arXiv subjects

Sandra Ortega-Martorell

Publications and source records attributed to Sandra Ortega-Martorell.

5 recordsLinked to original sources

arXiv2026

Translation of Black-Box Clinical Prediction Models into Standalone Transparent Nomograms: Temporal External Validation in Heart Transplantation

We convert black-box clinical prediction models for tabular data into standalone nomograms that can be audited term by term. PRiSM (Partial Responses in Structured Models) takes the shape of each effect and interaction from the source model, not merely which variables mattered, and lets the outcome select and weight them. We tested this in 50,356 heart transplant recipients, with validation in a later era than training. Nomograms from all 5 source models - a public clinical risk score, logistic regression, neural networks, random forests and extreme gradient boosting - met a prespecified noninferiority criterion for discrimination before any further simplification, and generally preserved calibration and clinical net benefit. Those from the 3 machine-learning models showed no detectable difference in discrimination from de novo generalized additive and explainable boosting models, exceeded neural additive models, and carried fewer terms than the explainable boosting model. PRiSM is released as an open-source Python package.

cs.LG↗

arXiv2026

Optimized HDBSCAN clustering for reconstructing the merger history of the Milky Way: applications and limitations

Clustering algorithms can help reconstruct the assembly history of the Milky Way by identifying groups of stars sharing similar properties in a kinematical or chemical abundance space. Despite being promising tools, their efficiency has not yet been fully tested in a realistic cosmological framework. We investigate the effectiveness of the HDBSCAN clustering algorithm in the recovery of the progenitors of Milky Way-type galaxies, using several systems from the Auriga suite of simulations. We develop a methodology aimed at improving the efficiency of the algorithm and avoiding fragmentation: First, we use a 12-dimensional feature space including a range of chemodynamical properties and stellar ages; furthermore, we optimise the algorithm using information from the internal structure of the clusters of accreted stars. We show that our approach yields good results in terms of both purity and completeness of clusters for galaxies with different types of accretion histories. We also evaluate the decrease in efficiency due to contamination by in situ stars. While for accreted-only haloes the algorithm matches well the recovered clusters with the individual progenitors and is able to recover accretion events up to a redshift of accretion $z_{\rm acc}\sim3$, for accreted + in situ haloes it can only identify the more recent accretion events ($z_{\rm acc} < 1$). However, the purity of the identified clusters remains remarkably high even in this case. Our results suggest that HDBSCAN can efficiently identify accreted debris in Milky Way-type galaxies in realistic conditions, however, it requires careful optimization to provide valid results.

astro-ph.GA↗

arXiv2024

Applying machine learning to Galactic Archaeology: how well can we recover the origin of stars in Milky Way-like galaxies?

We present several machine learning (ML) models developed to efficiently separate stars formed in-situ in Milky Way-type galaxies from those that were formed externally and later accreted. These models, which include examples from artificial neural networks, decision trees and dimensionality reduction techniques, are trained on a sample of disc-like, Milky Way-mass galaxies drawn from the ARTEMIS cosmological hydrodynamical zoom-in simulations. We find that the input parameters which provide an optimal performance for these models consist of a combination of stellar positions, kinematics, chemical abundances ([Fe/H] and [$α$/Fe]) and photometric properties. Models from all categories perform similarly well, with area under the precision-recall curve (PR-AUC) scores of $\simeq 0.6$. Beyond a galactocentric radius of $5$~kpc, models retrieve $>90\%$ of accreted stars, with a sample purity close to $60\%$, however the purity can be increased by adjusting the classification threshold. For one model, we also include host galaxy-specific properties in the training, to account for the variability of accretion histories of the hosts, however this does not lead to an improvement in performance. The ML models can identify accreted stars even in regions heavily dominated by the in-situ component (e.g., in the disc), and perform well on an unseen suite of simulations (the Auriga simulations). The general applicability bodes well for application of such methods on observational data to identify accreted substructures in the Milky Way without the need to resort to selection cuts for minimising the contamination from in-situ stars.

astro-ph.GA↗

arXiv2021

The Partial Response Network: a neural network nomogram

Among interpretable machine learning methods, the class of Generalised Additive Neural Networks (GANNs) is referred to as Self-Explaining Neural Networks (SENN) because of the linear dependence on explicit functions of the inputs. In binary classification this shows the precise weight that each input contributes towards the logit. The nomogram is a graphical representation of these weights. We show that functions of individual and pairs of variables can be derived from a functional Analysis of Variance (ANOVA) representation, enabling an efficient feature selection to be carried by application of the logistic Lasso. This process infers the structure of GANNs which otherwise needs to be predefined. As this method is particularly suited for tabular data, it starts by fitting a generic flexible model, in this case a Multi-layer Perceptron (MLP) to which the ANOVA decomposition is applied. This has the further advantage that the resulting GANN can be replicated as a SENN, enabling further refinement of the univariate and bivariate component functions to take place. The component functions are partial responses hence the SENN is a partial response network. The Partial Response Network (PRN) is equally as transparent as a traditional logistic regression model, but capable of non-linear classification with comparable or superior performance to the original MLP. In other words, the PRN is a fully interpretable representation of the MLP, at the level of univariate and bivariate effects. The performance of the PRN is shown to be competitive for benchmark data, against state-of-the-art machine learning methods including GBM, SVM and Random Forests. It is also compared with spline-based Sparse Additive Models (SAM) showing that a semi-parametric representation of the GAM as a neural network can be as effective as the SAM though less constrained by the need to set spline nodes.

cs.LG↗

arXiv2019

A Probabilistic framework for Quantum Clustering

Quantum Clustering is a powerful method to detect clusters in data with mixed density. However, it is very sensitive to a length parameter that is inherent to the Schrödinger equation. In addition, linking data points into clusters requires local estimates of covariance that are also controlled by length parameters. This raises the question of how to adjust the control parameters of the Schrödinger equation for optimal clustering. We propose a probabilistic framework that provides an objective function for the goodness-of-fit to the data, enabling the control parameters to be optimised within a Bayesian framework. This naturally yields probabilities of cluster membership and data partitions with specific numbers of clusters. The proposed framework is tested on real and synthetic data sets, assessing its validity by measuring concordance with known data structure by means of the Jaccard score (JS). This work also proposes an objective way to measure performance in unsupervised learning that correlates very well with JS.

stat.ML↗