Classification Tree Research Articles

Impact of vancomycin area under the curve in early or later phase on efficacy and nephrotoxicity in patients with enterococcal bloodstream infections: a multicenter study

BackgroundThe optimal pharmacokinetic and pharmacodynamic (PK/PD) parameters of vancomycin that can improve outcomes in enterococcal infections remain controversial. To clarify the therapeutic target for this antibiotic, this study aimed to determine vancomycin PK/PD parameters associated with efficacy in the early (during 72 h) or later (after 72 h) phase of treatment and nephrotoxicity in enterococcal bloodstream infection patients.MethodsThis multicenter retrospective study reviewed medical records of patients with enterococcal bloodstream infections treated with intravenous vancomycin infusion for at least 72 h between January 2016 and March 2024 at Phramongkutklao Hospital or Nopparatrajathanee Hospital in Bangkok, and Rachaburi Hospital in Rachaburi Province, Thailand. Patients with data available on serum vancomycin concentration were analyzed. The primary outcomes were 30-day mortality and acute kidney injury. The estimates of the mean 24-h area under the curve in the first 72 h (AUC24) and in steady state (AUCss) were determined by Bayesian theorem.ResultsOverall, 201 vancomycin concentrations were measured within the first 72 h after vancomycin treatment, while 156 were in a steady state (> 72 h). According to Classification and Regression Tree analysis, vancomycin AUC at 420 mg·h/l was the PK/PD target for 30-day mortality. Results reveal that patients with AUC24 (early phase) and AUCss < 420 mg·h/l (later phase) had significantly higher 14-day, 30-day, and in-hospital mortality than AUC ≥ 420 mg·h/l groups. In addition, patients with AUC24 ≥ 420 mg·h/l in the early phase had significantly reduced microbiological failure (p = 0.004). Patients with AUC ≥ 700 mg·h/l in early and later phases had significantly increased acute kidney injury risk. In addition, patients receiving concomitant nephrotoxic drugs had an AUC cutoff value of 650 mg·h/l. Multivariate Cox regression analysis showed that vancomycin AUCss < 420 mg·h/l, unknown source of bacteremia, and acute kidney injury were significantly associated with 30-day mortality.ConclusionsAUC 420–650 mg·h/l in early and later phases was the target of vancomycin’s PK/PD in enterococcal bacteremia patients for efficacy and to prevent acute kidney injury. This study suggests close monitoring of vancomycin levels to ensure efficacy and safety.

ML-AMPSIT: Machine Learning-based Automated Multi-method Parameter Sensitivity and Importance analysis Tool

Abstract. The accurate calibration of parameters in atmospheric and Earth system models is crucial for improving their performance but remains a challenge due to their inherent complexity, which is reflected in input–output relationships often characterised by multiple interactions between the parameters, thus hindering the use of simple sensitivity analysis methods. This paper introduces the Machine Learning-based Automated Multi-method Parameter Sensitivity and Importance analysis Tool (ML-AMPSIT), a new tool designed with the aim of providing a simple and flexible framework to estimate the sensitivity and importance of parameters in complex numerical weather prediction models. This tool leverages the strengths of multiple regression-based and probabilistic machine learning methods, including LASSO (see the list of abbreviations in Appendix B), support vector machine, classification and regression trees, random forest, extreme gradient boosting, Gaussian process regression, and Bayesian ridge regression. These regression algorithms are used to construct computationally inexpensive surrogate models to effectively predict the impact of input parameter variations on model output, thereby significantly reducing the computational burden of running high-fidelity models for sensitivity analysis. Moreover, the multi-method approach allows for a comparative analysis of the results. Through a detailed case study with the Weather Research and Forecasting (WRF) model coupled with the Noah-MP land surface model, ML-AMPSIT is demonstrated to efficiently predict the effects of varying the values of Noah-MP model parameters with a relatively small number of model runs by simulating a sea breeze circulation over an idealised flat domain. This paper points out how ML-AMPSIT can be an efficient tool for performing sensitivity and importance analysis for complex models, guiding the user through the different steps and allowing for a simplification and automatisation of the process.

