MATERIALS AND METHODS: This was a retrospective study using computed tomography (CT) scans from 3 hospitals. Inclusion criteria were scans with 1-5 nodules of diameter ≥5 mm; exclusion criteria were poor-quality scans or those with nodules measuring <5mm in diameter. In the lesion detection phase, 2,147 nodules from 219 scans were used to develop and train the deep learning 3D-CNN to detect lesions. The 3D-CNN was validated with 235 scans (354 lesions) for sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) analysis. In the path planning phase, Bayesian optimization was used to propose possible needle trajectories for lesion biopsy while avoiding vital structures. Software-proposed needle trajectories were compared with actual biopsy path trajectories from intraprocedural CT scans in 150 patients, with a match defined as an angular deviation of <5° between the 2 trajectories.
RESULTS: The model achieved an overall AUC of 97.4% (95% CI, 96.3%-98.2%) for lesion detection, with mean sensitivity of 93.5% and mean specificity of 93.2%. Among the software-proposed needle trajectories, 85.3% were feasible, with 82% matching actual paths and similar performance between supine and prone/oblique patient orientations (P = .311). The mean angular deviation between matching trajectories was 2.30° (SD ± 1.22); the mean path deviation was 2.94 mm (SD ± 1.60).
CONCLUSIONS: Segmentation, lesion detection, and path planning for CT-guided lung biopsy using an AI-guided software showed promising results. Future integration with automated robotic systems may pave the way toward fully automated biopsy procedures.
METHODS: To predict CD while prioritizing patient privacy, our study employed data anonymization involved adding Laplace noise to sensitive features like age and gender. The anonymized dataset underwent analysis using a differential privacy (DP) framework to preserve data privacy. DP ensured confidentiality while extracting insights. Compared with Logistic Regression (LR), Gaussian Naïve Bayes (GNB), and Random Forest (RF), the methodology integrated feature selection, statistical analysis, and SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) for interpretability. This approach facilitates transparent and interpretable AI decision-making, aligning with responsible AI development principles. Overall, it combines privacy preservation, interpretability, and ethical considerations for accurate CD predictions.
RESULTS: Our investigations from the DP framework with LR were promising, with an area under curve (AUC) of 0.848 ± 0.03, an accuracy of 0.797 ± 0.02, precision at 0.789 ± 0.02, recall at 0.797 ± 0.02, and an F1 score of 0.787 ± 0.02, with a comparable performance with the non-privacy framework. The SHAP and LIME based results support clinical findings, show a commitment to transparent and interpretable AI decision-making, and aligns with the principles of responsible AI development.
CONCLUSIONS: Our study endorses a novel approach in predicting CD, amalgamating data anonymization, privacy-preserving methods, interpretability tools SHAP, LIME, and ethical considerations. This responsible AI framework ensures accurate predictions, privacy preservation, and user trust, underscoring the significance of comprehensive and transparent ML models in healthcare. Therefore, this research empowers the ability to forecast CD, providing a vital lifeline to millions of CD patients globally and potentially preventing numerous fatalities.
METHODS: After 10 min of supine rest, the subject was tilted at a 70-degree angle on a tilt table for approximately a total of 35 min. 400 µg of glyceryl trinitrate (GTN) was administered sublingually after the first 20 min and monitoring continued for another 15 min. Mean imputation and K-nearest neighbors (KNN) imputation approaches to handle missing values. Next, feature selection techniques were implemented, including genetic algorithm, recursive feature elimination, and feature importance, to determine the crucial features. The Mann-Whitney U test was then performed to determine the statistical difference between two groups. Patients with VVS are categorized via machine learning models including Support Vector Machine (SVM), Gaussian Naïve Bayes (GNB), Multinomial Naïve Bayes (MNB), KNN, Logistic Regression (LR), and Random Forest (RF). The developed model is interpreted using an explainable artificial intelligence (XAI) model known as partial dependence plot.
RESULTS: A total of 137 subjects aged between 9 and 93 years were recruited for this study, 54 experienced clinical symptoms were considered positive tests, while the remaining 83 tested negative. Optimal results were obtained by combining the KNN imputation technique and three tilting features with SVM with 90.5% accuracy, 87.0% sensitivity, 92.7% specificity, 88.6% precision, 87.8% F1 score, and 95.4% ROC (receiver operating characteristics) AUC (area under curve).
