Machine learning-based causal models for predicting the response of individual patients to dexamethasone treatment as prophylactic antiemetic.
Ontology highlight
ABSTRACT:
SUBMITTER: Mizuguchi T
PROVIDER: S-EPMC10169123 | biostudies-literature | 2023 May
REPOSITORIES: biostudies-literature
Publications
Machine learning-based causal models for predicting the response of individual patients to dexamethasone treatment as prophylactic antiemetic.
Mizuguchi Taisuke T Sawamura Shigehito S
Scientific reports 20230509 1
Risk-based strategies are widely used for decision making in the prophylaxis of postoperative nausea and vomiting (PONV), a major complication of general anesthesia. However, whether risk is associated with individual treatment effect remains uncertain. Here, we used machine learning-based algorithms for estimating the conditional average treatment effect (CATE) (double machine learning [DML], doubly robust [DR] learner, forest DML, and generalized random forest) to predict the treatment respons ...[more]
Similar Datasets
Project description:Cancer immunotherapy has significantly improved patient survival. Yet, half of patients do not respond to immunotherapy. Gut microbiomes have been linked to clinical responsiveness of melanoma patients on immunotherapies; however, different taxa have been associated with response status with implicated taxa inconsistent between studies. We used a tumor-agnostic approach to find common gut microbiome features of response among immunotherapy patients with different advanced stage cancers. A combined meta-analysis of 16S rRNA gene sequencing data from our mixed tumor cohort and three published immunotherapy gut microbiome datasets from different melanoma patient cohorts found certain gut bacterial taxa correlated with immunotherapy response status regardless of tumor type. Using multivariate selbal analysis, we identified two separate groups of bacterial genera associated with responders versus non-responders. Statistical models of gut microbiome community features showed robust prediction accuracy of immunotherapy response in amplicon sequencing datasets and in cross-sequencing platform validation with shotgun metagenomic datasets. Results suggest baseline gut microbiome features may be predictive of clinical outcomes in oncology patients on immunotherapies, and some of these features may be generalizable across different tumor types, patient cohorts, and sequencing platforms. Findings demonstrate how machine learning models can reveal microbiome-immunotherapy interactions that may ultimately improve cancer patient outcomes.
| S-EPMC9295706 | biostudies-literature
Project description:ObjectiveTo assess both the feasibility and potential impact of predicting preventable hospital readmissions using causal machine learning applied to data from the implementation of a readmissions prevention intervention (the Transitions Program).Data sourcesElectronic health records maintained by Kaiser Permanente Northern California (KPNC).Study designRetrospective causal forest analysis of postdischarge outcomes among KPNC inpatients. Using data from both before and after implementation, we apply causal forests to estimate individual-level treatment effects of the Transitions Program intervention on 30-day readmission. These estimates are used to characterize treatment effect heterogeneity and to assess the notional impacts of alternative targeting strategies in terms of the number of readmissions prevented.Data collection1 539 285 index hospitalizations meeting the inclusion criteria and occurring between June 2010 and December 2018 at 21 KPNC hospitals.Principal findingsThere appears to be substantial heterogeneity in patients' responses to the intervention (omnibus test for heterogeneity p = 2.23 × 10-7 ), particularly across levels of predicted risk. Notably, predicted treatment effects become more positive as predicted risk increases; patients at somewhat lower risk appear to have the largest predicted effects. Moreover, these estimates appear to be well calibrated, yielding the same estimate of annual readmissions prevented in the actual treatment subgroup (1246, 95% confidence interval [CI] 1110-1381) as did a formal evaluation of the Transitions Program (1210, 95% CI 990-1430). Estimates of the impacts of alternative targeting strategies suggest that as many as 4458 (95% CI 3925-4990) readmissions could be prevented annually, while decreasing the number needed to treat from 33 to 23, by targeting patients with the largest predicted effects rather than those at highest risk.ConclusionsCausal machine learning can be used to identify preventable hospital readmissions, if the requisite interventional data are available. Moreover, our results suggest a mismatch between risk and treatment effects.
