Application Of Machine Learning Methods Research Articles

Chest x-ray images: transfer learning model in COVID-19 detection.

This research aims to develop an effective algorithm for diagnosing COVID-19 in chest X-rays using the transfer learning method and support vector machines. In total, data was collected from 10 clinics, including both large city hospitals and smaller medical institutions. This ensured a diverse range of geographical and demographic information in the sample. An extensive data set was collected, including 10,000 chest X-ray images. 5000 images represent normal cases, 3993 images represent pneumonia cases, and 1007 images represent COVID-19 cases. Machine learning methods were applied to develop a classification model, and the results were compared with seven state-of-the-art models and a lightweight CNN architecture. The results showed that the proposed method achieves high accuracy values (Accuracy): 0.95 for COVID-19, 0.89 for pneumonia, and 0.92 for normal images (p < 0.05). Comparison with other models demonstrates statistically significant superiority of our method in accuracy across all three classes. The EfficientNet-B0 model surpasses our method only in accuracy for normal images with p < 0.01, confirming the advantages of our method. Our method demonstrates high sensitivity values (Sensitivity): 0.96 for COVID-19, 0.88 for pneumonia, and 0.93 for normal images (p < 0.05), outperforming most of the compared models. Correlation analysis showed Pearson coefficients of 0.92, 0.89, and 0.94 for COVID-19, pneumonia, and normal images, respectively, confirming a high degree of consistency between predicted and true class labels. In addition, the model was validated on external datasets to assess its generalizability. This validation confirmed its high level of effectiveness in a variety of clinical settings. This study confirms the importance of applying machine learning methods in medical applications and opens new perspectives for early diagnosis of infectious diseases. The practical application of the obtained results can enhance the efficiency of diagnosis and control the spread of COVID-19, as well as contribute to the development of innovative methods in medical practice.

Research on in-vivo electron paramagnetic resonance spectrum classification and radiation dose prediction based on machine learning

The in-vivo electron paramagnetic resonance (EPR) method can be used for on-site, rapid, and non-invasive detection of radiation dose to casualties after nuclear and radiation emergencies. For in-vivo EPR spectrum analysis, manual labeling of peaks and calculation of signal intensity are often used, which have problems such as large workload and interference by subjective factors. In this study, a method for automatic classification and identification of in-vivo EPR spectra was established using support vector machine (SVM) technology, which can in-batch and automatically identify and screen out invalid spectra due to vibration and dental surface water interference during in-vivo EPR measurements. In this study, a spectrum analysis method based on genetic algorithm optimization neural network (GA-BPNN) was established, which can automatically identify the radiation-induced signals in in-vivo EPR spectra and predict the radiation doses received by the injured. The experimental results showed that the SVM and GA-BPNN spectrum processing methods established in this study could effectively accomplish the automatic spectra classification and radiation dose prediction, and could meet the needs of dose assessment in nuclear emergency. This study explored the application of machine learning methods in EPR spectrum processing, improved the intelligence level of EPR spectrum processing, and would help to enhance the efficiency of mass EPR spectra processing.

Application of machine learning method for energy reconstruction on space based high granularity calorimeter

Application of machine learning method for energy reconstruction on space based high granularity calorimeter

An adaptive meta-imitation learning-based recommendation environment simulator: A case study on ship-cargo matching

High-quality shipping is one of the effective ways for sustainable cities in inland river basins to improve transportation efficiency and reduce energy consumption. Currently, the biggest challenge faced by shipping is the high empty-ship rate, which makes it impossible to directly apply machine learning methods due to the cold-start problem. Although some researchers have tried to utilize deep reinforcement learning(DRL)-based recommendation that do not rely on manually labeled data to alleviate the cold-start problem, progress has been slow due to the lack of available training environment. Therefore, this paper introduces an adaptive meta-imitation learning-based recommendation environment simulator, termed AMIL-Simulator. Specifically, we construct a conditionally guided diffusion model to simulate shipowner behavior in a dynamically changing environment. Moreover, we propose a shipowner reward model based on adaptive meta-imitation learning, enabling the learning of shipowner rewards across multiple tasks, even when confronted with limited samples and imbalanced categories. By conducting extensive quantitative experimental evaluations and shipowner-cargo matching studies, the results demonstrate the effectiveness of AMIL-Simulator, particularly in smaller-scale and cold-start environments.

