Conformal Monte Carlo Meta-learners for Predictive Inference of Individual Treatment Effects

Knowledge of the effect of interventions, called the treatment effect, is paramount for decision-making. Approaches to estimating this treatment effect, e.g. by using Conditional Average Treatment Effect (CATE) estimators, often only provide a point estimate of this treatment effect, while additional uncertainty quantification is frequently desired instead. Therefore, we present a novel method, the Conformal Monte Carlo (CMC) meta-learners, leveraging conformal predictive systems, Monte Carlo sampling, and CATE meta-learners, to instead produce a predictive distribution usable in individualized decision-making. Furthermore, we show how specific assumptions on the noise distribution of the outcome heavily affect these uncertainty predictions. Nonetheless, the CMC framework shows strong experimental coverage while retaining small interval widths to provide estimates of the true individual treatment effect.

tsdownsample: high-performance time series downsampling for scalable visualization

Interactive line chart visualizations greatly enhance the effective exploration of large time series. Although downsampling has emerged as a well-established approach to enable efficient interactive visualization of large datasets, it is not an inherent feature in most visualization tools. Furthermore, there is no library offering a convenient interface for high-performance implementations of prominent downsampling algorithms. To address these shortcomings, we present tsdownsample, an open-source Python package specifically designed for CPU-based, in-memory time series downsampling. Our library focuses on performance and convenient integration, offering optimized implementations of leading downsampling algorithms. We achieve this optimization by leveraging low-level SIMD instructions and multithreading capabilities in Rust. In particular, SIMD instructions were employed to optimize the argmin and argmax operations. This SIMD optimization, along with some algorithmic tricks, proved crucial in enhancing the performance of various downsampling algorithms. We evaluate the performance of tsdownsample and demonstrate its interoperability with an established visualization framework. Our performance benchmarks indicate that the algorithmic runtime of tsdownsample approximates the CPU's memory bandwidth. This work marks a significant advancement in bringing high-performance time series downsampling to the Python ecosystem, enabling scalable visualization. The open-source code can be found at https://github.com/predict-idlab/tsdownsample

Perfectly predicting ICU length of stay: too good to be true

A paper of Alsinglawi et al was recently accepted and published in Scientific Reports. In this paper, the authors aim to predict length of stay (LOS), discretized into either long (> 7 days) or short stays (< 7 days), of lung cancer patients in an ICU department using various machine learning techniques. The authors claim to achieve perfect results with an Area Under the Receiver Operating Characteristic curve (AUROC) of 100% with a Random Forest (RF) classifier with ADASYN class balancing over sampling technique, which if accurate could have significant implications for hospital management. However, we have identified several methodological flaws within the manuscript which cause the results to be overly optimistic and would have serious consequences if used in a clinical practice. Moreover, the reporting of the methodology is unclear and many important details are missing from the manuscript, which makes reproduction extremely difficult. We highlight the effect these oversights have had on the result and provide a more believable result of 88.91% AUROC when these oversights are corrected.

Do Not Sleep on Linear Models: Simple and Interpretable Techniques Outperform Deep Learning for Sleep Scoring

Over the last few years, research in automatic sleep scoring has mainly focused on developing increasingly complex deep learning architectures. However, recently these approaches achieved only marginal improvements, often at the expense of requiring more data and more expensive training procedures. Despite all these efforts and their satisfactory performance, automatic sleep staging solutions are not widely adopted in a clinical context yet. We argue that most deep learning solutions for sleep scoring are limited in their real-world applicability as they are hard to train, deploy, and reproduce. Moreover, these solutions lack interpretability and transparency, which are often key to increase adoption rates. In this work, we revisit the problem of sleep stage classification using classical machine learning. Results show that state-of-the-art performance can be achieved with a conventional machine learning pipeline consisting of preprocessing, feature extraction, and a simple machine learning model. In particular, we analyze the performance of a linear model and a non-linear (gradient boosting) model. Our approach surpasses state-of-the-art (that uses the same data) on two public datasets: Sleep-EDF SC-20 (MF1 0.810) and Sleep-EDF ST (MF1 0.795), while achieving competitive results on Sleep-EDF SC-78 (MF1 0.775) and MASS SS3 (MF1 0.817). We show that, for the sleep stage scoring task, the expressiveness of an engineered feature vector is on par with the internally learned representations of deep learning models. This observation opens the door to clinical adoption, as a representative feature vector allows to leverage both the interpretability and successful track record of traditional machine learning models.

