UNASSIGNED: Sickle cell disease (SCD) is a severe hereditary form of anemia that contributes between 50% and 80% of under-five mortality in Africa. Eleven thousand babies are born with SCD annually in Tanzania, ranking 4th after Nigeria, the Democratic Republic of Congo and India. The absence of well-described SCD cohorts is a major barrier to health research in SCD in Africa.
UNASSIGNED: This paper describes the Sickle Pan African Consortium (SPARCO) database in Tanzania, from the development, design of the study instruments, data collection, analysis of data and management of data quality issues.
UNASSIGNED: The SPARCO registry used existing Muhimbili Sickle Cell Cohort (MSC) study case report forms (CRF) and later harmonized data elements from the SickleInAfrica consortium to develop Research Electronic Data Capture (REDCap) instruments. Patients were enrolled through various strategies, including mass screening following media sensitization and health education events during World Sickle Cell Day each June and the SCD awareness month in September. Additional patients were identified through active surveillance of previously participating patients in the MSC.
UNASSIGNED: Three thousand eight hundred patients were enrolled between October 2017 and May 2021. Of these, 1,946 (51.21%) were males and 1,864 (48.79%) were females. The hemoglobin phenotype distribution was 3,762 (99%) HbSS, 3 (0.08%) HbSC and 35 (0.92%) HbSb +thalassemia. Hemoglobin levels, admission history, blood transfusion and painful events were recorded from December 2017 to May 2021.
UNASSIGNED: The Tanzania SPARCO registry will improve healthcare for SCD in Africa through the facilitation of collaborative data-driven research for SCD.

Grapevine downy mildew (GDM), caused by the oomycete Plasmopara viticola, can cause 100% yield loss and vine death under conducive conditions. High resolution multispectral satellite platforms offer the opportunity to track rapidly spreading diseases like GDM over large, heterogeneous fields. Here, we investigate the capacity of PlanetScope (3 m) and SkySat (50 cm) imagery for season-long GDM detection and surveillance. A team of trained scouts rated GDM severity and incidence at a research vineyard in Geneva, NY, USA from June to August of 2020, 2021, and 2022. Satellite imagery acquired within 72 hours of scouting was processed to extract single-band reflectance and vegetation indices (VIs). Random forest models trained on spectral bands and VIs from both image datasets could classify areas of high and low GDM incidence and severity with maximum accuracies of 0.85 (SkySat) and 0.92 (PlanetScope). However, we did not observe significant differences between VIs of high and low damage classes until late July-early August. We identified cloud cover, image co-registration, and low spectral resolution as key challenges to operationalizing satellite-based GDM surveillance. This work establishes the capacity of spaceborne multispectral sensors to detect late-stage GDM and outlines steps towards incorporating satellite remote sensing in grapevine disease surveillance systems.

Given their central role in signal transduction, protein kinases (PKs) were first implicated in cancer development, caused by aberrant intracellular signaling events. Since then, PKs have become major targets in different therapeutic areas. The preferred approach to therapeutic intervention of PK-dependent diseases is the use of small molecules to inhibit their catalytic phosphate group transfer activity. PK inhibitors (PKIs) are among the most intensely pursued drug candidates, with currently 80 approved compounds and several hundred in clinical trials. Following the elucidation of the human kinome and development of robust PK expression systems and high-throughput assays, large volumes of PK/PKI data have been produced in industrial and academic environments, more so than for many other pharmaceutical targets. In addition, hundreds of X-ray structures of PKs and their complexes with PKIs have been reported. Substantial amounts of PK/PKI data have been made publicly available in part as a result of open science initiatives. PK drug discovery is further supported through the incorporation of data science approaches, including the development of various specialized databases and online resources. Compound and activity data wealth compared to other targets has also made PKs a focal point for the application of artificial intelligence (AI) in pharmaceutical research. Herein, we discuss the interplay of open and data science in PK drug discovery and review exemplary studies that have substantially contributed to its development, including kinome profiling or the analysis of PKI promiscuity versus selectivity. We also take a close look at how AI approaches are beginning to impact PK drug discovery in light of their increasing data orientation.

The healthcare industry has been put to test the need to manage enormous amounts of data provided by various sources, which are renowned for providing enormous quantities of heterogeneous information. The data are collected and analyzed with different Data Analytic (DA) and machine learning algorithm approaches. Researchers, scientists, and industrialists must manage or select the best approach associated with DA in healthcare. This scientific study is based on decision analysis between the DA factors and alternatives. The information affects the whole system in a rational manner. This information is very important in healthcare sector for appropriate prediction and analysis. The evaluation discusses its benefits and presents an analytic framework. The Fuzzy Analytic Hierarchy Process (Fuzzy AHP) approach is used to address the weight of the factors. The Fuzzy Techniques for Order Preference by Similarity to Ideal Solution (Fuzzy TOPSIS) address the rank of the data analytic alternatives used in healthcare sector. The models used in the article briefly discuss the challenges of DA and approaches to address those challenges. The assorted factors of DA are capture, cleaning, storage, security, stewardship, reporting, visualization, updating, sharing, and querying. The DA alternatives include descriptive, diagnostic, predictive, prescriptive, discovery, regression, cohort and inferential analyses. The most influential factors of the DA and the most suitable approach for the DA are evaluated. The \'cleaning\' factor has the highest weight, and \'updating\' is achieved at least by the Fuzzy-AHP approach. The regression approach of data analysis had the highest rank, and the diagnostic analysis had the lowest rank. Decision analyses are necessary for data scientists and medical providers to predict diseases appropriately in the healthcare domain. This analysis also revealed the cost benefits to hospitals.

The estimation of the global burden of animal diseases requires the integration of multidisciplinary models: economic, statistical, mathematical and conceptual. The output of one model often serves as input for another; therefore, consistency of the model components is critical. The Global Burden of Animal Diseases (GBADs) Informatics team aims to strengthen the scientific foundations of modelling by creating tools that address challenges related to reproducibility, as well as model, data and metadata interoperability. Aligning with these aims, several tools are under development: a) GBADs\'Trusted Animal Information Portal (TAIL) is a data acquisition platform that enhances the discoverability of data and literature and improves the user experience of acquiring data. TAIL leverages advanced semantic enrichment techniques (natural language processing and ontologies) and graph databases to provide users with a comprehensive repository of livestock data and literature resources. b) The interoperability of GBADs\'models is being improved through the development of an R-based modelling package and standardisation of parameter formats. This initiative aims to foster reproducibility, facilitate data sharing and enable seamless collaboration among stakeholders. c) The GBADs Knowledge Engine is being built to foster an inclusive and dynamic user community by offering data in multiple formats and providing user-friendly mechanisms to garner feedback from the community. These initiatives are critical in addressing complex challenges in animal health and underscore the importance of combining scientific rigour with user-friendly interfaces to empower global efforts in safeguarding animal populations and public health.
L\'estimation de l\'impact mondial des maladies animales nécessite l\'utilisation intégrée de modèles issus de diverses disciplines : économiques, statistiques, mathématiques et conceptuels. Les données de sortie d\'un modèle constituent souvent celles d\'entrée d\'un autre modèle ; la cohérence des composantes des différents modèles est donc primordiale. L\'équipe informatique du programme \" Impact mondial des maladies animales \" (GBADs) s\'efforce de consolider les bases scientifiques de l\'utilisation des modèles en mettant au point des outils permettant de résoudre les problèmes de reproductibilité et d\'améliorer l\'interopérabilité entre les différents modèles, données et métadonnées. En phase avec ces objectifs, plusieurs outils sont en cours de développement : a) le Portail du GBADs \" Trusted Animal Information Portal \" (TAIL) est une plateforme d\'acquisition de données qui facilite l\'accès aux données et à la littérature, tout en améliorant l\'expérience utilisateur lors de l\'acquisition des données. Le portail TAIL s\'appuie sur des techniques avancées d\'enrichissement sémantique (traitement du langage naturel et ontologies) et sur des bases de données graphiques pour apporter aux utilisateurs un référentiel complet des données et des ressources documentaires relatives aux animaux d\'élevage ; b) l\'interopérabilité des modèles du GBADs est en voie d\'amélioration grâce à la mise au point d\'un progiciel de modélisation fondé sur R et à la normalisation des formats de paramètres. Cette initiative vise à favoriser la reproductibilité, à faciliter le partage de données et à permettre une collaboration transparente entre les parties prenantes ; c) le moteur de connaissances du GBADs, en cours de construction, vise à encourager une communauté d\'utilisateurs inclusive et dynamique en proposant des données dans une multiplicité de formats ainsi que des mécanismes conviviaux pour recueillir les commentaires de la communauté. Ces initiatives se révéleront indispensables pour relever les défis complexes de la santé animale et soulignent l\'importance d\'associer une grande rigueur scientifique à la convivialité des interfaces, afin de donner encore plus d\'élan aux efforts déployés dans le monde pour protéger les populations animales et la santé publique.
La estimación del impacto global de las enfermedades animales requiere la integración de modelos multidisciplinarios: económicos, estadísticos, matemáticos y conceptuales. El resultado de un modelo a menudo sirve de entrada para otro; por lo tanto, la coherencia entre los distintos componentes es fundamental. El equipo de informática del programa sobre el Impacto Global de las Enfermedades Animales (GBADs) tiene como objetivo fortalecer los fundamentos científicos de la modelización mediante la creación de herramientas que aborden los retos relacionados con la reproducibilidad, así como con la interoperabilidad de los modelos, datos y metadatos. En consonancia con estos objetivos, se están desarrollando varias herramientas: a) El Portal del GBADs \"Trusted Animal Information Portal\" (TAIL) es una plataforma de adquisición de datos que mejora tanto la descubribilidad de datos y bibliografía como la experiencia del usuario a la hora de obtener datos. El portal TAIL utiliza técnicas avanzadas de enriquecimiento semántico (procesamiento del lenguaje natural y ontologías), así como bases de datos de grafos, para ofrecer a los usuarios un repositorio completo de datos sobre ganadería y recursos bibliográficos. b) Se está mejorando la interoperabilidad de los modelos del GBADs mediante el desarrollo de un paquete de modelización en R y la normalización de los formatos de los parámetros. Esta iniciativa pretende fomentar la reproducibilidad, facilitar el intercambio de datos y permitir una colaboración fluida entre las partes interesadas. c) El Motor de Conocimiento del GBADs se está construyendo con el objetivo de fomentar una comunidad de usuarios inclusiva y dinámica, ofreciendo datos en diferentes formatos y proporcionando mecanismos fáciles de usar para recopilar comentarios de la comunidad. Estas iniciativas son fundamentales para hacer frente a los complejos retos en el ámbito de la sanidad animal y subrayan la importancia de combinar el rigor científico con interfaces fáciles de usar para potenciar los esfuerzos mundiales encaminados a proteger a las poblaciones animales y la salud pública.