Discovering potential founders within academic institutions

AbstractTechnology transfer is central to the development of an iconic entrepreneurial university. To foster knowledge transfer, many universities undergo a scouting process by their innovation coaches. The goal is to find staff members and students, who have the knowledge, expertise, and the potential to found startups by transforming their research results into a product. Since there is no systematic approach to measure the innovation potential of university members based on their academic activities, the scouting process is typically subjective and relies heavily on the experience of the innovation coaches. In this paper, we study the discovery of potential founders to support the scouting process using a data-driven approach. We create a novel data set by integrating the founder profiles with the academic activities from 8 universities across 5 countries. We explain the process of data integration as well as feature engineering. By applying machine learning methods, we investigate the classification accuracy of founders based on their academic background. Our analysis shows that using a random forest (RF), it is possible to differentiate founders and non-founders with an average accuracy of 79%. This accuracy remains mostly stable when applying an RF trained on one university to another, suggesting the existence of a generic founder profile. The detailed analysis indicates a high significance of the career path as well as patent- and grant-related features among others. Furthermore, we show that using a RF, it is possible to exploit these features to predict the future founding probability up to 3 years in advance with an accuracy of 80%. Finally, by analyzing the academic disciplines of founders we show that the patent documents have more influence on the startup’s core orientation than the publications.

CRP, PCT, and D-dimer as Biomarkers for Disease Severity in COVID-19 Patients: A Retrospective Study in Kinshasa, Democratic Republic of Congo

Introduction: The COVID-19 pandemic has had a significant impact on global health, resulting in more than 6 million reported deaths worldwide as of April 2023. This study aimed to investigate the potential of C-reactive protein (CRP), procalcitonin (PCT), and D-dimer as biomarkers for assessing disease severity in COVID-19 patients in Kinshasa, Democratic Republic of Congo Methods:A retrospective examination was conducted involving 339 COVID-19 patients admitted to Kinshasa hospitals between January 2021 and March 2022. CRP, PCT, and D-dimer levels were measured in all patients and compared between those with severe and non-severe illnesses. Results: Our findings revealed significantly higher CRP, PCT, and D-dimer levels in severe cases compared to non-severe cases. Specifically, the median CRP level was 120.6 mg/L in severe cases, 47.3 mg/L in mild cases, and 13.5 mg/L in moderate cases. The median PCT levels were 0.26 ng/mL in severe cases, 0.08 ng/ mL in mild cases, and 0.07 ng/L in moderate cases. Additionally, the median D-dimer level was 1836.9 µg/L in severe cases and 597.6 µg/L in mild cases, with a value of 481.1 µg/L in moderate cases. System learning techniques were also employed to predict disease severity based on these biomarkers, achieving high accuracy. Conclusion: Our findings suggest that CRP, PCT, and D-dimer serve as valuable biomarkers for identifying severe COVID-19 cases in Kinshasa. Furthermore, the application of machine learning methods can yield accurate predictions of disease severity based on these biomarkers. These biomarkers hold the potential to assist clinicians in informed decision-making regarding patient management and contribute to improved clinical outcomes for COVID-19 patients.

Application of Machine Learning Methods to Analyze the Dependence of Vibration Acceleration Signals on the Tightening Forces of Bolted Connections

The article is devoted to the application of machine learning methods for the analysis of vibration acceleration signals in bolted joints that occur under impact. The relevance of the work is due to the need to ensure the reliability and operability of bolted joints under loads. One of the promising areas of non-destructive testing is the analysis of the characteristics of vibration acceleration signals that change with changes in the state of structures, for example, with an increase in the tightening torque. This allows for the timely detection of possible defects and the prevention of emergency situations, ensuring the safety and durability of structures. The vibration acceleration signals under impact action on a bolted joint were analyzed. After calculating the signal characteristics, data sets were formed, including the values of tightening torques and the corresponding calculated signal characteristics, a search for a correlation between the tightening torque of bolted joints and the obtained set of vibration signal parameters was carried out. The frequency spectrum of signals, the Higuchi fractal dimension, detrended fluctuations, spectral power density and position of signal peaks were calculated. Machine learning models such as decision trees, the nearest neighbor method, the k-means method and neural networks were used for the analysis. For these methods, an optimal set of parameters correlating with the tightening torque was searched for. The main results show that machine learning methods are effective in classifying signals and finding correlations with stress state parameters. They allow us to detect the relationship between a set of signal characteristics and tightening torque, which opens up opportunities for more accurate and reliable monitoring of the condition of bolted connections. This should help to increase their operational reliability and durability, as well as reduce the likelihood of failures and accidents. The use of such methods can improve the quality of monitoring and diagnostics of bolted connections.

