Bayesian doubly optimal group sequential designs for randomized clinical trials

When conducting a randomized comparative clinical trial, ethical, scientific or economic considerations often motivate the use of interim decision rules after successive groups of patients have been treated. These decisions may pertain to the comparative efficacy or safety of the treatments under study, cost considerations, the desire to accelerate the drug evaluation process, or the likelihood of therapeutic benefit for future patients. At the time of each interim decision, an important question is whether patient enrollment should continue or be terminated; either due to a high probability that one treatment is superior to the other, or a low probability that the experimental treatment will ultimately prove to be superior. The use of frequentist group sequential decision rules has become routine in the conduct of phase III clinical trials. In this dissertation, we will present a new Bayesian decision-theoretic approach to the problem of designing a randomized group sequential clinical trial, focusing on two-arm trials with time-to-failure outcomes. Forward simulation is used to obtain optimal decision boundaries for each of a set of possible models. At each interim analysis, we use Bayesian model selection to adaptively choose the model having the largest posterior probability of being correct, and we then make the interim decision based on the boundaries that are optimal under the chosen model. We provide a simulation study to compare this method, which we call Bayesian Doubly Optimal Group Sequential (BDOGS), to corresponding frequentist designs using either O'Brien-Fleming (OF) or Pocock boundaries, as obtained from EaSt 2000. Our simulation results show that, over a wide variety of different cases, BDOGS either performs at least as well as both OF and Pocock, or on average provides a much smaller trial. ^

Continuous safety screens for randomized controlled clinical trials with blinded treatment information

Standard methods for testing safety data are needed to ensure the safe conduct of clinical trials. In particular, objective rules for reliably identifying unsafe treatments need to be put into place to help protect patients from unnecessary harm. DMCs are uniquely qualified to evaluate accumulating unblinded data and make recommendations about the continuing safe conduct of a trial. However, it is the trial leadership who must make the tough ethical decision about stopping a trial, and they could benefit from objective statistical rules that help them judge the strength of evidence contained in the blinded data. We design early stopping rules for harm that act as continuous safety screens for randomized controlled clinical trials with blinded treatment information, which could be used by anyone, including trial investigators (and trial leadership). A Bayesian framework, with emphasis on the likelihood function, is used to allow for continuous monitoring without adjusting for multiple comparisons. Close collaboration between the statistician and the clinical investigators will be needed in order to design safety screens with good operating characteristics. Though the math underlying this procedure may be computationally intensive, implementation of the statistical rules will be easy and the continuous screening provided will give suitably early warning when real problems were to emerge. Trial investigators and trial leadership need these safety screens to help them to effectively monitor the ongoing safe conduct of clinical trials with blinded data.^

Selection bias and the cross-validation of regression models for prediction

Strategies are compared for the development of a linear regression model with stochastic (multivariate normal) regressor variables and the subsequent assessment of its predictive ability. Bias and mean squared error of four estimators of predictive performance are evaluated in simulated samples of 32 population correlation matrices. Models including all of the available predictors are compared with those obtained using selected subsets. The subset selection procedures investigated include two stopping rules, C$\sb{\rm p}$ and S$\sb{\rm p}$, each combined with an 'all possible subsets' or 'forward selection' of variables. The estimators of performance utilized include parametric (MSEP$\sb{\rm m}$) and non-parametric (PRESS) assessments in the entire sample, and two data splitting estimates restricted to a random or balanced (Snee's DUPLEX) 'validation' half sample. The simulations were performed as a designed experiment, with population correlation matrices representing a broad range of data structures.^ The techniques examined for subset selection do not generally result in improved predictions relative to the full model. Approaches using 'forward selection' result in slightly smaller prediction errors and less biased estimators of predictive accuracy than 'all possible subsets' approaches but no differences are detected between the performances of C$\sb{\rm p}$ and S$\sb{\rm p}$. In every case, prediction errors of models obtained by subset selection in either of the half splits exceed those obtained using all predictors and the entire sample.^ Only the random split estimator is conditionally (on $\\beta$) unbiased, however MSEP$\sb{\rm m}$ is unbiased on average and PRESS is nearly so in unselected (fixed form) models. When subset selection techniques are used, MSEP$\sb{\rm m}$ and PRESS always underestimate prediction errors, by as much as 27 percent (on average) in small samples. Despite their bias, the mean squared errors (MSE) of these estimators are at least 30 percent less than that of the unbiased random split estimator. The DUPLEX split estimator suffers from large MSE as well as bias, and seems of little value within the context of stochastic regressor variables.^ To maximize predictive accuracy while retaining a reliable estimate of that accuracy, it is recommended that the entire sample be used for model development, and a leave-one-out statistic (e.g. PRESS) be used for assessment. ^

