RESUMO
This paper describes a method Pprint2, which is an improved version of Pprint developed for predicting RNA-interacting residues in a protein. Training and independent/validation datasets used in this study comprises of 545 and 161 non-redundant RNA-binding proteins, respectively. All models were trained on training dataset and evaluated on the validation dataset. The preliminary analysis reveals that positively charged amino acids such as H, R and K, are more prominent in the RNA-interacting residues. Initially, machine learning based models have been developed using binary profile and obtain maximum area under curve (AUC) 0.68 on validation dataset. The performance of this model improved significantly from AUC 0.68 to 0.76, when evolutionary profile is used instead of binary profile. The performance of our evolutionary profile-based model improved further from AUC 0.76 to 0.82, when convolutional neural network has been used for developing model. Our final model based on convolutional neural network using evolutionary information achieved AUC 0.82 with Matthews correlation coefficient of 0.49 on the validation dataset. Our best model outperforms existing methods when evaluated on the independent/validation dataset. A user-friendly standalone software and web-based server named 'Pprint2' has been developed for predicting RNA-interacting residues (https://webs.iiitd.edu.in/raghava/pprint2 and https://github.com/raghavagps/pprint2).
Assuntos
Aminoácidos , RNA , Sítios de Ligação , RNA/metabolismo , Software , Proteínas de Ligação a RNA/metabolismoRESUMO
Peptide hormones serve as genome-encoded signal transduction molecules that play essential roles in multicellular organisms, and their dysregulation can lead to various health problems. In this study, we propose a method for predicting hormonal peptides with high accuracy. The dataset used for training, testing, and evaluating our models consisted of 1174 hormonal and 1174 non-hormonal peptide sequences. Initially, we developed similarity-based methods utilizing BLAST and MERCI software. Although these similarity-based methods provided a high probability of correct prediction, they had limitations, such as no hits or prediction of limited sequences. To overcome these limitations, we further developed machine and deep learning-based models. Our logistic regression-based model achieved a maximum AUROC of 0.93 with an accuracy of 86% on an independent/validation dataset. To harness the power of similarity-based and machine learning-based models, we developed an ensemble method that achieved an AUROC of 0.96 with an accuracy of 89.79% and a Matthews correlation coefficient (MCC) of 0.8 on the validation set. To facilitate researchers in predicting and designing hormone peptides, we developed a web-based server called HOPPred. This server offers a unique feature that allows the identification of hormone-associated motifs within hormone peptides. The server can be accessed at: https://webs.iiitd.edu.in/raghava/hoppred/.
RESUMO
Artificial intelligence (AI) has rapidly advanced in the past years, particularly in medicine for improved diagnostics. In clinical cytogenetics, AI is becoming crucial for analyzing chromosomal abnormalities and improving precision. However, existing software lack learning capabilities from experienced users. AI integration extends to genomic data analysis, personalized medicine and research, but ethical concerns arise. In this article, we discuss the challenges of the full automation in cytogenetic test interpretation and focus on its importance and benefits.
