BACKGROUND: Health care-associated infections due to multidrug-resistant organisms (MDROs), such as methicillin-resistant Staphylococcus aureus (MRSA) and Clostridioides difficile (CDI), place a significant burden on our health care infrastructure.
OBJECTIVE: Screening for MDROs is an important mechanism for preventing spread but is resource intensive. The objective of this study was to develop automated tools that can predict colonization or infection risk using electronic health record (EHR) data, provide useful information to aid infection control, and guide empiric antibiotic coverage.
METHODS: We retrospectively developed a machine learning model to detect MRSA colonization and infection in undifferentiated patients at the time of sample collection from hospitalized patients at the University of Virginia Hospital. We used clinical and nonclinical features derived from on-admission and throughout-stay information from the patient\'s EHR data to build the model. In addition, we used a class of features derived from contact networks in EHR data; these network features can capture patients\' contacts with providers and other patients, improving model interpretability and accuracy for predicting the outcome of surveillance tests for MRSA. Finally, we explored heterogeneous models for different patient subpopulations, for example, those admitted to an intensive care unit or emergency department or those with specific testing histories, which perform better.
RESULTS: We found that the penalized logistic regression performs better than other methods, and this model\'s performance measured in terms of its receiver operating characteristics-area under the curve score improves by nearly 11% when we use polynomial (second-degree) transformation of the features. Some significant features in predicting MDRO risk include antibiotic use, surgery, use of devices, dialysis, patient\'s comorbidity conditions, and network features. Among these, network features add the most value and improve the model\'s performance by at least 15%. The penalized logistic regression model with the same transformation of features also performs better than other models for specific patient subpopulations.
CONCLUSIONS: Our study shows that MRSA risk prediction can be conducted quite effectively by machine learning methods using clinical and nonclinical features derived from EHR data. Network features are the most predictive and provide significant improvement over prior methods. Furthermore, heterogeneous prediction models for different patient subpopulations enhance the model\'s performance.

Forest canopy cover (FCC) is essential in forest assessment and management, affecting ecosystem services such as carbon sequestration, wildlife habitat, and water regulation. Ongoing advancements in techniques for accurately and efficiently mapping and extracting FCC information require a thorough evaluation of their validity and reliability. The primary objectives of this study are to: (1) create a large-scale forest FCC dataset with a 1-meter spatial resolution, (2) assess the regional spatial distribution of FCC at a regional scale, and (3) investigate differences in FCC areas among the Global Forest Change (Hansen et al., 2013) and U.S. Forest Service Tree Canopy Cover products at various spatial scales in Arkansas (i.e., county and city levels). This study utilized high-resolution aerial imagery and a machine learning algorithm processed and analyzed using the Google Earth Engine cloud computing platform to produce the FCC dataset. The accuracy of this dataset was validated using one-third of the reference locations obtained from the Global Forest Change (Hansen et al., 2013) dataset and the National Agriculture Imagery Program (NAIP) aerial imagery with a 0.6-m spatial resolution. The results showed that the dataset successfully identified FCC at a 1-m resolution in the study area, with overall accuracy ranging between 83.31% and 94.35% per county. Spatial comparison results between the produced FCC dataset and the Hansen et al., 2013 and USFS products indicated a strong positive correlation, with R2 values ranging between 0.94 and 0.98 for county and city levels. This dataset provides valuable information for monitoring, forecasting, and managing forest resources in Arkansas and beyond. The methodology followed in this study enhances efficiency, cost-effectiveness, and scalability, as it enables the processing of large-scale datasets with high computational demands in a cloud-based environment. It also demonstrates that machine learning and cloud computing technologies can generate high-resolution forest cover datasets, which might be helpful in other regions of the world.

Children undergoing allogeneic hematopoietic stem cell transplantation (HSCT) are prone to developing acute kidney injury (AKI). Markers of kidney damage: kidney injury molecule (KIM)-1, interleukin (IL)-18, and neutrophil gelatinase-associated lipocalin (NGAL) may ease early diagnosis of AKI. The aim of this study was to assess serum concentrations of KIM-1, IL-18, and NGAL in children undergoing HSCT in relation to classical markers of kidney function (creatinine, cystatin C, estimated glomerular filtration rate (eGFR)) and to analyze their usefulness as predictors of kidney damage with the use of artificial intelligence tools. Serum concentrations of KIM-1, IL-18, NGAL, and cystatin C were assessed by ELISA in 27 children undergoing HSCT before transplantation and up to 4 weeks after the procedure. The data was used to build a Random Forest Classifier (RFC) model of renal injury prediction. The RFC model established on the basis of 3 input variables, KIM-1, IL-18, and NGAL concentrations in the serum of children before HSCT, was able to effectively assess the rate of patients with hyperfiltration, a surrogate marker of kidney injury 4 weeks after the procedure. With the use of the RFC model, serum KIM-1, IL-18, and NGAL may serve as markers of incipient renal dysfunction in children after HSCT.

