An Interpretable Early Dynamic Sequential Predictor for Sepsis-Induced Coagulopathy Progression in the Real-World Using Machine Learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Cui R
PROVIDER: S-EPMC8678506 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Background: Sepsis-induced coagulopathy (SIC) denotes an increased mortality rate and poorer prognosis in septic patients. Objectives: Our study aimed to develop and validate machine-learning models to dynamically predict the risk of SIC in critically ill patients with sepsis. Methods: Machine-learning models were developed and validated based on two public databases named Medical Information Mart for Intensive Care (MIMIC)-IV and the eICU Collaborative Research Database (eICU-CRD). Dynamic prediction of SIC involved an evaluation of the risk of SIC each day after the diagnosis of sepsis using 15 predictive models. The best model was selected based on its accuracy and area under the receiver operating characteristic curve (AUC), followed by fine-grained hyperparameter adjustment using the Bayesian Optimization Algorithm. A compact model was developed, based on 15 features selected according to their importance and clinical availability. These two models were compared with Logistic Regression and SIC scores in terms of SIC prediction. Results: Of 11,362 patients in MIMIC-IV included in the final cohort, a total of 6,744 (59%) patients developed SIC during sepsis. The model named Categorical Boosting (CatBoost) had the greatest AUC in our study (0.869; 95% CI: 0.850-0.886). Coagulation profile and renal function indicators were the most important features for predicting SIC. A compact model was developed with an AUC of 0.854 (95% CI: 0.832-0.872), while the AUCs of Logistic Regression and SIC scores were 0.746 (95% CI: 0.735-0.755) and 0.709 (95% CI: 0.687-0.733), respectively. A cohort of 35,252 septic patients in eICU-CRD was analyzed. The AUCs of the full and the compact models in the external validation were 0.842 (95% CI: 0.837-0.846) and 0.803 (95% CI: 0.798-0.809), respectively, which were still larger than those of Logistic Regression (0.660; 95% CI: 0.653-0.667) and SIC scores (0.752; 95% CI: 0.747-0.757). Prediction results were illustrated by SHapley Additive exPlanations (SHAP) values, which made our models clinically interpretable. Conclusions: We developed two models which were able to dynamically predict the risk of SIC in septic patients better than conventional Logistic Regression and SIC scores.
| S-EPMC7859637 | biostudies-literature
Project description:ObjectiveSepsis-induced coagulopathy (SIC) is extremely common in individuals with sepsis, significantly associated with poor outcomes. This study attempted to develop an interpretable and generalizable machine learning (ML) model for early predicting the risk of 28-day death in patients with SIC.MethodsIn this retrospective cohort study, we extracted SIC patients from the Medical Information Mart for Intensive Care III (MIMIC-III), MIMIC-IV, and eICU-CRD database according to Toshiaki Iba's scale. And the overlapping in the MIMIC-IV was excluded for this study. Afterward, only the MIMIC-III cohort was randomly divided into the training set, and the internal validation set according to the ratio of 7:3, while the MIMIC-IV and eICU-CRD databases were considered the external validation sets. The predictive factors for 28-day mortality of SIC patients were determined using recursive feature elimination combined with tenfold cross-validation (RFECV). Then, we constructed models using ML algorithms. Multiple metrics were used for evaluation of performance of the models, including the area under the receiver operating characteristic curve (AUROC), area under the precision recall curve (AUPRC), accuracy, sensitivity, specificity, negative predictive value, positive predictive value, recall, and F1 score. Finally, Shapley Additive Explanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME) were employed to provide a reasonable interpretation for the prediction results.ResultsA total of 3280, 2798, and 1668 SIC patients were screened from MIMIC-III, MIMIC-IV, and eICU-CRD databases, respectively. Seventeen features were selected to construct ML prediction models. XGBoost had the best performance in predicting the 28-day mortality of SIC patients, with AUC of 0.828, 0.913 and 0.923, the AUPRC of 0.807, 0.796 and 0.921, the accuracy of 0.785, 0.885 and 0.891, the F1 scores were 0.63, 0.69 and 0.70 in MIMIC-III (internal validation set), MIMIC-IV, and eICU-CRD databases. The importance ranking and SHAP analyses showed that initial SOFA score, red blood cell distribution width (RDW), and age were the top three critical features in the XGBoost model.ConclusionsWe developed an optimal and explainable ML model to predict the risk of 28-day death of SIC patients 28-day death risk. Compared with conventional scoring systems, the XGBoost model performed better. The model established will have the potential to improve the level of clinical practice for SIC patients.
