RESUMO

BACKGROUND: No-show to medical appointments has significant adverse effects on healthcare systems and their clients. Using machine learning to predict no-shows allows managers to implement strategies such as overbooking and reminders targeting patients most likely to miss appointments, optimizing the use of resources. METHODS: In this study, we proposed a detailed analytical framework for predicting no-shows while addressing imbalanced datasets. The framework includes a novel use of z-fold cross-validation performed twice during the modeling process to improve model robustness and generalization. We also introduce Symbolic Regression (SR) as a classification algorithm and Instance Hardness Threshold (IHT) as a resampling technique and compared their performance with that of other classification algorithms, such as K-Nearest Neighbors (KNN) and Support Vector Machine (SVM), and resampling techniques, such as Random under Sampling (RUS), Synthetic Minority Oversampling Technique (SMOTE) and NearMiss-1. We validated the framework using two attendance datasets from Brazilian hospitals with no-show rates of 6.65% and 19.03%. RESULTS: From the academic perspective, our study is the first to propose using SR and IHT to predict the no-show of patients. Our findings indicate that SR and IHT presented superior performances compared to other techniques, particularly IHT, which excelled when combined with all classification algorithms and led to low variability in performance metrics results. Our results also outperformed sensitivity outcomes reported in the literature, with values above 0.94 for both datasets. CONCLUSION: This is the first study to use SR and IHT methods to predict patient no-shows and the first to propose performing z-fold cross-validation twice. Our study highlights the importance of avoiding relying on few validation runs for imbalanced datasets as it may lead to biased results and inadequate analysis of the generalization and stability of the models obtained during the training stage.

Assuntos

RESUMO

BACKGROUND: Machine learning investigates how computers can automatically learn. The present study aimed to predict dietary patterns and compare algorithm performance in making predictions of dietary patterns. METHODS: We analysed the data of public employees (n = 12,667) participating in the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). The K-means clustering algorithm and six other classifiers (support vector machines, naïve Bayes, K-nearest neighbours, decision tree, random forest and xgboost) were used to predict the dietary patterns. RESULTS: K-means clustering identified two dietary patterns. Cluster 1, labelled the Western pattern, was characterised by a higher energy intake and consumption of refined cereals, beans and other legumes, tubers, pasta, processed and red meats, high-fat milk and dairy products, and sugary beverages; Cluster 2, labelled the Prudent pattern, was characterised by higher intakes of fruit, vegetables, whole cereals, white meats, and milk and reduced-fat milk derivatives. The most important predictors were age, sex, per capita income, education level and physical activity. The accuracy of the models varied from moderate to good (69%-72%). CONCLUSIONS: The performance of the algorithms in dietary pattern prediction was similar, and the models presented may provide support in screener tasks and guide health professionals in the analysis of dietary data.

Assuntos

RESUMO

In wells that operate by electrical submersible pump (ESP), the use of automation tools becomes essential in the interpretation of data. However, the fact that the wells work with automated systems does not guarantee the early diagnosis of operating conditions. The analysis of amperimetric charts is one of the ways to identify fail conditions. Generally, the analysis of these histographics is performed by operators who are often overloaded, generating a decrease in the efficiency of observing the well operating conditions. Currently, technologies based on machine learning (ML) algorithms create solutions to early diagnose abnormalities in the well's operation. Thus, this work aims to provide a proposal for detecting the operating conditions of the ESP pump from electrical current data from 24 wells in the city of Mossoró, Rio Grande do Norte state, Brazil. The algorithms used were Decision Tree, Support Vector Machine, K-Nearest Neighbor and Neural Network. The algorithms were tested without and with hyperparameter tuning based on a training dataset. The results confirm that the application of the ML algorithm is feasible for classifying the operating conditions of the ESP pump, as all had an accuracy greater than 87%, with the best result being the application of the SVM model, which reached an accuracy of 93%.

