Small Subset Research Articles

Hemodynamic response to inhaled nitric oxide in patients with pulmonary hypertension and chronic kidney disease: A retrospective cohort study.

Pulmonary hypertension (PH) associated with chronic kidney disease (CKD) (PH-CKD) affects approximately 20%-40% of CKD patients and is associated with increased morbidity and mortality. PH and CKD are both pathophysiologically associated with nitric oxide (NO) deficiency. The NO pathway, an important therapeutic domain in pulmonary arterial hypertension (PAH), is an intriguing but unexplored target in PH-CKD. We sought to improve understanding of the clinical significance of the NO pathway in patients with PH-CKD by assessing the hemodynamic response to inhaled NO (iNO) during right heart catheterization (RHC). In this retrospective cohort study, patients with diagnosis codes of PH and stage IV/V CKD or end-stage renal disease and estimated glomerular filtration rate < 60 mL/min/body surface areawho underwent RHC and hemodynamic drug study between July 2011 and June 2021 were eligible. Patients with mean pulmonary artery pressure (mPAP) > 20 mmHg and pulmonary vascular resistance (PVR) > 3Wood unitswere included. The final cohort included 37 patients (45.9% female, mean age 72.5 ± 9.7 years). A total of 56.7%of the cohort (21/37) had precapillary PH, while 43.2% (16/37) had combined precapillary postcapillary PH (Cpc-PH). Median survival was 3.1 years after RHC. iNO was associated with a significant decrease in both mPAP and PVR. Hemodynamic changes in mPAP and PVR were similar in precapillary and Cpc-PH groups. Among a small subset (n = 14) who were subsequently treated with PAH-targeted therapy, treatment response was mixed and did not reveal significant benefit. Further studies are warranted to better define the potential role of PAH therapy in PH-CKD.

DCMAI: A Dynamical Cross-Modal Alignment Interaction Framework for Document Key Information Extraction

Document key information extraction (DKIE) is a crucial topic that aims at automatically comprehending documents with complex formats and layouts (invoices, business insurance, etc.). While pre-trained approaches have shown high performance on many DKIE tasks, they suffer from three major challenges. First of all, these approaches ignore the ambiguity resulting from similar text representations before cross-modal interaction. Secondly, they do not consider cross-modal representation alignment before cross-modal interaction. Finally, self-attention layers in cross-modal interaction incur significant computing costs, making it hard to perform joint representation learning from all negative samples. To address these issues, we propose a Dynamical Cross-Modal Alignment Interaction framework (DCMAI). To be more specific, (1) A prior knowledge-guided module is designed to adaptively mine fine-grained visual information to disambiguate similar text representations. (2) A crossover alignment loss is formulated to align cross-modal representations before cross-modal interaction. (3) A hierarchical interaction sampling scheme is introduced to obtain a small but efficient subset of cross-modal negative samples, and a contrastive loss is employed to improve joint representation learning. Comprehensive experiments show that the proposed DCMAI achieves state-of-the-art performance than competitive baselines on several public downstream benchmarks. Code will be open to the public.

Long-circulating nanoparticles as passive targeting nanocarriers for the treatment of thrombosis.

Thrombosis is the major cause of cardiovascular diseases. Only a small subset of patients could benefit from thrombolytic therapy due to the high bleeding risk brought about by the repeated administration of thrombolytic drugs. Nanoparticles with targeting ligands have been developed as nanocarriers of thrombolytic drugs to deliver the drug to the thrombus through active targeting. However, the passive targeting effect of nanoparticles on the thrombus is yet to be investigated. Herein, we prepared silica cross-linked micelles (SCLMs) with a long blood circulation half-life as drug carriers to target the thrombus through passive targeting. Compared with SCLMs modified with an active targeting ligand cRGD, the SCLMs exhibited similar targeting behavior to the thrombus in vivo. Loaded with the thrombolytic drug tirofiban, the passive targeting SCLMs showed a comparable therapeutic effect to cRGD-modified SCLMs in a mice model with pulmonary embolism and arterial thrombosis.