| S-EPMC10763177 | biostudies-literature
Project description:Sepsis-induced coagulopathy has poor prognosis; however, there is no established tool for predicting it. We aimed to create predictive models for coagulopathy progression using machine-learning techniques to evaluate predictive accuracies of machine-learning and conventional techniques. A post-hoc subgroup analysis was conducted based on the Japan Septic Disseminated Intravascular Coagulation retrospective study. We used the International Society on Thrombosis and Haemostasis disseminated intravascular coagulation (DIC) score to calculate the ΔDIC score as ((DIC score on Day 3) - (DIC score on Day 1)). The primary outcome was to determine whether the predictive accuracy of ΔDIC was more than 0. The secondary outcome was the actual predictive accuracy of ΔDIC (predicted ΔDIC-real ΔDIC). We used the machine-learning methods, such as random forests (RF), support vector machines (SVM), and neural networks (NN); their predictive accuracies were compared with those of conventional methods. In total, 1017 patients were included. Regarding DIC progression, predictive accuracy of the multiple linear regression, RF, SVM, and NN models was 63.7%, 67.0%, 64.4%, and 59.8%, respectively. The difference between predicted ΔDIC and real ΔDIC was 2.05, 1.54, 2.24, and 1.77 for the multiple linear regression, RF, SVM, and NN models, respectively. RF had the highest predictive accuracy.
| S-EPMC7408668 | biostudies-literature
Project description:With a mortality rate of 5.4 million lives worldwide every year and a healthcare cost of more than 16 billion dollars in the USA alone, sepsis is one of the leading causes of hospital mortality and an increasing concern in the ageing western world. Recently, medical and technological advances have helped re-define the illness criteria of this disease, which is otherwise poorly understood by the medical society. Together with the rise of widely accessible Electronic Health Records, the advances in data mining and complex nonlinear algorithms are a promising avenue for the early detection of sepsis. This work contributes to the research effort in the field of automated sepsis detection with an open-access labelling of the medical MIMIC-III data set. Moreover, we propose MGP-AttTCN: a joint multitask Gaussian Process and attention-based deep learning model to early predict the occurrence of sepsis in an interpretable manner. We show that our model outperforms the current state-of-the-art and present evidence that different labelling heuristics lead to discrepancies in task difficulty. For instance, when predicting sepsis five hours prior to onset on our new realistic labels, our proposed model achieves an area under the ROC curve of 0.660 and an area under the PR curve of 0.483, whereas the (less interpretable) previous state-of-the-art model (MGP-TCN) achieves 0.635 AUROC and 0.460 AUPR and the popular commercial InSight model achieves 0.490 AUROC and 0.359 AUPR.
| S-EPMC8104377 | biostudies-literature
Project description:OBJECTIVES:Sepsis is among the leading causes of morbidity, mortality, and cost overruns in critically ill patients. Early intervention with antibiotics improves survival in septic patients. However, no clinically validated system exists for real-time prediction of sepsis onset. We aimed to develop and validate an Artificial Intelligence Sepsis Expert algorithm for early prediction of sepsis. DESIGN:Observational cohort study. SETTING:Academic medical center from January 2013 to December 2015. PATIENTS:Over 31,000 admissions to the ICUs at two Emory University hospitals (development cohort), in addition to over 52,000 ICU patients from the publicly available Medical Information Mart for Intensive Care-III ICU database (validation cohort). Patients who met the Third International Consensus Definitions for Sepsis (Sepsis-3) prior to or within 4 hours of their ICU admission were excluded, resulting in roughly 27,000 and 42,000 patients within our development and validation cohorts, respectively. INTERVENTIONS:None. MEASUREMENTS AND MAIN RESULTS:High-resolution vital signs time series and electronic medical record data were extracted. A set of 65 features (variables) were calculated on hourly basis and passed to the Artificial Intelligence Sepsis Expert algorithm to predict onset of sepsis in the proceeding T hours (where T = 12, 8, 6, or 4). Artificial Intelligence Sepsis Expert was used to predict onset of sepsis in the proceeding T hours and to produce a list of the most significant contributing factors. For the 12-, 8-, 6-, and 4-hour ahead prediction of sepsis, Artificial Intelligence Sepsis Expert achieved area under the receiver operating characteristic in the range of 0.83-0.85. Performance of the Artificial Intelligence Sepsis Expert on the development and validation cohorts was indistinguishable. CONCLUSIONS:Using data available in the ICU in real-time, Artificial Intelligence Sepsis Expert can accurately predict the onset of sepsis in an ICU patient 4-12 hours prior to clinical recognition. A prospective study is necessary to determine the clinical utility of the proposed sepsis prediction model.
