Machine learning using the extreme gradient boosting (XGBoost) algorithm predicts 5-day delta of SOFA score at ICU admission in COVID-19 patients
Ontology highlight
ABSTRACT: Background
Accurate risk stratification of critically ill patients with coronavirus disease 2019 (COVID-19) is essential for optimizing resource allocation, delivering targeted interventions, and maximizing patient survival probability. Machine learning (ML) techniques are attracting increased interest for the development of prediction models as they excel in the analysis of complex signals in data-rich environments such as critical care. Methods
We retrieved data on patients with COVID-19 admitted to an intensive care unit (ICU) between March and October 2020 from the RIsk Stratification in COVID-19 patients in the Intensive Care Unit (RISC-19-ICU) registry. We applied the Extreme Gradient Boosting (XGBoost) algorithm to the data to predict as a binary outcome the increase or decrease in patients’ Sequential Organ Failure Assessment (SOFA) score on day 5 after ICU admission. The model was iteratively cross-validated in different subsets of the study cohort. Results
The final study population consisted of 675 patients. The XGBoost model correctly predicted a decrease in SOFA score in 320/385 (83%) critically ill COVID-19 patients, and an increase in the score in 210/290 (72%) patients. The area under the mean receiver operating characteristic curve for XGBoost was significantly higher than that for the logistic regression model (0.86 vs. 0.69, P < 0.01 [paired t-test with 95% confidence interval]). Conclusions
The XGBoost model predicted the change in SOFA score in critically ill COVID-19 patients admitted to the ICU and can guide clinical decision support systems (CDSSs) aimed at optimizing available resources.
SUBMITTER: Montomoli J
PROVIDER: S-EPMC8531027 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The exploration of DNA-binding proteins (DBPs) is an important aspect of studying biological life activities. Research on life activities requires the support of scientific research results on DBPs. The decline in many life activities is closely related to DBPs. Generally, the detection method for identifying DBPs is achieved through biochemical experiments. This method is inefficient and requires considerable manpower, material resources and time. At present, several computational approaches have been developed to detect DBPs, among which machine learning (ML) algorithm-based computational techniques have shown excellent performance. In our experiments, our method uses fewer features and simpler recognition methods than other methods and simultaneously obtains satisfactory results. First, we use six feature extraction methods to extract sequence features from the same group of DBPs. Then, this feature information is spliced together, and the data are standardized. Finally, the extreme gradient boosting (XGBoost) model is used to construct an effective predictive model. Compared with other excellent methods, our proposed method has achieved better results. The accuracy achieved by our method is 78.26% for PDB2272 and 85.48% for PDB186. The accuracy of the experimental results achieved by our strategy is similar to that of previous detection methods.
| S-EPMC8837382 | biostudies-literature
Project description:BackgroundThe main cause of cancer death is lung cancer (LC) which usually presents at an advanced stage, but its early detection would increase the benefits of treatment. Blood is particularly favored in clinical research given the possibility of using it for relatively noninvasive analyses. Copy number variation (CNV) is a common genetic change in tumor genomes, and many studies have indicated that CNV-derived cell-free DNA (cfDNA) from plasma could be feasible as a biomarker for cancer diagnosis.MethodsIn this study, we determined the possibility of using chromosomal arm-level CNV from cfDNA as a biomarker for lung cancer diagnosis in a small cohort of 40 patients and 41 healthy controls. Arm-level CNV distributions were analyzed based on z score, and the machine-learning algorithm Extreme Gradient Boosting (XGBoost) was applied for cancer prediction.ResultsThe results showed that amplifications tended to emerge on chromosomes 3q, 8q, 12p, and 7q. Deletions were frequently detected on chromosomes 22q, 3p, 5q, 16q, 10q, and 15q. Upon applying a trained XGBoost classifier, specificity and sensitivity of 100% were finally achieved in the test group (12 patients and 13 healthy controls). In addition, five-fold cross-validation proved the stability of the model. Finally, our results suggested that the integration of four arm-level CNVs and the concentration of cfDNA into the trained XGBoost classifier provides a potential method for detecting lung cancer.ConclusionOur results suggested that the integration of four arm-level CNVs and the concentration from of cfDNA integrated withinto the trained XGBoost classifier could become provides a potentially method for detecting lung cancer detection.Key pointsSignificant findings of the study: Healthy individuals have different arm-level CNV profiles from cancer patients. Amplifications tend to emerge on chromosome 3q, 8q, 12p, 7q and deletions tend to emerge on chromosome 22q, 3p, 5q, 16q, 10q, 15q.What this study addsCfDNA concentration, arm 10q, 3q, 8q, 3p, and 22q are key features for prediction. Trained XGBoost classifier is a potential method for lung cancer detection.
