Step In Analysis Research Articles

MRI-Based Brain Tumor Instance Segmentation Using Mask R-CNN

Brain tumor segmentation is a crucial step in medical image analysis for the accurate diagnosis and treatment of patients. Traditional methods for tumor segmentation often require extensive manual effort and are prone to variability. In this study, we propose an automated approach for brain tumor segmentation using Mask R-CNN, a state-of-the-art deep learning model for instance segmentation. Our method leverages MRI images to identify and delineate brain tumors with high precision. We trained the Mask R-CNN model on a dataset of annotated MRI images and evaluated its performance using the mean Average Precision (mAP) metric. The results demonstrate that our model achieves a high mAP of 90.3%, indicating its effectiveness in accurately segmenting brain tumors. This automated approach not only reduces the manual effort required for tumor segmentation but also provides consistent and reliable results, potentially improving clinical outcomes.

Pharmacy stakeholders' views and experiences of the credentialing of advanced or specialist pharmacist practice: A mixed methods systematic review

BackgroundCredentialing of advanced and specialist pharmacist practice (ASPP) provides essential quality assurance for ASPP, which is significantly different to entry-level practice and is developing worldwide. Several credentialing models are in place or under development internationally. Synthesis of the views and experiences of pharmacists and other relevant stakeholders on credentialing is an important research gap. Objective(s)To determine pharmacy stakeholders' views and experiences of ASPP credentialing and to explore facilitators and barriers to credentialing implementation and uptake. MethodsThe Joanna Briggs Institute convergent integrated approach for mixed methods systematic reviews was followed. The review protocol was pre-registered with PROSPERO. Five electronic databases (Medline, CINAHL, Embase, Web of Science, Google Scholar) were searched from inception to August 2022 for qualitative, quantitative, or mixed methods studies that reported the views and experiences of pharmacy stakeholders on ASPP credentialing. The Mixed Methods Appraisal Tool was used to quality appraise included studies. Thematic synthesis was undertaken to analyse and integrate data from included studies. All screening and data analysis steps were performed by two reviewers independently, with additional author input where required. ResultsSixty studies were included, after screening titles and abstracts (n = 9055) and full texts (n = 228). Studies represented the views of pharmacists, pharmacy managers/employers and professional/representative bodies in hospital, community pharmacy, general practice/primary care, and academic sectors, from 40 countries. Four analytical themes were generated describing the factors, including facilitators and barriers, to be considered when developing or optimising ASPP credentialing: I. Drivers of credentialing, II. Developing ASPP competence, III. Optimising credentialing implementation, and IV. Enhancing credentialing uptake. ConclusionsThis systematic review is the first to synthesise pharmacy stakeholders' views and experiences of ASPP credentialing. A conceptual framework highlights contextual factors, facilitators, barriers, and inter-relationships which should be considered by pharmacists, policymakers, and other key stakeholders when implementing ASPP credentialing.

Systematic Comparison of Extract Clean-Up with Currently Used Sorbents for Dispersive Solid-Phase Extraction

Dispersive solid-phase extraction (dSPE) is a crucial step for multiresidue analysis used to remove matrix components from extracts. This purification prevents contamination of instrumental equipment and improves method selectivity, sensitivity, and reproducibility. Therefore, a clean-up step is recommended, but an over-purified extract can lead to analyte loss due to adsorption to the sorbent. This study provides a systematic comparison of the advantages and disadvantages of the well-established dSPE sorbents PSA, GCB, and C18 and the novel dSPE sorbents chitin, chitosan, multi-walled carbon nanotube (MWCNT), and Z-Sep® (zirconium-based sorbent). They were tested regarding their clean-up capacity by visual inspection, UV, and GC-MS measurements. The recovery rates of 98 analytes, including pesticides, active pharmaceutical ingredients, and emerging environmental pollutants with a broad range of physicochemical properties, were determined by GC-MS/MS. Experiments were performed with five different matrices, commonly used in food analysis (spinach, orange, avocado, salmon, and bovine liver). Overall, Z-Sep® was the best sorbent regarding clean-up capacity, reducing matrix components to the greatest extent with a median of 50% in UV and GC-MS measurements, while MWCNTs had the largest impact on analyte recovery, with 14 analytes showing recoveries below 70%. PSA showed the best performance overall.