Prediction of sepsis in the burn intensive care unit patient

Sepsis is a significant cause for multiple organ failure and death in the burn patient, yet identification in this population is confounded by chronic hypermetabolism and impaired immune function. The purpose of this study was twofold: 1) determine the ability of the systemic inflammatory response syndrome (SIRS) and American Burn Association (ABA) criteria to predict sepsis in the burn patient; and 2) develop a model representing the best combination of clinical predictors associated with sepsis in the same population. A retrospective, case-controlled, within-patient comparison of burn patients admitted to a single intensive care unit (ICU) was conducted for the period January 2005 to September 2010. Blood culture results were paired with clinical condition: "positive-sick"; "negative-sick", and "screening-not sick". Data were collected for the 72 hours prior to each blood culture. The most significant predictors were evaluated using logistic regression, Generalized Estimating Equations (GEE) and ROC area under the curve (AUC) analyses to assess model predictive ability. Bootstrapping methods were employed to evaluate potential model over-fitting. Fifty-nine subjects were included, representing 177 culture periods. SIRS criteria were not found to be associated with culture type, with an average of 98% of subjects meeting criteria in the 3 days prior. ABA sepsis criteria were significantly different among culture type only on the day prior (p = 0.004). The variables identified for the model included: heart rate>130 beats/min, mean blood pressure<60 mmHg, base deficit<-6 mEq/L, temperature>36°C, use of vasoactive medications, and glucose>150 mg/d1. The model was significant in predicting "positive culture-sick" and sepsis state, with AUC of 0.775 (p < 0.001) and 0.714 (p < .001), respectively; comparatively, the ABA criteria AUC was 0.619 (p = 0.028) and 0.597 (p = .035), respectively. SIRS criteria are not appropriate for identifying sepsis in the burn population. The ABA criteria perform better, but only for the day prior to positive blood culture results. The time period useful to diagnose sepsis using clinical criteria may be limited to 24 hours. A combination of predictors is superior to individual variable trends, yet algorithms or computer support will be necessary for the clinician to find such models useful. ^

Radiomics of NSCLC: Quantitative CT Image Feature Characterization and Tumor Shrinkage Prediction

Radiomics is the high-throughput extraction and analysis of quantitative image features. For non-small cell lung cancer (NSCLC) patients, radiomics can be applied to standard of care computed tomography (CT) images to improve tumor diagnosis, staging, and response assessment. The first objective of this work was to show that CT image features extracted from pre-treatment NSCLC tumors could be used to predict tumor shrinkage in response to therapy. This is important since tumor shrinkage is an important cancer treatment endpoint that is correlated with probability of disease progression and overall survival. Accurate prediction of tumor shrinkage could also lead to individually customized treatment plans. To accomplish this objective, 64 stage NSCLC patients with similar treatments were all imaged using the same CT scanner and protocol. Quantitative image features were extracted and principal component regression with simulated annealing subset selection was used to predict shrinkage. Cross validation and permutation tests were used to validate the results. The optimal model gave a strong correlation between the observed and predicted shrinkages with . The second objective of this work was to identify sets of NSCLC CT image features that are reproducible, non-redundant, and informative across multiple machines. Feature sets with these qualities are needed for NSCLC radiomics models to be robust to machine variation and spurious correlation. To accomplish this objective, test-retest CT image pairs were obtained from 56 NSCLC patients imaged on three CT machines from two institutions. For each machine, quantitative image features with concordance correlation coefficient values greater than 0.90 were considered reproducible. Multi-machine reproducible feature sets were created by taking the intersection of individual machine reproducible feature sets. Redundant features were removed through hierarchical clustering. The findings showed that image feature reproducibility and redundancy depended on both the CT machine and the CT image type (average cine 4D-CT imaging vs. end-exhale cine 4D-CT imaging vs. helical inspiratory breath-hold 3D CT). For each image type, a set of cross-machine reproducible, non-redundant, and informative image features was identified. Compared to end-exhale 4D-CT and breath-hold 3D-CT, average 4D-CT derived image features showed superior multi-machine reproducibility and are the best candidates for clinical correlation.

