RESUMO

INTRODUCTION AND OBJECTIVES: The increasing incidence of hepatocellular carcinoma (HCC) in China is an urgent issue, necessitating early diagnosis and treatment. This study aimed to develop personalized predictive models by combining machine learning (ML) technology with a demographic, medical history, and noninvasive biomarker data. These models can enhance the decision-making capabilities of physicians for HCC in hepatitis B virus (HBV)-related cirrhosis patients with low serum alpha-fetoprotein (AFP) levels. PATIENTS AND METHODS: A total of 6,980 patients treated between January 2012 and December 2018 were included. Pre-treatment laboratory tests and clinical data were obtained. The significant risk factors for HCC were identified, and the relative risk of each variable affecting its diagnosis was calculated using ML and univariate regression analysis. The data set was then randomly partitioned into validation (20 %) and training sets (80 %) to develop the ML models. RESULTS: Twelve independent risk factors for HCC were identified using Gaussian naïve Bayes, extreme gradient boosting (XGBoost), random forest, and least absolute shrinkage and selection operation regression models. Multivariate analysis revealed that male sex, age >60 years, alkaline phosphate >150 U/L, AFP >25 ng/mL, carcinoembryonic antigen >5 ng/mL, and fibrinogen >4 g/L were the risk factors, whereas hypertension, calcium <2.25 mmol/L, potassium ≤3.5 mmol/L, direct bilirubin >6.8 µmol/L, hemoglobin <110 g/L, and glutamic-pyruvic transaminase >40 U/L were the protective factors in HCC patients. Based on these factors, a nomogram was constructed, showing an area under the curve (AUC) of 0.746 (sensitivity = 0.710, specificity=0.646), which was significantly higher than AFP AUC of 0.658 (sensitivity = 0.462, specificity=0.766). Compared with several ML algorithms, the XGBoost model had an AUC of 0.832 (sensitivity = 0.745, specificity=0.766) and an independent validation AUC of 0.829 (sensitivity = 0.766, specificity = 0.737), making it the top-performing model in both sets. The external validation results have proven the accuracy of the XGBoost model. CONCLUSIONS: The proposed XGBoost demonstrated a promising ability for individualized prediction of HCC in HBV-related cirrhosis patients with low-level AFP.

RESUMO

BACKGROUND: Colorectal cancer has a high incidence and mortality rate due to a low rate of early diagnosis. Therefore, efficient diagnostic methods are urgently needed. PURPOSE: This study assesses the diagnostic effectiveness of Carbohydrate Antigen 19-9 (CA19-9), Carcinoembryonic Antigen (CEA), Alpha-fetoprotein (AFP), and Cancer Antigen 125 (CA125) serum tumor markers for colorectal cancer (CRC) and investigates a machine learning-based diagnostic model incorporating these markers with blood biochemical indices for improved CRC detection. METHOD: Between January 2019 and December 2021, data from 800 CRC patients and 697 controls were collected; 52 patients and 63 controls attending the same hospital in 2022 were collected as an external validation set. Markers' effectiveness was analyzed individually and collectively, using metrics like ROC curve AUC and F1 score. Variables chosen through backward regression, including demographics and blood tests, were tested on six machine learning models using these metrics. RESULT: In the case group, the levels of CEA, CA199, and CA125 were found to be higher than those in the control group. Combining these with a fourth serum marker significantly improved predictive efficacy over using any single marker alone, achieving an Area Under the Curve (AUC) value of 0.801. Using stepwise regression (backward), 17 variables were meticulously selected for evaluation in six machine learning models. Among these models, the Gradient Boosting Machine (GBM) emerged as the top performer in the training set, test set, and external validation set, boasting an AUC value of over 0.9, indicating its superior predictive power. CONCLUSION: Machine learning models integrating tumor markers and blood indices offer superior CRC diagnostic accuracy, potentially enhancing clinical practice.