Transforming Transcriptomics: The Impact of RNA Sequencing Technology

Aim: This study aimed to explore the advancements, methodologies, and applications of RNA sequencing (RNA-seq) technology, emphasizing its transformative impact on genomic research. Study Design: The research involved an in-depth review of RNA-seq technology, focusing on the steps of sample preparation, sequencing, and data analysis. Place and Duration of Study: Conducted through a detailed literature review over six months, at Hygia college of Pharmacy the study sourced information from various molecular biology and genomics publications. Methodology: Advanced computational techniques were utilized to map and quantify RNA sequences, facilitating a comprehensive analysis of gene expression patterns, alternative splicing, and novel transcript discovery. High-throughput sequencing platforms like Illumina and PacBio generated extensive datasets from diverse biological samples, including tissues, single cells, and environmental microbiomes. Results: The results highlighted RNA-seq's ability to provide a high-resolution view of the transcriptome, surpassing previous technologies in both sensitivity and accuracy. RNA-seq uncovered critical insights into differential gene expression, identifying significant pathways involved in development, disease, and environmental responses. The technology also discovered numerous previously unannotated transcripts and isoforms, contributing to the expansion of existing genomic databases. Conclusion: The study concludes that RNA-seq is a crucial advancement in molecular biology, offering unprecedented insights into gene regulation and expression. Its adoption has facilitated significant breakthroughs in understanding cellular processes, disease mechanisms, and therapeutic targets. As RNA-seq technology continues to evolve, it promises to drive further innovations and applications across diverse fields in the life sciences.

The implementation of learning writing and development of character values of high school students

This study aims to examine and describe the implementation of the stages of the learning writing process and the development of character values for senior high school students. The descriptive qualitative approach was used in the present study. The process of learning to write and developing student character values was analyzed and described. Data analysis steps include data reduction, data presentation, and drawing conclusions. The results of the research show that learning to write and develop students' character values is carried out in such stages as the context development stage (introduction), model review (core), and inference learning (closing). The characters fostered in learning include religiosity, discipline, curiosity, diligence, honesty, a love for reading, creativity, friendliness or communication skills, democracy, tolerance, independence, and responsibility.

A qualitative study on the experiences of hypertension patients undergoing cupping therapy

Hypertension is one of the silent killer diseases because patients often do not feel the symptoms. Therapies that are commonly applied are pharmacological and non-pharmacological therapies, which include complementary medicine. These complementary therapies play a role in promoting healing, comfort and care around the world. One of the treatments used in hypertensive patients is cupping. This study aims to explore the experiences and perceptions of hypertensive patients undergoing cupping complementary therapy. A qualitative descriptive design has been used in this study. There were 6 participants selected using purposive sampling from two clinics namely Rumah Sehat Insani and Rumah Sehat Holistik in Care. The data collection method used was in-depth interviews. Data were processed and analyzed using seven steps of data analysis based on Colaizzi. There are 4 theme findings including the description of patient perceptions related to hypertension which includes perceptions related to knowledge, causes and symptoms of hypertension; description of perceptions related to cupping therapy including unfamiliarity with the term complementary medicine, perceptions of cupping functions and types of cupping; benefits/effects of cupping felt by participants in the form of psychological effects and physiological effects; and reasons for participants undergoing cupping therapy in the form of the influence of family and friends, the influence of distance, religious factors, drug factors, and physical factors. Most participants were still unfamiliar with the term complementary medicine. The expression of positive effects experienced by participants that could be felt immediately after treatment was the reason for using cupping. This suggests its potential as part of a holistic approach in the management of this condition. The result encourage further research to validate this approach as a safe complementary treatment for hypertension.