CONCLUSIONS: The proposed algorithm effectively classifies VVS patients with over 90% accuracy. However, the study was confined to a small sample size. More clinical datasets are required to ensure that our approach is generalizable.
METHODS: We used data from 1108 population-representative studies with 141 million participants aged 18 years and older with measurements of fasting glucose and glycated haemoglobin (HbA1c), and information on diabetes treatment. We defined diabetes as having a fasting plasma glucose (FPG) of 7·0 mmol/L or higher, having an HbA1c of 6·5% or higher, or taking medication for diabetes. We defined diabetes treatment as the proportion of people with diabetes who were taking medication for diabetes. We analysed the data in a Bayesian hierarchical meta-regression model to estimate diabetes prevalence and treatment.
FINDINGS: In 2022, an estimated 828 million (95% credible interval [CrI] 757-908) adults (those aged 18 years and older) had diabetes, an increase of 630 million (554-713) from 1990. From 1990 to 2022, the age-standardised prevalence of diabetes increased in 131 countries for women and in 155 countries for men with a posterior probability of more than 0·80. The largest increases were in low-income and middle-income countries in southeast Asia (eg, Malaysia), south Asia (eg, Pakistan), the Middle East and north Africa (eg, Egypt), and Latin America and the Caribbean (eg, Jamaica, Trinidad and Tobago, and Costa Rica). Age-standardised prevalence neither increased nor decreased with a posterior probability of more than 0·80 in some countries in western and central Europe, sub-Saharan Africa, east Asia and the Pacific, Canada, and some Pacific island nations where prevalence was already high in 1990; it decreased with a posterior probability of more than 0·80 in women in Japan, Spain, and France, and in men in Nauru. The lowest prevalence in the world in 2022 was in western Europe and east Africa for both sexes, and in Japan and Canada for women, and the highest prevalence in the world in 2022 was in countries in Polynesia and Micronesia, some countries in the Caribbean and the Middle East and north Africa, as well as Pakistan and Malaysia. In 2022, 445 million (95% CrI 401-496) adults aged 30 years or older with diabetes did not receive treatment (59% of adults aged 30 years or older with diabetes), 3·5 times the number in 1990. From 1990 to 2022, diabetes treatment coverage increased in 118 countries for women and 98 countries for men with a posterior probability of more than 0·80. The largest improvement in treatment coverage was in some countries from central and western Europe and Latin America (Mexico, Colombia, Chile, and Costa Rica), Canada, South Korea, Russia, Seychelles, and Jordan. There was no increase in treatment coverage in most countries in sub-Saharan Africa; the Caribbean; Pacific island nations; and south, southeast, and central Asia. In 2022, age-standardised treatment coverage was lowest in countries in sub-Saharan Africa and south Asia, and treatment coverage was less than 10% in some African countries. Treatment coverage was 55% or higher in South Korea, many high-income western countries, and some countries in central and eastern Europe (eg, Poland, Czechia, and Russia), Latin America (eg, Costa Rica, Chile, and Mexico), and the Middle East and north Africa (eg, Jordan, Qatar, and Kuwait).
INTERPRETATION: In most countries, especially in low-income and middle-income countries, diabetes treatment has not increased at all or has not increased sufficiently in comparison with the rise in prevalence. The burden of diabetes and untreated diabetes is increasingly borne by low-income and middle-income countries. The expansion of health insurance and primary health care should be accompanied with diabetes programmes that realign and resource health services to enhance the early detection and effective treatment of diabetes.
FUNDING: UK Medical Research Council, UK Research and Innovation (Research England), and US Centers for Disease Control and Prevention.
METHODS: We searched PubMed, Web of Science, Cochrane, Embase, and SPORTDiscus from database establishment to 5 February 2024 to identify randomized controlled trials (RCTs) evaluating the effects of different dietary supplements on athletic performance in soccer players. The risk of bias was assessed using the revised Cochrane risk-of-bias tool for randomized trials. A Bayesian network meta-analysis was performed using the R software and Stata 18.0. A subgroup analysis was conducted based on the competitive level of the athletes.
