Explore the vast range of titles available.

Background The high heterogeneity of Parkinson's disease (PD) hinders personalized interventions. Brain structure reflects damage and neuroplasticity and is one of the biological bases of symptomatology. Subtyping PD in the framework of brain structure helps in the prediction of disease trajectories and optimizes treatment strategies. Methods The study included a total of 283 de novo PD and 141 healthy controls (HC). Structural heterogeneity between PD and HC was compared, and patients were classified using Heterogeneity through Discriminative Analysis. Gray matter volume (GMV), clinical symptoms, and substantia nigra free water (SNFW) among all subtypes were compared. These subtypes were followed for an average of 2.5 years to monitor motor impairment. Results Early PD patients possessed higher GMV heterogeneity than HC, and two subtypes based on GMV patterns were identified. Subtype 1 showed widespread GMV reductions, while subtype 2 had an increased volume in the basal ganglia and parts of the cortex. Subtype 1 had more severe motor and non‐motor symptoms, as well as higher posterior SNFW. The whole‐brain GMV in the PD group was negatively correlated with posterior SNFW; basal ganglia volume in subtype 1 was negatively correlated with Unified Parkinson's Disease Rating Scale (UPDRS)‐III scores, whereas no linear correlation was found in subtype 2. The UPDRS‐III progression rate was higher in subtype 1 than in subtype 2 (2.52 vs 0.92 points/year). Conclusion The heterogeneity of PD patients reflected the changes in their brain structure. The identification of these changes helps the classification of patients into different subtypes, additionally supported by clinical manifestations and SNFW, with consequent benefits for clinical consultancy and precision medicine. Control groups (represented by green dots) and patients (represented by red dots) are separated by convex polygon decision boundaries. The solid line represents the classifier, the dashed line represents the boundary, and the red highlighted solid line portion represents the convex polygon used to separate the patient from the control group.

Low bone mineral density (BMD) is a common age-related condition that elevates the risk of fractures and mortality. Machine learning (ML) techniques offer a promising approach for early prediction using readily available clinical, biochemical, and demographic data. To evaluate the predictive performance of eleven ML models in identifying low BMD and to determine the most influential risk factors using the best-performing model. Cross-sectional study. Data were obtained from National Health and Nutrition Examination Survey (2005-2010, 2013-2014, and 2017-2020), focusing on individuals aged ≥ 50 years with available femoral neck or total femur BMD data. After applying exclusion criteria, 12,108 participants were included. Supervised ML algorithms were trained using 57 clinical, biochemical, demographic, and behavioral features. Model performance was assessed using accuracy, area under the curve (AUC), recall, precision, and F1 score. SHAP analysis was employed to interpret model outputs and rank predictors. The extra trees classifier outperformed other ML methods, achieving an accuracy of 76.7% and an AUC of 0.85. Recursive Feature Elimination with Cross-Validation identified 14 key predictors of low BMD in descending order of importance: sex, age, body mass index, race, family income-to-poverty ratio, serum uric acid, diabetes status, HDL cholesterol, urinary creatinine, alkaline phosphatase, mean cell volume, lymphocyte count, diastolic blood pressure, and glycohemoglobin. Tree-based ML models, particularly Extra Trees, can effectively predict low BMD. The identified risk factors include both established and lesser-studied predictors. These findings support the use of ML for personalized osteoporosis and osteopenia screening and highlight its ability to capture complex, multifactorial relationships in population health data.

Conventional supervised and unsupervised machine learning models used for landslide susceptibility prediction (LSP) have many drawbacks, such as an insufficient number of recorded landslide samples, and the subjective and random selection of non-landslide samples. To overcome these drawbacks, a semi-supervised multiple-layer perceptron (SSMLP) is innovatively proposed with several processes: (1) an initial landslide susceptibility map (LSM) is produced using the multiple-layer perceptron (MLP) based on the original recorded landslide samples and related environmental factors; (2) the initial LSM is respectively classified into five areas with very high, high, moderate, low and very low susceptible levels; (3) some reasonable grid units from the areas with very high susceptible level are selected as new landslide samples to expand the original landslide samples; (4) reasonable non-landslide samples are selected from the areas with very low susceptible level; and (5) the expanded landslide samples, reasonable selected non-landslide samples and related environmental factors are put into the MLP once again to predict the final LSM. The Xunwu County of Jiangxi Province in China is selected as the study area. Conventional supervised machine learning (i.e. MLP) and unsupervised machine learning (i.e. K-means clustering model) are selected for comparisons. The comparative results indicate that the SSMLP model has a considerably higher LSP performance than the MLP and K-means clustering in Xunwu County. The SSMLP model successfully addresses the drawbacks existed in the conventional machine learning for LSP.