Assuntos

RESUMO

Diagnosis of Parkinson's disease (PD) remains a challenge in clinical practice, mostly due to lack of peripheral blood markers. Transcriptomic analysis of blood samples has emerged as a potential means to identify biomarkers and gene signatures of PD. In this context, classification algorithms can assist in detecting data patterns such as phenotypes and transcriptional signatures with potential diagnostic application. In this study, we performed gene expression meta-analysis of blood transcriptome from PD and control patients in order to identify a gene-set capable of predicting PD using classification algorithms. We examined microarray data from public repositories and, after systematic review, 4 independent cohorts (GSE6613, GSE57475, GSE72267 and GSE99039) comprising 711 samples (388 idiopathic PD and 323 healthy individuals) were selected. Initially, analysis of differentially expressed genes resulted in minimal overlap among datasets. To circumvent this, we carried out meta-analysis of 17,712 genes across datasets, and calculated weighted mean Hedges' g effect sizes. From the top-100- positive and negative gene effect sizes, algorithms of collinearity recognition and recursive feature elimination were used to generate a 59-gene signature of idiopathic PD. This signature was evaluated by 9 classification algorithms and 4 sample size-adjusted training groups to create 36 models. Of these, 33 showed accuracy higher than the non-information rate, and 2 models built on Support Vector Machine Regression bestowed best accuracy to predict PD and healthy control samples. In summary, the gene meta-analysis followed by machine learning methodology employed herein identified a gene-set capable of accurately predicting idiopathic PD in blood samples.

Assuntos

RESUMO

CONTEXT: Determining which patients are ready for discharge from an Intensive Care Unit (ICU) presents a huge challenge, as ICU readmissions are associated with several negative outcomes such as increased mortality, length of stay, and cost compared to those patients who are not readmitted during their hospital stay. For these reasons, enhancing risk stratification in order to identify patients at high risk of clinical deterioration might benefit and improve the outcomes of critically ill hospitalized patients. Existing work on predicting ICU readmissions relies on information available at the time of discharge, however, in order to be more useful and to prevent complications, predictions need to be made earlier. GOALS: In this work, we investigate the hypothesis that the basal characteristics and information collected at the time of the patient's admission can enable accurate predictions of ICU readmission. MATERIALS AND METHODS: We analyzed an anonymized dataset of 11,805 adult patients from three ICUs in a Brazilian university hospital. After excluding 1879 patients who died during their first ICU admission, our final dataset contained 9,926 patients. Of these, 658 patients (6.6%) had been readmitted to the ICU. The original dataset had 185 attributes, including demographics, length of stay prior to ICU admission, comorbidities, severity indexes, interventions, organ support care during ICU stay and laboratory results. The problem of predicting ICU readmissions was modeled as a binary classification task. We tested eight classification algorithms (including Bayesian algorithms, decision trees, rule-based, and ensemble methods) over different sets of attributes and evaluated their results based on six metrics. RESULTS: Predictions made solely based on the attributes collected at the admission are highly accurate. Their quality in terms of prediction is no different from predictions made using the complete set of attributes for our dataset and for a subset of attributes selected by a feature selection method. Furthermore, our AUROC score of 0.91 (95% CI [0.89,0.92]) is higher than existing results published in the literature for other datasets. DISCUSSION AND CONCLUSION: The results confirm our hypothesis. Our findings suggest that early markers can be used to anticipate patients at high risk of clinical deterioration after ICU discharge.

Assuntos

RESUMO

Classification of electromyographic signals has a wide range of applications, from clinical diagnosis of different muscular diseases to biomedical engineering, where their use as input for the control of prosthetic devices has become a hot topic of research. The challenge of classifying these signals relies on the accuracy of the proposed algorithm and the possibility of its implementation in hardware. This paper considers the problem of electromyography signal classification, solved with the proposed signal processing and feature extraction stages, with the focus lying on the signal model and time domain characteristics for better classification accuracy. The proposal considers a simple preprocessing technique that produces signals suitable for feature extraction and the Burg reflection coefficients to form learning and classification patterns. These coefficients yield a competitive classification rate compared to the time domain features used. Sometimes, the feature extraction from electromyographic signals has shown that the procedure can omit less useful traits for machine learning models. Using feature selection algorithms provides a higher classification performance with as few traits as possible. The algorithms achieved a high classification rate up to 100% with low pattern dimensionality, with other kinds of uncorrelated attributes for hand movement identification.

RESUMO

This review presents a retrospective of the studies carried out in the last 10 years (2006-2016) using spectroscopic methods as a research tool in the field of virology. Spectroscopic analyses are sensitive to variations in the biochemical composition of the sample, are non-destructive, fast and require the least sample preparation, making spectroscopic techniques tools of great interest in biological studies. Herein important chemometric algorithms that have been used in virological studies are also evidenced as a good alternative for analyzing the spectra, discrimination and classification of samples. Techniques that have not yet been used in the field of virology are also suggested. This methodology emerges as a new and promising field of research, and may be used in the near future as diagnosis tools for detecting diseases caused by viruses.