Model Evaluation Based on the Distribution of Estimated Absolute Prediction Error

The construction of a reliable, practically useful prediction rule for future response is heavily dependent on the "adequacy" of the fitted regression model. In this article, we consider the absolute prediction error, the expected value of the absolute difference between the future and predicted responses, as the model evaluation criterion. This prediction error is easier to interpret than the average squared error and is equivalent to the mis-classification error for the binary outcome. We show that the distributions of the apparent error and its cross-validation counterparts are approximately normal even under a misspecified fitted model. When the prediction rule is "unsmooth", the variance of the above normal distribution can be estimated well via a perturbation-resampling method. We also show how to approximate the distribution of the difference of the estimated prediction errors from two competing models. With two real examples, we demonstrate that the resulting interval estimates for prediction errors provide much more information about model adequacy than the point estimates alone.

Inference on Survival Data with Covariate Measurement Error - An Imputation-based Approach

We propose a new method for fitting proportional hazards models with error-prone covariates. Regression coefficients are estimated by solving an estimating equation that is the average of the partial likelihood scores based on imputed true covariates. For the purpose of imputation, a linear spline model is assumed on the baseline hazard. We discuss consistency and asymptotic normality of the resulting estimators, and propose a stochastic approximation scheme to obtain the estimates. The algorithm is easy to implement, and reduces to the ordinary Cox partial likelihood approach when the measurement error has a degenerative distribution. Simulations indicate high efficiency and robustness. We consider the special case where error-prone replicates are available on the unobserved true covariates. As expected, increasing the number of replicate for the unobserved covariates increases efficiency and reduces bias. We illustrate the practical utility of the proposed method with an Eastern Cooperative Oncology Group clinical trial where a genetic marker, c-myc expression level, is subject to measurement error.

Soft tissue profile changes following mandibular advancement and setback surgery an average of 12 years postoperatively

PURPOSE: The aim of this study was to assess long-term changes in position of soft tissue landmarks following mandibular advancement and setback surgery. MATERIALS AND METHODS: Twenty-seven patients (14 women, 13 men; mean age, 36 years) who had undergone either mandibular advancement (15 patients) or setback surgery (12 patients), were available for a long-term follow-up an average of 12 years postoperatively. In all of these cases, lateral cephalometric radiographs taken immediately before operation, at 1 week, 14 months, and 12 years postoperatively, were studied. RESULTS: During the 14 months postoperatively, soft tissue chin and mentolabial fold followed its underlying hard tissue in all patients. A continuous skeletal relapse was observable 12 years after mandibular advancement, but soft tissue chin moved more in an anterior direction. After mandibular setback, soft and hard tissue landmarks remained almost unchanged. Over the entire observation period, a thickening of soft tissue at pogonion was generally seen, and particularly a thickening of the whole chin in the setback group. All patients showed a significant lengthening and thinning of the upper lip. In all except 2 males, the patient's body weight increased markedly. CONCLUSION: In contrast to the immediate postoperative stage, soft tissue changes observed an average of 12 years after the primary operation do not directly follow the movements of the underlying skeletal structure. The soft tissue profile changes observed over such a long term seem to be influenced not only by the underlying skeletal structure but also by other factors such as weight gain and aging process.

Cervical soft tissue imaging using a mobile CBCT scanner with a flat panel detector in comparison with corresponding CT and MRI data sets

OBJECTIVE: The aim of this study was to evaluate soft tissue image quality of a mobile cone-beam computed tomography (CBCT) scanner with an integrated flat-panel detector. STUDY DESIGN: Eight fresh human cadavers were used in this study. For evaluation of soft tissue visualization, CBCT data sets and corresponding computed tomography (CT) and magnetic resonance imaging (MRI) data sets were acquired. Evaluation was performed with the help of 10 defined cervical anatomical structures. RESULTS: The statistical analysis of the scoring results of 3 examiners revealed the CBCT images to be of inferior quality regarding the visualization of most of the predefined structures. Visualization without a significant difference was found regarding the demarcation of the vertebral bodies and the pyramidal cartilages, the arteriosclerosis of the carotids (compared with CT), and the laryngeal skeleton (compared with MRI). Regarding arteriosclerosis of the carotids compared with MRI, CBCT proved to be superior. CONCLUSIONS: The integration of a flat-panel detector improves soft tissue visualization using a mobile CBCT scanner.

Soft tissue dehiscence coverage around endosseous implants: a prospective cohort study

AIM: To evaluate the healing outcome of soft tissue dehiscence coverage at implant sites. MATERIAL AND METHODS: Ten patients with one mucosal recession defect at an implant site and a contralateral unrestored clinical crown without recession were recruited. The soft tissue recessions were surgically covered using a coronally advanced flap in combination with a free connective tissue graft. Healing was studied at 1, 3 and 6 months post-operatively. RESULTS: Soft tissue dehiscences were covered with a coronal overcompensation of the flap margin up to 1.2 mm after the procedure. After 1 month, the coverage shrank to a mean of 75%, after 3 months to 70% and after 6 months to 66%. CONCLUSIONS: The implant sites revealed a substantial, clinically significant improvement following coronal mucosal displacement in combination with connective tissue grafting, but in none of the sites, a could complete implant soft tissue dehiscence coverage be achieved.

Influence of suture tension to the tearing characteristics of the soft tissues: an in vitro experiment

OBJECTIVES: To evaluate the influence of flap tension on the tearing characteristics of mucosal tissue samples in relation to various suture and needle characteristics. MATERIAL AND METHODS: Lining and masticatory mucosal tissue samples obtained from pig jaws were prepared for in vitro testing. Tension tearing diagrams of 60 experiments were traced for 3-0, 5-0 and 7-0 sutures with applied forces up to 20 N. In the second part, the same experiments were repeated with 100 diagrams to test the influence of needle characteristics with 5-0 and 6-0 sutures using only gingival tissue samples. RESULTS: 3-0 sutures mainly lead to tissue breakage at an average of 13.4 N. In contrast, 7-0 sutures only resulted in breakage of the thread at a mean applied force of 3.7 N. With 5-0 sutures, both events occurred at random at a mean force of 14.6 N. Irrespective of the needle characteristics, the mean breaking force for gingival samples with 5-0 and 6-0 sutures was approximately 10 N. CONCLUSIONS: Tissue trauma may be reduced by choosing finer suture diameters, because thinner (6-0, 7-0) sutures lead to thread breakage rather than tissue breakage.