Community stakeholder feedback for development of a volunteer-coached behavioral activation for youth in a low-resource community

Youth in low-resource communities have limited access to mental health (MH) services. This exploratory study reports community stakeholder feedback for stressors affecting youth MH and development of a volunteer-coach provided behavioral activation (BA) program for youth in a low-resource community. Eight focus groups with youth (n = 7) and adults (n = 35) were conducted during January-September 2023. Data analysis followed the inductive thematic analysis steps. Participants attributed the high prevalence of youth MH problems to high-pressure environment, lack of support, hopelessness about the future, and negative impact of social media. Youth participants expressed mistrust of MH professionals and were hesitant to endorse a volunteer-coached BA program. They stated the non-professionals will be better than professional therapists but mentioned the stigmatization of mental-health help-seeking and related fear of bullying. Adults were more supportive of the program but pointed out such practical barriers as lack of parental support and availability of youth time due to after-school extracurricular activities. Participants also provided suggestions to increase parents’ buy-in of the program. Stakeholder feedback illustrated multiple challenges for developing and implementing an evidence-based MH intervention program for youth in a low-resource community. MH literacy education and alleviation of stigma about MH help-seeking are essential steps.

Measurement uncertainty for Dissolution tests using Monte Carlo methods – Uncertainties arising from sampling and analytical steps

BackgroundThe dissolution test is a critical quality control method in the pharmaceutical industry, primarily used to assess drug bioavailability and ensure the consistency of manufactured batches. This test simulates the release of the active ingredient in the body and verifies compliance with specifications through multiple stages (e.g., S1, S2, S3). However, measurement uncertainty can undermine the reliability of test results, potentially leading to erroneous conformity decisions. This study aims to quantify the uncertainties arising from the dissolution, sampling, and quantification steps, as well as to estimate the risk of false conformity decisions in the dissolution test results for tablets. ResultsA comprehensive uncertainty evaluation was conducted for the dissolution, sampling, and quantification stages. The Monte Carlo method (MCM) was applied to assess the overall measurement uncertainty, which was determined to be approximately 5.2 %. The study revealed that sampling was the predominant contributor, accounting for 92 % of the total uncertainty, compared to 7 % from quantification and 1 % from dissolution steps. An MS Excel spreadsheet was developed to calculate the total risk value and classify it as either producer or consumer risk. This tool enables the evaluation of uncertainty in both individual tested units and mean values, depending on the stage criteria (e.g., S1, S2, S3). The proposed improved criteria were tested across various scenarios where the risk of false decisions due to measurement uncertainty was considered. These tests demonstrated the effectiveness of the criteria in managing consumer risk, highlighting the critical impact of sampling uncertainty on the decision-making process. Significance and noveltyThis study introduces novel, improved criteria for the dissolution test that account for the risk of false decisions due to measurement uncertainty. The proposed criteria significantly enhance the reliability of drug quality assessments. The study provides a robust framework for minimizing false conformity decisions. The development of a practical MS Excel tool further supports the reliable assessment of dissolution test results, ensuring higher standards of drug safety and efficacy in pharmaceutical quality control.

Overview and confirmatory and exploratory factor analysis of AI literacy scale

Comprehensive concepts of AI literacy (AIL) and valid measures are essential for research (e.g., intervention studies) and practice (e.g., personnel selection/development) alike. To date, several scales have been published, sharing standard features but differing in some aspects. We first aim to briefly overview instruments identified from unsystematic literature research in February 2023. We identified four scales and one collection of items. We describe the instruments and compare them. We identified common themes and overlaps in the instruments and developmental procedure. We also found differences regarding scale development procedures and latent dimensions. Following this literature research, we came to the conclusion that the literature on AI literacy measurement was fragmented, and little effort was undertaken to integrate different AI literacy conceptualizations. The second focus of this study is to test the factorial structures of existing AIL measurement instruments and identify latent dimensions of AIL across all instruments. We used robust maximum-likelihood confirmatory factor analysis to test factorial structures in a joint survey of all AIL items in an English-speaking online sample (N=219). We found general support for all instruments' factorial structures with minor deviations from the original factorial structures for some of the instruments. In a second analysis step, to address the issue of fragmented research on AI literacy conceptualization and measurement, we used principal axis exploratory factor analysis with oblique rotation to identify latent dimensions across all items. We found four correlated latent dimensions of AIL, which were mostly interpretable as the abilities to use and interact with AI, to design/program AI (incl. in-depth technical knowledge), to perform complex cognitive operations regarding AI (e.g., ethical considerations), and a common factor for the abilities to detect AI/differentiate between AI and humans and manage persuasive influences of AI (i.e., persuasion literacy). Our findings sort the multitude of AIL instruments and reveal four latent core dimensions of AIL. Thus, they contribute importantly to the conceptual understanding of AIL that has been fragmented so far.

English Foreign Language Teachers’ Strategy in Teaching Speaking Classes: A Case Study at the Rumah Inggris Jogja

This research aims to find out English teachers' strategies in teaching English-speaking classes at the Rumah English Jogja, explore the challenges faced by two English teachers in teaching speaking classes, and how they solve these problems. The present study utilized qualitative design with descriptive analysis, and the respondents were two teachers who teach English speaking classes. Observations and semi-structured interviews were employed to obtain the data. All data gathered were gone through several analysis steps: data reduction, data display, and conclusion. The findings revealed that the teaching strategies used by Mr. A were the question & answer, conversation, drilling, storytelling, and conversation strategy. Meanwhile, Mr. M, applied translation, repeating, group work, drilling, role play, reporting, game, story completion, interview, and question & answer. The result of the interview with Mr. A, and Mr M, revealed that they found it difficult to deal with new students as they were not well prepared to join the speaking class. Mr. A found it hard to stimulate and motivate his students who were not familiar with the topic discussed. Meanwhile, Mr. M, pointed out some of his difficulties, including the difference in learners' characteristics, and the variety of learners' needs, wants, and lacks in the class. Having a personal approach to students, being good friends, and creating an enjoyable learning atmosphere are several good efforts to do.

Problem Faced by Indonesian Internship Students in Thai English Language Teaching Classroom Context

What are the problems faced by Indonesian internship students in Thai English Language Teaching Classrooms Based on the problem statement, the proposed objective is to find out the problem or the obstacles experienced by internship students in English language teaching classrooms while teaching in Thailand School. Considering the different cultural backgrounds, this research is expected to explore the internship problems and whether internship students experience any cultural issues. This research uses a qualitative method that explores cross-cultural communication issues in participants, according to Creswell (2018, p. 294) In most cases, qualitative research presents the data, interprets the data, validates it, and shows the potential of the research results in order to expand the steps of data analysis and the methods used. In qualitative research, the social context is taken into consideration while examining events from the perspectives of the individuals being studied. This includes research that uses interpretative naturalistic techniques (Denzin & Lincoln, 2005 Kihlgren, 2016). The findings of the interviews from the three domains of problems faced by the internship students during the teaching internship program are based on the findings of the interview results that have been conducted by the researcher. 1. Teaching Learning Aspects as the Problem in ELT Classroom, 2. Personal Aspects as the Problem in ELT Classroom, 3. Communication Aspects as the Problem in ELT Classroom. Based on the findings that the researcher has found, the difficulties experienced by internship students during the internship program are quite varied, so it is in accordance with the problems found by the researcher that the main problems experienced by internship students in the internship program come from the cross-cultural problems that occur in English language teaching classrooms.

Clustering scRNA-seq data with the cross-view collaborative information fusion strategy.

Single-cell RNA sequencing (scRNA-seq) technology has revolutionized biological research by enabling high-throughput, cellular-resolution gene expression profiling. A critical step in scRNA-seq data analysis is cell clustering, which supports downstream analyses. However, the high-dimensional and sparse nature of scRNA-seq data poses significant challenges to existing clustering methods. Furthermore, integrating gene expression information with potential cell structure data remains largely unexplored. Here, we present scCFIB, a novel information bottleneck (IB)-based clustering algorithm that leverages the power of IB for efficient processing of high-dimensional sparse data and incorporates a cross-view fusion strategy to achieve robust cell clustering. scCFIB constructs a multi-feature space by establishing two distinct views from the original features. We then formulate the cell clustering problem as a target loss function within the IB framework, employing a collaborative information fusion strategy. To further optimize scCFIB's performance, we introduce a novel sequential optimization approach through an iterative process. Benchmarking against established methods on diverse scRNA-seq datasets demonstrates that scCFIB achieves superior performance in scRNA-seq data clustering tasks. Availability: the source code is publicly available on GitHub: https://github.com/weixiaojiao/scCFIB.

Power-Law Scaling Relating the Average Charge State and Kinetic Energy in Expanding Laser-Driven Plasmas.

A universal power-law scaling z[over ¯]∝E^{0.4} in the correlation between the average ion charge state z[over ¯] and kinetic energy E in expanding laser-driven tin plasmas is identified. Universality here refers to an insensitivity to all experimental conditions: target geometry, expansion direction, laser wavelength, and power density. The power law is accurately captured in an analytical consideration of the dependence of the charge state on temperature and the subsequent transfer of internal to kinetic energy in the expansion. These analytical steps are individually, and collectively, validated by a two-dimensional radiation-hydrodynamic simulation of an expanding laser-driven plasma. This power-law behavior is expected to hold also for dense plasma containing heavier, complex ions such as those relevant to current and future laser-driven plasma light sources.

Revolutionizing Bitcoin price forecasts: A comparative study of advanced hybrid deep learning architectures

This paper employs a deep learning network with a comprehensive architecture to forecast Bitcoin prices, enhancing accuracy by integrating two meta-heuristic optimization algorithms, INFO and NRBO. Empirical results demonstrate that the hybrid model significantly outperforms the LSTM in both fit and predictive accuracy across in-sample and out-of-sample data. Notably, the NRBO-CNN-BiLSTM-Attention model substantially improves accuracy in 5-day and 15-day forecasts, reducing the MAPE by over 50 % compared to the LSTM model, thereby significantly enhancing overall predictive performance. The robustness of our results is supported by the MCS tests. Furthermore, strategically modifying time steps in data analysis optimizes model performance.

Asymptotic Confidence Interval, Sample Size Formulas and Comparison Test for the Agreement Intra-Class Correlation Coefficient in Inter-Rater Reliability Studies.

The agreement intra-class correlation coefficient (ICCa) is a suitable statistical index for inter-rater reliability studies. With balanced Gaussian data, we prove the explicit form of ICCa asymptotic normality (ASN), valid both with analysis of variance (ANOVA), maximum likelihood (ML), or restricted ML (REML) estimates. An asymptotic confidence interval is then derived and its performances are examined by simulation compared to the most commonly used methods, under small, moderate and large sample size designs. Then, we deduce sample size calculation formulas, for the number of subjects and observers needed, to achieve a desired confidence interval width or an acceptable ICCa value test power and give concrete examples of their use. Finally, we propose a likelihood ratio test (LRT) to compare two ICCa's from two distinct subpopulations of patients (or raters) and study by simulation its first order risk and power properties. These methods are illustrated using data from two inter-rater reliability studies, one in physiotherapy with 42 patients and 10 raters and the second in neonatology with 80 subjects and 14 raters. In conclusion, we made recommendations to employ the proposed confidence interval for medium to large samples combined with the quantification of the minimal required sample size at the planning step, or the posterior-power at the analysis step, using simple dedicated formulas. Furthermore, with sufficient sizes, the proposed LRT seems suitable to compare inter-rater reliability between two patient subpopulations. Used wisely, this proposed methods toolbox can remedy common current issues in inter-rater reliability studies.

Adaptation of an Eddy Current Model for Characterizing Subsurface Defects in CFRP Plates Using FEM Analysis Based on Energy Functional

In this work, a known Eddy Current (EC) model is adapted to characterize subsurface defects in carbon fiber-reinforced polymer (CFRP) plates intended for the civil aerospace industry. The considered defects include delaminations, microcracks, porosity, fiber breakage, and the simultaneous presence of these defects. Each defect is modeled as an additive variation in the material’s electrical conductivity tensor, allowing for a detailed mathematical representation of the defect’s influence on the CFRP’s electromagnetic behavior. The additivity of the variations in the conductivity tensor is justified by the assumption that the defects are not visible to the naked eye, implying that the material does not require non-destructive testing. The adapted EC model admits a unique and stable solution by verifying that all analytical steps are satisfied. To reconstruct 2D maps of the magnetic flux density amplitude, a FEM formulation is adopted, based on the energy functional because it ensures a stable and consistent numerical formulation given its coercivity. Moreover, the numerical approach allows precise and reliable numerical solutions, enhancing the capability to detect and quantify defects. The numerical results show that the obtained 2D maps are entirely superimposable on those highlighting the distribution of mechanical stress states known in the literature, offering a clear advantage in terms of detection costs. This approach provides an effective and economical solution for the non-destructive inspection of CFRP, ensuring accurate and timely defect diagnosis for maintaining structural integrity.

An automatic approach for the stability analysis of multi-relaxation-time lattice Boltzmann models

This paper is concerned with the weighted L2-stability of the lattice Boltzmann method (LBM) for the incompressible Navier-Stokes equations. Such stability is formulated for the linearized LBM and can lead to convergence proof of the nonlinear problem. A key step in this stability analysis is to find an appropriate decomposition for the Jacobian matrix of the collision term. For multi-relaxation-time (MRT) models, it is very difficult to analytically obtain such a decomposition and how to overcome this difficulty for MRT models is still a challenge. In this paper, we propose an automatic approach to prove the weighted L2-stability of the LBM with general collision models. Instead of exploring the decomposition for each specific model, we partially fix the decomposition and turn to show the symmetry and semi-negative definiteness of the other part of the decomposition, which can be automatically examined by a simple computer code. We apply our automatic approach to ten MRT models and stability conditions are generated by the code immediately. In particular, for the popular D2Q9 orthogonal MRT model, the stability condition we obtained has one less constraint than that given in previous work. As verifications, we also provide some analytical proofs for the stability of orthogonal and weighted-orthogonal MRT models. The proofs are much more complicated than the automatic approach, not to mention that those for nonorthogonal models are unavailable. These demonstrate the efficiency and superiority of the proposed automatic approach. With this approach, proving the weighted L2-stability and thereby the convergence of general MRT models becomes straightforward.

DATA DRIVEN AND CELL SPECIFIC DETERMINATION OF NUCLEI-ASSOCIATED ACTIN STRUCTURE

In the specialized field of cellular mechanosignaling, the intricate relationship between the cytoskeleton and nucleus is crucial for determining the behavior and fate of mesenchymal stem cells (MSCs). Existing analytical methods for filamentous actin fibers (F-actin) suffer from issues of accuracy and reproducibility. To address this, our research introduces a significant advancement in image analysis by utilizing two deep-learning segmentation Convolutional Neural Networks (CNNs) based on U-Net architecture. This algorithm precisely quantifies F-actin and offers reproducible data from 3D confocal microscopy images. Our CNNs automatically extract the 3D shape of both the nucleus and individual actin fibers, thereby enabling the geometric reconstruction of these critical cellular components. We applied this methodology to MSCs exposed to low-intensity vibration, and hypothesized that mechanical stimuli will induce perinuclear actin remodeling. Confocal Z-stack images of MSCs were captured using a 40x oil lens and a Zeiss LSM 900 microscope. Nucleus and F-actin structures were stained with Hoechst 33342 and Phalloidin, respectively. Nucleus-based images were employed to mask and isolate actin fibers within the nuclear vicinity. A specialized deep-learning segmentation model was engineered within the PyTorch framework. For model training, a selective 2% of nuclei and F-actin images were annotated. Specifically, three layers from each of six representative nuclei, among approximately 500 cross-sectional layers, were meticulously selected; a similar approach was employed for actin. The model underwent 200 epochs of training. Post-training, the deep-learning model was employed to process all collected cross-sectional images of F-actin and nuclei. A subsequent analytical step involved the scrutiny of intersecting segmented fibers between consecutive layers for geometrically accurate actin fiber reconstruction. We analyzed 102 control and 110 vibration-treated mesenchymal stem cells (MSCs) by utilizing our deep-learning-based reconstruction algorithm on confocal Z-stack images. Our data revealed an 8% decrease in nuclear height from 5.73 µm to 5.28 µm (p < 0.001) upon application of low-intensity vibration. In contrast, the two groups observed no significant difference in nuclear volume. Accompanying these changes at the nuclear level, the following changes in the F-actin cytoskeleton were observed upon LIV application. The total number of actin filaments per cell increased from 117 to 150. The average volume of individual actin fibers rose from 0.40 µm³ to 0.43 µm³. Notably, the volume of fibers at the apical nuclear surface increased from 0.35 µm³ to 0.46 µm³. While the average length of actin fibers in the apical nuclear surface remained largely unchanged due to the addition of smaller fibers in LIV groups, the LIV group had a larger number of fibers that were larger than 15µm.

An open-source framework for end-to-end analysis of electronic health record data

With progressive digitalization of healthcare systems worldwide, large-scale collection of electronic health records (EHRs) has become commonplace. However, an extensible framework for comprehensive exploratory analysis that accounts for data heterogeneity is missing. Here we introduce ehrapy, a modular open-source Python framework designed for exploratory analysis of heterogeneous epidemiology and EHR data. ehrapy incorporates a series of analytical steps, from data extraction and quality control to the generation of low-dimensional representations. Complemented by rich statistical modules, ehrapy facilitates associating patients with disease states, differential comparison between patient clusters, survival analysis, trajectory inference, causal inference and more. Leveraging ontologies, ehrapy further enables data sharing and training EHR deep learning models, paving the way for foundational models in biomedical research. We demonstrate ehrapy’s features in six distinct examples. We applied ehrapy to stratify patients affected by unspecified pneumonia into finer-grained phenotypes. Furthermore, we reveal biomarkers for significant differences in survival among these groups. Additionally, we quantify medication-class effects of pneumonia medications on length of stay. We further leveraged ehrapy to analyze cardiovascular risks across different data modalities. We reconstructed disease state trajectories in patients with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) based on imaging data. Finally, we conducted a case study to demonstrate how ehrapy can detect and mitigate biases in EHR data. ehrapy, thus, provides a framework that we envision will standardize analysis pipelines on EHR data and serve as a cornerstone for the community.

Marine spatial planning for socio‐ecological management of animal‐associated microbiomes

AbstractBiodiversity changes and habitat shifts are two phenomena substantially reshaping marine life on our present and future planet. Although those phenomena are well recognized on the macrobial level, they currently do not receive similar attention on the microbial level. Generally, microbiome diversity and function, associated with and governing the health and fitness of their host organisms, are neglected in conservation efforts. This is especially problematic as previous research has highlighted that host‐associated microbes (microbiomes) may display distribution patterns that are not only correlated with host animal biogeographies but also with other factors such as prevailing environmental conditions. Here, marine spatial planning for socio‐ecological management of animal‐associated microbiomes is discussed, using deep‐sea sponge and coral‐associated microbiomes as an example of how to incorporate microbial diversity into conservation planning. We advocate for a holistic and integrative approach to marine spatial planning that incorporates the larger habitat, the host, the microbiome, as well as the socio‐economic and cultural perspective, throughout the whole decision‐making process. A general workflow containing the needed steps to establish microbiome‐integrated marine protected areas is presented, as well as the analytical steps and results underlying the implementation of the world's first microbiome‐considered marine conservation network on the Scotian Shelf off eastern Canada.