Enhancing dietary analysis: Using machine learning for food caloric and health risk assessment.

In the wake of growing concerns regarding diet-related health issues, this study investigates the application of machine learning methods to estimate the energy content and classify the health risks of foods based on the USDA National Nutrient Database. The caloric content of foods was estimated using the nutritional composition (i.e., carbohydrates, protein, total lipid, and total sugar content) and classified based on their weighted health risks, considering their carbohydrate, lipid, and glycemic index levels. The algorithms used for modeling include multiple linear regression (MLR), K-nearest neighbors, support vector machine, random forest regression (RFR), gradient-boosted regression, decision trees (DT), and deep neural networks. The MLR model demonstrated high accuracy on the training dataset (R2=0.99, mean absolute error [MAE]=7.71kcal, and root mean squared error [RMSE]=17.89kcal) and testing dataset (R2=0.99, MAE=7.75kcal, and RMSE=18kcal) in energy estimation, indicating its effectiveness in dietary assessment. The RFR and DT models were useful in categorizing foods into low-health-risk foods, but their performance was reduced in medium and high-health-risk groups. This research contributes to developing tools that could aid in personalized dietary planning and public health interventions to mitigate diet-related health risks. PRACTICAL APPLICATION: This study applies machine learning to estimate how many calories are in food and to understand the health risks different foods might have. By investigating the fats, cholesterol, and sugars in food items listed in a public database, we can better plan diets or develop apps that help people make healthier eating choices. This work aims to improve public access to nutritional information, supporting efforts to combat diet-related diseases through educational materials and applications that guide dietary choices in various settings.

Application of Machine Learning Methods in Predicting Lysine-specific Histone Demethylase 1 (LSD1) Inhibitors

Background: Lysine-specific histone demethylase 1 (LSD1) is a well-known anti-cancer target for drug discovery. Novel reversible inhibitors of LSD1 are desirable to be developed. Objective: This study aimed to build reliable predictive models to evaluate the antineoplastic efficacy of compounds and reveal the structural foundation underlying the inhibitory activity of LSD1. Methods: Multiple artificial intelligence algorithms were utilized in the development of quantitative structure-activity relationship (QSAR) models. A dataset comprising 915 compounds with welldefined IC50 values against LSD1 was assembled for analysis. The structures of these compounds were described by different descriptor packages. Principal component analysis (PCA) was performed to explore the chemical space distribution of each dataset. Y-randomization test and applicability domain (AD) analysis were deployed to validate the reliability of models. Results: For regression models, a consensus model was constructed by integrating the predictions of four top-performing individual models (SVM_ECFP4, RFR_PyDescriptor, RFR_RDKIT, and TRANSNNI), resulting in enhanced predictive performance as compared to the individual models. The consensus model achieved a determination coefficient (r2, for the test set) value of 0.82. For classification models, the consensus model was derived from the amalgamation of three individual models (ASNN_RDKIT, ASNN_ECFP4, and RFR_ECFP4), and the overall prediction accuracy of the model was 0.96 for external validation. Conclusion: The reliable models could be used to identify highly active LSD1 inhibitors for the purpose of efficient virtual screening. In addition, the important molecular properties and structural fragments derived from this work can provide guidance for the structural optimization of novel LSD1 inhibitors.

Neural representations of concreteness and concrete concepts are specific to the individual.

