Predicting the Onset of Diabetes with Machine Learning Methods

Construction and validation of risk prediction models for pulmonary embolism in hospitalized patients based on different machine learning methods

Objective

This study aims to apply different machine learning (ML) methods to construct risk prediction models for pulmonary embolism (PE) in hospitalized patients, and to evaluate and compare the predictive efficacy and clinical benefit of each model.

Methods

We conducted a retrospective study involving 332 participants (172 PE positive cases and 160 PE negative cases) recruited from Guangdong Medical University. Participants were randomly divided into a training group (70%) and a validation group (30%). Baseline data were analyzed using univariate analysis, and potential independent risk factors associated with PE were further identified through univariate and multivariate logistic regression analysis. Six ML models, namely Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Support Vector Machine (SVM), and AdaBoost were developed. The predictive efficacy of each model was compared using the receiver operating characteristic (ROC) curve analysis and the area under the curve (AUC). Clinical benefit was assessed using decision curve analysis (DCA).

Results

Logistic regression analysis identified lower extremity deep venous thrombosis, elevated D-dimer, shortened activated partial prothrombin time, and increased red blood cell distribution width as potential independent risk factors for PE. Among the six ML models, the RF model achieved the highest AUC of 0.778. Additionally, DCA consistently indicated that the RF model offered the greatest clinical benefit.

Conclusion

This study developed six ML models, with the RF model exhibiting the highest predictive efficacy and clinical benefit in the identification and prediction of PE occurrence in hospitalized patients.

Sialic acids cleavage induced by elastin-derived peptides impairs the interaction between insulin and its receptor in adipocytes 3T3-L1

The insulin receptor (IR) plays an important role in insulin signal transduction, the defect of which is believed to be the root cause of type 2 diabetes. In 3T3-L1 adipocytes as in other cell types, the mature IR is a heterotetrameric cell surface glycoprotein composed of two α subunits and two β subunits. Our objective in our study, is to understand how the desialylation of N-glycan chains, induced by elastin-derived peptides, plays a major role in the function of the IR. Using the 3T3-L1 adipocyte line, we show that removal of the sialic acid from N-glycan chains (N893 and N908), induced by the elastin receptor complex (ERC) and elastin derived-peptides (EDPs), leads to a decrease in the autophosphorylation activity of the insulin receptor. We demonstrate by molecular dynamics approaches that the absence of sialic acids on one of these two sites is sufficient to generate local and general modifications of the structure of the IR. Biochemical approaches highlight a decrease in the interaction between insulin and its receptor when ERC sialidase activity is induced by EDPs. Therefore, desialylation by EDPs is synonymous with a decrease of IR sensitivity in adipocytes and could thus be a potential source of insulin resistance associated with diabetic conditions.

Predicting Male Infertility Using Artificial Neural Networks: A Review of the Literature

Male infertility is a relevant public health problem, but there is no systematic review of the different machine learning (ML) models and their accuracy so far. The present review aims to comprehensively investigate the use of ML algorithms in predicting male infertility, thus reporting the accuracy of the used models in the prediction of male infertility as a primary outcome. Particular attention will be paid to the use of artificial neural networks (ANNs). A comprehensive literature search was conducted in PubMed, Scopus, and Science Direct between 15 July and 23 October 2023, conducted under the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We performed a quality assessment of the included studies using the recommended tools suggested for the type of study design adopted. We also made a screening of the Risk of Bias (RoB) associated with the included studies. Thus, 43 relevant publications were included in this review, for a total of 40 different ML models detected. The studies included reported a good quality, even if RoB was not always good for all the types of studies. The included studies reported a median accuracy of 88% in predicting male infertility using ML models. We found only seven studies using ANN models for male infertility prediction, reporting a median accuracy of 84%.