| S-EPMC6938748 | biostudies-literature
Project description:In the drug development process, approximately 30% of failures are attributed to drug safety issues. In particular, the first-in-human (FIH) trial of a new drug represents one of the highest safety risks, and initial dose selection is crucial for ensuring safety in clinical trials. With traditional dose estimation methods, which extrapolate data from animals to humans, catastrophic events have occurred during Phase I clinical trials due to interspecies differences in compound sensitivity and unknown molecular mechanisms. To address this issue, this study proposes a CrossFuse-extreme gradient boosting (XGBoost) method that can directly predict the maximum recommended daily dose of a compound based on existing human research data, providing a reference for FIH dose selection. This method not only integrates multiple features, including molecular representations, physicochemical properties and compound-protein interactions, but also improves feature selection based on cross-validation. The results demonstrate that the CrossFuse-XGBoost method not only improves prediction accuracy compared to that of existing local weighted methods [k-nearest neighbor (k-NN) and variable k-NN (v-NN)] but also solves the low prediction coverage issue of v-NN, achieving full coverage of the external validation set and enabling more reliable predictions. Furthermore, this study offers a high level of interpretability by identifying the importance of different features in model construction. The 241 features with the most significant impact on the maximum recommended daily dose were selected, providing references for optimizing the structure of new compounds and guiding experimental research. The datasets and source code are freely available at https://github.com/cqmu-lq/CrossFuse-XGBoost.
| S-EPMC10786712 | biostudies-literature
Project description:Type IV secreted effectors (T4SEs) can be translocated into the cytosol of host cells via type IV secretion system (T4SS) and cause diseases. However, experimental approaches to identify T4SEs are time- and resource-consuming, and the existing computational tools based on machine learning techniques have some obvious limitations such as the lack of interpretability in the prediction models. In this study, we proposed a new model, T4SE-XGB, which uses the eXtreme gradient boosting (XGBoost) algorithm for accurate identification of type IV effectors based on optimal features based on protein sequences. After trying 20 different types of features, the best performance was achieved when all features were fed into XGBoost by the 5-fold cross validation in comparison with other machine learning methods. Then, the ReliefF algorithm was adopted to get the optimal feature set on our dataset, which further improved the model performance. T4SE-XGB exhibited highest predictive performance on the independent test set and outperformed other published prediction tools. Furthermore, the SHAP method was used to interpret the contribution of features to model predictions. The identification of key features can contribute to improved understanding of multifactorial contributors to host-pathogen interactions and bacterial pathogenesis. In addition to type IV effector prediction, we believe that the proposed framework can provide instructive guidance for similar studies to construct prediction methods on related biological problems. The data and source code of this study can be freely accessed at https://github.com/CT001002/T4SE-XGB.
| S-EPMC7541839 | biostudies-literature
Project description:Associations between microRNAs (miRNAs) and human diseases have been identified by increasing studies and discovering new ones is an ongoing process in medical laboratories. To improve experiment productivity, researchers computationally infer potential associations from biological data, selecting the most promising candidates for experimental verification. Predicting potential miRNA-disease association has become a research area of growing importance. This paper presents a model of Extreme Gradient Boosting Machine for MiRNA-Disease Association (EGBMMDA) prediction by integrating the miRNA functional similarity, the disease semantic similarity, and known miRNA-disease associations. The statistical measures, graph theoretical measures, and matrix factorization results for each miRNA-disease pair were calculated and used to form an informative feature vector. The vector for known associated pairs obtained from the HMDD v2.0 database was used to train a regression tree under the gradient boosting framework. EGBMMDA was the first decision tree learning-based model used for predicting miRNA-disease associations. Respectively, AUCs of 0.9123 and 0.8221 in global and local leave-one-out cross-validation proved the model's reliable performance. Moreover, the 0.9048 ± 0.0012 AUC in fivefold cross-validation confirmed its stability. We carried out three different types of case studies of predicting potential miRNAs related to Colon Neoplasms, Lymphoma, Prostate Neoplasms, Breast Neoplasms, and Esophageal Neoplasms. The results indicated that, respectively, 98%, 90%, 98%, 100%, and 98% of the top 50 predictions for the five diseases were confirmed by experiments. Therefore, EGBMMDA appears to be a useful computational resource for miRNA-disease association prediction.
