conclusion. For patients with advanced gastric cancer and acute intestinal obstruction, it is safe and feasible to use somatostatin combined with transnasal intestinal obstruction catheterization to restore gastrointestinal function, improve inflammatory response, and promote the improvement of quality of life with high safety and feasibility.