Voxel-Wise Brain Graphs From Diffusion MRI: Intrinsic Eigenspace Dimensionality and Application to Functional MRI

<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Goal:</i> Structural brain graphs are conventionally limited to defining nodes as gray matter regions from an atlas, with edges reflecting the density of axonal projections between pairs of nodes. Here we explicitly model the entire set of voxels within a brain mask as nodes of high-resolution, subject-specific graphs. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Methods:</i> We define the strength of local voxel-to-voxel connections using diffusion tensors and orientation distribution functions derived from diffusion MRI data. We study the graphs' Laplacian spectral properties on data from the Human Connectome Project. We then assess the extent of inter-subject variability of the Laplacian eigenmodes via a procrustes validation scheme. Finally, we demonstrate the extent to which functional MRI data are shaped by the underlying anatomical structure via graph signal processing. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Results:</i> The graph Laplacian eigenmodes manifest highly resolved spatial profiles, reflecting distributed patterns that correspond to major white matter pathways. We show that the intrinsic dimensionality of the eigenspace of such high-resolution graphs is only a mere fraction of the graph dimensions. By projecting task and resting-state data on low-frequency graph Laplacian eigenmodes, we show that brain activity can be well approximated by a small subset of low-frequency components. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Conclusions:</i> The proposed graphs open new avenues in studying the brain, be it, by exploring their organisational properties via graph or spectral graph theory, or by treating them as the scaffold on which brain function is observed at the individual level.

The natural history of benign prostatic hyperplasia-related voiding symptoms following penile prosthesis implantation.

There is a rising prevalence of benign prostatic hyperplasia (BPH)-related urinary symptoms along with erectile dysfunction in the aging male population. Therefore, assessment of lower urinary tract symptoms (LUTS) is advised before penile prosthesis surgery with some men requiring preoperative transurethral surgical management to reduce the risk of post-procedure complications. However, less is known about the natural history of men with uncomplicated LUTS who do not require surgical management for BPH before penile prosthesis. We sought to assess the natural history of BPH-related uncomplicated LUTS in men following penile prosthesis surgery. Single institution retrospective review. Following institutional review board approval, we performed a retrospective review of all adult males with a preoperative diagnosis of LUTS undergoing penile prosthesis surgery at our institution from January 2017 to November 2022. The primary outcome was progression to transurethral surgery. From 2017 to 2022, 211 patients with preexisting LUTS underwent penile prosthesis surgery and met all criteria for inclusion including no history of transurethral surgery. The median (interquartile range, IQR) AUA symptom score (AUA-SS) was 12 (12). Post-void residual was below 200 cc in 96.2% of patients preoperatively and 99.1% of patients after surgery. At a median (IQR) follow-up duration of 9 (23) months after surgery, 5.7% (12/211) of patients had progressed to bladder outlet surgery and 35.5% of patients endorsed LUTS bother with a median (IQR) AUA-SS of 14.5 (11.8). The majority of patients with uncomplicated LUTS did not require bladder outlet surgery following penile prosthesis implantation and could be managed with conservative or pharmacologic measures alone. Prostate gland size was significantly larger in patients who progressed to bladder outlet surgery. While the results are overall reassuring, further study is needed to identify specific factors associated with pursuing bladder outlet surgery in this small subset of patients.

Mechanisms underlying therapeutic resistance of tyrosine kinase inhibitors in chronic myeloid leukemia.

Chronic myeloid leukemia (CML) is a malignant clonal disease involving hematopoietic stem cells that is characterized by myeloid cell proliferation in bone marrow and peripheral blood, and the presence of the Philadelphia (Ph) chromosome with BCR-ABL fusion gene. Treatment of CML has dramatically improved since the advent of tyrosine kinase inhibitors (TKI). However, there are a small subset of CML patients who develop resistance to TKI. Mutations in the ABL kinase domain (KD) are currently recognized as the leading cause of TKI resistance in CML. In this review, we discuss the concept of resistance and summarize recent advances exploring the mechanisms underlying CML resistance. Overcoming TKI resistance appears to be the most successful approach to reduce the burden of leukemia and enhance cures for CML. Advances in new strategies to combat drug resistance may rapidly change the management of TKI-resistant CML and expand the prospects for available therapies.

Chapter 8: Management of Radioiodine Refractory Thyroid Cancer

ABSTRACT A small subset of patients with differentiated thyroid cancers (DTCs), over the course of their natural disease progression, undergo dedifferentiation which leads to altered tumor biology and an inability to concentrate and respond to radioactive iodine (RAI), despite being able to functionally produce and release thyroglobulin. They broadly consist of two groups – (a) thyroglobulin-elevated negative iodine scintigraphy and (b) radioiodine refractory DTC. This review deals with their definitions, presentation, and overall management principles, highlighting the key points of their treatment philosophy. Whole-body 18F positron emission tomography-computed tomography is the investigation of choice since majority of these become fludeoxyglucose avid once they lose their iodine avidity. Asymptomatic patients with low disease burden may be observed. Surgical ablation, for symptomatic patients with accessible disease is the prime treatment modality. For those deemed inoperable with high tumor burden and increasing symptomatology are best treated with multikinase inhibitors. External beam Radiation may be a choice for painful bony metastasis, while those refractory to multikinase inhibitors may be offered newer forms of localized therapy such as radiofrequency ablation, newer isotope therapy, and transarterial chemoembolization.

Enhancing breast cancer classification via histopathological image analysis: Leveraging self-supervised contrastive learning and transfer learning

Breast cancer, a significant threat to women's health, demands early detection. Automating histopathological image analysis offers a promising solution to enhance efficiency and accuracy in diagnosis. This study addresses the challenge of breast cancer histopathological image classification by leveraging the ResNet architecture, known for its depth and skip connections. In this work, two distinct approaches were pursued, each driven by unique motivations. The first approach aimed to improve the learning process through self-supervised contrastive learning. It utilizes a small subset of the training data for initial model training and progressively expands the training set by incorporating confidently labeled data from the unlabeled pool, ultimately achieving a reliable model with limited training data. The second approach focused on optimizing the architecture by combining ResNet50 and Inception module to get a lightweight and efficient classifier. The dataset utilized in this work comprises histopathological images categorized into benign and malignant classes at varying magnification levels (40X, 100X, 200X, 400X), all originating from the same source image. The results demonstrate state-of-the-art performance, achieving 98% accuracy for images magnified at 40X and 200X, and 94% for 100X and 400X. Notably, the proposed architecture boasts a substantially reduced parameter count of approximately 3.6 million, contrasting with existing leading architectures, which possess parameter sizes at least twice as large.

Two-Step Hyperparameter Optimization Method: Accelerating Hyperparameter Search by Using a Fraction of a Training Dataset

Abstract Hyperparameter optimization (HPO) is an important step in machine learning (ML) model development, but common practices are archaic—primarily relying on manual or grid searches. This is partly because adopting advanced HPO algorithms introduces added complexity to the workflow, leading to longer computation times. This poses a notable challenge to ML applications, as suboptimal hyperparameter selections curtail the potential of ML model performance, ultimately obstructing the full exploitation of ML techniques. In this article, we present a two-step HPO method as a strategic solution to curbing computational demands and wait times, gleaned from practical experiences in applied ML parameterization work. The initial phase involves a preliminary evaluation of hyperparameters on a small subset of the training dataset, followed by a reevaluation of the top-performing candidate models postretraining with the entire training dataset. This two-step HPO method is universally applicable across HPO search algorithms, and we argue it has attractive efficiency gains. As a case study, we present our recent application of the two-step HPO method to the development of neural network emulators for aerosol activation. Although our primary use case is a data-rich limit with many millions of samples, we also find that using up to 0.0025% of the data—a few thousand samples—in the initial step is sufficient to find optimal hyperparameter configurations from much more extensive sampling, achieving up to 135× speedup. The benefits of this method materialize through an assessment of hyperparameters and model performance, revealing the minimal model complexity required to achieve the best performance. The assortment of top-performing models harvested from the HPO process allows us to choose a high-performing model with a low inference cost for efficient use in global climate models (GCMs).

Oilfield Reservoir Parameter Inversion Based on 2D Ground Deformation Measurements Acquired by a Time-Series MSBAS-InSAR Method

Time-series ground deformation monitoring and reservoir parameter inversion are crucial for the dynamic assessment of oilfield resources and sustainable exploitation in oilfields. As some of the regions with the richest oil reserves in China, the oilfield areas in the western Qaidam Basin were selected as a typical study area. Firstly, we used SAR images collected by the Sentinel-1A satellite from January 2021 to December 2022 and applied the multidimensional small baseline subset (MSBAS) method to obtain vertical and east–west deformation measurements. On this basis, a nonlinear Bayesian inversion method was applied to model the shallow reservoir in a series of complex deformation areas, based on a single-source model and a multi-source model, respectively. As a result, the ground deformation monitoring results obtained by long time-series InSAR clearly reflect the uneven ground deformation caused by the oil extraction and water injection operation processes. There was slight subsidence in the Huatugou oilfield, while significant uplift deformation occurred in the Ganchaigou oilfield and the Youshashan oilfield, with a maximum uplift rate of 48 mm/year. Further analysis indicated that the introduction of the 2D deformation field helps to improve the robustness of oilfield reservoir parameter inversion. Moreover, the dual-source model is more suitable than the single-source model for inverting reservoir parameters of complex deformation. This study not only fills the gap of InSAR deformation monitoring for the oilfields in the western Qaidam Basin but also provides a theoretical reference for the model and method selection of reservoir parameter inversion in other oilfields.

Educational Podcasts in Plastic Surgery: A Cross-Sectional Analysis of Content, Metrics, and Target Audiences

Podcasts provide an efficient means for asynchronous learning. However, no study to date has thoroughly assessed the landscape of educational podcasts in plastic surgery. Thus, this study aims to evaluate and characterize current educational plastic surgery podcasts to ultimately inform future efforts. Three platforms were queried for educational plastic surgery podcasts: Apple Podcasts, Spotify, and Google Podcasts. Podcast descriptions and episodes were then independently reviewed to determine primary target audiences, performance metrics, and content categories. There were a total of 163 plastic surgery podcasts. 145 of these 163 podcasts were targeted toward a nonmedical audience. The remaining 18 podcasts met inclusion criteria as educational plastic surgery podcasts. Of all educational podcast episodes, 8.8% targeted a medical student audience, 33.8% targeted trainees (residents/fellows), and 57.4% targeted practicing surgeons or emphasized recent research in the field. Episode content categories included breast (14.2%), cosmetic (11.8%), experimental (0.5%), hand/peripheral nerve (8.6%), pediatric/craniofacial (8.2%), reconstructive (15.6%), practice management (14.8%), residency (6.6%), and others (19.6%). Despite the large number of plastic surgery podcasts available, few podcasts focus on educating a medical audience. Within this small subset, there is a paucity of content targeted towards medical students interested in plastic surgery. While there is a wide breadth of content available, there is significant room for growth and refinement in the podcast sector for plastic surgery education.

Data-driven development of an oral lipid-based nanoparticle formulation of a hydrophobic drug.

Due to its cost-effectiveness, convenience, and high patient adherence, oral drug administration normally remains the preferred approach. Yet, the effective delivery of hydrophobic drugs via the oral route is often hindered by their limited water solubility and first-pass metabolism. To mitigate these challenges, advanced delivery systems such as solid lipid nanoparticles (SLNs) and nanostructured lipid carriers (NLCs) have been developed to encapsulate hydrophobic drugs and enhance their bioavailability. However, traditional design methodologies for these complex formulations often present intricate challenges because they are restricted to a relatively narrow design space. Here, we present a data-driven approach for the accelerated design of SLNs/NLCs encapsulating a model hydrophobic drug, cannabidiol, that combines experimental automation and machine learning. A small subset of formulations, comprising 10% of all formulations in the design space, was prepared in-house, leveraging miniaturized experimental automation to improve throughput and decrease the quantity of drug and materials required. Machine learning models were then trained on the data generated from these formulations and used to predict properties of all SLNs/NLCs within this design space (i.e., 1215 formulations). Notably, formulations predicted to be high-performers via this approach were confirmed to significantly enhance the solubility of the drug by up to 3000-fold and prevented degradation of drug. Moreover, the high-performance formulations significantly enhanced the oral bioavailability of the drug compared to both its free form and an over-the-counter version. Furthermore, this bioavailability matched that of a formulation equivalent in composition to the FDA-approved product, Epidiolex®.

Decoupled Progressive Distillation for Sequential Prediction with Interaction Dynamics

Sequential prediction has great value for resource allocation due to its capability in analyzing intents for next prediction. A fundamental challenge arises from real-world interaction dynamics where similar sequences involving multiple intents may exhibit different next items. More importantly, the character of volume candidate items in sequential prediction may amplify such dynamics, making deep networks hard to capture comprehensive intents. This article presents a sequential prediction framework with Decoupled Progressive Distillation (DePoD), drawing on the progressive nature of human cognition. We redefine target and non-target item distillation according to their different effects in the decoupled formulation. This can be achieved through two aspects: (1) Regarding how to learn, our target item distillation with progressive difficulty increases the contribution of low-confidence samples in the later training phase while keeping high-confidence samples in the earlier phase. And, the non-target item distillation starts from a small subset of non-target items from which size increases according to the item frequency. (2) Regarding whom to learn from, a difference evaluator is utilized to progressively select an expert that provides informative knowledge among items from the cohort of peers. Extensive experiments on four public datasets show DePoD outperforms state-of-the-art methods in terms of accuracy-based metrics.

A Comprehensive Evaluation of Generalizability of Deep Learning-Based Hi-C Resolution Improvement Methods.

Hi-C is a widely used technique to study the 3D organization of the genome. Due to its high sequencing cost, most of the generated datasets are of a coarse resolution, which makes it impractical to study finer chromatin features such as Topologically Associating Domains (TADs) and chromatin loops. Multiple deep learning-based methods have recently been proposed to increase the resolution of these datasets by imputing Hi-C reads (typically called upscaling). However, the existing works evaluate these methods on either synthetically downsampled datasets, or a small subset of experimentally generated sparse Hi-C datasets, making it hard to establish their generalizability in the real-world use case. We present our framework-Hi-CY-that compares existing Hi-C resolution upscaling methods on seven experimentally generated low-resolution Hi-C datasets belonging to various levels of read sparsities originating from three cell lines on a comprehensive set of evaluation metrics. Hi-CY also includes four downstream analysis tasks, such as TAD and chromatin loops recall, to provide a thorough report on the generalizability of these methods. We observe that existing deep learning methods fail to generalize to experimentally generated sparse Hi-C datasets, showing a performance reduction of up to 57%. As a potential solution, we find that retraining deep learning-based methods with experimentally generated Hi-C datasets improves performance by up to 31%. More importantly, Hi-CY shows that even with retraining, the existing deep learning-based methods struggle to recover biological features such as chromatin loops and TADs when provided with sparse Hi-C datasets. Our study, through the Hi-CY framework, highlights the need for rigorous evaluation in the future. We identify specific avenues for improvements in the current deep learning-based Hi-C upscaling methods, including but not limited to using experimentally generated datasets for training.

Uncertainty quantification in the strain response of prestressed reinforced concrete structures using fractile based sampling

The probabilistic evaluation of the capacity and response of structural systems is often done by probabilistic simulation. This approach relies on a considerable number of deterministic analyses to obtain an accurate estimation of the desired statistical characteristics. However, the need of performing a large number of analyses hinders the application of probabilistic simulation in practice, especially when the deterministic calculation of the structural response is computationally expensive in itself (e.g. nonlinear finite element analysis). To increase the appeal of probabilistic simulation, the number of analyses should be very small (i.e. ten or less). This study shows how different sampling techniques can be adopted to select a very small sample subset of analyses to be run, and how they can yield accurate results in estimating the shear capacity of prestressed reinforced concrete beams. Based on the results of the study, the Fractile Based Sampling (FBS) method emerges as a more promising sampling strategy than other sampling techniques, like Latin Hypercube Sampling (LHS). For the same small number of samples, the results show that FBS is preferable over LHS and other sampling techniques for capturing both the general distribution of the response and the tails of the distribution, which shows its usefulness in assessing probability of failure and reliability.

Detection and analysis of potential landslides based on SBAS-InSAR technology in alpine canyon region.

The Lancang River flows through the alpine canyon region of southwest China, an area that has experienced frequent geological disasters over the years. Early monitoring of geological hazards is essential for disaster prevention and mitigation. However, traditional ground monitoring techniques are limited by the complex terrain conditions in high-altitude valley regions. In contrast, interferometric synthetic aperture radar (InSAR) technology can provide a high-precision, wide-range monitoring of slow rock-slope deformation, making it an effective tool for studying geological hazards. Within the study area, multiple synthetic aperture radar (SAR) images from the Sentinel-1A satellite were collected, and surface deformation was obtained using the small baseline subset InSAR (SBAS-InSAR). The results demonstrate that combining ascending and descending orbit images can be successfully applied to landslide monitoring in complex mountainous areas. Over 30 potential landslides were identified by combining InSAR results with optical images. The Line-Of-Sight (LOS) direction deformation features and their relationship with precipitation were analyzed based on two typical landslides, and two-dimensional/three-dimensional (2D/3D) deformation decomposition was carried out to reveal its motion characteristics. It was found that the cumulative deformation fluctuation amplitude was higher during the rainy season, and the main movement direction of the landslide was east-west. In addition, based on the spatial distribution and statistical analysis of deformation points along with meteorological data, geological elements, human activities, and topographic conditions, it is inferred that factors such as low vegetation coverage, tectonic movements, human activities, and high-altitude glacier thawing may contribute to the occurrence of disasters. And it was found that areas with high vegetation cover, high rainfall, and snow cover exhibit lower coherence coefficients. This study offers valuable insights for investigating large-scale geological in alpine canyon regions.