Characterization of Plant-Derived Natural Inhibitors of Dipeptidyl Peptidase-4 as Potential Antidiabetic Agents: A Computational Study

Diabetes, characterized by elevated blood sugar levels, poses significant health and economic risks, correlating with complications like cardiovascular disease, kidney failure, and blindness. Dipeptidyl peptidase-4 (DPP-4), also referred to as T-cell activation antigen CD26 (EC 3.4.14.5.), plays a crucial role in glucose metabolism and immune function. Inhibiting DPP-4 was anticipated as a potential new therapy for diabetes. Therefore, identification of plant-based natural inhibitors of DPP-4 would help in eradicating diabetes worldwide. Here, for the identification of the potential natural inhibitors of DPP-4, we developed a phytochemicals library consisting of over 6000 phytochemicals detected in 81 medicinal plants that exhibited anti-diabetic potency. The library has been docked against the target proteins, where isorhamnetin, Benzyl 5-Amino-5-deoxy-2,3-O-isopropyl-alpha-D-mannofuranoside (DTXSID90724586), and 5-Oxo-7-[4-(trifluoromethyl) phenyl]-4H,6H,7H-[1,2]thiazolo[4,5-b]pyridine 3-carboxylic acid (CHEMBL3446108) showed binding affinities of -8.5, -8.3, and -8.3 kcal/mol, respectively. These compounds exhibiting strong interactions with DPP-4 active sites (Glu205, Glu206, Tyr547, Trp629, Ser630, Tyr662, His740) were identified. ADME/T and bioactivity predictions affirmed their pharmacological safety. Density functional theory calculations assessed stability and reactivity, while molecular dynamics simulations demonstrated persistent stability. Analyzing parameters like RMSD, RG, RMSF, SASA, H-bonds, MM-PBSA, and FEL confirmed stable protein-ligand compound formation. Principal component analysis provided structural variation insights. Our findings suggest that those compounds might be possible candidates for developing novel inhibitors targeting DPP-4 for treating diabetes.

Ethical and regulatory challenges of AI technologies in healthcare: A narrative review

Over the past decade, there has been a notable surge in AI-driven research, specifically geared toward enhancing crucial clinical processes and outcomes. The potential of AI-powered decision support systems to streamline clinical workflows, assist in diagnostics, and enable personalized treatment is increasingly evident. Nevertheless, the introduction of these cutting-edge solutions poses substantial challenges in clinical and care environments, necessitating a thorough exploration of ethical, legal, and regulatory considerations. A robust governance framework is imperative to foster the acceptance and successful implementation of AI in healthcare. This article delves deep into the critical ethical and regulatory concerns entangled with the deployment of AI systems in clinical practice. It not only provides a comprehensive overview of the role of AI technologies but also offers an insightful perspective on the ethical and regulatory challenges, making a pioneering contribution to the field. This research aims to address the current challenges in digital healthcare by presenting valuable recommendations for all stakeholders eager to advance the development and implementation of innovative AI systems.

Improving diabetes disease patients classification using stacking ensemble method with PIMA and local healthcare data

Diabetes mellitus, a chronic metabolic disorder, continues to be a major public health issue around the world. It is estimated that one in every two diabetics is undiagnosed. Early diagnosis and management of diabetes can also prevent or delay the onset of complications. With the help of a variety of machine learning and deep learning models, stacking algorithms, and other techniques, our study's goal is to detect diseases early. In this study, we propose two stacking-based models for diabetes disease classification using a combination of the PIMA Indian diabetes dataset, simulated data, and additional data collected from a local healthcare facility. We use both the classical and deep neural network stacking ensemble methods to combine the predictions of multiple classification models and improve classification accuracy and robustness. In the evaluation protocol, we used both the train-test and cross-validation (CV) techniques to validate our proposed model. The highest accuracy is obtained by stacking ensemble with three NN architectures, resulting in an accuracy of 95.50 %, precision of 94 %, recall of 97 %, and f1-score of 96 % using 5-fold CV on simulation study. The stacked accuracy obtained from ML algorithms for the Pima Indian Diabetes dataset is 75.03 % using the train-test split protocol, while the accuracy obtained from the CV protocol is 77.10 % on the stacked model. The range of performance scores that outperformed the CV protocol 2.23 %-12 %. Our proposed method achieves a high accuracy range from 92 % to 95 %, precision, recall, and F1-score ranges from 88 % to 96 % using classical and deep neural network (NN)-based stacking method on the primary dataset. The proposed dataset and ensemble method could be useful in the early detection and treatment of diabetes, as well as in the advancement of machine learning and data analysis techniques in the healthcare industry.