Efficient diagnosis of diabetes mellitus using an improved ensemble method

Diabetes is a growing health concern in developing countries, causing considerable mortality rates. While machine learning (ML) approaches have been widely used to improve early detection and treatment, several studies have shown low classification accuracies due to overfitting, underfitting, and data noise. This research employs parallel and sequential ensemble ML approaches paired with feature selection techniques to boost classification accuracy. The Pima India Diabetes Data from the UCI ML Repository served as the dataset. Data preprocessing included cleaning the dataset by replacing missing values with column means and selecting highly correlated features using forward and backward selection methods. The dataset was split into two parts: training (70%), and testing (30%). Python was used for classification in Jupyter Notebook, and there were two design phases. The first phase utilized J48, Classification and Regression Tree (CART), and Decision Stump (DS) to create a random forest model. The second phase employed the same algorithms alongside sequential ensemble methods—XG Boost, AdaBoostM1, and Gradient Boosting—using an average voting algorithm for binary classification. Evaluation revealed that XG Boost, AdaBoostM1, and Gradient Boosting achieved classification accuracies of 100%, with performance metrics including F1 score, MCC, Precision, Recall, AUC-ROC, and AUC-PR all equal to 1.00, indicating reliable predictions of diabetes presence. Researchers and practitioners can leverage the predictive model developed in this work to make quick predictions of diabetes mellitus, which could save many lives.

A Systematic Review on Website Phishing Attack Detection for Online Users

Phishing is the criminal effort to steal delicate information such as account details, passwords, usernames, credit, and debit card details for malicious use. Phishing fraud might be the most popular cybercrime used today. The online and webmail payment sectors are highly affected by phishing attacks. Nowadays, attackers create many techniques that pave the way for them to steal all personal information from the selected victims easily. However, numerous anti-phishing techniques are used to detect the phishing attack, such as blacklist, visual similarity, heuristic detection, Deep Learning (DL), and Machine Learning (ML) techniques. ML techniques are more efficient at detecting phishing attacks, and these techniques also rectify the drawbacks of existing approaches. This paper provides a detailed review of various phishing techniques, encompassing phishing mediums, phishing vectors, and numerous technical approaches. Also, new research works are analyzed to detect phishing websites using heuristic, visual similarity, DL, and ML models. Neural Networks (NNs), Convolutional Neural Networks (CNNs), Deep Neural Networks (DNNs), Support Vector Machine (SVM), fuzzy logic methods, Long Short-Term Memory (LSTM) techniques, Random Forest (RF), Decision Tree (DT), Adaboost –Extra Tree (AET) classifiers based on ML models are examined in this review paper.

Short-Wave Infrared Spectroscopy for On-Site Discrimination of Hazardous Mineral Fibers Using Machine Learning Techniques

Asbestos fibers are well-known carcinogens, and their rapid detection is critical for ensuring safety, protecting public health, and promoting environmental sustainability. In this work, short-wave infrared (SWIR) spectroscopy, combined with machine learning (ML), was evaluated as an environmentally friendly analytical approach for simultaneously distinguishing the asbestos type, asbestos-containing materials in various forms, asbestos-contaminated/-uncontaminated soil, and asbestos-contaminated/-uncontaminated cement, simultaneously. This approach offers a noninvasive and efficient alternative to traditional laboratory methods, aligning with sustainable practices by reducing hazardous waste generation and enabling in situ testing. Different chemometrics techniques were applied to discriminate the material classes. In more detail, partial least squares discriminant analysis (PLS-DA), principal component analysis-based discriminant analysis (PCA-DA), principal component analysis-based K-nearest neighbors classification (PCA-KNN), classification and regression trees (CART), and error-correcting output-coding support vector machine (ECOC SVM) classifiers were tested. The tested classifiers showed different performances in discriminating between the analyzed samples. CART and ECOC SVM performed best (RecallM and AccuracyM equal to 1.00), followed by PCA-KNN (RecallM of 0.98–1.00 and AccuracyM equal to 1.00). Poorer performances were obtained by PLS-DA (RecallM of 0.68–0.72 and AccuracyM equal to 0.95) and PCA-DA (RecallM of 0.66–0.70 and AccuracyM equal to 0.95). This research aligns with the United Nations’ Sustainable Development Goals (SDGs), particularly SDG 3 (Good Health and Well-Being), by enhancing human health protection through advanced asbestos detection methods, and SDG 12 (Responsible Consumption and Production), by promoting sustainable, low-waste testing methodologies.