RESUMO
OBJECTIVE: Accurate prediction of survival prognosis is helpful to guide clinical decision-making. The aim of this study was to develop a model using machine learning techniques to predict the occurrence of composite thromboembolic events (CTEs) in elderly patients with atrial fibrillation(AF). These events encompass newly diagnosed cerebral ischemia events, cardiovascular events, pulmonary embolism, and lower extremity arterial embolism. METHODS: This retrospective study included 6,079 elderly hospitalized patients (≥ 75 years old) with AF admitted to the People's Liberation Army General Hospital in China from January 2010 to June 2022. Random forest imputation was used for handling missing data. In the descriptive statistics section, patients were divided into two groups based on the occurrence of CTEs, and differences between the two groups were analyzed using chi-square tests for categorical variables and rank-sum tests for continuous variables. In the machine learning section, the patients were randomly divided into a training dataset (n = 4,225) and a validation dataset (n = 1,824) in a 7:3 ratio. Four machine learning models (logistic regression, decision tree, random forest, XGBoost) were trained on the training dataset and validated on the validation dataset. RESULTS: The incidence of composite thromboembolic events was 19.53%. The Least Absolute Shrinkage and Selection Operator (LASSO) method, using 5-fold cross-validation, was applied to the training dataset and identified a total of 18 features that exhibited a significant association with the occurrence of CTEs. The random forest model outperformed other models in terms of area under the curve (ACC: 0.9144, SEN: 0.7725, SPE: 0.9489, AUC: 0.927, 95% CI: 0.9105-0.9443). The random forest model also showed good clinical validity based on the clinical decision curve. The Shapley Additive exPlanations (SHAP) showed that the top five features associated with the model were history of ischemic stroke, high triglyceride (TG), high total cholesterol (TC), high plasma D-dimer, age. CONCLUSIONS: This study proposes an accurate model to stratify patients with a high risk of CTEs. The random forest model has good performance. History of ischemic stroke, age, high TG, high TC and high plasma D-Dimer may be correlated with CTEs.
Assuntos
Fibrilação Atrial , Técnicas de Apoio para a Decisão , Aprendizado de Máquina , Valor Preditivo dos Testes , Tromboembolia , Humanos , Fibrilação Atrial/diagnóstico , Fibrilação Atrial/epidemiologia , Feminino , Masculino , Idoso , Estudos Retrospectivos , Medição de Risco , China/epidemiologia , Tromboembolia/epidemiologia , Tromboembolia/diagnóstico , Tromboembolia/etiologia , Fatores de Risco , Idoso de 80 Anos ou mais , Incidência , Prognóstico , Fatores Etários , Reprodutibilidade dos Testes , População do Leste AsiáticoRESUMO
Real-time flood forecasting is one of the most pivotal measures for flood management, and real-time error correction is a critical step to guarantee the reliability of forecasting results. However, it is still challenging to develop a robust error correction technique due to the limited cognitions of catchment mechanisms and multi-source errors across hydrological modeling. In this study, we proposed a hydrologic similarity-based correction (HSBC) framework, which hybridizes hydrological modeling and multiple machine learning algorithms to advance the error correction of real-time flood forecasting. This framework can quickly and accurately retrieve similar historical simulation errors for different types of real-time floods by integrating clustering, supervised classification, and similarity retrieval methods. The simulation errors "carried" by similar historical floods are extracted to update the real-time forecasting results. Here, combining the Xin'anjiang model-based forecasting platform with k-means, K-nearest neighbor (KNN), and embedding based subsequences matching (EBSM) method, we constructed the HSBC framework and applied it to China's Dufengkeng Basin. Three schemes, including "non-corrected" (scheme 1), "auto-regressive (AR) corrected" (scheme 2), and "HSBC corrected" (scheme 3), were built for comparison purpose. The results indicated the following: 1) the proposed framework can successfully retrieval similar simulation errors with a considerable retrieval accuracy (2.79) and time consumption (228.18 s). 2) four evaluation metrics indicated that the HSBC-based scheme 3 performed much better than the AR-based scheme 2 in terms of both the whole flood process and the peak discharge; 3) the proposed framework overcame the shortcoming of the AR model that have poor correction for the flood peaks and can provide more significant correction for the floods with bad forecasting performance. Overall, the HSBC framework demonstrates the advancement of benefiting the real-time error correction from hydrologic similarity theory and provides a novel methodological alternative for flood control and water management in wider areas.
Assuntos
Inundações , Aprendizado de Máquina , Reprodutibilidade dos Testes , Simulação por Computador , PrevisõesRESUMO
PURPOSE: An accurate prediction of survival prognosis is beneficial to guide clinical decision-making. This prospective study aimed to develop a model to predict one-year mortality among older patients with coronary artery disease (CAD) combined with impaired glucose tolerance (IGT) or diabetes mellitus (DM) using machine learning techniques. METHODS: A total of 451 patients with CAD combined with IGT and DM were finally enrolled, and those patients randomly split 70:30 into training cohort (n = 308) and validation cohort (n = 143). RESULTS: The one-year mortality was 26.83%. The least absolute shrinkage and selection operator (LASSO) method and ten-fold cross-validation identified that seven characteristics were significantly associated with one-year mortality with creatine, N-terminal pro-B-type natriuretic peptide (NT-proBNP), and chronic heart failure being risk factors and hemoglobin, high density lipoprotein cholesterol, albumin, and statins being protective factors. The gradient boosting machine model outperformed other models in terms of Brier score (0.114) and area under the curve (0.836). The gradient boosting machine model also showed favorable calibration and clinical usefulness based on calibration curve and clinical decision curve. The Shapley Additive exPlanations (SHAP) found that the top three features associated with one-year mortality were NT-proBNP, albumin, and statins. The web-based application could be available at https://starxueshu-online-application1-year-mortality-main-49cye8.streamlitapp.com/ . CONCLUSIONS: This study proposes an accurate model to stratify patients with a high risk of one-year mortality. The gradient boosting machine model demonstrates promising prediction performance. Some interventions to affect NT-proBNP and albumin levels, and statins, are beneficial to improve survival outcome among patients with CAD combined with IGT or DM.
Assuntos
Doença da Artéria Coronariana , Diabetes Mellitus , Intolerância à Glucose , Inibidores de Hidroximetilglutaril-CoA Redutases , Humanos , Albuminas , Doença da Artéria Coronariana/diagnóstico , Doença da Artéria Coronariana/mortalidade , Diabetes Mellitus/diagnóstico , Diabetes Mellitus/mortalidade , População do Leste Asiático , Intolerância à Glucose/diagnóstico , Inibidores de Hidroximetilglutaril-CoA Redutases/uso terapêutico , Aprendizado de Máquina , Estudos ProspectivosRESUMO
The objective of this study was to reveal the signs and symptoms for the classification of pediatric patients at risk of CKD using decision trees and extreme gradient boost models for predicting outcomes. A case-control study was carried out involving children with 376 chronic kidney disease (cases) and a control group of healthy children (n = 376). A family member responsible for the children answered a questionnaire with variables potentially associated with the disease. Decision tree and extreme gradient boost models were developed to test signs and symptoms for the classification of children. As a result, the decision tree model revealed 6 variables associated with CKD, whereas twelve variables that distinguish CKD from healthy children were found in the "XGBoost". The accuracy of the "XGBoost" model (ROC AUC = 0.939, 95%CI: 0.911 to 0.977) was the highest, while the decision tree model was a little lower (ROC AUC = 0.896, 95%CI: 0.850 to 0.942). The cross-validation of results showed that the accuracy of the evaluation database model was like that of the training. CONCLUSION: In conclusion, a dozen symptoms that are easy to be clinically verified emerged as risk indicators for chronic kidney disease. This information can contribute to increasing awareness of the diagnosis, mainly in primary care settings. Therefore, healthcare professionals can select patients for more detailed investigation, which will reduce the chance of wasting time and improve early disease detection. WHAT IS KNOWN: ⢠Late diagnosis of chronic kidney disease in children is common, increasing morbidity. ⢠Mass screening of the whole population is not cost-effective. WHAT IS NEW: ⢠With two machine-learning methods, this study revealed 12 symptoms to aid early CKD diagnosis. ⢠These symptoms are easily obtainable and can be useful mainly in primary care settings.