Different people listening to the same story may converge upon a largely shared interpretation while still developing idiosyncratic experiences atop that shared foundation. What linguistic properties support this individualized experience of natural language? Here, we investigate how the "concrete-abstract" axis - i.e., the extent to which a word is grounded in sensory experience - relates to within- and across-subject variability in the neural representations of language. Leveraging a dataset of human participants of both sexes who each listened to four auditory stories while undergoing functional MRI, we demonstrate that neural representations of "concreteness" are both reliable across stories and relatively unique to individuals, while neural representations of "abstractness" are variable both within individuals and across the population. Using natural language processing tools, we show that concrete words exhibit similar neural representations despite spanning larger distances within a high-dimensional semantic space, which potentially reflects an underlying representational signature of sensory experience - namely, imageability - shared by concrete words but absent from abstract words. Our findings situate the concrete-abstract axis as a core dimension that supports both shared and individualized representations of natural language.Significance Statement The meaning of spoken language is often ambiguous. As a result, people may form different interpretations despite being presented with the same information. What properties of language does the brain leverage to form this diverse, individual experience? Analyses of functional MRI data demonstrated that "concreteness", the extent to which language is related to sensory experience, evoked reliable neural patterns that were unique to individual subjects and allowed us to identify individuals solely based on their neural data. Application of machine learning methods showed that sets of concrete concepts, but not abstract concepts, show stable neural patterns, potentially due to a sensory signature: imageability. Overall, this study characterizes concreteness as a central property supporting the individualized experience of real-world language.

Classification of Air Pollutant Index on Data with Outliers and Imbalance Class Problem

The problem of air pollution has become a global issue that has received attention from various countries. Jakarta, Indonesia's capital city, is unavoidable from the same problem. This study will use four parameters of substances PM10, SO2, CO, O3, and nitrogen dioxide to categorize Jakarta's air quality (NO2). The data used is daily data taken from the Air Quality Monitoring Station in Jakarta throughout 2020. The methods used include SVM, Random Forest, Logistic Regression, KNN, CART, and Stacking Algorithm. At the data preparation stage, we found missing values, outliers, and class imbalance problems. Before applying machine learning methods and evaluating accuracy, we used data pre-processing techniques such as the MissForest method, median substitution, and ADASYN. The results prove that the original dataset has a higher accuracy score (0.882 – 0.977) than the balanced dataset (0.829 – 0.976). According to the evaluation results, the Random Forest method has the highest accuracy score for original and balanced datasets. The overall result is better than the identical research, which produces 96.61% accuracy using a neural network. It shows that preprocessing steps such as missing values handling an imbalanced class handling is essential in classification performance.

Analysis of applying machine learning methods in rock classification problems on core samples

Relevance. Core studies in the oil and gas industry allow us to obtain some filtration and capacity characteristics of rocks, as well as to give an idea of the composition and structure of the subsoil. This information is extremely important in the early stages of field development, as it allows us to formulate a primary version of the development project, which is then refined during the course of field drilling. However, core analysis and description are an extremely labor-intensive and human-influenced works that require automation. Thus, core image research is a popular task in the oil and gas industry that requires high accuracy and care during work; especially considering the volume of images that have to be analyzed. Aim. To review and analyze existing algorithms for classifying rocks from core images based on machine learning methods; as well as to use the information obtained to formulate recommendations for the development of these algorithms. Methods. Machine learning methods, including neural networks. Results. The work analyzed existing approaches to the study of core samples. The main advantages and disadvantages of each of them were noted and, based on the findings, a plan and requirements for conducting further research on core samples using machine learning were developed. As a result, using a convolutional neural network on the U-Net architecture, the authors have trained a model to solve the problem of segmentation of core samples in daytime images and presented the results of the model operation.

Predicting the risk of diabetes complications using machine learning and social administrative data in a country with ethnic inequities in health: Aotearoa New Zealand

BackgroundIn the age of big data, linked social and administrative health data in combination with machine learning (ML) is being increasingly used to improve prediction in chronic disease, e.g., cardiovascular diseases (CVD). In this study we aimed to apply ML methods on extensive national-level health and social administrative datasets to assess the utility of these for predicting future diabetes complications, including by ethnicity.MethodsFive ML models were used to predict CVD events among all people with known diabetes in the population of New Zealand, utilizing nationwide individual-level administrative data.ResultsThe Xgboost ML model had the best predictive power for predicting CVD events three years into the future among the population with diabetes (N = 145,600). The optimization procedure also found limited improvement in prediction by ethnicity (using area under the receiver operating curve, [AUC]). The results indicated no trade-off between model predictive performance and equity gap of prediction by ethnicity (that is improving model prediction and reducing performance gaps by ethnicity can be achieved simultaneously). The list of variables of importance was different among different models/ethnic groups, for example: age, deprivation (neighborhood-level), having had a hospitalization event, and the number of years living with diabetes.Discussion and conclusionsWe provide further evidence that ML with administrative health data can be used for meaningful future prediction of health outcomes. As such, it could be utilized to inform health planning and healthcare resource allocation for diabetes management and the prevention of CVD events. Our results may suggest limited scope for developing prediction models by ethnic group and that the major ways to reduce inequitable health outcomes is probably via improved delivery of prevention and management to those groups with diabetes at highest need.