| S-EPMC5849212 | biostudies-literature
Project description:We used the extreme gradient boosting (XGB) algorithm to predict the experimental solubility of chemical compounds in water and organic solvents and to select significant molecular descriptors. The accuracy of prediction of our forward stepwise top-importance XGB (FSTI-XGB) on curated solubility data sets in terms of RMSE was found to be 0.59-0.76 Log(S) for two water data sets, while for organic solvent data sets it was 0.69-0.79 Log(S) for the Methanol data set, 0.65-0.79 for the Ethanol data set, and 0.62-0.70 Log(S) for the Acetone data set. That was the first step. In the second step, we used uncurated and curated AquaSolDB data sets for applicability domain (AD) tests of Drugbank, PubChem, and COCONUT databases and determined that more than 95% of studied ca. 500,000 compounds were within the AD. In the third step, we applied conformal prediction to obtain narrow prediction intervals and we successfully validated them using test sets' true solubility values. With prediction intervals obtained in the last fourth step, we were able to estimate individual error margins and the accuracy class of the solubility prediction for molecules within the AD of three public databases. All that was possible without the knowledge of experimental database solubilities. We find these four steps novel because usually, solubility-related works only study the first step or the first two steps.
| S-EPMC10779886 | biostudies-literature
Project description:BackgroundIdentifying one or more biologically-active/native decoys from millions of non-native decoys is one of the major challenges in computational structural biology. The extreme lack of balance in positive and negative samples (native and non-native decoys) in a decoy set makes the problem even more complicated. Consensus methods show varied success in handling the challenge of decoy selection despite some issues associated with clustering large decoy sets and decoy sets that do not show much structural similarity. Recent investigations into energy landscape-based decoy selection approaches show promises. However, lack of generalization over varied test cases remains a bottleneck for these methods.ResultsWe propose a novel decoy selection method, ML-Select, a machine learning framework that exploits the energy landscape associated with the structure space probed through a template-free decoy generation. The proposed method outperforms both clustering and energy ranking-based methods, all the while consistently offering better performance on varied test-cases. Moreover, ML-Select shows promising results even for the decoy sets consisting of mostly low-quality decoys.ConclusionsML-Select is a useful method for decoy selection. This work suggests further research in finding more effective ways to adopt machine learning frameworks in achieving robust performance for decoy selection in template-free protein structure prediction.
| S-EPMC7724862 | biostudies-literature
Project description:BACKGROUND:High glycemic variability (GV) is common in critically ill patients; however, the prevalence and mortality association with early GV in patients with sepsis remains unclear. METHODS:This retrospective cohort study was conducted in a medical intensive care unit (ICU) in central Taiwan. Patients in the ICU with sepsis between January 2014 and December 2015 were included for analysis. All of these patients received protocol-based management, including blood sugar monitoring every 2 h for the first 24 h of ICU admission. Mean amplitude of glycemic excursions (MAGE) and coefficient of variation (CoV) were used to assess GV. RESULTS:A total of 452 patients (mean age 71.4?±?14.7 years; 76.7% men) were enrolled for analysis. They were divided into high GV (43.4%, 196/452) and low GV (56.6%, 256/512) groups using MAGE 65 mg/dL as the cut-off point. Patients with high GV tended to have higher HbA1c (6.7?±?1.8% vs. 5.9?±?0.9%, p?<?0.01) and were more likely to have diabetes mellitus (DM) (50.0% vs. 23.4%, p?<?0.01) compared with those in the low GV group. Kaplan-Meier analysis showed that a high GV was associated with increased 30-day mortality (log-rank test, p?=?0.018). The association remained strong in the non-DM (log-rank test, p?=?0.035), but not in the DM (log-rank test, p?=?0.254) group. Multivariate Cox proportional hazard regression analysis identified that high APACHE II score (adjusted hazard ratio (aHR) 1.045, 95% confidence interval (CI) 1.013-1.078), high serum lactate level at 0 h (aHR 1.009, 95% CI 1.003-1.014), having chronic airway disease (aHR 0.478, 95% CI 0.302-0.756), high mean day 1 glucose (aHR 1.008, 95% CI 1.000-1.016), and high MAGE (aHR 1.607, 95% CI 1.008-2.563) were independently associated with increased 30-day mortality. The association with 30-day mortality remained consistent when using CoV to assess GV. CONCLUSIONS:We found that approximately 40% of the septic patients had a high early GV, defined as MAGE >?65 mg/dL. Higher GV within 24 h of ICU admission was independently associated with increased 30-day mortality. These findings highlight the need to monitor GV in septic patients early during an ICU admission.