Hyperbilirubinemia affects many newborn infants and, if not treated appropriately, can lead to irreversible brain injury.BACKGROUNDHyperbilirubinemia affects many newborn infants and, if not treated appropriately, can lead to irreversible brain injury.This study aims to develop predictive models of follow-up total serum bilirubin measurement and to compare their accuracy with that of clinician predictions.OBJECTIVEThis study aims to develop predictive models of follow-up total serum bilirubin measurement and to compare their accuracy with that of clinician predictions.Subjects were patients born between June 2015 and June 2019 at 4 hospitals in Massachusetts. The prediction target was a follow-up total serum bilirubin measurement obtained <72 hours after a previous measurement. Birth before versus after February 2019 was used to generate a training set (27,428 target measurements) and a held-out test set (3320 measurements), respectively. Multiple supervised learning models were trained. To further assess model performance, predictions on the held-out test set were also compared with corresponding predictions from clinicians.METHODSSubjects were patients born between June 2015 and June 2019 at 4 hospitals in Massachusetts. The prediction target was a follow-up total serum bilirubin measurement obtained <72 hours after a previous measurement. Birth before versus after February 2019 was used to generate a training set (27,428 target measurements) and a held-out test set (3320 measurements), respectively. Multiple supervised learning models were trained. To further assess model performance, predictions on the held-out test set were also compared with corresponding predictions from clinicians.The best predictive accuracy on the held-out test set was obtained with the multilayer perceptron (ie, neural network, mean absolute error [MAE] 1.05 mg/dL) and Xgboost (MAE 1.04 mg/dL) models. A limited number of predictors were sufficient for constructing models with the best performance and avoiding overfitting: current bilirubin measurement, last rate of rise, proportion of time under phototherapy, time to next measurement, gestational age at birth, current age, and fractional weight change from birth. Clinicians made a total of 210 prospective predictions. The neural network model accuracy on this subset of predictions had an MAE of 1.06 mg/dL compared with clinician predictions with an MAE of 1.38 mg/dL (P<.0001). In babies born at 35 weeks of gestation or later, this approach was also applied to predict the binary outcome of subsequently exceeding consensus guidelines for phototherapy initiation and achieved an area under the receiver operator characteristic curve of 0.94 (95% CI 0.91 to 0.97).RESULTSThe best predictive accuracy on the held-out test set was obtained with the multilayer perceptron (ie, neural network, mean absolute error [MAE] 1.05 mg/dL) and Xgboost (MAE 1.04 mg/dL) models. A limited number of predictors were sufficient for constructing models with the best performance and avoiding overfitting: current bilirubin measurement, last rate of rise, proportion of time under phototherapy, time to next measurement, gestational age at birth, current age, and fractional weight change from birth. Clinicians made a total of 210 prospective predictions. The neural network model accuracy on this subset of predictions had an MAE of 1.06 mg/dL compared with clinician predictions with an MAE of 1.38 mg/dL (P<.0001). In babies born at 35 weeks of gestation or later, this approach was also applied to predict the binary outcome of subsequently exceeding consensus guidelines for phototherapy initiation and achieved an area under the receiver operator characteristic curve of 0.94 (95% CI 0.91 to 0.97).This study developed predictive models for neonatal follow-up total serum bilirubin measurements that outperform clinicians. This may be the first report of models that predict specific bilirubin values, are not limited to near-term patients without risk factors, and take into account the effect of phototherapy.CONCLUSIONSThis study developed predictive models for neonatal follow-up total serum bilirubin measurements that outperform clinicians. This may be the first report of models that predict specific bilirubin values, are not limited to near-term patients without risk factors, and take into account the effect of phototherapy.