Identifying Proteomic Prognostic Markers for Alzheimer's Disease with Survival Machine Learning: the Framingham Heart Study.

Protein abundance levels, sensitive to both physiological changes and external interventions, are useful for assessing the Alzheimer's disease (AD) risk and treatment efficacy. However, identifying proteomic prognostic markers for AD is challenging by their high dimensionality and inherent correlations. Our study analyzed 1128 plasma proteins, measured by the SOMAscan platform, from 858 participants 55 years and older (mean age 63 years, 52.9% women) of the Framingham Heart Study (FHS) Offspring cohort. We conducted regression analysis and machine learning models, including LASSO-based Cox proportional hazard regression model (LASSO) and generalized boosted regression model (GBM), to identify protein prognostic markers. These markers were used to construct a weighted proteomic composite score, the AD prediction performance of which was assessed using time-dependent area under the curve (AUC). The association between the composite score and memory domain was examined in 339 (of the 858) participants with available memory scores, and in an independent group of 430 participants younger than 55 years (mean age 46, 56.7% women). Over a mean follow-up of 20 years, 132 (15.4%) participants developed AD. After adjusting for baseline age, sex, education, and APOE ε4+ status, regression models identified 309 proteins (P ≤ 0.2). After applying machine learning methods, nine of these proteins were selected to develop a composite score. This score improved AD prediction beyond the factors of age, sex, education, and APOE ε4+ status across 15 to 25 years of follow-up, achieving its peak AUC of 0.84 in the LASSO model at the 22-year follow-up. It also showed a consistent negative association with memory scores in 339 participants (beta = -0.061, P = 0.046), 430 independent participants (beta = -0.060, P = 0.018), and the pooled 769 samples (beta = -0.058, P = 0.003). These findings highlight the utility of proteomic markers in improving AD prediction and emphasize the complex pathology of AD. The composite score may aid early AD detection and efficacy monitoring, warranting further validation in diverse populations.

Using ensemble learning method and binary decision tree algorithm for drought intensity level classification

This study applies machine learning methods such as Decision Tree (CART) and Random Forest to classify drought intensity based on meteorological data. The goal of the study was to evaluate the effectiveness of these methods for drought classification and their use in water resource management and agriculture. The methodology involved using two machine learning models that analyzed temperature and humidity indicators, as well as wind speed indicators. The models were trained and tested on real meteorological data to assess their accuracy and identify key factors affecting predictions. Results showed that the Random Forest model achieved the highest accuracy of 94.4% when analyzing temperature and humidity indicators, while the Decision Tree (CART) achieved an accuracy of 93.2%. When analyzing wind speed indicators, the models’ accuracies were 91.3% and 93.0%, respectively. Feature importance revealed that atmospheric pressure, temperature at 2 m, and wind speed are key factors influencing drought intensity. One of the study’s limitations was the insufficient amount of data for high drought levels (classes 4 and 5), indicating the need for further data collection. The innovation of this study lies in the integration of various meteorological parameters to build drought classification models, achieving high prediction accuracy. Unlike previous studies, our approach demonstrates that using a wide range of meteorological data can significantly improve drought classification accuracy. Significant findings include the necessity to expand the dataset and integrate additional climatic parameters to improve models and enhance their reliability.

Prediction of Donor Heart Acceptance for Transplant and Its Clinical Implications: Results From The Donor Heart Study.