| S-EPMC7704477 | biostudies-literature
Project description:IntroductionAlthough clinical, functional, and biomarker data predict asthma exacerbations, newer approaches providing high accuracy of prognosis are needed for real-world decision-making in asthma. Machine learning (ML) leverages mathematical and statistical methods to detect patterns for future disease events across large datasets from electronic health records (EHR). This study conducted training and fine-tuning of ML algorithms for the real-world prediction of asthma exacerbations in patients with physician-diagnosed asthma.MethodsAdults with ≥ 2 ICD9/10 asthma codes within 1 year and at least 30 days apart were identified from the Optum Panther EHR database between 2016 and 2023. An emergency department (ED), urgent care, or inpatient visit for asthma, while on systemic administration of corticosteroids, was considered an exacerbation. To predict factors associated with exacerbations in a 6-month study period, clinical information from patients was retrieved in the preceding 6-month baseline period. Clinical information included demographics, lab results, diagnoses, medications, immunizations, and allergies. Three models built using Extreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM), and Transformers algorithms were trained and tested on independent datasets. Predictions were explained using the SHAP (SHapley Additive exPlanations) library.ResultsOf 1,331,934 patients with asthma, 16,279 (1.2%) experienced ≥ 1 exacerbation. XGBoost was the best predictive algorithm (area under the curve [AUC] = 0.964). Factors associated with exacerbations included a prior history of exacerbation, prednisone usage, high-dose albuterol usage, and elevated troponin I. Reduced probability of exacerbations was associated with receiving inhaled albuterol, vitamins, aspirin, statins, furosemide, and influenza vaccination.ConclusionThis ML-based study on asthma in the real world confirmed previously known features associated with increased exacerbation risk for asthma, while uncovering not entirely understood features associated with reduced risk of asthma exacerbations. These findings are hypothesis-generating and should contribute to ongoing discussion of the strengths and limitations of ML and other supervised learning models in patient risk stratification.
| S-EPMC11782383 | biostudies-literature
Project description:BackgroundMaternal morbidity and mortality remain critical health concerns globally. As a result, reducing the maternal mortality ratio (MMR) is part of goal 3 in the global sustainable development goals (SDGs), and previously, it was an important indicator in the Millennium Development Goals (MDGs). Therefore, identifying high-risk groups during pregnancy is crucial for decision-makers and medical practitioners to mitigate mortality and morbidity. However, the availability of accurate predictive models for maternal mortality and maternal health risks is challenging. Compared with traditional predictive models, machine learning algorithms have emerged as promising predictive modelling methods providing accurate predictive models.MethodsThis work aims to explore the potential of machine learning (ML) algorithms in maternal risk level prediction using a nationwide maternal mortality dataset from Oman for the first time. A total of 402 maternal deaths from 1991 to 2023 in Oman were included in this study. We utilised principal component analysis (PCA) in the ML algorithms and compared them to the results of model performance without PCA. We employed and compared ten ML algorithms, including decision tree (DT), random forest (RF), K-Nearest Neighbors (KNN), Naïve Bayes (NB), Extreme Gradient Boosting (xgboost), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Logistic Regression (LR), Support Vector Machine (SVM) and Artificial Neural Network (ANN). Different metrics, including, accuracy, sensitivity, precision, and the F1- score, were utilised to assess Model performance.ResultsThe results indicated that the RF model outperformed the other methods in predicting the risk level (low or high) with an accuracy of 75.2%, precision of 85.7% and F1- score of 73% after PCA was applied.ConclusionsWe applied several machine learning models to predict maternal risk levels for the first time using real data from Oman. RF outperformed the other algorithms in this classification problem. A reliable estimate of maternal risk level would facilitate intervention plans for medical practitioners to reduce maternal death.