OBJECTIVE: Regular users of hormonal contraceptive pills show marked heterogeneity in metabolic effects with variations in compositions. This might be due to choice of outcome variables for comparison. Total cholesterol-high-density lipoprotein ratio (TC/HDL) discordance with low-density lipoprotein (LDL-C) has now become an established marker of future risk for atherosclerotic cardiovascular disease and stable to variations in user.
METHODS: The present study was a randomized controlled trial to compare prevalence of TC/HDL and LDL discordance among non-obese women with polycystic ovarian syndrome (PCOS) treated with hormonal pills. Women were randomized into three arms, two arms received ultra-low dose pills (Ethinylestradiol [EE] 20 μg with drosperinone 3 mg or EE 15 μg with gestodene 60 μg) and one arm received low dose pill (EE 30 μg with desogestrel 150 μg). The role of baseline participant features and pill composition on discordance was determined.
RESULTS: Discordance was observed in more than a quarter of the participants before intervention. After 1 year of treatment, less than a fifth of the participants were discordant. Ultralow-dose pill users had lower discordance, LDL, and TC than low-dose pill users after 1 year of treatment. The random forest, a non-linear classifier, showed the highest accuracy in predicting discordance. The baseline Parameters with the maximal impact on the occurrence of discordance were triglyceride, homeostatic model assessment for insulin resistance, body mass index, and high density lipoprotein.
CONCLUSIONS: Non-obese PCOS women on ultra-low dose pill have a lower risk of acquiring future atherosclerotic cardiovascular disease.

Production plantation forestry has many economic benefits but can also have negative environmental impacts such as the spreading of invasive pines to native forest habitats. Monitoring forest for the presence of invasive pines helps with the management of this issue. However, detection of vegetation change over a large time period is difficult due to changes in image quality and sensor types, and by the spectral similarity of evergreen species and frequent cloud cover in the study area. The costs of high-resolution images are also prohibitive for routine monitoring in resource-constrained countries. This research investigated the use of remote sensing to identify the spread of Pinus caribaea over a 21-year period (2000 to 2021) in Belihuloya, Sri Lanka, using Landsat images. It applied a range of techniques to produce cloud free images, extract vegetation features, and improve vegetation classification accuracy, followed by the use of Geographical Information System to spatially analyze the spread of invasive pines. The results showed most invading pines were found within 100 m of the pine plantations\' borders where broadleaved forests and grasslands are vulnerable to invasion. However, the extent of invasive pine had an overall decline of 4 ha over the 21 years. The study confirmed that remote sensing combined with spatial analysis are effective tools for monitoring invasive pines in countries with limited resources. This study also provides information to conservationists and forest managers to conduct strategic planning for sustainable forest management and conservation in Sri Lanka.

Despite being composed of highly plastic neurons with extensive positive feedback, the nervous system maintains stable overall function. To keep activity within bounds, it relies on a set of negative feedback mechanisms that can induce stabilizing adjustments and that are collectively termed \"homeostatic plasticity.\" Recently, a highly excitable microdomain, located at the proximal end of the axon-the axon initial segment (AIS)-was found to exhibit structural modifications in response to activity perturbations. Though AIS plasticity appears to serve a homeostatic purpose, many aspects governing its expression and its functional role in regulating neuronal excitability remain elusive. A central challenge in studying the phenomenon is the rich heterogeneity of its expression (distal/proximal relocation, shortening, lengthening) and the variability of its functional role. A potential solution is to track AISs of a large number of neurons over time and attempt to induce structural plasticity in them. To this end, a promising approach is to use extracellular electrophysiological readouts to track a large number of neurons at high spatiotemporal resolution by means of high-density microelectrode arrays (HD-MEAs). However, an analysis framework that reliably identifies specific activity signatures that uniquely map on to underlying microstructural changes is missing. In this study, we assessed the feasibility of such a task and used the distal relocation of the AIS as an exemplary problem. We used sophisticated computational models to systematically explore the relationship between incremental changes in AIS positions and the specific consequences observed in simulated extracellular field potentials. An ensemble of feature changes in the extracellular fields that reliably characterize AIS plasticity was identified. We trained models that could detect these signatures with remarkable accuracy. Based on these findings, we propose a hybrid analysis framework that could potentially enable high-throughput experimental studies of activity-dependent AIS plasticity using HD-MEAs.