| S-EPMC5851825 | biostudies-literature
Project description:IntroductionThe New Zealand (NZ) Central Region Stroke Network, serving 1.17 million catchment population, changed to tenecteplase for stroke thrombolysis in 2020 but was forced to revert to Alteplase in 2021 due to a sudden cessation of drug supply. We used this unique opportunity to assess for potential before and after temporal trend confounding.Patients and methodsIn NZ all reperfused patients are entered prospectively into a national database for safety monitoring. We assessed Central Region patient outcomes and treatment metrics over three time periods: alteplase use (January 2018-January 2020); during switch to tenecteplase (February 2020-February 2021) and after reverting to alteplase (February 2021-December 2022) adjusting regression analyses for hospital, age, onset-to-needle, NIHSS, pre-morbid mRS and thrombectomy.ResultsBetween January 2018 and December 2022, we treated 1121 patients with Alteplase and 286 with tenecteplase. Overall, patients treated with tenecteplase had greater odds of favorable outcome ordinal mRS [aOR = 1.43 (95% CI = 1.11-1.85)]; shorter door-to-needle (DTN) time [median 52 (IQR 47-83) vs 61 (45-84) minutes, p < 0.0001] and needle to groin (NTG) times [118 (74.5-218.5) vs 185 (118-255); p = 0.02)]. Symptomatic intracerebral hemorrhage (sICH) rate was lower in tenecteplase group [aOR 0.29 (0.09-0.95)]. Findings similarly favored tenecteplase when comparing tenecteplase to only the second alteplase phase. There was no inter-group difference when comparing the two alteplase phases.ConclusionsOur results suggest that previously reported benefits from tenecteplase in a real-world setting were not likely attributable to a temporal confounding.
| S-EPMC10683726 | biostudies-literature
Project description:BackgroundEarly and reliable identification of patients with sepsis who are at high risk of mortality is important to improve clinical outcomes. However, 3 major barriers to artificial intelligence (AI) models, including the lack of interpretability, the difficulty in generalizability, and the risk of automation bias, hinder the widespread adoption of AI models for use in clinical practice.ObjectiveThis study aimed to develop and validate (internally and externally) a conformal predictor of sepsis mortality risk in patients who are critically ill, leveraging AI-assisted prediction modeling. The proposed approach enables explaining the model output and assessing its confidence level.MethodsWe retrospectively extracted data on adult patients with sepsis from a database collected in a teaching hospital at Beth Israel Deaconess Medical Center for model training and internal validation. A large multicenter critical care database from the Philips eICU Research Institute was used for external validation. A total of 103 clinical features were extracted from the first day after admission. We developed an AI model using gradient-boosting machines to predict the mortality risk of sepsis and used Mondrian conformal prediction to estimate the prediction uncertainty. The Shapley additive explanation method was used to explain the model.ResultsA total of 16,746 (80%) patients from Beth Israel Deaconess Medical Center were used to train the model. When tested on the internal validation population of 4187 (20%) patients, the model achieved an area under the receiver operating characteristic curve of 0.858 (95% CI 0.845-0.871), which was reduced to 0.800 (95% CI 0.789-0.811) when externally validated on 10,362 patients from the Philips eICU database. At a specified confidence level of 90% for the internal validation cohort the percentage of error predictions (n=438) out of all predictions (n=4187) was 10.5%, with 1229 (29.4%) predictions requiring clinician review. In contrast, the AI model without conformal prediction made 1449 (34.6%) errors. When externally validated, more predictions (n=4004, 38.6%) were flagged for clinician review due to interdatabase heterogeneity. Nevertheless, the model still produced significantly lower error rates compared to the point predictions by AI (n=1221, 11.8% vs n=4540, 43.8%). The most important predictors identified in this predictive model were Acute Physiology Score III, age, urine output, vasopressors, and pulmonary infection. Clinically relevant risk factors contributing to a single patient were also examined to show how the risk arose.ConclusionsBy combining model explanation and conformal prediction, AI-based systems can be better translated into medical practice for clinical decision-making.