Despite a shortage of potential donors for heart transplant in the United States, most potential donor hearts are discarded. We evaluated predictors of donor heart acceptance in the United States and applied machine learning methods to improve prediction. We included a nationwide (2005-2020) cohort of potential heart donors in the United States (n=73 948) from the Scientific Registry of Transplant Recipients and a more recent (2015-2020) rigorously phenotyped cohort of potential donors from DHS (Donor Heart Study; n=4130). We identified predictors of acceptance for heart transplant in both cohorts using multivariate logistic regression, incorporating time-interaction terms to characterize their varying effects over time. We fit models predicting acceptance for transplant in a 50% training subset of DHS using logistic regression, least absolute shrinkage and selection operator, and random forest algorithms and compared their performance in the remaining 50% (test) of the subset. Predictors of donor heart acceptance were similar in the nationwide and DHS cohorts. Among these, older age (P value for time interaction, 0.0001) has become increasingly predictive of discard over time while other factors, including those related to drug use, infection, and mild cardiac diagnostic abnormalities, have become less influential (P value for time interaction, <0.05 for all). A random forest model (area under the curve, 0.908; accuracy, 0.831) outperformed other prediction algorithms in the test subset and was used as the basis of a novel web-based prediction tool. Predictors of donor heart acceptance for transplantation have changed significantly over the last 2 decades, likely reflecting evolving evidence regarding their impact on posttransplant outcomes. Real-time prediction of donor heart acceptance, using our web-based tool, may improve efficiency during donor management and heart allocation.

Recent advances in the integration of protein mechanics and machine learning

Mechanics underlies protein properties and behavior. From a theoretical standpoint, it is possible to derive these based on physical rules. This is appealing because they provide insights into physiology and disease, as well as aid in protein engineering; however, the convoluted nature of the biological system and current computational speeds limit its feasibility. Machine learning (ML) architectures are known for their ability to make inferences on complex data, such as the relationship between protein mechanics, properties, and behavior. Substantial efforts have been made to learn such correlations in tasks such as the prediction of structure, stability, natural frequency, mechanical strength, folding rate, solubility, and function. Each of these properties is interconnected through protein mechanics, and it is not surprising that the methods used in these tasks overlap highly in model input and architecture. In this review, we evaluate ML methods for the seven aforementioned prediction tasks to identify current trends in ML research in the field of protein sciences, focusing on the input and model architecture of each method. A short overview of de novo protein design is also provided. Finally, we highlight trends in the application of ML methods in the field of protein science, as well as directions for future improvements.

Phlebotomine sand flies (Diptera: Psychodidae) of Bosnia and Herzegovina: distribution, ecology and environmental preferences

Sand flies (Diptera: Phlebotominae) are the principal vectors for the protozoan parasites Leishmania spp. and for phleboviruses. The sand fly fauna on the Balkan Peninsula, including Bosnia and Herzegovina (BIH), is diverse and the circulation of Leishmania infantum as well as phleboviruses has been proven. However, recent data on the sand fly fauna in BIH are scarce. In this study, we surveyed understudied regions in central and northeastern BIH to update the sand fly distribution and gain insights into the ecological and environmental factors shaping their appearance. CDC light trapping was conducted in 2022 and 2023 and a combination of morphological and molecular methods (cytochrome oxidase I barcoding) was performed for species identifications. We mapped the currently known distribution, modelled climatic suitability patterns and performed environmental analyses by applying machine learning methods. In addition, we analyzed blood meals by host gene sequencing and MALDI-TOF peptide mass mapping and screened for Leishmania spp. DNA and Phlebovirus RNA.Altogether, 591 sand flies of four species were trapped, predominantly Phlebotomus neglectus (97 %), but also Ph. balcanicus, Ph. mascittii, and Ph. papatasi. Records of seven sand fly species known to be endemic were plotted onto distribution maps based on 101 datapoints, identifying Ph. neglectus as the overall predominant species. The environmental analyses of sand fly species indicated variation in altitudinal, thermal, and precipitation conditions across the sand fly-positive sites. Phlebotomus simici, Phlebotomus tobbi, and Sergentomyia minuta are typically found exclusively in Mediterranean and subtropical climate zones, whereas other species typically inhabit continental regions. The Inverse Distance Weighted (IDW) interpolation of sand fly species numbers and Shannon entropy values suggested the southeastern coastal region of BIH as a primary focus for sand fly occurrence. This finding was corroborated by modeled average climatic suitability patterns for sand flies, depicting four distinct meso-regions for sand fly occurrence. The results of the ensemble method highlight the importance of annual precipitation to distinguish between positive and negative sand fly trapping sites in BIH. In total, 55 blood meals of two sand fly species, Ph. neglectus and Ph. balcanicus, were analyzed and five host species identified.Our comprehensive assessment of ecological and environmental preferences of sand flies in BIH may support further entomological surveys and help to better understand and evaluate potential hot spots of disease transmission in the country.