Artificial metaplasticity prediction model for cognitive rehabilitation outcome in acquired brain injury patients

Objective The main purpose of this research is the novel use of artificial metaplasticity on multilayer perceptron (AMMLP) as a data mining tool for prediction the outcome of patients with acquired brain injury (ABI) after cognitive rehabilitation. The final goal aims at increasing knowledge in the field of rehabilitation theory based on cognitive affectation. Methods and materials The data set used in this study contains records belonging to 123 ABI patients with moderate to severe cognitive affectation (according to Glasgow Coma Scale) that underwent rehabilitation at Institut Guttmann Neurorehabilitation Hospital (IG) using the tele-rehabilitation platform PREVIRNEC©. The variables included in the analysis comprise the neuropsychological initial evaluation of the patient (cognitive affectation profile), the results of the rehabilitation tasks performed by the patient in PREVIRNEC© and the outcome of the patient after a 3–5 months treatment. To achieve the treatment outcome prediction, we apply and compare three different data mining techniques: the AMMLP model, a backpropagation neural network (BPNN) and a C4.5 decision tree. Results The prediction performance of the models was measured by ten-fold cross validation and several architectures were tested. The results obtained by the AMMLP model are clearly superior, with an average predictive performance of 91.56%. BPNN and C4.5 models have a prediction average accuracy of 80.18% and 89.91% respectively. The best single AMMLP model provided a specificity of 92.38%, a sensitivity of 91.76% and a prediction accuracy of 92.07%. Conclusions The proposed prediction model presented in this study allows to increase the knowledge about the contributing factors of an ABI patient recovery and to estimate treatment efficacy in individual patients. The ability to predict treatment outcomes may provide new insights toward improving effectiveness and creating personalized therapeutic interventions based on clinical evidence.

EPA-0882 - Prediction of diagnosis of early-onset schizophrenia spectrum disorders using support vector machines

To develop a Support Vector Machine (SVM) algorithm as a predictive tool for diagnostic outcome in patients with FE-EOP, based on clinical and biomedical data at the emergence of the illness.

Prediction of the stability of DNA triplexes.

We present rules that allow one to predict the stability of DNA pyrimidine.purine.pyrimidine (Y.R.Y) triple helices on the basis of the sequence. The rules were derived from van't Hoff analysis of 23 oligonucleotide triplexes tested at a variety of pH values. To predict the enthalpy of triplex formation (delta H degrees), a simple nearest-neighbor model was found to be sufficient. However, to accurately predict the free energy of the triplex (delta G degrees), a combination model consisting of five parameters was needed. These parameters were (i) the delta G degrees for helix initiation, (ii) the delta G degrees for adding a T-A.T triple, (iii) the delta G degrees for adding a C(+)-G.C triple, (iv) the penalty for adjacent C bases, and (v) the pH dependence of the C(+)-G.C triple's stability. The fitted parameters are highly consistent with thermodynamic data from the basis set, generally predicting both delta H degrees and delta G degrees to within the experimental error. Examination of the parameters points out several interesting features. The combination model predicts that C(+) -G.C. triples are much more stabilizing than T-A.T triples below pH 7.0 and that the stability of the former increases approximately equal to 1 kcal/mol per pH unit as the pH is decreased. Surprisingly though, the most stable sequence is predicted to be a CT repeat, as adjacent C bases partially cancel the stability of one another. The parameters successfully predict tm values from other laboratories, with some interesting exceptions.

