暂无摘要。

Decision tree (DT) models provide a transparent approach to prediction of patient\'s outcomes within a probabilistic framework. Averaging over DT models under certain conditions can deliver reliable estimates of predictive posterior probability distributions, which is of critical importance in the case of predicting an individual patient\'s outcome. Reliable estimations of the distribution can be achieved within the Bayesian framework using Markov chain Monte Carlo (MCMC) and its Reversible Jump extension enabling DT models to grow to a reasonable size. Existing MCMC strategies however have limited ability to control DT structures and tend to sample overgrown DT models, making unreasonably small partitions, thus deteriorating the uncertainty calibration. This happens because the MCMC explores a DT model parameter space within a limited knowledge of the distribution of data partitions. We propose a new adaptive strategy which overcomes this limitation, and show that in the case of predicting trauma outcomes the number of data partitions can be significantly reduced, so that the unnecessary uncertainty of estimating the predictive posterior density is avoided. The proposed and existing strategies are compared in terms of entropy which, being calculated for predicted posterior distributions, represents the uncertainty in decisions. In this framework, the proposed method has outperformed the existing sampling strategies, so that the unnecessary uncertainty in decisions is efficiently avoided.

Traumatic brain injury (TBI) poses a particular health risk for the elderly. The recently developed elderly TBI (eTBI) score combines the prognostic information of the risk factors characteristic of the geriatric population. We aimed to determine its validity and reliability on an independent sample.
We present a retrospective analysis of 506 consecutive patients after TBI aged ≥65 years. The previously described nomogram and the eTBI score were used. The primary outcome measure was mortality or vegetative state at 30 days after hospital admission.
Mortality or vegetative state rate was 21.3%. The nomogram and eTBI Score showed similar predictive performance with accuracy of 83.8% (95% confidence interval 80.2%-87%) and 84.4% (95% confidence interval 80.8%-87.6%), respectively. On the basis of the Youden index and C4.5 algorithm, we divided patients according to the 3-tier pattern into low-, high-, and medium-risk groups. The outcome prediction in the first 2 groups was correct in 93.1% (survival in the low-risk group) and 94.4% (mortality in the high-risk group). Patients included in the medium-risk group usually required surgical treatment (85.3%) and were characterized by increased mortality or vegetative state (55%). Among patients with eTBI ≥5 (n = 221), there was no difference in outcome between those treated conservatively and surgically.
This is the first study confirming the validity of the eTBI Score and its close association with outcome of geriatric population after TBI. The novel 3-tier risk stratification scheme was applicable to both conservatively and surgically treated patients.