Assuntos
Insuficiência Renal Crônica , Humanos , Criança , Estudos de Casos e Controles , Insuficiência Renal Crônica/diagnóstico , Fatores de Risco , Diagnóstico Precoce , Aprendizado de MáquinaRESUMO
Web surveys have replaced Face-to-Face and computer assisted telephone interviewing (CATI) as the main mode of data collection in most countries. This trend was reinforced as a consequence of COVID-19 pandemic-related restrictions. However, this mode still faces significant limitations in obtaining probability-based samples of the general population. For this reason, most web surveys rely on nonprobability survey designs. Whereas probability-based designs continue to be the gold standard in survey sampling, nonprobability web surveys may still prove useful in some situations. For instance, when small subpopulations are the group under study and probability sampling is unlikely to meet sample size requirements, complementing a small probability sample with a larger nonprobability one may improve the efficiency of the estimates. Nonprobability samples may also be designed as a mean for compensating for known biases in probability-based web survey samples by purposely targeting respondent profiles that tend to be underrepresented in these surveys. This is the case in the Survey on the impact of the COVID-19 pandemic in Spain (ESPACOV) that motivates this paper. In this paper, we propose a methodology for combining probability and nonprobability web-based survey samples with the help of machine-learning techniques. We then assess the efficiency of the resulting estimates by comparing them with other strategies that have been used before. Our simulation study and the application of the proposed estimation method to the second wave of the ESPACOV Survey allow us to conclude that this is the best option for reducing the biases observed in our data.
Assuntos
COVID-19 , Humanos , COVID-19/epidemiologia , Espanha/epidemiologia , Pandemias , Inquéritos e Questionários , Probabilidade , Aprendizado de MáquinaRESUMO
Forensic science is a field that requires precise and reliable methods for the detection and analysis of evidence. One such method is Fourier Transform Infrared (FTIR) spectroscopy, which provides high sensitivity and selectivity in the detection of samples. In this study, the use of FTIR spectroscopy and statistical multivariate analysis to identify high explosive (HE) materials (C-4, TNT, and PETN) in the residues after high- and low-order explosions is demonstrated. Additionally, a detailed description of the data pre-treatment process and the use of various machine learning classification techniques to achieve successful identification is also provided. The best results were obtained with the hybrid LDA-PCA technique, which was implemented using the R environment, a code-driven open-source platform that promotes reproducibility and transparency.
RESUMO
Introduction: A no-show appointment occurs when a patient does not attend a previously booked appointment. This situation can cause other problems, such as discontinuity of patient treatments as well as a waste of both human and financial resources. One of the latest approaches to address this issue is predicting no-shows using machine learning techniques. This study aims to propose a predictive analytical approach for developing a patient no-show appointment model in Hospital Kuala Lumpur (HKL) using machine learning algorithms. Methods: This study uses outpatient data from the HKL's Patient Management System (SPP) throughout 2019. The final data set has 246,943 appointment records with 13 attributes used for both descriptive and predictive analyses. The predictive analysis was carried out using seven machine learning algorithms, namely, logistic regression (LR), decision tree (DT), k-near neighbours (k-NN), Naïve Bayes (NB), random forest (RF), gradient boosting (GB) and multilayer perceptron (MLP). Results: The descriptive analysis showed that the no-show rate was 28%, and attributes such as the month of the appointment and the gender of the patient seem to influence the possibility of a patient not showing up. Evaluation of the predictive model found that the GB model had the highest accuracy of 78%, F1 score of 0.76 and area under the curve (AUC) value of 0.65. Conclusion: The predictive model could be used to formulate intervention steps to reduce no-shows, improving patient care quality.
