Informatics in Medicine Unlocked最新文献

Recent developments in artificial intelligence and medical imaging technologies have significantly improved disease analysis and prediction, especially regarding identifying brain tumors (BTs). With the advancement of medical imaging technology, 3D brain scans can now be captured using a variety of modalities, offering a comprehensive perspective for tumor diagnosis. A key stage in the diagnosis tactic is extracting pertinent features from magnetic resonance imaging (MRI) scans, and several researchers have suggested various methods. This work aims to develop an accurate BTs detection and classification system using machine and deep learning techniques. The system is designed to classify BTs and healthy data using three merged datasets. Deep learning algorithms, including 2D convolutional neural network (CNN) with 13 layers, CNN long short-term memory (LSTM), and another 2D CNN with nine layers, are employed to improve the classification performance of the system. All three deep learning models achieve high accuracy, with 2D CNN LSTM yielding the highest accuracy of 98.47%, followed by another 2D CNN at 97.71% and 2D CNN at 92.36%. These models are then combined using ensemble learning to make a hybrid network, which further improves the system’s accuracy. The comparative analysis demonstrates that the ensemble deep learning models outperform all other classifiers, achieving an accuracy of 98.82%, precision of 99%, and recall of 99%. The work findings indicate that the developed brain tumor detection and classification system, which combines deep learning techniques, offers high accuracy and precision, making it a promising tool for accurately diagnosing brain tumors.

This study aimed to develop a predictive model using lifestyle behavioral factors related to chronic skin disease symptoms and machine learning techniques. A cross-sectional survey was conducted among patients with chronic skin diseases currently receiving treatment at 19 Saengki Korean Medical Clinics specializing in the treatment of chronic skin diseases. Data were collected from 264 participants through an online survey conducted over a three-month period. We used changes in patients' skin symptoms as the dependent variable and lifestyle, behavioral, and treatment variables that affect chronic skin disease remission as predictors. Based on previous studies, we evaluated the performance of the six models using machine learning techniques (decision tree, logistic regression [LR], random forest [RF], CatBoost, gradient boosting classifier, and LightGBM) that are commonly used to create predictive models using categorical factors. The results showed that RF and LR performed well. We selected LR as the final model based on the confusion matrix and receiver operating characteristic (ROC) curve. The LR results showed that herbal medicine use and hospital visits were associated with chronic skin disease symptoms, whereas the RF results showed that herbal medicine use, exercise, and wheat flour consumption were associated with chronic skin disease symptoms. These findings suggest that both the treatment and lifestyle behaviors are associated with chronic skin disease symptoms.

Bladder cancer (BC) remains a significant global health challenge, requiring the development of accurate predictive models for diagnosis. In this study, a new Binary Modified White Whale Optimization (B-MBWO) algorithm is proposed to address the BC problem. The proposed method utilizes circular transitivity optimization and the Probabilistic State Mutation Algorithm (PSMA) to enhance its optimization performance. The new method is called the BBWORCPS algorithm. High-dimensional and complex medical datasets pose challenges to the original optimization algorithms in addressing the BC problem, motivating the proposed modifications to the original Beluga Whale Optimization algorithm. These enhancements, including quantum-inspired mutation and circular crossing, aim to improve solution space exploration and enhance the algorithm's effectiveness in handling intricate feature spaces. Through comprehensive experiments on BC datasets, the superiority of the BBWORCPS algorithm in terms of feature selection accuracy and computational efficiency is demonstrated compared to existing optimization methods. The obtained findings suggest that BBWORCPS offers a promising approach for developing more precise and reliable predictive models for bladder cancer analysis.