TP53 Mutant Variant Allele Frequency and Cytogenetics Determine Prognostic Groups in MDS/AML for Transplantation.

Results following hematopoietic stem cell transplantation (HSCT) for TP53-mutated myeloid malignancies are disappointing. Several HSCT centers decline to perform HSCT for patients with TP53 mutation because of poor outcomes. In this study, we analyzed 240 patients with TP53-mutated myelodysplastic syndrome (MDS) or acute myeloid leukemia (AML) that underwent HSCT. We aimed to identify the patients that benefit most from HSCT. The primary outcome was progression-free survival (PFS). Fifty-two percent of the cohort had AML and the median age of the cohort was 62. AML and MDS outcomes were similar. We identified several favorable prognostic factors for PFS including the absence of complex cytogenetics/5q deletion/7q deletion, a lower variant allele frequency (VAF), a mono-hit status and the use of a matched-related donor. Using classification and regression tree analysis, we identified VAF and cytogenetics as the two most important prognostic factors. Patients with TP53mut VAF ≥ 50% had a 2-year PFS of 3%, patients with TP53mut VAF < 50% and complex/5q/7q cytogenetics abnormalities had 2-year PFS of 22%. Patients with TP53mut VAF < 50% and without complex/5q/7q cytogenetics had 2-year PFS of 60%. This data informs clinical practice and helps patients decide whether to pursue HSCT.

Sarcasm Identification and Classification in Hindi Newspaper Headlines

Sarcasm identification in textual data is the most captivating area of research in the current research trends. It is a challenging task for humans as well as for the computer. In this paper, we have tried to identify sarcasm in the Hindi newspaper headlines of two of the most-read Hindi newspapers in India, namely Hindustan and Dainik Jagran. Initially, we collected 88,518 Hindi newspaper headlines and identified 1,945 headlines to be sarcastic, which we have considered for the present study. The headlines taken into consideration belong to the political domain and were published during some of the recent Legislative Assembly Elections of 2020, 2021 and 2022. Various machine learning and deep learning techniques have been used to develop the baseline models. It justifies the assumption that sarcastic text does not always bear a negative sentiment. It may bear a positive sentiment depending on the context. The present paper aims at the creation of a dataset consisting of 1,945 Hindi newspaper headlines, training and testing machine learning and deep learning models, namely Extra Trees Classifier, Random Forest Classifier, XGBClassifier, fasttext-stackedTCN and mBERT-stackedTCN for sarcasm identification on the dataset and comparing the results obtained by the models after the experiment. Out of all the choosen models, the Random Forest Classifier performs better with F 1 score of 92.11 before data augmentation and and 90.68 after data augmentation.

Development and Evaluation of a New Gastroenteritis Clinical Severity Score for Children Aged Under 5.

To develop and internally validate a new severity score to more accurately assess the clinical severity forms of acute gastroenteritis (AGE) in children from birth to age 5 years. We included children consulting for AGE in the emergency department of the University Hospital of Nantes (March 2017-June 2019). We developed and evaluated a new predictive score (GASTROVIM score) using the classification and regression trees. We compared its diagnostic performance with the two existing scores: the Vesikari score and clinical dehydration scale (CDS). A clinical expert a posteriori evaluated children's medical records to determine the severity form of AGE as the gold standard. Of the 200 children included, 129 (64.5%) had severe forms of AGE according to the GASTROVIM score (maximal number of liquid stools and vomiting per day, weight loss and CDS), with sensitivity 90.0% (95% CI: 83.5-94.6) and specificity 82.9% (72.0-90.8). The Vesikari score had similar sensitivity (97.3%) but lower specificity (17.0%) and the CDS had lower sensitivity (28.3%) and higher specificity (100%) than the GASTROVIM score. The GASTROVIM score could discriminate severe forms of AGE with good diagnostic performance. Nevertheless, external validation in other populations and/or other countries is needed.