RESUMO
BACKGROUND: We evaluated different machine learning (ML) models for predicting soybean productivity up to 1 month in advance for the Matopiba agricultural frontier (States of Maranhão, Tocantins, Piauí, and Bahia). We collected meteorological data on the NASA-POWER platform and soybean yield on the SIDRA/IBGE base between 2008 and 2017. The ML models evaluated were random forest (RF), artificial neural networks, radial base support vector machines (SVM_RBF), linear model and polynomial regression. To assess the performance of the models, cross-validation was used, obtaining the value of precision by R2 , accuracy by root mean square error (RMSE), and trend by the mean error of the estimate (EME). RESULTS: The results showed that the RF algorithm achieves the highest precision and accuracy, with R2 of 0.81, RMSE of 176.93 kg ha-1 and trend (EME) of 1.99 kg ha-1 . On the other hand, the SVM_RBF algorithm showed the lowest performance, with R2 of 0.74, RMSE of 213.58 kg ha-1 and EME of -15.06 kg ha-1 . The average yield values predicted by the models were within the expected range for the region, which has a historical average value of 2.730 kg ha-1 . CONCLUSION: All models had acceptable precision, accuracy and trend indices, which makes it possible to use all algorithms to be applied in the prediction of soybean crop yield, observing the particularities of the region to be studied, in addition to being a useful tool for agricultural planning and decision making in soy-producing regions such as the Brazilian Cerrado. © 2021 Society of Chemical Industry.
Assuntos
Fabaceae , Glycine max , Algoritmos , Brasil , Aprendizado de Máquina , Máquina de Vetores de SuporteRESUMO
Lumpy skin disease virus (LSDV) causes an infectious disease in cattle. Due to its direct relationship with the survival of arthropod vectors, geospatial and climatic features play a vital role in the epidemiology of the disease. The objective of this study was to assess the ability of some machine learning algorithms to forecast the occurrence of LSDV infection based on meteorological and geological attributes. Initially, ExtraTreesClassifier algorithm was used to select the important predictive features in forecasting the disease occurrence in unseen (test) data among meteorological, animal population density, dominant land cover, and elevation attributes. Some machine learning techniques revealed high accuracy in predicting the LSDV occurrence in test data (up to 97%). In terms of area under curve (AUC) and F1 performance metric scores, the artificial neural network (ANN) algorithm outperformed other machine learning methods in predicting the occurrence of LSDV infection in unseen data with the corresponding values of 0.97 and 0.94, respectively. Using this algorithm, the model consisted of all predictive features and the one which only included meteorological attributes as important features showed similar predictive performance. According to the findings of this research, ANN can be used to forecast the occurrence of LSDV infection with high precision using geospatial and meteorological parameters. Applying the forecasting power of these methods could be a great help in conducting screening and awareness programs, as well as taking preventive measures like vaccination in areas where the occurrence of LSDV infection is a high risk.
Assuntos
Doenças dos Bovinos , Doença Nodular Cutânea , Vírus da Doença Nodular Cutânea , Animais , Bovinos , Doenças dos Bovinos/epidemiologia , Doença Nodular Cutânea/diagnóstico , Doença Nodular Cutânea/epidemiologia , Aprendizado de Máquina , Vacinação/veterináriaRESUMO
The present study concerns the modeling of the thermal behavior of a porous longitudinal fin under fully wetted conditions with linear, quadratic, and exponential thermal conductivities surrounded by environments that are convective, conductive, and radiative. Porous fins are widely used in various engineering and everyday life applications. The Darcy model was used to formulate the governing non-linear singular differential equation for the heat transfer phenomenon in the fin. The universal approximation power of multilayer perceptron artificial neural networks (ANN) was applied to establish a model of approximate solutions for the singular non-linear boundary value problem. The optimization strategy of a sports-inspired meta-heuristic paradigm, the Tiki-Taka algorithm (TTA) with sequential quadratic programming (SQP), was utilized to determine the thermal performance and the effective use of fins for diverse values of physical parameters, such as parameter for the moist porous medium, dimensionless ambient temperature, radiation coefficient, power index, in-homogeneity index, convection coefficient, and dimensionless temperature. The results of the designed ANN-TTA-SQP algorithm were validated by comparison with state-of-the-art techniques, including the whale optimization algorithm (WOA), cuckoo search algorithm (CSA), grey wolf optimization (GWO) algorithm, particle swarm optimization (PSO) algorithm, and machine learning algorithms. The percentage of absolute errors and the mean square error in the solutions of the proposed technique were found to lie between 10-4 to 10-5 and 10-8 to 10-10, respectively. A comprehensive study of graphs, statistics of the solutions, and errors demonstrated that the proposed scheme's results were accurate, stable, and reliable. It was concluded that the pace at which heat is transferred from the surface of the fin to the surrounding environment increases in proportion to the degree to which the wet porosity parameter is increased. At the same time, inverse behavior was observed for increase in the power index. The results obtained may support the structural design of thermally effective cooling methods for various electronic consumer devices.
