Jaakko Riihimäki

Risk of recurrence of gastrointestinal stromal tumour after surgery: an analysis of pooled population-based cohorts.

BACKGROUND The risk of recurrence of gastrointestinal stromal tumour (GIST) after surgery needs to be estimated when considering adjuvant systemic therapy. We assessed prognostic factors of patients with operable GIST, to compare widely used risk-stratification schemes and to develop a new method for risk estimation. METHODS Population-based cohorts of patients diagnosed with operable GIST, who were not given adjuvant therapy, were identified from the literature. Data from ten series and 2560 patients were pooled. Risk of tumour recurrence was stratified using the National Institute of Health (NIH) consensus criteria, the modified consensus criteria, and the Armed Forces Institute of Pathology (AFIP) criteria. Prognostic factors were examined using proportional hazards and non-linear models. The results were validated in an independent centre-based cohort consisting of 920 patients with GIST. FINDINGS Estimated 15-year recurrence-free survival (RFS) after surgery was 59·9% (95% CI 56·2-63·6); few recurrences occurred after the first 10 years of follow-up. Large tumour size, high mitosis count, non-gastric location, presence of rupture, and male sex were independent adverse prognostic factors. In receiver operating characteristics curve analysis of 10-year RFS, the NIH consensus criteria, modified consensus criteria, and AFIP criteria resulted in an area under the curve (AUC) of 0·79 (95% CI 0·76-0·81), 0·78 (0·75-0·80), and 0·82 (0·80-0·85), respectively. The modified consensus criteria identified a single high-risk group. Since tumour size and mitosis count had a non-linear association with the risk of GIST recurrence, novel prognostic contour maps were generated using non-linear modelling of tumour size and mitosis count, and taking into account tumour site and rupture. The non-linear model accurately predicted the risk of recurrence (AUC 0·88, 0·86-0·90). INTERPRETATION The risk-stratification schemes assessed identify patients who are likely to be cured by surgery alone. Although the modified NIH classification is the best criteria to identify a single high-risk group for consideration of adjuvant therapy, the prognostic contour maps resulting from non-linear modelling are appropriate for estimation of individualised outcomes. FUNDING Academy of Finland, Cancer Society of Finland, Sigrid Juselius Foundation and Helsinki University Research Funds.

Modeling the length of the care episode after hip fracture: does the type of fracture Matter?

Background and Aims: Hip fractures are common events that require intensive operative hospital care and a lengthy rehabilitation. The effect of hip fracture type on successful rehabilitation is not well known. The aim of this study is to model and compare the length of the care episodes between intra- and extracapsular hip fractures in Finland. Material and Methods: 15544 hip fracture patients living at home in Finland 1998–2001 were followed using register-based data. Patient characteristics, outcomes, and length of stay (LOS) distributions were analyzed using a Bayesian nonparametric multilayer perceptron (MLP) network model. Results: Mortality was similar in intra- and extracapsular hip fractures. Patients were more likely to need long-term care after extracapsular hip fracture. The average LOS at the surgical ward was similar for intra- and extracapsular fractures (1.7 weeks), but there was a considerable difference for the total inpatient LOS between the groups (5.2 weeks vs. 6.9 weeks). Intracapsular fractures had a simple unimodal LOS distribution, whereas the LOS distribution for the extracapsular fractures was multimodal with two clear peaks. Patients with more comorbidities required a longer LOS. Conclusions: The causes for differences in LOS between fracture types were most likely due to the different surgical methods and rehabilitation practices for the fracture types. As national guidelines suggest similar rehabilitation for all hip fracture patients, there is a need for early and aggressive rehabilitation of patients with extracapsular fractures, including full-weight bearing for all but selected patients.

Laplace Approximation for Logistic Gaussian Process Density Estimation and Regression

Logistic Gaussian process (LGP) priors provide a flexible alternative for modelling unknown densities. The smoothness properties of the density estimates can be controlled through the prior covariance structure of the LGP, but the challenge is the analytically intractable inference. In this paper, we present approximate Bayesian inference for LGP density estimation in a grid using Laplaces method to integrate over the non-Gaussian posterior distribution of latent function values and to determine the covariance function parameters with type-II maximum a posteriori (MAP) estimation. We demonstrate that Laplaces method with MAP is sufficiently fast for practical interactive visualisation of 1D and 2D densities. Our experiments with simulated and real 1D data sets show that the estimation accuracy is close to a Markov chain Monte Carlo approximation and state-of-the-art hierarchical infinite Gaussian mixture models. We also construct a reduced-rank approximation to speed up the computations for dense 2D grids, and demonstrate density regression with the proposed Laplace approach.

A Connection between Extreme Learning Machine and Neural Network Kernel

We study a connection between extreme learning machine (ELM) and neural network kernel (NNK). NNK is derived from a neural network with an infinite number of hidden units. We interpret ELM as an approximation to this infinite network. We show that ELM and NNK can, to certain extent, replace each other. ELM can be used to form a kernel, and NNK can be decomposed into feature vectors to be used in the hidden layer of ELM. The connection reveals possible importance of weight variance as a parameter of ELM. Based on our experiments, we recommend that model selection on ELM should consider not only the number of hidden units, as is the current practice, but also the variance of weights. We also study the interaction of variance and the number of hidden units, and discuss some properties of ELM, that may have been too strongly interpreted previously.

Sparse Spatio-temporal Gaussian processes with general likelihoods

In this paper, we consider learning of spatio-temporal processes by formulating a Gaussian process model as a solution to an evolution type stochastic partial differential equation. Our approach is based on converting the stochastic infinite-dimensional differential equation into a finite dimensional linear time invariant (LTI) stochastic differential equation (SDE) by discretizing the process spatially. The LTI SDE is time-discretized analytically, resulting in a state space model with linear-Gaussian dynamics. We use expectation propagation to perform approximate inference on non-Gaussian data, and show how to incorporate sparse approximations to further reduce the computational complexity. We briefly illustrate the proposed methodology with a simulation study and with a real world modelling problem.