Description and Prediction of Freezing of Gait in Parkinson's Disease from Wearable Inertial Measurements Units

Parkinson's disease (PD) is a neuro-degenerative disorder, the second most common after Alzheimer's disease. After diagnosis, treatments can help to relieve the symptoms, but there is no known cure for PD. PD is characterized by a combination of motor and no-motor dysfunctions. Among the motor symptoms there is the so called Freezing of Gait (FoG). The FoG is a phenomenon in PD patients in which the feet stock to the floor and is difficult for the patient to initiate movement. FoG is a severe problem, since it is associated with falls, anxiety, loss of mobility, accidents, mortality and it has substantial clinical and social consequences decreasing the quality of life in PD patients. Medicine can be very successful in controlling movements disorders and dealing with some of the PD symptoms. However, the relationship between medication and the development of FoG remains unclear. Several studies have demonstrated that visual or auditory rhythmical cuing allows PD patients to improve their motor abilities. Rhythmic auditory stimulation (RAS) was shown to be particularly effective at improving gait, specially with patients that manifest FoG. While RAS allows to reduce the time and the effects of FoGs occurrence in PD patients after the FoG is detected, it can not avoid the episode due to the latency of detection. An improvement of the system would be the prediction of the FoG. This thesis was developed following two main objectives: (1) the finding of specifics properties during pre FoG periods different from normal walking context and other walking events like turns and stops using the information provided by the inertial measurements units (IMUs) and (2) the formulation of a model for automatically detect the pre FoG patterns in order to completely avoid the upcoming freezing event in PD patients. The first part focuses on the analysis of different methods for feature extraction which might lead in the FoG occurrence.

Precision medicine in patients with allergic diseases: Airway diseases and atopic dermatitis-PRACTALL document of the European Academy of Allergy and Clinical Immunology and the American Academy of Allergy, Asthma & Immunology

In this consensus document we summarize the current knowledge on major asthma, rhinitis, and atopic dermatitis endotypes under the auspices of the PRACTALL collaboration platform. PRACTALL is an initiative of the European Academy of Allergy and Clinical Immunology and the American Academy of Allergy, Asthma & Immunology aiming to harmonize the European and American approaches to best allergy practice and science. Precision medicine is of broad relevance for the management of asthma, rhinitis, and atopic dermatitis in the context of a better selection of treatment responders, risk prediction, and design of disease-modifying strategies. Progress has been made in profiling the type 2 immune response-driven asthma. The endotype driven approach for non-type 2 immune response asthma, rhinitis, and atopic dermatitis is lagging behind. Validation and qualification of biomarkers are needed to facilitate their translation into pathway-specific diagnostic tests. Wide consensus between academia, governmental regulators, and industry for further development and application of precision medicine in management of allergic diseases is of utmost importance. Improved knowledge of disease pathogenesis together with defining validated and qualified biomarkers are key approaches to precision medicine.

Contribution of Genetic Background and Clinical Risk Factors to Low-Trauma Fractures in Human Immunodeficiency Virus (HIV)-Positive Persons: The Swiss HIV Cohort Study.

Background.  The impact of human genetic background on low-trauma fracture (LTF) risk has not been evaluated in the context of human immunodeficiency virus (HIV) and clinical LTF risk factors. Methods.  In the general population, 6 common single-nucleotide polymorphisms (SNPs) associate with LTF through genome-wide association study. Using genome-wide SNP arrays and imputation, we genotyped these SNPs in HIV-positive, white Swiss HIV Cohort Study participants. We included 103 individuals with a first, physician-validated LTF and 206 controls matched on gender, whose duration of observation and whose antiretroviral therapy start dates were similar using incidence density sampling. Analyses of nongenetic LTF risk factors were based on 158 cases and 788 controls. Results.  A genetic risk score built from the 6 LTF-associated SNPs did not associate with LTF risk, in both models including and not including parental hip fracture history. The contribution of clinical LTF risk factors was limited in our dataset. Conclusions.  Genetic LTF markers with a modest effect size in the general population do not improve fracture prediction in persons with HIV, in whom clinical LTF risk factors are prevalent in both cases and controls.