RESUMO
It is difficult to manage massive amounts of data in an overlying environment with a single server. Therefore, it is necessary to comprehend the security provisions for erratic data in a dynamic environment. The authors are concerned about the security risk of vulnerable data in a Mobile Edge based distributive environment. As a result, edge computing appears to be an excellent perspective in which training can be done in an Edge-based environment. The combination of Edge computing and consensus approach of Blockchain in conjunction with machine learning techniques can further improve data security, mitigate the possibility of exposed data, and it reduces the risk of a data breach. As a result, the concept of federated learning provides a path for training the shared data. A dataset was collected that contained several vulnerable, exposed, recovered, and secured data and data security was precepted under the surveillance of two-factor authentication. This paper discusses the evolution of data and security flaws and their corresponding solutions in smart edge computing devices. The proposed model incorporates data security using consensus approach of Blockchain and machine learning techniques that include several classifiers and optimization techniques. Further, the authors applied the proposed algorithms in an edge computing environment by distributing several batches of data to different clients. As a result, the client privacy was maintained by using Blockchain servers. Furthermore, the authors segregated the client data into batches that were trained using the federated learning technique. The results obtained in this paper demonstrate the implementation of a Blockchain-based training model in an edge-based computing environment.
RESUMO
PURPOSE: To assess the prevalence of sleep disturbances among university students and investigate potential correlated factors and their relative importance in quantifying sleep quality using advanced machine learning techniques. METHODS: A total of 1600 university students participated in this cross-sectional study. Sociodemographic information was collected, and the Pittsburgh Sleep Quality Index (PSQI) was administered to assess sleep quality among university students. Study variables were evaluated using logistic regression and advanced machine learning techniques. Study variables that were significant in the logistic regression and had high mean decrease in model accuracy in the machine learning technique were considered important predictors of sleep quality. RESULTS: The mean (SD) age of the sample was 26.65 (6.38) and 57% of them were females. The prevalence of poor sleep quality in our sample was 70%. The most accurate and balanced predictive model was the random forest model with a 74% accuracy and a 95% specificity. Age and number of cups of tea per day were identified as protective factors for a better sleep quality, while electronics usage hours, headache, other systematic diseases, and neck pain were found risk factors for poor sleep quality. CONCLUSIONS: Six predictors of poor sleep quality were identified in university students in which 2 of them were protective and 3 were risk factors. The results of this study can be used to promote health and well-being in university students, improve their academic performance, and assist in developing appropriate interventions.
Assuntos
Qualidade do Sono , Transtornos do Sono-Vigília/epidemiologia , Estudantes/estatística & dados numéricos , Adulto , Estudos Transversais , Feminino , Humanos , Jordânia/epidemiologia , Aprendizado de Máquina , Masculino , Prevalência , Universidades , Adulto JovemRESUMO
This article provides a systematic review of studies on recognising bathroom activities in older adults using wearable sensors. Bathroom activities are an important part of Activities of Daily Living (ADL). The performance on ADL activities is used to predict the ability of older adults to live independently. This paper aims to provide an overview of the studied bathroom activities, the wearable sensors used, different applied methodologies and the tested activity recognition techniques. Six databases were screened up to March 2020, based on four categories of keywords: older adults, activity recognition, bathroom activities and wearable sensors. In total, 4262 unique papers were found, of which only seven met the inclusion criteria. This small number shows that few studies have been conducted in this field. Therefore, in addition, this critical review resulted in several recommendations for future studies. In particular, we recommend to (1) study complex bathroom activities, including multiple movements; (2) recruit participants, especially the target population; (3) conduct both lab and real-life experiments; (4) investigate the optimal number and positions of wearable sensors; (5) choose a suitable annotation method; (6) investigate deep learning models; (7) evaluate the generality of classifiers; and (8) investigate both detection and quality performance of an activity.