Frailty and falls are two adverse characteristics of aging that impair the quality of life of senior people and increase the burden on the healthcare system. Various methods exist to evaluate frailty, but none of them are considered the gold standard. Technological methods have also been proposed to assess the risk of falling in seniors. This study aims to propose an objective method for complementing existing methods used to identify the frail state and risk of falling in older adults.
A total of 712 subjects (age: 71.3 ± 8.2 years, including 505 women and 207 men) were recruited from two Japanese cities. Two hundred and three people were classified as frail according to the Kihon Checklist. One hundred and forty-two people presented with a history of falling during the previous 12 months. The subjects performed a 45 s standing balance test and a 20 m round walking trial. The plantar pressure data were collected using a 7-sensor insole. One hundred and eighty-four data features were extracted. Automatic learning random forest algorithms were used to build the frailty and faller classifiers. The discrimination capabilities of the features in the classification models were explored.
The overall balanced accuracy for the recognition of frail subjects was 0.75 ± 0.04 (F1-score: 0.77 ± 0.03). One sub-analysis using data collected for men aged > 65 years only revealed accuracies as high as 0.78 ± 0.07 (F1-score: 0.79 ± 0.05). The overall balanced accuracy for classifying subjects with a recent history of falling was 0.57 ± 0.05 (F1-score: 0.62 ± 0.04). The classification of subjects relative to their frailty state primarily relied on features extracted from the plantar pressure series collected during the walking test.
In the future, plantar pressures measured with smart insoles inserted in the shoes of senior people may be used to evaluate aspects of frailty related to the physical dimension (e.g., gait and balance alterations), thus allowing assisting clinicians in the early identification of frail individuals.

UNASSIGNED: Atrial fibrillation (AF) is one of the most common cardiovascular problems, and its asymptomatic tendency makes AF detection challenging. Machine and deep learning methods are commonly used in AF detection.
UNASSIGNED: The purpose of this study was to evaluate the information provided by convolutional neural network (CNN) and random forest (RF) machine learning models for AF classification.
UNASSIGNED: We manually extracted 166 time-frequency domains and linear and nonlinear features to classify single-lead electrocardiograms (ECGs) as normal, AF, other, or noisy sinus rhythms. We selected a subset of 56 robust features using a genetic algorithm that was used in the RF model. In a separate study, a 1-dimensional, 12-layer CNN was designed on the raw ECG rhythms. Four features from the output layer and 128 features from the fully connected layer of CNN were explored independently for classification. The models were trained and internally validated on 8,528 ECGs and externally validated on a hidden dataset containing 3,658 ECGs. Next,we analyzed the correlation between engineered and CNN-learned features.
UNASSIGNED: An RF classifier trained with 56-engineered features resulted in an F1 score of 0.91, 0.78, and 0.72 for normal, AF, and other rhythms, respectively. However, an ensemble of support vector machine and the CNN model resulted in an F1 score of 0.92, 0.87, and 0.80, respectively.
UNASSIGNED: We explored various features and machine learning models to identify AF rhythms using short (9-61 seconds) single-lead ECG recordings. Our results showed that the proposed CNN model abstracted distinctive features for AF classification.

One major challenge limiting the use of dexterous robotic hand prostheses controlled via electromyography and pattern recognition relates to the important efforts required to train complex models from scratch. To overcome this problem, several studies in recent years proposed to use transfer learning, combining pre-trained models (obtained from prior subjects) with training sessions performed on a specific user. Although a few promising results were reported in the past, it was recently shown that the use of conventional transfer learning algorithms does not increase performance if proper hyperparameter optimization is performed on the standard approach that does not exploit transfer learning. The objective of this paper is to introduce novel analyses on this topic by using a random forest classifier without hyperparameter optimization and to extend them with experiments performed on data recorded from the same patient, but in different data acquisition sessions. Two domain adaptation techniques were tested on the random forest classifier, allowing us to conduct experiments on healthy subjects and amputees. Differently from several previous papers, our results show that there are no appreciable improvements in terms of accuracy, regardless of the transfer learning techniques tested. The lack of adaptive learning is also demonstrated for the first time in an intra-subject experimental setting when using as a source ten data acquisitions recorded from the same subject but on five different days.

Diabetes Mellitus (DM) has become the third chronic non-communicable disease that hits patients after tumors, cardiovascular and cerebrovascular diseases, and has become one of the major public health problems in the world. Therefore, it is of great importance to identify individuals at high risk for DM in order to establish prevention strategies for DM.
Aiming at the problem of high-dimensional feature space and high feature redundancy of medical data, as well as the problem of data imbalance often faced. This study explored different supervised classifiers, combined with SVM-SMOTE and two feature dimensionality reduction methods (Logistic stepwise regression and LAASO) to classify the diabetes survey sample data with unbalanced categories and complex related factors. Analysis and discussion of the classification results of 4 supervised classifiers based on 4 data processing methods. Five indicators including Accuracy, Precision, Recall, F1-Score and AUC are selected as the key indicators to evaluate the performance of the classification model.
According to the result, Random Forest Classifier combining SVM-SMOTE resampling technology and LASSO feature screening method (Accuracy = 0.890, Precision = 0.869, Recall = 0.919, F1-Score = 0.893, AUC = 0.948) proved the best way to tell those at high risk of DM. Besides, the combined algorithm helps enhance the classification performance for prediction of high-risk people of DM. Also, age, region, heart rate, hypertension, hyperlipidemia and BMI are the top six most critical characteristic variables affecting diabetes.
The Random Forest Classifier combining with SVM-SMOTE and LASSO feature reduction method perform best in identifying high-risk people of DM from individuals. And the combined method proposed in the study would be a good tool for early screening of DM.