Preoperative and early postoperative factors associated with visual outcome after macular-off retinal detachment surgery.

To evaluate preoperative and early postoperative factors associated with changes in visual acuity in macula-off rhegmatogenous retinal detachment (RRD) patients. A retrospective review of 59 eyes from 59 patients who underwent pars plana vitrectomy (PPV) and silicone oil (SiO) tamponade for macula-off RRD. Preoperative and early postoperative characteristics were analyzed using the classification and regression tree (CART) analysis. The baseline preoperative BCVA improved from 1.67 ± 0.97 logMAR to 0.21 ± 0.22 logMAR at final visit. Central foveal thickness (CFT) and BCVA showed significant increases from 1 week post-surgery onward. Mean CFT significantly increased from 136.97 ± 40.17 μm to 192.54 ± 34.09 μm (p < 0.001). The percentage of eyes with integrated external limiting membrane (ELM) and ellipsoid zone (EZ) was progressively increased from 45.76% and 10.17% to 98.31% and 71.19%, respectively (p < 0.001). BCVA at 1week after surgery, ELM integrity, preoperative intraretinal cysts, and macula-off duration were significantly associated with final visual recovery after surgery. The first week postoperative BCVA is the most powerful predictor for final BCVA. ELM integrity, intraretinal cysts, and macula-off duration are also significantly associated with final visual recovery.

P1122 Identification of responder subpopulations in moderately-to-severely active Crohn’s disease patients treated with mirikizumab: Results from the VIVID-1 study

Abstract Background Mirikizumab (MIRI), an anti-IL-23p19 antibody, demonstrated robust efficacy in improving clinical and endoscopic endpoints with an acceptable safety profile in IBD1. Bowel urgency is common and impactful among patients with Crohn’s disease (CD).2 CD patients show a remarkable heterogeneity in their individual response levels to targeted therapies,3 including MIRI. We explored the existence of subgroups among MIRI-treated, moderate-to-severely active CD patients1 by investigating symptom trajectories and their relationship to treatment outcome. Methods A Growth Mixture Model was used to determine the existence and number of distinct patient clusters based on individual patient daily diary data used to construct Crohn’s Disease Activity Index (CDAI) based response trajectories. Response predictors were assessed with Classification and Regression Trees analysis. Week (W) 12 and 52 clinical endpoints were assessed by trajectory group. Non-responder imputation and modified baseline observation carried forward was used. Results Four response trajectory groups could be statistically separated: Super Responder (N=105; 18.4%), Responder (N=128; 22.4%), Delayed Responder (N=169; 29.5%), and Non/Incomplete Responder (unstable response over time) (N=170; 29.7%) (Figure 1). Patient Reported Outcome (PRO) Response (≥30% decrease in stool frequency and/or abdominal pain and neither score worse than baseline) at W12 was a marker of overall responder group. For patients with a baseline CDAI ≥350, W8 Bowel Urgency Response (≥3-point improvement on 0-10-point Urgency Numeric Ration Scale) was a marker of being a Super Responder. At W12 and W52, efficacy remission endpoints were achieved differentially: Super Responder, Responder, and Delayed Responder groups, respectively: clinical (W12/W52): 62%/80%, 38%/69%, 23%/49% (Table 1); endoscopic: 17%/41%, 20%/30%, 21%/37%; bowel urgency: 52%/72%, 35%/56%, 22%/43%; histologic: 21%/38%, 22%/38%, 24%/32%. Conclusion For MIRI treatment of CD, PRO Response and Bowel Urgency Response are early markers of overall treatment response. The overall response rate was 70.3%. Four symptom response trajectory groups were identified: Super Responder, Responder, Delayed Responder, and Non/Incomplete Responder. Efficacy was robust across all response groups except Non/Incomplete Responders. Super Responders followed by Responders and then Delayed Responders achieved the highest rates of W52 remission endpoints, including endoscopic/histologic, suggesting fast, robust response may lead to higher gains in long-term efficacy. Replication and molecular analysis are needed to investigate whether MIRI differential response kinetics identify CD endophenotypes.

