Metaparametric Neural Networks for Survival Analysis.

Survival analysis is a critical tool for the modeling of time-to-event data, such as life expectancy after a cancer diagnosis or optimal maintenance scheduling for complex machinery. However, current neural network models provide an imperfect solution for survival analysis as they either restrict the shape of the target probability distribution or restrict the estimation to predetermined times. As a consequence, current survival neural networks lack the ability to estimate a generic function without prior knowledge of its structure. In this article, we present the metaparametric neural network framework that encompasses the existing survival analysis methods and enables their extension to solve the aforementioned issues. This framework allows survival neural networks to satisfy the same independence of generic function estimation from the underlying data structure that characterizes their regression and classification counterparts. Furthermore, we demonstrate the application of the metaparametric framework using both simulated and large real-world datasets and show that it outperforms the current state-of-the-art methods in: 1) capturing nonlinearities and 2) identifying temporal patterns, leading to more accurate overall estimations while placing no restrictions on the underlying function structure.

Personalized estimation of one-year mortality risk after elective hip or knee arthroplasty for osteoarthritis.

AIMS: To develop and validate patient-centred algorithms that estimate individual risk of death over the first year after elective joint arthroplasty surgery for osteoarthritis. METHODS: A total of 763,213 hip and knee joint arthroplasty episodes recorded in the National Joint Registry for England and Wales (NJR) and 105,407 episodes from the Norwegian Arthroplasty Register were used to model individual mortality risk over the first year after surgery using flexible parametric survival regression. RESULTS: The one-year mortality rates in the NJR were 10.8 and 8.9 per 1,000 patient-years after hip and knee arthroplasty, respectively. The Norwegian mortality rates were 9.1 and 6.0 per 1,000 patient-years, respectively. The strongest predictors of death in the final models were age, sex, body mass index, and American Society of Anesthesiologists grade. Exposure variables related to the intervention, with the exception of knee arthroplasty type, did not add discrimination over patient factors alone. Discrimination was good in both cohorts, with c-indices above 0.76 for the hip and above 0.70 for the knee. Time-dependent Brier scores indicated appropriate estimation of the mortality rate (≤ 0.01, all models). CONCLUSION: Simple demographic and clinical information may be used to calculate an individualized estimation for one-year mortality risk after hip or knee arthroplasty (https://jointcalc.shef.ac.uk). These models may be used to provide patients with an estimate of the risk of mortality after joint arthroplasty. Cite this article: Bone Joint Res 2020;9(11):808-820.

Bone remodelling in the mouse tibia is spatio-temporally modulated by oestrogen deficiency and external mechanical loading: A combined in vivo/in silico study.

Osteoporosis disrupts the healthy remodelling process in bone and affects its mechanical properties. Mechanical loading has been shown to be effective in stimulating bone formation to mitigate initial bone loss. However, no study has investigated the effects of repeated mechanical loading, with a pause of one week in between, in the mouse tibia with oestrogen deficiency. This study uses a combined experimental and computational approach, through longitudinal monitoring with micro-computed tomography, to evaluate the effects of loading on bone adaptation in the tibiae of ovariectomised (OVX) C57BL/6 mice from 14 to 22 weeks of age. Micro-FE models coupled with bone adaptation algorithms were used to estimate changes in local tissue strains due to OVX and mechanical loading, and to quantify the relationship between local strain and remodelling. The first in vivo mechanical loading increased apposition, by 50-150%, while resorption decreased by 50-60%. Both endosteal and periosteal resorption increased despite the second mechanical loading, and periosteal resorption was up to 70% higher than that after the first loading. This was found to correlate with an initial decrease in average strain energy density after the first loading, which was lower and more localised after the second loading. Predictions of bone adaptation showed that between 50 and 90% of the load-induced bone apposition is linearly strain driven at the organ-level, but resorption is more biologically driven at the local level. The results imply that a systematic increase in peak load or loading rate may be required to achieve a similar bone adaptation rate in specific regions of interests.

Estimating an Individual's Probability of Revision Surgery After Knee Replacement: A Comparison of Modeling Approaches Using a National Data Set.

Tools that provide personalized risk prediction of outcomes after surgical procedures help patients make preference-based decisions among the available treatment options. However, it is unclear which modeling approach provides the most accurate risk estimation. We constructed and compared several parametric and nonparametric models for predicting prosthesis survivorship after knee replacement surgery for osteoarthritis. We used 430,455 patient-procedure episodes between April 2003 and September 2015 from the National Joint Registry for England, Wales, Northern Ireland, and the Isle of Man. The flexible parametric survival and random survival forest models most accurately captured the observed probability of remaining event-free. The concordance index for the flexible parametric model was the highest (0.705, 95% confidence interval (CI): 0.702, 0.707) for total knee replacement and was 0.639 (95% CI: 0.634, 0.643) for unicondylar knee replacement and 0.589 (95% CI: 0.586, 0.592) for patellofemoral replacement. The observed-to-predicted ratios for both the flexible parametric and the random survival forest approaches indicated that models tended to underestimate the risks for most risk groups. Our results show that the flexible parametric model has a better overall performance compared with other tested parametric methods and has better discrimination compared with the random survival forest approach.

Lead optimization using matched molecular pairs: inclusion of contextual information for enhanced prediction of HERG inhibition, solubility, and lipophilicity.

Previous studies of the analysis of molecular matched pairs (MMPs) have often assumed that the effect of a substructural transformation on a molecular property is independent of the context (i.e., the local structural environment in which that transformation occurs). Experiments with large sets of hERG, solubility, and lipophilicity data demonstrate that the inclusion of contextual information can enhance the predictive power of MMP analyses, with significant trends (both positive and negative) being identified that are not apparent when using conventional, context-independent approaches.

Prepatterning in the stem cell compartment.

The mechanism by which an apparently uniform population of cells can generate a heterogeneous population of differentiated derivatives is a fundamental aspect of pluripotent and multipotent stem cell behaviour. One possibility is that the environment and the differentiation cues to which the cells are exposed are not uniform. An alternative, but not mutually exclusive possibility is that the observed heterogeneity arises from the stem cells themselves through the existence of different interconvertible substates that pre-exist before the cells commit to differentiate. We have tested this hypothesis in the case of apparently homogeneous pluripotent human embryonal carcinoma (EC) stem cells, which do not follow a uniform pattern of differentiation when exposed to retinoic acid. Instead, they produce differentiated progeny that include both neuronal and non-neural phenotypes. Our results suggest that pluripotent NTERA2 stem cells oscillate between functionally distinct substates that are primed to select distinct lineages when differentiation is induced.