B-cell receptor immunoglobulin stereotypy in chronic lymphocytic leukemia: Key to understanding disease biology and stratifying patients

Sequence convergence, otherwise stereotypy, of B-cell receptor immunoglobulin (BcR IG) from unrelated patients is a distinctive feature of the IG gene repertoire in chronic lymphocytic leukemia (CLL) whereby patients expressing a particular BcR IG archetype are classified into groups termed stereotyped subsets. From a biological perspective, the fact that a considerable fraction (∼41%) of patients with CLL express (quasi)identical or stereotyped BcR IG underscores the key role of antigen selection in the natural history of CLL. From a clinical perspective, at odds with the pronounced heterogeneity of CLL at large, patients belonging to the same stereotyped subset display consistent clinical presentation and outcome, including response to treatment, likely as a reflection of consistent biological background. Many major stereotyped subsets were recently shown to have satellites, that is, smaller subsets that are immunogenetically similar. Preliminary evidence supports that this similarity extends to shared biological and even clinical features, with important implications for patient stratification. Consequently, BcR IG stereotypy emerges as a powerful tool for dissecting the heterogeneity of CLL toward refined risk stratification and, eventually, more precise therapeutic interventions.

Analysis of the Spatial Distribution and Deformation Types of Active Landslides in the Upper Jinsha River, China, Using Integrated Remote Sensing Technologies

The Upper Jinsha River (UJSR) has great water resource potential, but large-scale active landslides hinder water resource development and utilization. It is necessary to understand the spatial distribution and deformation trend of active landslides in the UJSR. In areas of high elevations, steep terrain or otherwise inaccessible to humans, extensive landslide studies remain challenging using traditional geological surveys and monitoring equipment. Stacking interferometry synthetic aperture radar (stacking-InSAR) technology, optical satellite images and unmanned aerial vehicle (UAV) photography are applied to landslide identification. Small baseline subset interferometry synthetic aperture radar (SBAS-InSAR) was used to obtain time-series deformation curves of samples to reveal the deformation types of active landslides. A total of 246 active landslides were identified within the study area, of which 207 were concentrated in three zones (zones I, II and III). Among the 31 landslides chosen as research samples, six were linear-type landslides, three were upward concave-type landslides, 10 were downward concave-type landslides, and 12 were step-type landslides based on the curve morphology. The results can aid in monitoring and early-warning systems for active landslides within the UJSR and provide insights for future studies on active landslides within the basin.

Statistical relationships between the Interdecadal Pacific Oscillation and El Niño–Southern Oscillation

AbstractThe climate of the Pacific Ocean varies on interannual, decadal, and longer timescales. This variability is dominated by the El Niño–Southern Oscillation (ENSO) and the Interdecadal Pacific Oscillation (IPO), both of which have profound impacts on countries within and well beyond the Pacific. To date, previous studies have only examined a small subset of the possible links between ENSO, its diversity, and the IPO. Here we focus on the statistical relationship between decadal variability in ENSO properties and the IPO, testing the null hypothesis that the IPO arises from random decadal changes in ENSO activity, including ENSO diversity. We use observed sea surface temperature (SST) records since 1920 to investigate how the timing, structure, frequency, duration, and magnitude of El Niño and La Niña events differ between IPO phases. We find that using the relative frequency of El Niño and La Niña events and either the mean event duration or SST magnitude can reproduce up to 60% of the IPO Tripole Index timeseries. While the spatial SST patterns that represent the IPO and ENSO are similar, the IPO is meridionally broader in the central to eastern Pacific, which may be caused by a lagged relationship with low-frequency SST variability in the equatorial Pacific. In addition, North Pacific SST anomalies of opposite sign to the tropical Pacific SST anomalies is a unique feature of the IPO that cannot be explained by decadal ENSO variability. This suggests a clear IPO and ENSO relationship, but also independence in some of the IPO’s characteristics.

Feature Selection Problem and Metaheuristics: A Systematic Literature Review about Its Formulation, Evaluation and Applications.

Feature selection is becoming a relevant problem within the field of machine learning. The feature selection problem focuses on the selection of the small, necessary, and sufficient subset of features that represent the general set of features, eliminating redundant and irrelevant information. Given the importance of the topic, in recent years there has been a boom in the study of the problem, generating a large number of related investigations. Given this, this work analyzes 161 articles published between 2019 and 2023 (20 April 2023), emphasizing the formulation of the problem and performance measures, and proposing classifications for the objective functions and evaluation metrics. Furthermore, an in-depth description and analysis of metaheuristics, benchmark datasets, and practical real-world applications are presented. Finally, in light of recent advances, this review paper provides future research opportunities.