RESUMO

Image segmentation is a computer vision technique that involves dividing an image into distinct and meaningful regions or segments. The objective was to partition the image into areas that share similar visual characteristics. Noise and undesirable artifacts introduce inconsistencies and irregularities in image data. These inconsistencies severely affect the ability of most segmentation algorithms to distinguish between true image features, leading to less reliable and lower-quality results. Cellular Automata (CA) is a computational concept that consists of a grid of cells, each of which can be in a finite number of states. These cells evolve over discrete time steps based on a set of predefined rules that dictate how a cell's state changes according to its own state and the states of its neighboring cells. In this paper, a new segmentation approach based on the CA model was introduced. The proposed approach consisted of three phases. In the initial two phases of the process, the primary objective was to eliminate noise and undesirable artifacts that can interfere with the identification of regions exhibiting similar visual characteristics. To achieve this, a set of rules is designed to modify the state value of each cell or pixel based on the states of its neighboring elements. In the third phase, each element is assigned a state that is chosen from a set of predefined states. These states directly represent the final segmentation values for the corresponding elements. The proposed method was evaluated using different images, considering important quality indices. The experimental results indicated that the proposed approach produces better-segmented images in terms of quality and robustness.

RESUMO

Motivated by the implementation of a SARS-Cov-2 sewer surveillance system in Chile during the COVID-19 pandemic, we propose a set of mathematical and algorithmic tools that aim to identify the location of an outbreak under uncertainty in the network structure. Given an upper bound on the number of samples we can take on any given day, our framework allows us to detect an unknown infected node by adaptively sampling different network nodes on different days. Crucially, despite the uncertainty of the network, the method allows univocal detection of the infected node, albeit at an extra cost in time. This framework relies on a specific and well-chosen strategy that defines new nodes to test sequentially, with a heuristic that balances the granularity of the information obtained from the samples. We extensively tested our model in real and synthetic networks, showing that the uncertainty of the underlying graph only incurs a limited increase in the number of iterations, indicating that the methodology is applicable in practice.

Assuntos

RESUMO

The Ordered Weighted Averaging (OWA) operator is a multicriteria method that has conquered space among researchers in the composite indicators field. Typically, OWA operator weights are defined by the decision maker. This type of weighting is highly criticized, as decision-makers are susceptible to errors and bias in judgment. Some methods have been used to define OWA operator weights objectively. However, none of them is concerned about the quality of the composite indicator. This paper introduces a method that defines the weights of the OWA operator based on two quality parameters of the composite indicator: the ability to capture the concept of the multidimensional phenomenon and the informational loss. The method can be implemented in Microsoft Excel Solver and has a high degree of flexibility and applicability in problems of a multidimensional nature and a high degree of appropriation by researchers and practitioners in the area.•Defines weights that maximize the ability of the composite indicator to capture the concept of the multidimensional phenomenon.•Considers restrictions to limit the informational loss of the composite indicator or emphasize positive or negative aspects of the multidimensional phenomenon.•Offers flexibility in setting the objective and constraints of the optimization algorithm.

RESUMO

BACKGROUND: Global access to acute stroke treatment is variable worldwide, with notable gaps in low and middle-income countries (LMIC), especially in rural areas. Ensuring a standardized method for pinpointing the existing regional coverage and proposing potential sites for new stroke centers is essential to change this scenario. AIMS: To create and apply computational strategies (CSs) to determine optimal locations for new acute stroke centers (ASCs), with a pilot application in nine Latin American regions/countries. METHODS: Hospitals treating acute ischemic stroke (AIS) with intravenous thrombolysis (IVT) and meeting the minimum infrastructure requirements per structured protocols were categorized as ASCs. Hospitals with emergency departments, noncontrast computed tomography (NCCT) scanners, and 24/7 laboratories were identified as potential acute stroke centers (PASCs). Hospital geolocation data were collected and mapped using the OpenStreetMap data set. A 45-min drive radius was considered the ideal coverage area for each hospital based on the drive speeds from the OpenRouteService database. Population data, including demographic density, were obtained from the Kontur Population data sets. The proposed CS assessed the population covered by ASCs and proposed new ASCs or artificial points (APs) settled in densely populated areas to achieve a target population coverage (TPC) of 95%. RESULTS: The observed coverage in the region presented significant disparities, ranging from 0% in the Bahamas to 73.92% in Trinidad and Tobago. No country/region reached the 95% TPC using only its current ASCs or PASCs, leading to the proposal of APs. For example, in Rio Grande do Sul, Brazil, the introduction of 132 new centers was suggested. Furthermore, it was observed that most ASCs were in major urban hubs or university hospitals, leaving rural areas largely underserved. CONCLUSIONS: The MAPSTROKE project has the potential to provide a systematic approach to identify areas with limited access to stroke centers and propose solutions for increasing access to AIS treatment. DATA ACCESS STATEMENT: Data used for this publication are available from the authors upon reasonable request.

Assuntos

RESUMO

BACKGROUND: Structural variants (SVs) are genomic polymorphisms defined by their length (>50 bp). The usual types of SVs are deletions, insertions, translocations, inversions, and copy number variants. SV detection and genotyping is fundamental given the role of SVs in phenomena such as phenotypic variation and evolutionary events. Thus, methods to identify SVs using long-read sequencing data have been recently developed. FINDINGS: We present an accurate and efficient algorithm to predict germline SVs from long-read sequencing data. The algorithm starts collecting evidence (signatures) of SVs from read alignments. Then, signatures are clustered based on a Euclidean graph with coordinates calculated from lengths and genomic positions. Clustering is performed by the DBSCAN algorithm, which provides the advantage of delimiting clusters with high resolution. Clusters are transformed into SVs and a Bayesian model allows to precisely genotype SVs based on their supporting evidence. This algorithm is integrated into the single sample variants detector of the Next Generation Sequencing Experience Platform, which facilitates the integration with other functionalities for genomics analysis. We performed multiple benchmark experiments, including simulation and real data, representing different genome profiles, sequencing technologies (PacBio HiFi, ONT), and read depths. CONCLUSION: The results show that our approach outperformed state-of-the-art tools on germline SV calling and genotyping, especially at low depths, and in error-prone repetitive regions. We believe this work significantly contributes to the development of bioinformatic strategies to maximize the use of long-read sequencing technologies.

Assuntos

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

Accurate classification of electromyographic (EMG) signals is vital in biomedical applications. This study evaluates different architectures of recurrent neural networks for the classification of EMG signals associated with five movements of the right upper extremity. A Butterworth filter was implemented for signal preprocessing, followed by segmentation into 250 ms windows, with an overlap of 190 ms. The resulting dataset was divided into training, validation, and testing subsets. The Grey Wolf Optimization algorithm was applied to the gated recurrent unit (GRU), long short-term memory (LSTM) architectures, and bidirectional recurrent neural networks. In parallel, a performance comparison with support vector machines (SVMs) was performed. The results obtained in the first experimental phase revealed that all the RNN networks evaluated reached a 100% accuracy, standing above the 93% achieved by the SVM. Regarding classification speed, LSTM ranked as the fastest architecture, recording a time of 0.12 ms, followed by GRU with 0.134 ms. Bidirectional recurrent neural networks showed a response time of 0.2 ms, while SVM had the longest time at 2.7 ms. In the second experimental phase, a slight decrease in the accuracy of the RNN models was observed, standing at 98.46% for LSTM, 96.38% for GRU, and 97.63% for the bidirectional network. The findings of this study highlight the effectiveness and speed of recurrent neural networks in the EMG signal classification task.

RESUMO

This article proposes an evolutionary algorithm integrating Erdos-Rényi complex networks to regulate population crossovers, enhancing candidate solution refinement across generations. In this context, the population is conceptualized as a set of interrelated solutions, resembling a complex network. The algorithm enhances solutions by introducing new connections between them, thereby influencing population dynamics and optimizing the problem-solving process. The study conducts experiments comparing four instances of the traditional optimization problem known as the Traveling Salesman Problem (TSP). These experiments employ the traditional evolutionary algorithm, alternative algorithms utilizing different types of complex networks, and the proposed algorithm. The findings suggest that the approach guided by an Erdos-Rényi dynamic network surpasses the performance of the other algorithms. The proposed model exhibits improved convergence rates and shorter execution times. Thus, strategies based on complex networks reveal that network characteristics provide valuable information for solving optimization problems. Therefore, complex networks can regulate the decision-making process, similar to optimizing problems. This work emphasizes that the network structure is crucial in adding value to decision-making.