The artificial intelligence (AI) framework is intended to solve a the problem of bias--variance tradeoff for supervised learning methodsin real-life applications. The AI framework It comprises of bootstrapping to create multiple training and testing datasetsdata sets with various characteristics, design, and analysis of statistical experiments to identify optimal feature subsets and optimal hyper-parameters for machine learning (ML) methods, and data contamination to test for the robustness of the classifiers. Key Features: Using ML methods by itself doesn't does notensure building classifiers that generalize well for new data. Identifying optimal feature subsets and hyper-parameters of ML methods can be resolved using the design and analysis of statistical experiments. Using a bootstrapping approach to massive sampling of training and tests datasets with various data characteristics (e.g.: contaminated training sets) allows dealing with bias. Developing of anSAS-based table-driven environment allows managing the management of all meta-data related to the proposed AI framework and creating the creation of interoperability with R libraries to accomplish a variety of statistical and machine-learning tasks. Computer programs in R and SAS that create AI frameworks are available on GitHub.

Higher education institutions aim to forecast student success which is an important research subject. Forecasting student success can enable teachers to prevent students from dropping out before final examinations, identify those who need additional help and boost institution ranking and prestige. Machine learning techniques in educational data mining aim to develop a model for discovering meaningful hidden patterns and exploring useful information from educational settings. The key traditional characteristics of students (demographic, academic background and behavioural features) are the main essential factors that can represent the training dataset for supervised machine learning algorithms. In this study, we compared the performances of several supervised machine learning algorithms, such as Decision Tree, Naïve Bayes, Logistic Regression, Support Vector Machine, K-Nearest Neighbour, Sequential Minimal Optimisation and Neural Network. We trained a model by using datasets provided by courses in the bachelor study programmes of the College of Computer Science and Information Technology, University of Basra, for academic years 2017-2018 and 2018-2019 to predict student performance on final examinations. Results indicated that logistic regression classifier is the most accurate in predicting the exact final grades of students (68.7% for passed and 88.8% for failed).

Machine learning methods hold promise for personalized care in psychiatry, demonstrating the potential to tailor treatment decisions and stratify patients into clinically meaningful taxonomies. Subsequently, publication counts applying machine learning methods have risen, with different data modalities, mathematically distinct models, and samples of varying size being used to train and test models with the promise of clinical translation. Consequently, and in part due to the preliminary nature of such works, many studies have reported largely varying degrees of accuracy, raising concerns over systematic overestimation and methodological inconsistencies. Furthermore, a lack of procedural evaluation guidelines for non-expert medical professionals and funding bodies leaves many in the field with no means to systematically evaluate the claims, maturity, and clinical readiness of a project. Given the potential of machine learning methods to transform patient care, albeit, contingent on the rigor of employed methods and their dissemination, we deem it necessary to provide a review of current methods, recommendations, and future directions for applied machine learning in psychiatry. In this review we will cover issues of best practice for model training and evaluation, sources of systematic error and overestimation, model explainability vs. trust, the clinical implementation of AI systems, and finally, future directions for our field.

Internet of Medical Things (IoMT) provides an excellent opportunity to investigate better automatic medical decision support tools with the effective integration of various medical equipment and associated data. This study explores two such medical decision-making tasks, namely COVID-19 detection and lung area segmentation detection, using chest radiography images. We also explore different cutting-edge machine learning techniques, such as federated learning, semi-supervised learning, transfer learning, and multi-task learning to explore the issue. To analyze the applicability of computationally less capable edge devices in the IoMT system, we report the results using Raspberry Pi devices as accuracy, precision, recall, Fscore for COVID-19 detection, and average dice score for lung segmentation detection tasks. We also publish the results obtained through server-centric simulation for comparison. The results show that Raspberry Pi-centric devices provide better performance in lung segmentation detection, and server-centric experiments provide better results in COVID-19 detection. We also discuss the IoMT application-centric settings, utilizing medical data and decision support systems, and posit that such a system could benefit all the stakeholders in the IoMT domain.