Automatic Blood Disease Identification System Using Machine Learning Algorithms with Hemogram Reports

Objectives: The primary objective of this research is to create prediction models with machine learning algorithms that can detect blood illnesses in their early stages, including sickle cell disease, leukemia, anemia, and lymphoma. Methods: Reducing the amount of deaths linked to these illnesses and increasing the precision of disease detection. The study used machine learning algorithms: Decision Tree, Random Forest, and XGBoost classifier, and it used a dataset of complete blood count reports. Based on the characteristics of the total blood count, these algorithms were trained on the dataset to forecast the probability of blood diseases. Findings: According to the study, there is a better chance of a cure for blood problems since machine learning models can correctly detect them in their early stages. The findings imply that using predictive models can both lower the death rate and enhance the quality of life for those with these conditions. With a 99.10% accuracy rate, the Random Forest method outperforms other algorithms like Decision Tree, and XGBoost. Novelty: This research is unique because it uses a dataset of complete blood count reports results to use machine learning algorithms for blood condition prediction. Healthcare systems may detect blood problems early on and enhance patient outcomes by using classifier algorithms such as Decision Tree, Random Forest, and XGBoost. This opens up new avenues for illness identification. Keywords: Machine Learning, Decision Tree, Random Forest, XGBoost, Blood Diseases

A comparative study of decision tree-based learners to classify the switching transient disturbances in real microgrid network

ABSTRACT Detection and classification of power system instabilities due to the raised transient effect during switching operation of different kinds of load, capacitor bank, large sized induction motor is challenging in microgrid network because of inconstant direction of current and complexity of network. However, this classification study is a mandatory measure to maintain quality power in modern microgrid network. A novel decision tree (DT) classification based machine learning technique is proposed in this study to do this significant task. The test transient signals during several switching operation have been extracted from a real microgrid network in India. The statistical attributes are computed from the coefficients of discrete wavelet transform (DWT) of transient voltage signals. The significant features are selected according to the performance of the processed DWT. The fine, medium, and coarse DT classifiers considering different number of splits and ensembled tree based on bagging have been trained in the next stage of algorithm. The performances of each classifier are assessed in terms of confusion matrix and receiver operating characteristics curve. The accuracy and training time of each classifier are compared to recommend a specific method to detect and classify the similar type of transient events. A 99.4% accuracy has been achieved with a very lower detection time from fine DT.

Musician's Experience After Breast Cancer Treatment: Defining Musical Toxicity and its Frequency.

Over 50% of households in the United States have at least one musician-many musicians are also breast cancer survivors. This group has not been well studied, and given the level of fine sensory-motor skill required for musicianship, we hypothesized that musicians experience unique manifestations of breast cancer treatment toxicities. A nine-item Musical Toxicity Questionnaire (MTQ) was distributed to patients who had consented to participate in the Mayo Clinic Breast Cancer Registry. The MTQ screened participants by asking if they played a musical instrument or sang in the last 10 years: questions populated for those who answered yes. Respondents were asked if they noticed difficulty with their musical endeavor during or after breast cancer treatment, defined as acute musical toxicity (AMT). The questionnaire asked which side effect and cancer-directed therapy most influenced musical ability, what musical attributes were affected, and the timeline of resolution. Multivariable and classification tree analyses assessed relationships between AMT and treatment characteristics. Of 1,871 survey respondents, 29% (535/1,871) self-identified as musicians. Over a quarter (27%, 144/535) reported AMT, and for 57% (82/144), AMT had not resolved at the time of survey. Of the treatments each participant received, chemotherapy was most often reported as most negatively impactful (63/89 who received chemotherapy, 71%). Decreased endurance was the most common musical difficulty (64% of those with AMT, 92/144), followed by decreased accuracy, trouble playing/singing quickly, and difficulty using proper technique. Multivariable and classification tree analyses revealed that receipt of chemotherapy was most strongly correlated with AMT. These results will help oncology care teams counsel musicians, answer questions about impacts on musicality, and provide a timeline for resolution of musical symptoms.

Multi-Label Classification of Complaint Texts: Civil Aviation Service Quality Case Study

Customer complaints play an important role in the adjustment of business operations and improvement of services, particularly in the aviation industry. However, extracting adequate textual features to perform a multi-label classification of complaints remains a difficult problem. Current multi-label classification methods applied to complaint texts have not been able to fully utilize complaint information, and little research has been performed on complaint classification in the aviation industry. Therefore, to solve the problems of insufficient text feature extraction and the insufficient learning of inter-feature relationships, we constructed a multi-label classification model (MAG, or multi-feature attention gradient boosting decision tree classifier) for civil aviation service quality complaint texts. This model incorporates multiple features and attention mechanisms to improve the classification accuracy. First, the BERT (Bidirectional Encoder Representations from Transformers) model and attention mechanisms are used to represent the semantic and label features of the text. Then, the Text-CNN (a convolutional neural network) and BiLSTM (bidirectional long short-term memory) multi-channel feature extraction networks are used to extract the local and global features of the complaint text, respectively. Subsequently, a co-attention mechanism is used to learn the relationship between the local and global features. Finally, the travelers’ complaint texts are accurately classified by integrating the base classifiers. The results show that our proposed model improves the multi-label classification accuracy, outperforming other modern algorithms. We demonstrate how the label feature representation based on association rules and the multi-channel feature extraction network can enrich textual information and more fully extract features. Overall, the co-attention mechanism can effectively learn the relationships between text features, thereby improving the classification accuracy of the model and enabling better identification of travelers’ complaints. This study not only effectively extracted text features by integrating multiple features and attention mechanisms, but also constructed a targeted feature word set for complaint texts based on the domain-specific characteristics of the civil aviation industry. Furthermore, by iterating the basic classifier using a multi-label classification model, a classifier with higher accuracy was successfully obtained, providing strong technical support and new practical paths for improving the civil aviation service quality and complaint management.

Robust classification model for identifying stroke patients utilising a machine learning-based ensemblestacking method

Abstract Purpose of the study: Cerebrovascular accident (CVA) occurs swiftly&amp;#xD;and disrupts brain blood flow, causing neurological issues. Risk factors include&amp;#xD;smoking, diabetes, hyperlipidemia, hypertension, and atrial fibrillation. Many brain&amp;#xD;stroke prediction systems are computationally demanding, sluggish, and unreliable.&amp;#xD;This study uses interpolation spline curves impute data and Principal Component&amp;#xD;Analysis to identify the most important factors for stroke prediction. By using stack&amp;#xD;ensemble machine learning methods, the goal is to improve the precision of stroke&amp;#xD;disease identification.&amp;#xD;Used method: Using interpolation spline curve data imputation and Principal&amp;#xD;Component Analysis to preprocess and extract EHR data is unique. In addition, this&amp;#xD;article also proposes a novel stacking ensemble technique using bagging and boosting&amp;#xD;as foundation learners. Bagging and boosting enhance prediction by reducing variation&amp;#xD;and bias. Stack-based ensemble learning classifies brain strokes. Build base and meta-&amp;#xD;learners with Random Forest, XGBoost, Decision tree classifier, KNN, and Logistic&amp;#xD;Regression. Evaluation of machine learning model efficiency determines the optimal&amp;#xD;stacking ensemble meta-learner model.&amp;#xD;Brief Description of Results: The results emphasize the stacking ensemble’s best&amp;#xD;meta-learner model and imputation technique’s impact on electronic health record&amp;#xD;representation. By using PCA, most important factors has identified for detecting&amp;#xD;stroke. The analysis results showed that the Logistic Regression as a meta learner had&amp;#xD;the best predictive performance which achieves 0.96 precision and 0.98 recall value&amp;#xD;respectively with 97% accuracy and AUC curve value of 0.99.&amp;#xD;Findings: The Decision Tree Classifier and K-Nearest Neighbour as meta learner got&amp;#xD;95%, 96%accuracy, and both 0.95 AOC curve values on this dataset, showing that the&amp;#xD;method works. Precision values of 0.93, and 0.95 for the Decision Tree Classifier and&amp;#xD;KNN Classifiers as meta-learner confirm their robustness. These findings suggest that&amp;#xD;interpolation spline curve and stacking based ensemble machine learning can improve&amp;#xD;the identification of brain stroke from incomplete electronic health records.

Deciphering abbreviations in Malaysian clinical notes using machine learning.

This is the first Malaysian machine learning model to detect and disambiguate abbreviations in clinical notes. The model has been designed to be incorporated into MyHarmony, a Natural Language Processing system, that extracts clinical information for healthcare management. The model utilizes word embedding to ensure feasibility of use, not in real-time but for secondary analysis, within the constraints of low-resource settings. A Malaysian clinical embedding, based on Word2Vec model, was developed using 29,895 electronic discharge summaries. The embedding was compared against conventional rule-based and FastText embedding on two tasks: abbreviation detection and abbreviation disambiguation. Machine Learning classifiers were applied to assess performance. The Malaysian clinical word embedding contained 7 million word-tokens, 24,352 unique vocabularies, and 100 dimensions. For abbreviation detection, the Decision Tree classifier augmented with the Malaysian clinical embedding showed the best performance (F-score of 0.9519). For abbreviation disambiguation, the classifier with the Malaysian clinical embedding had the best performance for most of the abbreviations (F-score of 0.9903). Despite having a smaller vocabulary and dimension, our local clinical word embedding performed better than the larger non-clinical FastText embedding. Word embedding with simple machine learning algorithms can decipher abbreviations well. It also requires lower computational resources and is suitable for implementation in low-resource settings such as Malaysia. The integration of this model into MyHarmony will improve recognition of clinical terms, thus improving the information generated for monitoring Malaysian healthcare services and policymaking.

Cotton production areas are at high risk of invasion by Amrasca biguttula (Ishida) (Cicadellidae: Hemiptera): potential distribution under climate change.

The cotton jassid, Amrasca biguttula, a dangerous and polyphagous pest, has recently invaded the Middle East, Africa and South America, raising concerns about the future of cotton and other food crops including okra, eggplant and potato. However, its potential distribution remains largely unknown, posing a challenge in developing effective phytosanitary strategies. We used an ensemble model of six machine-learning algorithms including random forest, maxent, support vector machines, classification and regression tree, generalized linear model and boosted regression trees to forecast the potential distribution of A. biguttula in the present and future using presence records of the pest and bioclimatic predictors. The accuracy of these algorithms was assessed based on the area under the curve (AUC), correlation (COR), deviance and true skill statistic (TSS). All algorithms showed good performance in forecasting the distribution of A. biguttula (AUC ≥ 0.91, COR ≥ 0.72, TSS ≥ 0.77 and deviance ≤ 0.65). Mean temperature of wettest quarter, mean temperature of driest quarter and precipitation of the wettest month were the key variables that contributed to predicting A. biguttula occurrence. Projection of the model showed that cotton production areas in Asia, sub-Saharan Africa, and South America are at threat of invasion by A. biguttula under the current climatic scenario. Additionally, range expansion for A. biguttula is projected in the future in sub-Saharan Africa, South America and China, indicating a suitable ecological niche for A. biguttula to thrive. Our results provide early warning and decision-making information that can guide efforts to prevent this pest's further spread and invasion into new areas. © 2025 Society of Chemical Industry.

Disparities in anxiety and related factors among Chinese older adults across different aged-care models: a comparison of two cross-sectional studies

BackgroundAnxiety disorders in older adults have become a prominent public health problem due to their concomitant chronic conditions, reduced quality of life and even death. However, fewer studies have been conducted on differences in anxiety among older individuals in different aged-care models, and the interactive relationship between the influencing factors on anxiety remains unclear. The study aimed to examine the disparities in the prevalence of anxiety between community-dwelling and institutionalized older adults and related influencing factors.MethodsData were collected from the Anhui Healthy Longevity Survey (AHLS) and the Anhui Elderly Caring Social Organizations Survey (AECSOS). Data on demographic variables, lifestyle factors and health-related variables in 6968 older adults were used for analysis. Anxiety symptoms were evaluated using the Generalized Anxiety Disorder Assessment Scale (GAD-7). Binary logistic regression models and a Classification and Regression Tree model (CART) were utilized to examine the relationship between variables.ResultsThe prevalence of anxiety were 24.3% and 16.7% among community-dwelling older adults and institutionalized older adults, respectively. Several factors including age, gender, residence, education, income level, live alone, and number of chronic diseases showed a linkage with anxiety among community-dwelling older adults. For the institutionalized older adults, gender, residence, source of income, and number of chronic diseases exhibited a significant association with anxiety. We noted the interactive effect, suggesting that community-dwelling female older adults with an income level of less than 6500 RMB per year and reported chronic disease comorbidities had the highest likelihood of anxiety, and institutionalized female older adults with income sources such as pension, subsidy, family providing, and resident in rural areas have the greatest risk of experiencing anxiety.ConclusionsThis study has brought to light the higher risk of anxiety among community-dwelling older adults compared to institutionalized older adults. Targeted interventions are, therefore emphasized to address the negative impact of anxiety for populations at higher risk.

Machine learning recognition of hybrid lead halide perovskites and perovskite-related structures from X-ray diffraction patterns.

Identification of crystal structures is a crucial stage in the exploration of novel functional materials. This procedure is usually time-consuming and can be false-positive or false-negative. This necessitates a significant level of expert proficiency in the field of crystallography and, especially, requires deep experience in perovskite-related structures of hybrid perovskites. Our work is devoted to the machine learning classification of structure types of hybrid lead halides based on available X-ray diffraction data. Here, we proposed a simple approach for quickly identifying the dimensionality of inorganic substructures, types of connections of lead halide polyhedra and structure types using common powder XRD data and a ML-decision tree classification model. The average accuracy of our ML algorithm in predicting the dimensionality of inorganic substructures, the type of connection of lead halide and inorganic substructure topology based on theoretically calculated XRD patterns among 14 most common structure types reached 0.76 ± 0.07, 0.827 ± 0.028 and 0.71 ± 0.05, respectively. To test the transferability of the developed ML model, we expanded our dataset to 30 structure types. The average accuracy of our ML algorithm in predicting the dimensionality of inorganic substructures, the type of connection of lead halide and inorganic substructure topology based on theoretically calculated XRD patterns among 30 structure types reached 0.820 ± 0.022, 0.74 ± 0.05 and 0.633 ± 0.018, respectively. The validation of our decision tree classification ML model on experimental XRD data shows accuracies of 1.0 and 0.82 for dimension and structure type prediction. Thus, our approach can significantly simplify and accelerate the interpretation of highly complicated XRD data for hybrid lead halides.

Differences in Characteristics of Peripartum Patients Who Did and Did Not Require an Upgrade to the Intensive Care Unit: A Propensity Score Matching Study.

Background and Objectives: This study sought to identify predictors for peripartum patients admitted to non-intensive care wards who later upgraded to the Intensive Care Unit (ICU). Materials and Methods: This was a retrospective observational study of patients admitted to the Maternal Fetal Ward between 01/2017 and 12/2022, who later upgraded to the ICU. Upgraded patients were 1:1 propensity score matched with those who remained on the Maternal Fetal Ward (control). The Classification And Regression Tree, a machine learning algorithm, was used to identify significant predictors of ICU upgrade. Multivariable ordinal regression analysis was used to assess the time interval to upgrade. Results: From 1855 peripartum patients, we analyzed 37 control and 34 upgrade patients. Mean maternal age (±Standard Deviation) and gestational age for the group was 29.5 (±5.8) years and 31.5 (±7.5) weeks, respectively. The Median Sequential Organ Failure Assessment Score [Interquartile] at ward admission for the controls was 0 [0-1] versus 2 [0-3.3, p = 0.001] for upgrade patients. The Sequential Organ Failure Assessment score at Maternal Fetal Ward admission was most predictive, followed by the Acute Physiology and Chronic Health Evaluation II (APACHE II) score, and lactate dehydrogenase levels. The APACHE II score was also associated with ICU upgrade within 12 h of hospital admission (OR 1.4, 95% CI 1.08-1.91, p = 0.01). Conclusions: Compared to control patients, peripartum patients upgraded to the ICU are associated with higher physiologic scores at Maternal Fetal Ward admission. Until further studies are performed to confirm our observation, clinicians should pay attention to these physiologic scores, since they may be associated with higher-risk patients.