| S-EPMC11657143 | biostudies-literature
Project description:BackgroundUndertriaged patients have worse outcomes than appropriately triaged patients. Machine learning provides better triage prediction than conventional triage in emergency departments, but no machine learning-based undertriage prediction models have yet been developed for prehospital telephone triage. We developed and validated machine learning models for telephone triage.Materials and methodsWe conducted a retrospective cohort study with the largest after-hour house-call (AHHC) service dataset in Japan. Participants were ≥16 years and used the AHHC service between 1 November 2018 and 31 January 2021. We developed five prediction models based on support vector machine (SVM), lasso regression (LR), random forest (RF), gradient-boosted decision tree (XGB), and deep neural network (DNN). The primary outcome was undertriage, and predictors were telephone triage level and routinely available telephone-based data, including age, sex, 80 chief complaint categories and 10 comorbidities. We measured the area under the receiver operating characteristic curve (AUROC) for all the models.ResultsWe identified 15,442 eligible patients (age: 38.4 ± 16.6, male: 57.2%), including 298 (1.9%; age: 58.2 ± 23.9, male: 55.0%) undertriaged patients. RF and XGB outperformed the other models, with the AUROC values (95% confidence interval; 95% CI) of the SVM, LR, RF, XGB and DNN for undertriage being 0.62 (0.55-0.69), 0.79 (0.74-0.83), 0.81 (0.76-0.86), 0.80 (0.75-0.84) and 0.77 (0.73-0.82), respectively.ConclusionsWe found that RF and XGB outperformed other models. Our findings suggest that machine learning models can facilitate the early detection of undertriage and early intervention to yield substantially improved patient outcomes.KEY MESSAGESUndertriaged patients experience worse outcomes than appropriately triaged patients; thus, we developed machine learning models for predicting undertriage in the prehospital setting. In addition, we identified the predictors of risk factors associated with undertriage.Random forest and gradient-boosted decision tree models demonstrated better prediction performance, and the models identified the risk factors associated with undertriage.Machine learning models aid in the early detection of undertriage, leading to significantly improved patient outcomes and identifying undertriage-associated risk factors, including chief complaint categories, could help prioritize conventional telephone triage protocol revision.
| S-EPMC9621252 | biostudies-literature
Project description:Strategic preparedness reduces the adverse health impacts of hurricanes and tropical storms, referred to collectively as tropical cyclones (TCs), but its protective impact could be enhanced by a more comprehensive and rigorous characterization of TC epidemiology. To generate the insights and tools necessary for high-precision TC preparedness, we introduce a machine learning approach that standardizes estimation of historic TC health impacts, discovers common patterns and sources of heterogeneity in those health impacts, and enables identification of communities at highest health risk for future TCs. The model integrates (i) a causal inference component to quantify the immediate health impacts of recent historic TCs at high spatial resolution and (ii) a predictive component that captures how TC meteorological features and socioeconomic/demographic characteristics of impacted communities are associated with health impacts. We apply it to a rich data platform containing detailed historic TC exposure information and records of all-cause mortality and cardiovascular- and respiratory-related hospitalization among Medicare recipients. We report a high degree of heterogeneity in the acute health impacts of historic TCs, both within and across TCs, and, on average, substantial TC-attributable increases in respiratory hospitalizations. TC-sustained windspeeds are found to be the primary driver of mortality and respiratory risks.
| S-EPMC10102905 | biostudies-literature
Project description:BackgroundAccurately predicting hospital discharge events could help improve patient flow and the efficiency of healthcare delivery. However, using machine learning and diverse electronic health record (EHR) data for this task remains incompletely explored.MethodsWe used EHR data from February-2017 to January-2020 from Oxfordshire, UK to predict hospital discharges in the next 24 h. We fitted separate extreme gradient boosting models for elective and emergency admissions, trained on the first two years of data and tested on the final year of data. We examined individual-level and hospital-level model performance and evaluated the impact of training data size and recency, prediction time, and performance in subgroups.ResultsOur models achieve AUROCs of 0.87 and 0.86, AUPRCs of 0.66 and 0.64, and F1 scores of 0.61 and 0.59 for elective and emergency admissions, respectively. These models outperform a logistic regression model using the same features and are substantially better than a baseline logistic regression model with more limited features. Notably, the relative performance increase from adding additional features is greater than the increase from using a sophisticated model. Aggregating individual probabilities, daily total discharge estimates are accurate with mean absolute errors of 8.9% (elective) and 4.9% (emergency). The most informative predictors include antibiotic prescriptions, medications, and hospital capacity factors. Performance remains robust across patient subgroups and different training strategies, but is lower in patients with longer admissions and those who died in hospital.ConclusionsOur findings highlight the potential of machine learning in optimising hospital patient flow and facilitating patient care and recovery.
