Evaluating single multiplicative neuron models in physics-informed neural networks for differential equations.

Machine learning is a prominent and highly effective field of study, renowned for its ability to yield favorable outcomes in estimation and classification tasks. Within this domain, artificial neural networks (ANNs) have emerged as one of the most powerful methodologies. Physics-informed neural networks (PINNs) have proven particularly adept at solving physics problems formulated as differential equations, incorporating boundary and initial conditions into the ANN's loss function. However, a critical challenge in ANNs lies in determining the optimal architecture, encompassing the selection of the appropriate number of neurons and layers. Traditionally, the Single Multiplicative Neuron Model (SMNM) has been explored as a solution to this issue, utilizing a single neuron with a multiplication function in the hidden layer to enhance computational efficiency. This study initially aimed to apply the SMNM within the PINNs framework, targeting the differential equation y ' - y = 0 with boundary conditions y ( 0 ) = 1 and y ( 1 ) = e . Upon implementation, however, it was discovered that while the conventional SMNM approach was theorized to offer significant advantages, multiplicative aggregate function led to a failure in convergence. Consequently, we introduced a "mimic single multiplicative neuron model (mimic-SMNM)" employing an architecture with a single neuron, designed to simulate the SMNM's conceptual advantages while ensuring convergence and computational efficiency. Comparative analysis revealed that the real-PINNs accurately solved the equation, the true SMNM failed to converge, and the mimic model was highlighted for its architectural simplicity and computational feasibility, directly implying it is faster and more efficient than real PINNs for the solution of simple differential equations. Furthermore, our findings demonstrated that our proposed mimic-SMNM model achieves a five-times increase in computational speed compared to real PINNs after 30,000 epochs.

ChatGPT-Enhanced ROC Analysis (CERA): A shiny web tool for finding optimal cutoff points in biomarker analysis.

Diagnostic tests play a crucial role in establishing the presence of a specific disease in an individual. Receiver Operating Characteristic (ROC) curve analyses are essential tools that provide performance metrics for diagnostic tests. Accurate determination of the cutoff point in ROC curve analyses is the most critical aspect of the process. A variety of methods have been developed to find the optimal cutoffs. Although the R programming language provides a variety of package programs for conducting ROC curve analysis and determining the appropriate cutoffs, it typically needs coding skills and a substantial investment of time. Specifically, the necessity for data preprocessing and analysis can present a significant challenge, especially for individuals without coding experience. We have developed the CERA (ChatGPT-Enhanced ROC Analysis) tool, a user-friendly ROC curve analysis web tool using the shiny interface for faster and more effective analyses to solve this problem. CERA is not only user-friendly, but it also interacts with ChatGPT, which interprets the outputs. This allows for an interpreted report generated by R-Markdown to be presented to the user, enhancing the accessibility and understanding of the analysis results.

Enhancing severe hypoglycemia prediction in type 2 diabetes mellitus through multi-view co-training machine learning model for imbalanced dataset.

Patients with type 2 diabetes mellitus (T2DM) who have severe hypoglycemia (SH) poses a considerable risk of long-term death, especially among the elderly, demanding urgent medical attention. Accurate prediction of SH remains challenging due to its multifaced nature, contributed from factors such as medications, lifestyle choices, and metabolic measurements. In this study, we propose a systematic approach to improve the robustness and accuracy of SH predictions using machine learning models, guided by clinical feature selection. Our focus is on developing long-term SH prediction models using both semi-supervised learning and supervised learning algorithms. Using the action to control cardiovascular risk in diabetes trial, which includes electronic health records for over 10,000 individuals, we focus on studying adults with T2DM. Our results indicate that the application of a multi-view co-training method, incorporating the random forest algorithm, improves the specificity of SH prediction, while the same setup with Naive Bayes replacing random forest demonstrates better sensitivity. Our framework also provides interpretability of machine learning models by identifying key predictors for hypoglycemia, including fasting plasma glucose, hemoglobin A1c, general diabetes education, and NPH or L insulins. The integration of data routinely available in electronic health records significantly enhances our model's capability to predict SH events, showcasing its potential to transform clinical practice by facilitating early interventions and optimizing patient management. By enhancing prediction accuracy and identifying crucial predictive features, our study contributes to advancing the understanding and management of hypoglycemia in this population.

Liver biopsy-based validation, confirmation and comparison of the diagnostic performance of established and novel non-invasive steatotic liver disease indexes: Results from a large multi-center study.

BACKGROUND: Non-invasive tools (NIT) for metabolic-dysfunction associated liver disease (MASLD) screening or diagnosis need to be thoroughly validated using liver biopsies. PURPOSE: To externally validate NITs designed to differentiate the presence or absence of liver steatosis as well as more advanced disease stages, to confirm fully validated indexes (n = 7 NITs), to fully validate partially validated indexes (n = 5 NITs), and to validate for the first time one new index (n = 1 NIT). METHODS: This is a multi-center study from two Gastroenterology-Hepatology Departments (Greece and Australia) and one Bariatric-Metabolic Surgery Department (Italy). Overall, n = 455 serum samples of patients with biopsy-proven MASLD (n = 374, including 237 patients with metabolic-dysfunction associated steatohepatitis (MASH)) and Controls (n = 81) were recruited. A complete validation analysis was performed to differentiate the presence of MASLD vs. Controls, MASH vs. metabolic-dysfunction associated steatotic liver (MASL), histological features of MASH, and fibrosis stages. RESULTS: The index of NASH (ION) demonstrated the highest differentiation ability for the presence of MASLD vs. Controls, with the area under the curve (AUC) being 0.894. For specific histological characterization of MASH, no NIT demonstrated adequate performance, while in the case of specific features of MASH, such as hepatocellular ballooning and lobular inflammation, ION demonstrated the best performance with AUC being close to or above 0.850. For fibrosis (F) classification, the highest AUC was reached by the aspartate aminotransferase to platelet ratio index (APRI) being ~0.850 yet only with the potential to differentiate the severe fibrosis stages (F3, F4) vs. mild or moderate fibrosis (F0-2) with an AUC > 0.900 in patients without T2DM. When we excluded patients with morbid obesity, the differentiation ability of APRI was improved, reaching AUC = 0.802 for differentiating the presence of fibrosis F2-4 vs. F0-1. The recommended by current guidelines index FIB-4 seemed to differentiate adequately between severe (i.e., F3-4) and mild or moderate fibrosis (F0-2) with an AUC = 0.820, yet this was not the case when FIB-4 was used to classify patients with fibrosis F2-4 vs. F0-1. Trying to improve the predictive value of all NITs, using Youden's methodology, to optimize the suggested cut-off points did not materially improve the results. CONCLUSIONS: The validation of currently available NITs using biopsy-proven samples provides new evidence for their ability to differentiate between specific disease stages, histological features, and, most importantly, fibrosis grading. The overall performance of the examined NITs needs to be further improved for applications in the clinic.