| S-EPMC10985608 | biostudies-literature
Project description:The umami taste is one of the five basic taste modalities normally linked to the protein content in food. The implementation of fast and cost-effective tools for the prediction of the umami taste of a molecule remains extremely interesting to understand the molecular basis of this taste and to effectively rationalise the production and consumption of specific foods and ingredients. However, the only examples of umami predictors available in the literature rely on the amino acid sequence of the analysed peptides, limiting the applicability of the models. In the present study, we developed a novel ML-based algorithm, named VirtuousUmami, able to predict the umami taste of a query compound starting from its SMILES representation, thus opening up the possibility of potentially using such a model on any database through a standard and more general molecular description. Herein, we have tested our model on five databases related to foods or natural compounds. The proposed tool will pave the way toward the rationalisation of the molecular features underlying the umami taste and toward the design of specific peptide-inspired compounds with specific taste properties.
| S-EPMC9758219 | biostudies-literature
Project description:IntroductionA dynamic molecular biomarker that can identify early efficacy of immune checkpoint inhibitor (ICI) therapy remains an unmet clinical need. Here we evaluate if a novel circulating tumor DNA (ctDNA) assay, xM, used for treatment response monitoring (TRM), that quantifies changes in ctDNA tumor fraction (TF), can predict outcome benefits in patients treated with ICI alone or in combination with chemotherapy in a real-world (RW) cohort.MethodsThis retrospective study consisted of patients with advanced cancer from the Tempus de-identified clinical genomic database who received longitudinal liquid-based next-generation sequencing. Eligible patients had a blood sample ≤ 40 days prior to the start of ICI initiation and an on-treatment blood sample 15-180 days post ICI initiation. TF was calculated via an ensemble algorithm that utilizes TF estimates derived from variants and copy number information. Patients with molecular response (MR) were defined as patients with a ≥ 50% decrease in TF between tests. In the subset of patients with rw-imaging data between 2 and 18 weeks of ICI initiation, the predictive value of MR in addition to rw-imaging was compared to a model of rw-imaging alone.ResultsThe evaluable cohort (N = 86) was composed of 14 solid cancer types. Patients received either ICI monotherapy (38.4%, N = 33) or ICI in combination with chemotherapy (61.6%, N = 53). Patients with MR had significantly longer rw-overall survival (rwOS) (hazard ratio (HR) 0.4, P = 0.004) and rw-progression free survival (rwPFS) (HR 0.4, P = 0.005) than patients with molecular non-response (nMR). Similar results were seen in the ICI monotherapy subcohort; HR 0.2, P = 0.02 for rwOS and HR 0.2, P = 0.01 for rwPFS. In the subset of patients with matched rw-imaging data (N = 51), a model incorporating both MR and rw-imaging was superior in predicting rwOS than rw-imaging alone (P = 0.02).ConclusionsxM used for TRM is a novel serial quantitative TF algorithm that can be used clinically to evaluate ICI therapy efficacy.
| S-EPMC11333675 | biostudies-literature
Project description:Precision medicine is currently a topic of great interest in clinical and intervention science. A key component of precision medicine is that it is evidence-based, i.e., data-driven, and consequently there has been tremendous interest in estimation of precision medicine strategies using observational or randomized study data. One way to formalize precision medicine is through a treatment regime, which is a sequence of decision rules, one per stage of clinical intervention, that map up-to-date patient information to a recommended treatment. An optimal treatment regime is defined as maximizing the mean of some cumulative clinical outcome if applied to a population of interest. It is well-known that even under simple generative models an optimal treatment regime can be a highly nonlinear function of patient information. Consequently, a focal point of recent methodological research has been the development of flexible models for estimating optimal treatment regimes. However, in many settings, estimation of an optimal treatment regime is an exploratory analysis intended to generate new hypotheses for subsequent research and not to directly dictate treatment to new patients. In such settings, an estimated treatment regime that is interpretable in a domain context may be of greater value than an unintelligible treatment regime built using 'black-box' estimation methods. We propose an estimator of an optimal treatment regime composed of a sequence of decision rules, each expressible as a list of "if-then" statements that can be presented as either a paragraph or as a simple flowchart that is immediately interpretable to domain experts. The discreteness of these lists precludes smooth, i.e., gradient-based, methods of estimation and leads to non-standard asymptotics. Nevertheless, we provide a computationally efficient estimation algorithm, prove consistency of the proposed estimator, and derive rates of convergence. We illustrate the proposed methods using a series of simulation examples and application to data from a sequential clinical trial on bipolar disorder.
| S-EPMC6373443 | biostudies-literature