Improving Triage Accuracy in Prehospital Emergency Telemedicine: Scoping Review of Machine Learning-Enhanced Approaches.

Prehospital telemedicine triage systems combined with machine learning (ML) methods have the potential to improve triage accuracy and safely redirect low-acuity patients from attending the emergency department. However, research in prehospital settings is limited but needed; emergency department overcrowding and adverse patient outcomes are increasingly common. In this scoping review, we sought to characterize the existing methods for ML-enhanced telemedicine emergency triage. In order to support future research, we aimed to delineate what data sources, predictors, labels, ML models, and performance metrics were used, and in which telemedicine triage systems these methods were applied. A scoping review was conducted, querying multiple databases (MEDLINE, PubMed, Scopus, and IEEE Xplore) through February 24, 2023, to identify potential ML-enhanced methods, and for those eligible, relevant study characteristics were extracted, including prehospital triage setting, types of predictors, ground truth labeling method, ML models used, and performance metrics. Inclusion criteria were restricted to the triage of emergency telemedicine services using ML methods on an undifferentiated (disease nonspecific) population. Only primary research studies in English were considered. Furthermore, only those studies using data collected remotely (as opposed to derived from physical assessments) were included. In order to limit bias, we exclusively included articles identified through our predefined search criteria and had 3 researchers (DR, JS, and KS) independently screen the resulting studies. We conducted a narrative synthesis of findings to establish a knowledge base in this domain and identify potential gaps to be addressed in forthcoming ML-enhanced methods. A total of 165 unique records were screened for eligibility and 15 were included in the review. Most studies applied ML methods during emergency medical dispatch (7/15, 47%) or used chatbot applications (5/15, 33%). Patient demographics and health status variables were the most common predictors, with a notable absence of social variables. Frequently used ML models included support vector machines and tree-based methods. ML-enhanced models typically outperformed conventional triage algorithms, and we found a wide range of methods used to establish ground truth labels. This scoping review observed heterogeneity in dataset size, predictors, clinical setting (triage process), and reported performance metrics. Standard structured predictors, including age, sex, and comorbidities, across articles suggest the importance of these inputs; however, there was a notable absence of other potentially useful data, including medications, social variables, and health system exposure. Ground truth labeling practices should be reported in a standard fashion as the true model performance hinges on these labels. This review calls for future work to form a standardized framework, thereby supporting consistent reporting and performance comparisons across ML-enhanced prehospital triage systems.

Machine learning methods to discover hidden patterns in well-being and resilience for healthy aging.

A whole person approach to healthy aging can provide insight into social factors that may be critical. Digital technologies, such as mobile health (mHealth) applications, hold promise to provide novel insights for healthy aging and the ability to collect data between clinical care visits. Machine learning/artificial intelligence methods have the potential to uncover insights into healthy aging. Nurses and nurse informaticians have a unique lens to shape the future use of this technology. The purpose of this research was to apply machine learning methods to MyStrengths+MyHealth de-identified data (N = 988) for adults 45 years of age and older. An exploratory data analysis process guided this work. Overall (n = 988), the average Strength was 66.1% (SD = 5.1), average Challenges 66.5% (SD = 7.5), and average Needs 60.06% (SD = 3.1). There was a significant difference between Strengths and Needs (p < 0.001), between Challenges and Needs (p < 0.001), and no significant differences between average Strengths and Challenges. Four concept groups were identified from the data (Thinking, Moving, Emotions, and Sleeping). The Thinking group had the most statistically significant challenges (11) associated with having at least one Thinking Challenge and the highest average Strengths (66.5%) and Needs (83.6%) compared to the other groups. This retrospective analysis applied machine learning methods to de-identified whole person health resilience data from the MSMH application. Adults 45 and older had many Strengths despite numerous Challenges and Needs. The Thinking group had the highest Strengths, Challenges, and Needs, which aligns with the literature and highlights the co-occurring health challenges experienced by this group. Machine learning methods applied to consumer health data identify unique insights applicable to specific conditions (e.g., cognitive) and healthy aging. The next steps involve testing personalized interventions with nurses leading artificial intelligence integration into clinical care.