Dataset Information

Evaluation of the Effect of a Continuous Treatment: A Machine Learning Approach with an Application to Treatment for Traumatic Brain Injury.

ABSTRACT: For a continuous treatment, the generalised propensity score (GPS) is defined as the conditional density of the treatment, given covariates. GPS adjustment may be implemented by including it as a covariate in an outcome regression. Here, the unbiased estimation of the dose-response function assumes correct specification of both the GPS and the outcome-treatment relationship. This paper introduces a machine learning method, the 'Super Learner', to address model selection in this context. In the two-stage estimation approach proposed, the Super Learner selects a GPS and then a dose-response function conditional on the GPS, as the convex combination of candidate prediction algorithms. We compare this approach with parametric implementations of the GPS and to regression methods. We contrast the methods in the Risk Adjustment in Neurocritical care cohort study, in which we estimate the marginal effects of increasing transfer time from emergency departments to specialised neuroscience centres, for patients with acute traumatic brain injury. With parametric models for the outcome, we find that dose-response curves differ according to choice of specification. With the Super Learner approach to both regression and the GPS, we find that transfer time does not have a statistically significant marginal effect on the outcomes.

SUBMITTER: Kreif N

PROVIDER: S-EPMC4744663 | biostudies-literature | 2015 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Evaluation of the Effect of a Continuous Treatment: A Machine Learning Approach with an Application to Treatment for Traumatic Brain Injury.

Kreif Noémi N Grieve Richard R Díaz Iván I Harrison David D

Health economics 20150608 9

For a continuous treatment, the generalised propensity score (GPS) is defined as the conditional density of the treatment, given covariates. GPS adjustment may be implemented by including it as a covariate in an outcome regression. Here, the unbiased estimation of the dose-response function assumes correct specification of both the GPS and the outcome-treatment relationship. This paper introduces a machine learning method, the 'Super Learner', to address model selection in this context. In the t ...[more]

PMID: 26059721

Similar Datasets

Project description:Background: Traumatic brain injury-induced coagulopathy (TBI-IC), is a disease with poor prognosis and increased mortality rate. Objectives: Our study aimed to identify predictors as well as develop machine learning (ML) models to predict the risk of coagulopathy in this population. Methods: ML 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). Candidate predictors, including demographics, family history, comorbidities, vital signs, laboratory findings, injury type, therapy strategy and scoring system were included. Models were compared on area under the curve (AUC), accuracy, sensitivity, specificity, positive and negative predictive values, and decision curve analysis (DCA) curve. Results: Of 999 patients in MIMIC-IV included in the final cohort, a total of 493 (49.35%) patients developed coagulopathy following TBI. Recursive feature elimination (RFE) selected 15 variables, including international normalized ratio (INR), prothrombin time (PT), sepsis related organ failure assessment (SOFA), activated partial thromboplastin time (APTT), platelet (PLT), hematocrit (HCT), red blood cell (RBC), hemoglobin (HGB), blood urea nitrogen (BUN), red blood cell volume distribution width (RDW), creatinine (CRE), congestive heart failure, myocardial infarction, sodium, and blood transfusion. The external validation in eICU-CRD demonstrated that adapting boosting (Ada) model had the highest AUC of 0.924 (95% CI: 0.902-0.943). Furthermore, in the DCA curve, the Ada model and the extreme Gradient Boosting (XGB) model had relatively higher net benefits (ie, the correct classification of coagulopathy considering a trade-off between false- negatives and false-positives)-over other models across a range of threshold probability values. Conclusions: The ML models, as indicated by our study, can be used to predict the incidence of TBI-IC in the intensive care unit (ICU).