Toward better outcomes with tacrolimus therapy: Population pharmacokinetics and individualized dosage prediction in adult liver transplantation

Patient outcomes in transplantation would improve if dosing of immunosuppressive agents was individualized. The aim of this study is to develop a population pharmacokinetic model of tacrolimus in adult liver transplant recipients and test this model in individualizing therapy. Population analysis was performed on data from 68 patients. Estimates were sought for apparent clearance (CL/F) and apparent volume of distribution (V/F) using the nonlinear mixed effects model program (NONMEM). Factors screened for influence on these parameters were weight, age, sex, transplant type, biliary reconstructive procedure, postoperative day, days of therapy, liver function test results, creatinine clearance, hematocrit, corticosteroid dose, and interacting drugs. The predictive performance of the developed model was evaluated through Bayesian forecasting in an independent cohort of 36 patients. No linear correlation existed between tacrolimus dosage and trough concentration (r(2) = 0.005). Mean individual Bayesian estimates for CL/F and V/F were 26.5 8.2 (SD) L/hr and 399 +/- 185 L, respectively. CL/F was greater in patients with normal liver function. V/F increased with patient weight. CL/F decreased with increasing hematocrit. Based on the derived model, a 70-kg patient with an aspartate aminotransferase (AST) level less than 70 U/L would require a tacrolimus dose of 4.7 mg twice daily to achieve a steady-state trough concentration of 10 ng/mL. A 50-kg patient with an AST level greater than 70 U/L would require a dose of 2.6 mg. Marked interindividual variability (43% to 93%) and residual random error (3.3 ng/mL) were observed. Predictions made using the final model were reasonably nonbiased (0.56 ng/mL), but imprecise (4.8 ng/mL). Pharmacokinetic information obtained will assist in tacrolimus dosing; however, further investigation into reasons for the pharmacokinetic variability of tacrolimus is required.

Structural basis and prediction of substrate specificity in protein serine/threonine kinases

The large number of protein kinases makes it impractical to determine their specificities and substrates experimentally. Using the available crystal structures, molecular modeling, and sequence analyses of kinases and substrates, we developed a set of rules governing the binding of a heptapeptide substrate motif (surrounding the phosphorylation site) to the kinase and implemented these rules in a web-interfaced program for automated prediction of optimal substrate peptides, taking only the amino acid sequence of a protein kinase as input. We show the utility of the method by analyzing yeast cell cycle control and DNA damage checkpoint pathways. Our method is the only available predictive method generally applicable for identifying possible substrate proteins for protein serine/threonine kinases and helps in silico construction of signaling pathways. The accuracy of prediction is comparable to the accuracy of data from systematic large-scale experimental approaches.

A clinical and echocardiographic score for assigning risk of major events after dobutamine echocardiograms

OBJECTIVES We sought to develop and validate a risk score combining both clinical and dobutamine echocardiographic (DbE) features in 4,890 patients who underwent DbE at three expert laboratories and were followed for death or myocardial infarction for up to five years. BACKGROUND In contrast to exercise scores, no score exists to combine clinical, stress, and echocardiographic findings with DbE. METHODS Dobutamine echocardiography was performed for evaluation of known or suspected coronary artery disease in 3,156 patients at two sites in the U.S. After exclusion of patients with incomplete follow-up, 1,456 DbEs were randomly selected to develop a multivariate model for prediction of events. After simplification of each model for clinical use, the models were internally validated in the remaining DbE patients in the same series and externally validated in 1,733 patients in an independent series. RESULTS The following score was derived from regression models in the modeling group (160 events): DbE risk = (age (.) 0.02) + (heart failure + rate-pressure product <15,000) (.) 0.4 + (ischemia + scar) (.) 0.6. The presence of each variable was scored as 1 and its absence scored as 0, except for age (continuous variable). Using cutoff values of 1.2 and 2.6, patients were classified into groups with five-year event-free survivals >95%, 75% to 95%, and <75%. Application of the score in the internal validation group (265 events) gave equivalent results, as did its application in the external validation group (494 events, C index = 0.72). CONCLUSIONS A risk score based on clinical and echocardiographic data may be used to quantify the risk of events in patients undergoing DbE. (C) 2004 by the American College of Cardiology Foundation.