Ovarian cancer (OC) is one of the most prevalent types of cancer in women. Early and accurate diagnosis is crucial for the survival of the patients. However, the majority of women are diagnosed in advanced stages due to the lack of effective biomarkers and accurate screening tools. While previous studies sought a common biomarker, our study suggests different biomarkers for the premenopausal and postmenopausal populations. This can provide a new perspective in the search for novel predictors for the effective diagnosis of OC. Genetic algorithm has been utilized to identify the most significant biomarkers. The XGBoost classifier is then trained on the selected features and high ROC-AUC scores of 0.864 and 0.911 have been obtained for the premenopausal and postmenopausal populations, respectively. Lack of explainability is one major limitation of current AI systems. The stochastic nature of the ML algorithms raises concerns about the reliability of the system as it is difficult to interpret the reasons behind the decisions. To increase the trustworthiness and accountability of the diagnostic system as well as to provide transparency and explanations behind the predictions, explainable AI has been incorporated into the ML framework. SHAP is employed to quantify the contributions of the selected biomarkers and determine the most discriminative features. Merging SHAP with the ML models enables clinicians to investigate individual decisions made by the model and gain insights into the factors leading to that prediction. Thus, a hybrid decision support system has been established that can eliminate the bottlenecks caused by the black-box nature of the ML algorithms providing a safe and trustworthy AI tool. The diagnostic accuracy obtained from the proposed system outperforms the existing methods as well as the state-of-the-art ROMA algorithm by a substantial margin which signifies its potential to be an effective tool in the differential diagnosis of OC.

Terminalia Catappa fruits are recognized for their use in diabetes treatment, yet the mechanism by which they inhibit diabetes-related enzymes remain largely undefined. This study aimed to elucidate the therapeutic potential and interactions of T. catappa fruit extract through in vitro and in silico approaches. The compounds from T. catappa fruit were extracted using microwave-assisted extraction techniques, followed by qualitative phytochemical screening and quantitative analysis via GC-MS. The physicochemical properties were evaluated according to the Lipinski rule and ADMET criteria. Antidiabetic analyses, both in vitro and in silico, were performed on the secondary metabolites found in T. catappa fruit, targeting α-amylase and α-glucosidase enzymes. The methanol and ethyl acetate extracts of T. catappa fruit contained alkaloids, flavonoids, saponins, steroids, and terpenoids. These extracts inhibited α-glucosidase and α-amylase in a dose-dependent manner, with the methanol extract of T. catappa showing significantly higher inhibitory activity than pure acarbose (by two- and five-fold, respectively) and the ethyl acetate extract. Furthermore, the antioxidant activity of the methanolic extract was seven times greater than that of the ethyl acetate extract. Molecular docking studies supported these findings, revealing that the ΔG values of gibberellic acid, rescinnamine, and digoxin were comparable to those of acarbose. Notably, digoxin has higher ΔG values against α-amylase than acarbose, while gibberellic acid, rescinnamine, and nerolidol showed ΔG values similar to acarbose. Gibberellic acid, unique to the methanol extract, demonstrated high ΔG values, suggesting its significant role in the extract's enhanced glucosidase and amylase inhibitory activities. This study identifies specific compounds (digitoxin, rescinnamine, gibberellic acid, and nerolidol) and proposes the potential of multi-target drugs in diabetes treatment. Understanding these phytochemical constituents and their effects on diabetes-involved enzymes could benefit individuals with type 2 diabetes, particularly those at higher risk of complications.

Reverse vaccinology is an emerging concept in the field of vaccine development as it facilitates the identification of potential vaccine candidates. Biomedical research has been revolutionized with the recent innovations in Generative Artificial Intelligence (AI) and Large Language Models (LLMs). The intersection of these two technologies is explored in this study. In this study, the impact of Generative AI and LLMs in the field of vaccinology is explored. Through a comprehensive analysis of existing research, prospective use cases, and an experimental case study, this research highlights that LLMs and Generative AI have the potential to enhance the efficiency and accuracy of vaccine candidate identification. This work also discusses the ethical and privacy challenges, such as data consent and potential biases, raised by such applications that require careful consideration. This study paves the way for experts, researchers, and policymakers to further investigate the role and impact of Generative AI and LLM in vaccinology and medicine.