Revolutionizing Diabetes Diagnosis: Machine Learning Techniques Unleashed

The intricate and multifaceted nature of diabetes disrupts the body's crucial glucose processing mechanism, which serves as a fundamental energy source for the cells. This research aims to predict the occurrence of diabetes in individuals by harnessing the power of machine learning algorithms, utilizing the PIMA diabetes dataset. The selected algorithms employed in this study encompass Decision Tree, K-Nearest Neighbor, Random Forest, Logistic Regression, and Support Vector Machine. To execute the experiments, two software tools, namely Waikato Environment for Knowledge Analysis (WEKA) version 3.8.1 and Python version 3.10, were utilized. To evaluate the performance of the algorithms, several metrics were employed, including true positive rate, false positive rate, precision, recall, F-measure, Matthew's correlation coefficient, receiver operating characteristic area, and precision-recall curves area. Furthermore, various errors such as Mean Absolute Error, Root Mean Squared Error, Relative Absolute Error, and Root Relative Squared Error were examined to assess the accuracy of the models. Upon conducting the experiments, it was observed that Logistic Regression outperformed the other techniques, exhibiting the highest precision of 81 percent using Python and 80.43 percent using WEKA. These findings shed light on the efficacy of machine learning in predicting diabetes and highlight the potential of Logistic Regression as a valuable tool in this domain.

The risk of developing type 2 diabetes mellitus among the students of Hail University, Saudi Arabia

Background

Globally, it is estimated that approximately 537 million adults are living with diabetes. Of them, more than 90% have type 2 diabetes (T2DM). In 2023, a previous meta-analysis showed that the prevalence of T2DM among the general adult population in Saudi Arabia was 28%. This study was conducted to assess the risk of developing T2DM among the students at Hail University, Saudi Arabia.

Methods

This cross-sectional study was conducted in 2022/2023 among a census sample of 740 students (both genders, aged 17-26 years) studying at nine colleges of Hail University, Saudi Arabia. The diabetes risk score was assessed using the Australian Type 2 Diabetes Risk Assessment Tool (AUSDRISK). Anthropometric measurements were measured and recorded using standard methods. Socio-demographic variables were also obtained with an interview-based questionnaire. Statistical analysis was performed using SPSS version 25.

Results

A total of 740 students were included in the final analysis. Of them, 274 (37.0%) were male students and 466 (63.0%) were female students. The mean age of the study participants is 19.9 ± 1.6 years. The findings showed that 61.9% of the study participants were at intermediate and high risk of diabetes (59.7 and 2.2%, respectively). The majority 85.7% of male students were at intermediate risk of diabetes, and 5.8% were at high risk of diabetes. In total, 44.4% of female students were at intermediate risk of diabetes, and none of them were at high risk of diabetes. For the following variables (age, gender, college name, area of the university, academic years, weight, height, and BMI), the differences were statistically significant between different categories of diabetes risk scores (P-values < 0.005).

Conclusion

More than half of the students at the Hail University of Saudi Arabia have an intermediate and high risk of T2DM. Male students are at a higher risk compared to female students. The high risk of T2DM among university students should be seriously considered.

Mitochondrial Dynamics and Insulin Secretion

Mitochondria are involved in the regulation of cellular energy metabolism, calcium homeostasis, and apoptosis. For mitochondrial quality control, dynamic processes, such as mitochondrial fission and fusion, are necessary to maintain shape and function. Disturbances of mitochondrial dynamics lead to dysfunctional mitochondria, which contribute to the development and progression of numerous diseases, including Type 2 Diabetes (T2D). Compelling evidence has been put forward that mitochondrial dynamics play a significant role in the metabolism-secretion coupling of pancreatic β cells. The disruption of mitochondrial dynamics is linked to defects in energy production and increased apoptosis, ultimately impairing insulin secretion and β cell death. This review provides an overview of molecular mechanisms controlling mitochondrial dynamics, their dysfunction in pancreatic β cells, and pharmaceutical agents targeting mitochondrial dynamic proteins, such as mitochondrial division inhibitor-1 (mdivi-1), dynasore, P110, and 15-oxospiramilactone (S3).