Assuntos
Atividades Cotidianas , Dispositivos Eletrônicos Vestíveis , Idoso , Humanos , Movimento , Reconhecimento Psicológico , BanheirosRESUMO
Until now, clinicians are not able to evaluate the Psychogenic Non-Epileptic Seizures (PNES) from the rest-electroencephalography (EEG) readout. No EEG marker can help differentiate PNES cases from healthy subjects. In this paper, we have investigated the power spectrum density (PSD), in resting-state EEGs, to evaluate the abnormalities in PNES affected brains. Additionally, we have used functional connectivity tools, such as phase lag index (PLI), and graph-derived metrics to better observe the integration of distributed information of regular and synchronized multi-scale communication within and across inter-regional brain areas. We proved the utility of our method after enrolling a cohort study of 20 age- and gender-matched PNES and 19 healthy control (HC) subjects. In this work, three classification models, namely support vector machine (SVM), linear discriminant analysis (LDA), and Multilayer perceptron (MLP), have been employed to model the relationship between the functional connectivity features (rest-HC versus rest-PNES). The best performance for the discrimination of participants was obtained using the MLP classifier, reporting a precision of 85.73%, a recall of 86.57%, an F1-score of 78.98%, and, finally, an accuracy of 91.02%. In conclusion, our results hypothesized two main aspects. The first is an intrinsic organization of functional brain networks that reflects a dysfunctional level of integration across brain regions, which can provide new insights into the pathophysiological mechanisms of PNES. The second is that functional connectivity features and MLP could be a promising method to classify rest-EEG data of PNES form healthy controls subjects.
Assuntos
Eletroencefalografia , Convulsões , Estudos de Coortes , Humanos , Aprendizado de Máquina , DescansoRESUMO
BACKGROUND: Interest in models for calculating the risk of death in traumatic patients admitted to ICUs remains high. These models use variables derived from the deviation of physiological parameters and/or the severity of anatomical lesions with respect to the affected body areas. Our objective is to create different predictive models of the mortality of critically traumatic patients using machine learning techniques. METHODS: We used 9625 records from the RETRAUCI database (National Trauma Registry of 52 Spanish ICUs in the period of 2015-2019). Hospital mortality was 12.6%. Data on demographic variables, affected anatomical areas and physiological repercussions were used. The Weka Platform was used, along with a ten-fold cross-validation for the construction of nine supervised algorithms: logistic regression binary (LR), neural network (NN), sequential minimal optimization (SMO), classification rules (JRip), classification trees (CT), Bayesian networks (BN), adaptive boosting (ADABOOST), bootstrap aggregating (BAGGING) and random forest (RFOREST). The performance of the models was evaluated by accuracy, specificity, precision, recall, F-measure, and AUC. RESULTS: In all algorithms, the most important factors are those associated with traumatic brain injury (TBI) and organic failures. The LR finds thorax and limb injuries as independent protective factors of mortality. The CT generates 24 decision rules and uses those related to TBI as the first variables (range 2.0-81.6%). The JRip detects the eight rules with the highest risk of mortality (65.0-94.1%). The NN model uses a hidden layer of ten nodes, which requires 200 weights for its interpretation. The BN find the relationships between the different factors that identify different patient profiles. Models with the ensemble methodology (ADABOOST, BAGGING and RandomForest) do not have greater performance. All models obtain high values ââin accuracy, specificity, and AUC, but obtain lower values ââin recall. The greatest precision is achieved by the SMO model, and the BN obtains the best recall, F-measure, and AUC. CONCLUSION: Machine learning techniques are useful for creating mortality classification models in critically traumatic patients. With clinical interpretation, the algorithms establish different patient profiles according to the relationship between the variables used, determine groups of patients with different evolutions, and alert clinicians to the presence of rules that indicate the greatest severity.