| S-EPMC11574281 | biostudies-literature
Project description:The COVID-19 pandemic has had a significant impact on public life and health worldwide, putting the world's healthcare systems at risk. The first step in stopping this outbreak is to detect the infection in its early stages, which will relieve the risk, control the outbreak's spread, and restore full functionality to the world's healthcare systems. Currently, PCR is the most prevalent diagnosis tool for COVID-19. However, chest X-ray images may play an essential role in detecting this disease, as they are successful for many other viral pneumonia diseases. Unfortunately, there are common features between COVID-19 and other viral pneumonia, and hence manual differentiation between them seems to be a critical problem and needs the aid of artificial intelligence. This research employs deep- and transfer-learning techniques to develop accurate, general, and robust models for detecting COVID-19. The developed models utilize either convolutional neural networks or transfer-learning models or hybridize them with powerful machine-learning techniques to exploit their full potential. For experimentation, we applied the proposed models to two data sets: the COVID-19 Radiography Database from Kaggle and a local data set from Asir Hospital, Abha, Saudi Arabia. The proposed models achieved promising results in detecting COVID-19 cases and discriminating them from normal and other viral pneumonia with excellent accuracy. The hybrid models extracted features from the flatten layer or the first hidden layer of the neural network and then fed these features into a classification algorithm. This approach enhanced the results further to full accuracy for binary COVID-19 classification and 97.8% for multiclass classification.
| S-EPMC8357494 | biostudies-literature
Project description:Climate change is a shift in nature yet a devastating phenomenon, mainly caused by human activities, sometimes with the intent to generate usable energy required in humankind's daily life. Addressing this alarming issue requires an urge for energy consumption evaluation. Predicting energy consumption is essential for determining what factors affect a site's energy usage and in turn, making actionable suggestions to reduce wasteful energy consumption. Recently, a rising number of researchers have applied machine learning in various fields, such as wind turbine performance prediction, energy consumption prediction, thermal behavior analysis, and more. In this research study, using data publicly made available by the Women in Data Science (WiDS) Datathon 2022 (contains data on building characteristics and information collected by sensors), after appropriate data preparation, we experimented four main machine learning methods (random forest (RF), gradient boost decision tree (GBDT), support vector regressor (SVR), and decision tree for regression (DT)). The most performant model was selected using evaluation metrics: root mean square error (RMSE) and mean absolute error (MAE). The reported results proved the robustness of the proposed concept in capturing the insight and hidden patterns in the dataset, and effectively predicting the energy usage of buildings.
| S-EPMC9823370 | biostudies-literature
Project description:ObjectiveGeneralized anxiety disorder (GAD) is a prevalent mental health disorder that often goes untreated. A core aspect of GAD is worry, which is associated with negative health outcomes, accentuating a need for simple treatments for worry. The present study leveraged pretreatment individual differences to predict personalized treatment response to a digital intervention.MethodsLinear mixed-effect models were used to model changes in daytime and nighttime worry duration and frequency for 163 participants who completed a six-day worry postponement intervention. Ensemble-based machine learning regression and classification models were implemented to predict changes in worry across the intervention. Model feature importance was derived using SHapley Additive exPlanation (SHAP).ResultsModerate predictive performance was obtained for predicting changes in daytime worry duration (test r2 = 0.221, AUC = 0.77) and nighttime worry frequency (test r2 = 0.164, AUC = 0.72), while poor predictive performance was obtained for nighttime worry duration and daytime worry frequency. Baseline levels of worry and subjective health complaints were most important in driving model predictions.LimitationsA complete-case analysis was leveraged to analyze the present data, which was collected from participants that were Dutch and majority female.ConclusionsThis study suggests that treatment response to a digital intervention for GAD can be accurately predicted using baseline characteristics. Particularly, this worry postponement intervention may be most beneficial for individuals with high baseline worry but fewer subjective health complaints. The present findings highlight the complexities of and need for further research into daily worry dynamics and the personalizable utility of digital interventions.
| S-EPMC10037342 | biostudies-literature