Diabetes Detection Models in Mexican Patients by Combining Machine Learning Algorithms and Feature Selection Techniques for Clinical and Paraclinical Attributes: A Comparative Evaluation

The development of medical diagnostic models to support healthcare professionals has witnessed remarkable growth in recent years. Among the prevalent health conditions affecting the global population, diabetes stands out as a significant concern. In the domain of diabetes diagnosis, machine learning algorithms have been widely explored for generating disease detection models, leveraging diverse datasets primarily derived from clinical studies. The performance of these models heavily relies on the selection of the classifier algorithm and the quality of the dataset. Therefore, optimizing the input data by selecting relevant features becomes essential for accurate classification. This research presents a comprehensive investigation into diabetes detection models by integrating two feature selection techniques: the Akaike information criterion and genetic algorithms. These techniques are combined with six prominent classifier algorithms, including support vector machine, random forest, k-nearest neighbor, gradient boosting, extra trees, and naive Bayes. By leveraging clinical and paraclinical features, the generated models are evaluated and compared to existing approaches. The results demonstrate superior performance, surpassing accuracies of 94%. Furthermore, the use of feature selection techniques allows for working with a reduced dataset. The significance of feature selection is underscored in this study, showcasing its pivotal role in enhancing the performance of diabetes detection models. By judiciously selecting relevant features, this approach contributes to the advancement of medical diagnostic capabilities and empowers healthcare professionals in making informed decisions regarding diabetes diagnosis and treatment.

A Review of the Role of Artificial Intelligence in Healthcare

Artificial intelligence (AI) applications have transformed healthcare. This study is based on a general literature review uncovering the role of AI in healthcare and focuses on the following key aspects: (i) medical imaging and diagnostics, (ii) virtual patient care, (iii) medical research and drug discovery, (iv) patient engagement and compliance, (v) rehabilitation, and (vi) other administrative applications. The impact of AI is observed in detecting clinical conditions in medical imaging and diagnostic services, controlling the outbreak of coronavirus disease 2019 (COVID-19) with early diagnosis, providing virtual patient care using AI-powered tools, managing electronic health records, augmenting patient engagement and compliance with the treatment plan, reducing the administrative workload of healthcare professionals (HCPs), discovering new drugs and vaccines, spotting medical prescription errors, extensive data storage and analysis, and technology-assisted rehabilitation. Nevertheless, this science pitch meets several technical, ethical, and social challenges, including privacy, safety, the right to decide and try, costs, information and consent, access, and efficacy, while integrating AI into healthcare. The governance of AI applications is crucial for patient safety and accountability and for raising HCPs' belief in enhancing acceptance and boosting significant health consequences. Effective governance is a prerequisite to precisely address regulatory, ethical, and trust issues while advancing the acceptance and implementation of AI. Since COVID-19 hit the global health system, the concept of AI has created a revolution in healthcare, and such an uprising could be another step forward to meet future healthcare needs.

Carotenoids Composition of Green Algae Caulerpa racemosa and Their Antidiabetic, Anti-Obesity, Antioxidant, and Anti-Inflammatory Properties

Green alga Caulerpa racemosa is an underexploited species of macroalgae, even though it is characterized by a green color that indicates an abundance of bioactive pigments, such as chlorophyll and possibly xanthophyll. Unlike chlorophyll, which has been well explored, the composition of the carotenoids of C. racemosa and its biological activities have not been reported. Therefore, this study aims to look at the carotenoid profile and composition of C. racemose and determine their biological activities, which include antidiabetic, anti-obesity, anti-oxidative, anti-inflammatory, and cytotoxicity in vitro. The detected carotenoids were all xanthophylls, which included fucoxanthin, lutein, astaxanthin, canthaxanthin, zeaxanthin, β-carotene, and β-cryptoxanthin based on orbitrap-mass spectrometry (MS) and a rapid ultra-high performance liquid chromatography (UHPLC) diode array detector. Of the seven carotenoids observed, it should be highlighted that β-carotene and canthaxanthin were the two most dominant carotenoids present in C. racemosa. Interestingly, the carotenoid extract of C. racemosa has good biological activity in inhibiting α-glucosidase, α-amylase, DPPH and ABTS, and the TNF-α and mTOR, as well as upregulating the AMPK, which makes it a drug candidate or functional antidiabetic food, a very promising anti-obesity and anti-inflammatory. More interestingly, the cytotoxicity value of the carotenoid extract of C. racemosa shows a level of safety in normal cells, which makes it a potential for the further development of nutraceuticals and pharmaceuticals.