The rapidly developing field of artificial intelligence (AI) may soon equip clinicians with algorithms that model and predict perioperative problems with extreme accuracy. Here, we outline emerging AI applications in preoperative risk stratification and intraoperative event prediction, where algorithm performance has been shown to outstrip commonly used conventional risk prediction tools. While offering an enticing view of a novel perioperative practice with superhuman foresight, AI\'s limited scope and lack of transparency remain key challenges for widespread adoption. As yet it is unclear whether machine learning alone can influence human clinical practice to exert real-world effects on patient outcomes.

BACKGROUND: Survival analysis based on cancer registry data is of paramount importance for monitoring the effectiveness of health care. As new methods arise, the compendium of statistical tools applicable to cancer registry data grows. In recent years, machine learning approaches for survival analysis were developed. The aim of this study is to compare the model performance of the well established Cox regression and novel machine learning approaches on a previously unused dataset.
METHODS: The study is based on lung cancer data from the Schleswig-Holstein Cancer Registry. Four survival analysis models are compared: Cox Proportional Hazard Regression (CoxPH) as the most commonly used statistical model, as well as Random Survival Forests (RSF) and two neural network architectures based on the DeepSurv and TabNet approaches. The models are evaluated using the concordance index (C-I), the Brier score and the AUC-ROC score. In addition, to gain more insight in the decision process of the models, we identified the features that have an higher impact on patient survival using permutation feature importance scores and SHAP values.
RESULTS: Using a dataset including the cancer stage established by the Union for International Cancer Control (UICC), the best performing model is the CoxPH (C-I: 0.698±0.005), while using a dataset which includes the tumor size, lymph node and metastasis status (TNM) leads to the RSF as best performing model (C-I: 0.703±0.004). The explainability metrics show that the models rely on the combined UICC stage and the metastasis status in the first place, which corresponds to other studies.
CONCLUSIONS: The studied methods are highly relevant for epidemiological researchers to create more accurate survival models, which can help physicians make informed decisions about appropriate therapies and management of patients with lung cancer, ultimately improving survival and quality of life.

暂无摘要。

UNASSIGNED: \"Data scientists\" quickly became ubiquitous, often infamously so, but they have struggled with the ambiguity of their novel role. This article studies data science\'s collective definition on Twitter.
UNASSIGNED: The analysis responds to the challenges of studying an emergent case with unclear boundaries and substance through a cultural perspective and complementary datasets ranging from 1,025 to 752,815 tweets. It brings together relations between accounts that tweeted about data science, the hashtags they used, indicating purposes, and the topics they discussed.
UNASSIGNED: The first results reproduce familiar commercial and technical motives. Additional results reveal concerns with new practical and ethical standards as a distinctive motive for constructing data science.
UNASSIGNED: The article provides a sensibility for local meaning in usually abstract datasets and a heuristic for navigating increasingly abundant datasets toward surprising insights. For data scientists, it offers a guide for positioning themselves vis-à-vis others to navigate their professional future.

Background: Fold change is a common metric in biomedical research for quantifying group differences in omics variables. However, inconsistent calculation methods and inadequate reporting lead to discrepancies in results. This study evaluated various fold-change calculation methods aiming at a recommendation of a preferred approach. Methods: The primary distinction in fold-change calculations lies in defining group expected values for log ratio computation. To challenge method interchangeability in a \"stress test\" scenario, we generated diverse artificial data sets with varying distributions (identity, uniform, normal, log-normal, and a mixture of these) and compared calculated fold-changes to known values. Additionally, we analyzed a multi-omics biomedical data set to estimate to what extent the findings apply to real-world data. Results: Using arithmetic means as expected values for treatment and reference groups yielded inaccurate fold-change values more frequently than other methods, particularly when subgroup distributions and/or standard deviations differed significantly. Conclusions: The arithmetic mean method, often perceived as standard or picked without considering alternatives, is inferior to other definitions of the group expected value. Methods using median, geometric mean, or paired fold-change combinations are more robust against violations of equal variances or dissimilar group distributions. Adhering to methods less sensitive to data distribution without trade-offs and accurately reporting calculation methods in scientific reports is a reasonable practice to ensure correct interpretation and reproducibility.