Plotly-Resampler: Effective Visual Analytics for Large Time Series

Visual analytics is arguably the most important step in getting acquainted with your data. This is especially the case for time series, as this data type is hard to describe and cannot be fully understood when using for example summary statistics. To realize effective time series visualization, four requirements have to be met; a tool should be (1) interactive, (2) scalable to millions of data points, (3) integrable in conventional data science environments, and (4) highly configurable. We observe that open source Python visualization toolkits empower data scientists in most visual analytics tasks, but lack the combination of scalability and interactivity to realize effective time series visualization. As a means to facilitate these requirements, we created Plotly-Resampler, an open source Python library. Plotly-Resampler is an add-on for Plotly's Python bindings, enhancing line chart scalability on top of an interactive toolkit by aggregating the underlying data depending on the current graph view. Plotly-Resampler is built to be snappy, as the reactivity of a tool qualitatively affects how analysts visually explore and analyze data. A benchmark task highlights how our toolkit scales better than alternatives in terms of number of samples and time series. Additionally, Plotly-Resampler's flexible data aggregation functionality paves the path towards researching novel aggregation techniques. Plotly-Resampler's integrability, together with its configurability, convenience, and high scalability, allows to effectively analyze high-frequency data in your day-to-day Python environment.

Powershap: A Power-full Shapley Feature Selection Method

Feature selection is a crucial step in developing robust and powerful machine learning models. Feature selection techniques can be divided into two categories: filter and wrapper methods. While wrapper methods commonly result in strong predictive performances, they suffer from a large computational complexity and therefore take a significant amount of time to complete, especially when dealing with high-dimensional feature sets. Alternatively, filter methods are considerably faster, but suffer from several other disadvantages, such as (i) requiring a threshold value, (ii) not taking into account intercorrelation between features, and (iii) ignoring feature interactions with the model. To this end, we present powershap, a novel wrapper feature selection method, which leverages statistical hypothesis testing and power calculations in combination with Shapley values for quick and intuitive feature selection. Powershap is built on the core assumption that an informative feature will have a larger impact on the prediction compared to a known random feature. Benchmarks and simulations show that powershap outperforms other filter methods with predictive performances on par with wrapper methods while being significantly faster, often even reaching half or a third of the execution time. As such, powershap provides a competitive and quick algorithm that can be used by various models in different domains. Furthermore, powershap is implemented as a plug-and-play and open-source sklearn component, enabling easy integration in conventional data science pipelines. User experience is even further enhanced by also providing an automatic mode that automatically tunes the hyper-parameters of the powershap algorithm, allowing to use the algorithm without any configuration needed.

R-GCN: The R Could Stand for Random

The inception of Relational Graph Convolutional Networks (R-GCNs) marked a milestone in the Semantic Web domain as it allows for end-to-end training of machine learning models that operate on Knowledge Graphs (KGs). R-GCNs generate a representation for a node of interest by repeatedly aggregating parametrised, relation-specific transformations of its neighbours. However, in this paper, we argue that the the R-GCN's main contribution lies in this "message passing" paradigm, rather than the learned parameters. To this end, we introduce the "Random Relational Graph Convolutional Network" (RR-GCN), which constructs embeddings for nodes in the KG by aggregating randomly transformed random information from neigbours, i.e., with no learned parameters. We empirically show that RR-GCNs can compete with fully trained R-GCNs in both node classification and link prediction settings. The implications of these results are two-fold: on the one hand, our technique can be used as a quick baseline that novel KG embedding methods should be able to beat. On the other hand, it demonstrates that further research might reveal more parameter-efficient inductive biases for KGs.

tsflex: flexible time series processing & feature extraction

Time series processing and feature extraction are crucial and time-intensive steps in conventional machine learning pipelines. Existing packages are limited in their real-world applicability, as they cannot cope with irregularly-sampled and asynchronous data. We therefore present $\texttt{tsflex}$, a domain-independent, flexible, and sequence first Python toolkit for processing & feature extraction, that is capable of handling irregularly-sampled sequences with unaligned measurements. This toolkit is sequence first as (1) sequence based arguments are leveraged for strided-window feature extraction, and (2) the sequence-index is maintained through all supported operations. $\texttt{tsflex}$ is flexible as it natively supports (1) multivariate time series, (2) multiple window-stride configurations, and (3) integrates with processing and feature functions from other packages, while (4) making no assumptions about the data sampling rate regularity and synchronization. Other functionalities from this package are multiprocessing, in-depth execution time logging, support for categorical & time based data, chunking sequences, and embedded serialization. $\texttt{tsflex}$ is developed to enable fast and memory-efficient time series processing & feature extraction. Results indicate that $\texttt{tsflex}$ is more flexible than similar packages while outperforming these toolkits in both runtime and memory usage.

Overly Optimistic Prediction Results on Imbalanced Data: Flaws and Benefits of Applying Over-sampling

Information extracted from electrohysterography recordings could potentially prove to be an interesting additional source of information to estimate the risk on preterm birth. Recently, a large number of studies have reported near-perfect results to distinguish between recordings of patients that will deliver term or preterm using a public resource, called the Term/Preterm Electrohysterogram database. However, we argue that these results are overly optimistic due to a methodological flaw being made. In this work, we focus on one specific type of methodological flaw: applying over-sampling before partitioning the data into mutually exclusive training and testing sets. We show how this causes the results to be biased using two artificial datasets and reproduce results of studies in which this flaw was identified. Moreover, we evaluate the actual impact of over-sampling on predictive performance, when applied prior to data partitioning, using the same methodologies of related studies, to provide a realistic view of these methodologies' generalization capabilities. We make our research reproducible by providing all the code under an open license.