RESULTS: Eighty RCTs were included, with 1,425 soccer players randomly receiving 31 different dietary supplements or placebo. The network meta-analysis showed that compared with placebo, carbohydrate + protein (SMD: 2.2, very large), carbohydrate + electrolyte (SMD: 1.3, large), bovine colostrum (SMD: moderate) and caffeine (SMD: 0.29, small) were associated with a significant effect on increasing the distance covered. Kaempferia parviflora (SMD: 0.46, small) was associated with a significant effect on enhancing muscular strength. Beta-alanine (SMD: 0.83, moderate), melatonin (SMD: 0.75, moderate), caffeine (SMD: 0.37, small), and creatine (SMD: 0.33, small) were associated with a significant effect on enhancing jump height. Magnesium creatine chelate (SMD: -3.0, very large), melatonin (SMD: -1.9, large), creatine + sodium bicarbonate (SMD: -1.4, large), and arginine (SMD: -1.2, moderate) were associated with a significant effect on decreasing sprint time. Creatine + sodium bicarbonate (SMD: -2.3, very large) and caffeine (SMD: -0.38, small) were associated with a significant effect on improving agility. Sodium pyruvate (SMD: 0.50, small) was associated with a significant effect on increasing peak power. Magnesium creatine chelate (SMD: 1.3, large) and sodium pyruvate (SMD: 0.56, small) were associated with a significant effect on increasing mean power. Carbohydrate + electrolyte (SMD: -0.56, small) was associated with a significant effect on improving the rating of perceived exertion.
CONCLUSIONS: This study suggests that a range of dietary supplements, including caffeine, creatine, creatine + sodium bicarbonate, magnesium creatine chelate, carbohydrate + electrolyte, carbohydrate + protein, arginine, beta-alanine, bovine colostrum, Kaempferia parviflora, melatonin, and sodium pyruvate, can improve athletic performance in soccer players. This review provides evidence-based guidance for soccer coaches and nutritionists on using dietary supplements to enhance specific performance measures.
AIM: This study investigated ADR signalling techniques to detect serious ADRs in Malaysian children aged from birth to 12 years old using an electronic ADRs' database.
METHODS: Four techniques (Proportional Reporting Ratio (PRR), Reporting Odds Ratio (ROR), Bayesian Confidence Propagation Neural Network (BCPNN) and Multi-item Gamma Poisson Shrinker (MGPS)) were tested on ADR reports submitted to the National Pharmaceutical Regulatory Agency between 2016 and 2020. Sensitivity, Specificity, Positive Predictive Value (PPV) and Negative Predictive Value (NPV) of the techniques were compared.
RESULTS: A total of 31 medicine-Important Medical Event pairs were found and examined among the 3152 paediatric ADR reports. Three techniques (PRR, ROR, MGPS) signalled oculogyric crisis and dystonia for metoclopramide. BCPNN and MGPS signalled angioedema for paracetamol, amoxicillin and ibuprofen. Similar performances were found for PRR, ROR and BCPNN (sensitivity of 12%, specificity of 100%, PPV of 100% and NPV of 21%). MGPS revealed the highest sensitivity (20%) and NPV (23%), as well as similar specificity and PPV (100%).
CONCLUSIONS: This study suggests that medication safety signalling techniques could be applied on electronic health records to monitor medication safety issues in children. Clinicians and medication safety specialist could prioritise the signals for further clinical consideration and prompt response.
RESULTS: We developed a fast Bayesian method which uses the sequencing coverage information determined from the concentration of an RNA sample to estimate the posterior distribution of a true gene count. Our method has better or comparable performance compared to NOISeq and GFOLD, according to the results from simulations and experiments with real unreplicated data. We incorporated a previously unused sequencing coverage parameter into a procedure for differential gene expression analysis with RNA-Seq data.
CONCLUSIONS: Our results suggest that our method can be used to overcome analytical bottlenecks in experiments with limited number of replicates and low sequencing coverage. The method is implemented in CORNAS (Coverage-dependent RNA-Seq), and is available at https://github.com/joel-lzb/CORNAS .