| S-EPMC7007493 | biostudies-literature
Project description:Identification of hot spots, a small portion of protein-protein interface residues that contribute the majority of the binding free energy, can provide crucial information for understanding the function of proteins and studying their interactions. Based on our previous method (PredHS), we propose a new computational approach, PredHS2, that can further improve the accuracy of predicting hot spots at protein-protein interfaces. Firstly we build a new training dataset of 313 alanine-mutated interface residues extracted from 34 protein complexes. Then we generate a wide variety of 600 sequence, structure, exposure and energy features, together with Euclidean and Voronoi neighborhood properties. To remove redundant and irrelevant information, we select a set of 26 optimal features utilizing a two-step feature selection method, which consist of a minimum Redundancy Maximum Relevance (mRMR) procedure and a sequential forward selection process. Based on the selected 26 features, we use Extreme Gradient Boosting (XGBoost) to build our prediction model. Performance of our PredHS2 approach outperforms other machine learning algorithms and other state-of-the-art hot spot prediction methods on the training dataset and the independent test set (BID) respectively. Several novel features, such as solvent exposure characteristics, second structure features and disorder scores, are found to be more effective in discriminating hot spots. Moreover, the update of the training dataset and the new feature selection and classification algorithms play a vital role in improving the prediction quality.
| S-EPMC6155324 | biostudies-literature
Project description:Due to industrial development, designing and optimal operation of processes in chemical and petroleum processing plants require accurate estimation of the hydrogen solubility in various hydrocarbons. Equations of state (EOSs) are limited in accurately predicting hydrogen solubility, especially at high-pressure or/and high-temperature conditions, which may lead to energy waste and a potential safety hazard in plants. In this paper, five robust machine learning models including extreme gradient boosting (XGBoost), adaptive boosting support vector regression (AdaBoost-SVR), gradient boosting with categorical features support (CatBoost), light gradient boosting machine (LightGBM), and multi-layer perceptron (MLP) optimized by Levenberg-Marquardt (LM) algorithm were implemented for estimating the hydrogen solubility in hydrocarbons. To this end, a databank including 919 experimental data points of hydrogen solubility in 26 various hydrocarbons was gathered from 48 different systems in a broad range of operating temperatures (213-623 K) and pressures (0.1-25.5 MPa). The hydrocarbons are from six different families including alkane, alkene, cycloalkane, aromatic, polycyclic aromatic, and terpene. The carbon number of hydrocarbons is ranging from 4 to 46 corresponding to a molecular weight range of 58.12-647.2 g/mol. Molecular weight, critical pressure, and critical temperature of solvents along with pressure and temperature operating conditions were selected as input parameters to the models. The XGBoost model best fits all the experimental solubility data with a root mean square error (RMSE) of 0.0007 and an average absolute percent relative error (AAPRE) of 1.81%. Also, the proposed models for estimating the solubility of hydrogen in hydrocarbons were compared with five EOSs including Soave-Redlich-Kwong (SRK), Peng-Robinson (PR), Redlich-Kwong (RK), Zudkevitch-Joffe (ZJ), and perturbed-chain statistical associating fluid theory (PC-SAFT). The XGBoost model introduced in this study is a promising model that can be applied as an efficient estimator for hydrogen solubility in various hydrocarbons and is capable of being utilized in the chemical and petroleum industries.
| S-EPMC8429697 | biostudies-literature