Assuntos
Aprendizado de Máquina , Redes Neurais de Computação , Algoritmos , Teorema de Bayes , Humanos , Modelos LogísticosRESUMO
BACKGROUND: Doubly robust estimation produces an unbiased estimator for the average treatment effect unless both propensity score (PS) and outcome models are incorrectly specified. Studies have shown that the doubly robust estimator is subject to more bias than the standard weighting estimator when both PS and outcome models are incorrectly specified. METHOD: We evaluated whether various machine learning methods can be used for estimating conditional means of the potential outcomes to enhance the robustness of the doubly robust estimator to various degrees of model misspecification in terms of reducing bias and standard error. We considered four types of methods to predict the outcomes: least squares, tree-based methods, generalized additive models and shrinkage methods. We also considered an ensemble method called the Super Learner (SL), which is a linear combination of multiple learners. We conducted simulations considering different scenarios by the complexity of PS and outcome-generating models and some ranges of treatment prevalence. RESULTS: The shrinkage methods performed well with robust doubly robust estimates in term of bias and mean squared error across the scenarios when the models became rich by including all 2-way interactions of the covariates. The SL performed similarly to the best method in each scenario. CONCLUSIONS: Our findings indicate that machine learning methods such as the SL or the shrinkage methods using interaction models should be used for more accurate doubly robust estimators.
Assuntos
Causalidade , Interpretação Estatística de Dados , Aprendizado de Máquina , Modelos Estatísticos , Farmacoepidemiologia/métodos , Viés , Simulação por Computador , Humanos , Pontuação de PropensãoRESUMO
Since 2001, cardiovascular disease (CVD) has had the second-highest mortality rate, about 15,700 people per year, in Taiwan. It has thus imposed a substantial burden on medical resources. This study was triggered by the following three factors. First, the CVD problem reflects an urgent issue. A high priority has been placed on long-term therapy and prevention to reduce the wastage of medical resources, particularly in developed countries. Second, from the perspective of preventive medicine, popular data-mining methods have been well learned and studied, with excellent performance in medical fields. Thus, identification of the risk factors of CVD using these popular techniques is a prime concern. Third, the Framingham risk score is a core indicator that can be used to establish an effective prediction model to accurately diagnose CVD. Thus, this study proposes an integrated predictive model to organize five notable classifiers: the rough set (RS), decision tree (DT), random forest (RF), multilayer perceptron (MLP), and support vector machine (SVM), with a novel use of the Framingham risk score for attribute selection (i.e., F-attributes first identified in this study) to determine the key features for identifying CVD. Verification experiments were conducted with three evaluation criteria-accuracy, sensitivity, and specificity-based on 1190 instances of a CVD dataset available from a Taiwan teaching hospital and 2019 examples from a public Framingham dataset. Given the empirical results, the SVM showed the best performance in terms of accuracy (99.67%), sensitivity (99.93%), and specificity (99.71%) in all F-attributes in the CVD dataset compared to the other listed classifiers. The RS showed the highest performance in terms of accuracy (85.11%), sensitivity (86.06%), and specificity (85.19%) in most of the F-attributes in the Framingham dataset. The above study results support novel evidence that no classifier or model is suitable for all practical datasets of medical applications. Thus, identifying an appropriate classifier to address specific medical data is important. Significantly, this study is novel in its calculation and identification of the use of key Framingham risk attributes integrated with the DT technique to produce entropy-based decision rules of knowledge sets, which has not been undertaken in previous research. This study conclusively yielded meaningful entropy-based knowledgeable rules in tree structures and contributed to the differentiation of classifiers from the two datasets with three useful research findings and three helpful management implications for subsequent medical research. In particular, these rules provide reasonable solutions to simplify processes of preventive medicine by standardizing the formats and codes used in medical data to address CVD problems. The specificity of these rules is thus significant compared to those of past research.