Project description:Self-reported complaints are common after mild traumatic brain injury (mTBI). Particularly in the elderly with mTBI, the pre-injury status might play a relevant role in the recovery process. In most mTBI studies, however, pre-injury complaints are neither analyzed nor are the elderly included. Here, we aimed to identify which individual pre- and post-injury complaints are potential prognostic markers for incomplete recovery (IR) in elderly patients who sustained an mTBI. Since patients report many complaints across several domains that are strongly related, we used an interpretable machine learning (ML) approach to robustly deal with correlated predictors and boost classification performance. Pre- and post-injury levels of 20 individual complaints, as self-reported in the acute phase, were analyzed. We used data from two independent studies separately: UPFRONT study was used for training and validation and ReCONNECT study for independent testing. Functional outcome was assessed with the Glasgow Outcome Scale Extended (GOSE). We dichotomized functional outcome into complete recovery (CR; GOSE = 8) and IR (GOSE ≤ 7). In total 148 elderly with mTBI (median age: 67 years, interquartile range [IQR]: 9 years; UPFRONT: N = 115; ReCONNECT: N = 33) were included in this study. IR was observed in 74 (50%) patients. The classification model (IR vs. CR) achieved a good performance (the area under the receiver operating characteristic curve [ROC-AUC] = 0.80; 95% CI: 0.74-0.86) based on a subset of only 8 out of 40 pre- and post-injury complaints. We identified increased neck pain (p = 0.001) from pre- to post-injury as the strongest predictor of IR, followed by increased irritability (p = 0.011) and increased forgetfulness (p = 0.035) from pre- to post-injury. Our findings indicate that a subset of pre- and post-injury physical, emotional, and cognitive complaints has predictive value for determining long-term functional outcomes in elderly patients with mTBI. Particularly, post-injury neck pain, irritability, and forgetfulness scores were associated with IR and should be assessed early. The application of an ML approach holds promise for application in self-reported questionnaires to predict outcomes after mTBI.

Project description:ObjectivesAfter traumatic brain injury, continuous electroencephalography is widely used to detect electrographic seizures. With the development of standardized continuous electroencephalography terminology, we aimed to describe the prevalence and burden of ictal-interictal patterns, including electrographic seizures after moderate-to-severe traumatic brain injury and to correlate continuous electroencephalography features with functional outcome.DesignPost hoc analysis of the prospective, randomized controlled phase 2 multicenter INTREPID study (ClinicalTrials.gov: NCT00805818). Continuous electroencephalography was initiated upon admission to the ICU. The primary outcome was the 3-month Glasgow Outcome Scale-Extended. Consensus electroencephalography reviews were performed by raters certified in standardized continuous electroencephalography terminology blinded to clinical data. Rhythmic, periodic, or ictal patterns were referred to as "ictal-interictal continuum"; severe ictal-interictal continuum was defined as greater than or equal to 1.5 Hz lateralized rhythmic delta activity or generalized periodic discharges and any lateralized periodic discharges or electrographic seizures.SettingTwenty U.S. level I trauma centers.PatientsPatients with nonpenetrating traumatic brain injury and postresuscitation Glasgow Coma Scale score of 4-12 were included.InterventionsNone.Measurements and main resultsAmong 152 patients with continuous electroencephalography (age 34 ± 14 yr; 88% male), 22 (14%) had severe ictal-interictal continuum including electrographic seizures in four (2.6%). Severe ictal-interictal continuum burden correlated with initial prognostic scores, including the International Mission for Prognosis and Analysis of Clinical Trials in Traumatic Brain Injury (r = 0.51; p = 0.01) and Injury Severity Score (r = 0.49; p = 0.01), but not with functional outcome. After controlling clinical covariates, unfavorable outcome was independently associated with absence of posterior dominant rhythm (common odds ratio, 3.38; 95% CI, 1.30-9.09), absence of N2 sleep transients (3.69; 1.69-8.20), predominant delta activity (2.82; 1.32-6.10), and discontinuous background (5.33; 2.28-12.96) within the first 72 hours of monitoring.ConclusionsSevere ictal-interictal continuum patterns, including electrographic seizures, were associated with clinical markers of injury severity but not functional outcome in this prospective cohort of patients with moderate-to-severe traumatic brain injury. Importantly, continuous electroencephalography background features were independently associated with functional outcome and improved the area under the curve of existing, validated predictive models.

Dataset Information

Evaluation of the Effect of a Continuous Treatment: A Machine Learning Approach with an Application to Treatment for Traumatic Brain Injury.

Publications

Evaluation of the Effect of a Continuous Treatment: A Machine Learning Approach with an Application to Treatment for Traumatic Brain Injury.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets