Aliado - A design concept of AI for decision support in oncological liver surgery.

BACKGROUND: The interest in artificial intelligence (AI) is increasing. Systematic reviews suggest that there are many machine learning algorithms in surgery, however, only a minority of the studies integrate AI applications in clinical workflows. Our objective was to design and evaluate a concept to use different kinds of AI for decision support in oncological liver surgery along the treatment path. METHODS: In an exploratory co-creation between design experts, surgeons, and data scientists, pain points along the treatment path were identified. Potential designs for AI-assisted solutions were developed and iteratively refined. Finally, an evaluation of the design concept was performed with n = 20 surgeons to get feedback on the different functionalities and evaluate the usability with the System Usability Scale (SUS). Participating surgeons had a mean of 14.0 ± 5.0 years of experience after graduation. RESULTS: The design concept was named "Aliado". Five different scenarios were identified where AI could support surgeons. Mean score of SUS was 68.2 ( ± 13.6 SD). The highest valued functionalities were "individualized prediction of survival, short-term mortality and morbidity", and "individualized recommendation of surgical strategy". CONCLUSION: Aliado is a design prototype that shows how AI could be integrated into the clinical workflow. Even without a fleshed out user interface, the SUS already yielded borderline good results. Expert surgeons rated the functionalities favorably, and most of them expressed their willingness to work with a similar application in the future. Thus, Aliado can serve as a surgical vision of how an ideal AI-based assistance could look like.

Health data science course for clinicians: Time to bridge the skills gap?

BACKGROUND: Data science skills are highly relevant for clinicians working in an era of big data in healthcare. However, these skills are not routinely taught, representing a growing unmet educational need. This education report presents a structured short course that was run to teach clinicians data science and the lessons learnt. METHODS: A 1-day introductory course was conducted within a tertiary hospital in London. It consisted of lectures followed by facilitated pair programming exercises in R, an object-oriented programming language. Feedback was collated and participant responses were graded using a Likert scale. RESULTS: The course was attended by 20 participants. The majority of participants (69%) were in higher speciality cardiology training. While more than half of the participants (56%) received prior training in statistics either through formal taught programmes (e.g., a Master's degree) or online courses, the participants reported several barriers to expanding their skills in data science due to limited programming skills, lack of dedicated time, training opportunities and awareness. After the short course, there was a significant increase in participants' self-rated confidence in using R for data analysis (mean response; before the course: 1.69 ± 1.0, after the course: 3.2 ± 0.9, p = .0005) and awareness of the capabilities of R (mean response; before the course: 2.1 ± 0.9, after the course: 3.6 ± 0.7, p = .0001, on a 5-point Likert scale). CONCLUSION: This proof-of-concept study demonstrates that a structured short course can effectively introduce data science skills to clinicians and supports future educational initiatives to integrate data science teaching into medical education.

From Fetus to Eight: the CHILD Cohort Study.

The CHILD Cohort Study is an active multi-center longitudinal, prospective, population pregnancy cohort study following Canadian infants from fetal life until adulthood. We hypothesized that early life physical and psychosocial environments interact with biological factors (e.g. immunologic, genetic, physiologic, and metabolic) influencing burdensome non-communicable disease outcomes, including asthma and allergic disorders, growth and development, cardio-metabolic health, and neurodevelopmental outcomes that manifest during the life-course. Detailed clinical and physiologic phenotyping at strategic intervals was complemented by environmental sampling, actigraphy and global positioning system measures, biological sampling including gut, breastmilk and nasal microbiome, nutritional studies, genetics, and epigenetic profiling. Of 3,454 families recruited from 2008 to 2012, study retention was 96.0% at 1-year, 93.2% at 5-years and 90.7% at 8-years. Data collection during the SARS-2 COVID-19 pandemic was partially completed via virtual visits. A sub-cohort was implemented, capturing detailed information on the prevalence and predictors of SARS-CoV-2 infection and the health and psychosocial impact of the pandemic on Canadian families. The 13-year clinical assessment launched in 2022 will be completed in 2025. Ultimately, the CHILD Cohort Study provides a data science platform designed to enable a deep understanding of early life factors associated with the development of chronic non-communicable diseases and multimorbidity.

Remdesivir-associated survival outcomes among immunocompromised patients hospitalized for COVID-19: real-world evidence from the Omicron dominant era.

BACKGROUND: Patients with immunocompromising conditions are at an increased risk for coronavirus disease 2019 (COVID-19)-related hospitalizations and mortality. Randomized clinical trials provide limited enrollment, if any, to inform outcomes of such patients treated with remdesivir. METHODS: Using the US PINC AI Healthcare Database, we identified adult patients with immunocompromising conditions, hospitalized for COVID-19 between December 2021 and February 2024. Primary outcome was all-cause inpatient mortality examined in propensity score (PS) matched patients in remdesivir versus non-remdesivir groups. Subgroup analyses were performed for patients with cancer, hematologic malignancies, and solid organ/hematopoietic stem cell transplant recipients. RESULTS: Of 28,966 patients included in the study, 16,730 (58%) received remdesivir during first two days of hospitalization. After PS matching, 8,822 patients in remdesivir and 8,822 patients in non-remdesivir group were analyzed. Remdesivir was associated with a significantly lower mortality among patients with no supplemental oxygen (aHR [95% CI]: 14-day, 0.73 [0.62-0.86]; 28-day, 0.79 [0.68-0.91]) and among those with supplemental oxygen (14-day, 0.75 [0.67-0.85]; 28-day, 0.78 [0.70-0.86]). Remdesivir was also associated with lower mortality in subgroups of patients with cancer, hematological malignancies (including leukemia, lymphoma, and multiple myeloma), and solid organ/hematopoietic stem cell transplantation. CONCLUSIONS: In this large cohort of patients with immunocompromising conditions hospitalized for COVID-19, remdesivir was associated with significant improvement in survival, including patients with varied underlying immunocompromising conditions. The integration of current real-world evidence into clinical guideline recommendations can inform clinical communities to optimize treatment decisions in the evolving COVID-19 era, extending beyond the conclusion of the public health emergency declaration.

Remdesivir Effectiveness in Reducing the Risk of 30-day Readmission in Vulnerable Patients Hospitalized for COVID-19: A Retrospective US Cohort Study Using Propensity Scores.

BACKGROUND: Reducing hospital readmission offer potential benefits for patients, providers, payers, and policymakers to improve quality of healthcare, reduce cost, and improve patient experience. We investigated effectiveness of remdesivir in reducing 30-day COVID-19-related readmission during the Omicron era, including older adults and those with underlying immunocompromising conditions. METHODS: This retrospective study utilized the US PINC AI Healthcare Database to identify adult patients discharged alive from an index COVID-19 hospitalization between December 01, 2021 and February 29, 2024. Odds of 30-day COVID-19-related readmission to the same hospital were compared between patients who received remdesivir vs those not, after balancing characteristics of two groups using inverse probability of treatment weighting (IPTW). Analyses were stratified by maximum supplemental oxygen requirement during index hospitalization. RESULTS: Of 326,033 patients hospitalized for COVID-19 during study period, 210,586 patients met the eligibility criteria. Of these, 109,551 (52%) patients were treated with remdesivir. After IPTW, lower odds of 30-day COVID-19-related readmission were observed in patients who received remdesivir vs those who did not, in the overall population (3.3% vs 4.2%, respectively; odds ratio [95% confidence interval]: 0.78 [0.75-0.80]), elderly population (3.7% vs 4.7%, respectively; 0.78 [0.75-0.81]), and those with underlying immunocompromising conditions (5.3% vs 6.2%, respectively; 0.86 [0.80-0.92]). These results were consistent irrespective of supplemental oxygen requirements. CONCLUSIONS: Treating patients hospitalized for COVID-19 with remdesivir was associated with a significantly lower likelihood of 30-day COVID-19-related readmission across all patients discharged alive from the initial COVID-19 hospitalization, including older adults and those with underlying immunocompromising conditions.

Primary Care Informatics: Vitalizing the Bedrock of Health Care.

Primary care informatics (PCI) professionals address workflow and technology solutions in a wide spectrum of health, ranging from optimizing the experience of the individual patient in the clinic room to supporting the health of populations and augmenting the work of frontline primary care clinical teams. PCI overlaps uniquely with 2 disciplines with an impact on societal health-primary care and health informatics. Primary care is a gateway to health care access and aims to synthesize and coordinate numerous, complex elements of patients' health and medical care in a holistic manner. However, over the past 25 years, primary care has become a specialty in crisis: in a post-COVID-19 world, workforce shortages, clinician burnout, and continuing challenges in health care access all contribute to difficulties in sustaining primary care. Informatics professionals are poised to change this trajectory. In this viewpoint, we aim to inform readers of the discipline of PCI and its importance in the design, support, and maintenance of essential primary care services. Although this work focuses on primary care in the United States, which includes general internal medicine, family medicine, and pediatrics (and depending on definition, includes specialties such as obstetrics and gynecology), many of the principles outlined can also be applied to comparable health care services and settings in other countries. We highlight (1) common global challenges in primary care, (2) recent trends in the evolution of PCI (personalized medicine, population health, social drivers of health, and team-based care), and (3) opportunities to move forward PCI with current and emerging technologies using the 4Cs of primary care framework. In summary, PCI offers important contributions to health care and the informatics field, and there are many opportunities for informatics professionals to enhance the primary care experience for patients, families, and their care teams.

Method to apply temporal graph analysis on electronic patient record data to explore healthcare professional-patient interaction intensity: a cohort study.

AIM: Interactions between patients and healthcare professionals (HCP) during hospital admissions are complex and difficult to interrogate using traditional analysis of electronic patient record (EPR) data. The objective of this study was to determine the feasibility of applying temporal network analytics to EPR data, focusing on HCP-patient interactions over time. METHOD: Network (graph) analysis was applied to routinely collected structured data from an EPR for HCP interactions with individual patients during admissions for patients undergoing renal transplantation between May 2019 and June 2023. Networks were constructed per day of admission within a session, defined by whether the patient was in the intensive care unit (ICU) or standard hospital ward. Connections between HCP were defined using a 60 min period. Reports were generated visualising daily interaction network structures, across individual admissions. RESULTS: 2300 individual networks were constructed from 127 hospital admissions for renal transplantation. The number of nodes or HCP per network varied from 2 to 45, and network metrics provided detail regarding variation in the density and transitivity, changes in structure with different diameters and radii, and variations in centralisation. Each network analysis metric has a contribution to play in describing the dynamics of a daily HCP network and the composite findings provide insights that cannot be determined with standard approaches. CONCLUSIONS: Network analysis provides a novel approach to investigate and visualise patterns of HCP-patient interactions which allow for a deeper understanding of the complex nature of hospital patient care and could have numerous practical operational applications.

Thinking points for effective batch correction on biomedical data.

Batch effects introduce significant variability into high-dimensional data, complicating accurate analysis and leading to potentially misleading conclusions if not adequately addressed. Despite technological and algorithmic advancements in biomedical research, effectively managing batch effects remains a complex challenge requiring comprehensive considerations. This paper underscores the necessity of a flexible and holistic approach for selecting batch effect correction algorithms (BECAs), advocating for proper BECA evaluations and consideration of artificial intelligence-based strategies. We also discuss key challenges in batch effect correction, including the importance of uncovering hidden batch factors and understanding the impact of design imbalance, missing values, and aggressive correction. Our aim is to provide researchers with a robust framework for effective batch effects management and enhancing the reliability of high-dimensional data analyses.

An integrated analysis of the Passifloraceae virome using public-domain data.

Passifloraceae is a plant family that includes several species of interest in the food, medicinal, and ornamental industries. The most relevant species are the purple and yellow varieties of P. edulis, which are among the most highly prized tropical fruits in the international markets. Unfortunately, the rapid expansion of this crop worldwide has resulted in the emergence of several viral diseases that endangered the productivity of this crop. In this work, we performed an integrated analysis of the Passifloraceae virome using public data. We investigated Pubmed and Genbank records and analyzed all the transcriptome data available for members of this plant family. This analysis resulted in the identification of six novel virus associations and six putative new viral species. We also used RNAseq to inspect virus accumulation levels and mixed infections. Using network analysis, we also examined the global distribution of Passiflora viruses and their associations with alternative hosts, which is valuable information in implementing viral disease management strategies. Our data suggest that a large diversity of viruses remains to be discovered. Finally, we used the information gathered in this work to estimate the cross-transmission risk of viruses in Colombian Passiflora fields.

Present and Future Applications of Artificial Intelligence in Kidney Transplantation.

Artificial intelligence (AI) has a wide and increasing range of applications across various sectors. In medicine, AI has already made an impact in numerous fields, rapidly transforming healthcare delivery through its growing applications in diagnosis, treatment and overall patient care. Equally, AI is swiftly and essentially transforming the landscape of kidney transplantation (KT), offering innovative solutions for longstanding problems that have eluded resolution through traditional approaches outside its spectrum. The purpose of this review is to explore the present and future applications of artificial intelligence in KT, with a focus on pre-transplant evaluation, surgical assistance, outcomes and post-transplant care. We discuss its great potential and the inevitable limitations that accompany these technologies. We conclude that by fostering collaboration between AI technologies and medical practitioners, we can pave the way for a future where advanced, personalised care becomes the standard in KT and beyond.

Networks as tools for defining emergent properties of microbiomes and their stability.

The potential promise of the microbiome to ameliorate a wide range of societal and ecological challenges, from disease prevention and treatment to the restoration of entire ecosystems, hinges not only on microbiome engineering but also on the stability of beneficial microbiomes. Yet the properties of microbiome stability remain elusive and challenging to discern due to the complexity of interactions and often intractable diversity within these communities of bacteria, archaea, fungi, and other microeukaryotes. Networks are powerful tools for the study of complex microbiomes, with the potential to elucidate structural patterns of stable communities and generate testable hypotheses for experimental validation. However, the implementation of these analyses introduces a cascade of dichotomies and decision trees due to the lack of consensus on best practices. Here, we provide a road map for network-based microbiome studies with an emphasis on discerning properties of stability. We identify important considerations for data preparation, network construction, and interpretation of network properties. We also highlight remaining limitations and outstanding needs for this field. This review also serves to clarify the varying schools of thought on the application of network theory for microbiome studies and to identify practices that enhance the reproducibility and validity of future work. Video Abstract.

Harnessing population diversity: in search of tools of the trade.

Big neuroscience datasets are not big small datasets when it comes to quantitative data analysis. Neuroscience has now witnessed the advent of many population cohort studies that deep-profile participants, yielding hundreds of measures, capturing dimensions of each individual's position in the broader society. Indeed, there is a rebalancing from small, strictly selected, and thus homogenized cohorts toward always larger, more representative, and thus diverse cohorts. This shift in cohort composition is prompting the revision of incumbent modeling practices. Major sources of population stratification increasingly overshadow the subtle effects that neuroscientists are typically studying. In our opinion, as we sample individuals from always wider diversity backgrounds, we will require a new stack of quantitative tools to realize diversity-aware modeling. We here take inventory of candidate analytical frameworks. Better incorporating driving factors behind population structure will allow refining our understanding of how brain-behavior relationships depend on human subgroups.

Biobanking, digital health and privacy: the choices of 1410 volunteers and neurological patients regarding limitations on use of data and biological samples, return of results and sharing.

BACKGROUND: The growing diffusion of artificial intelligence, data science and digital health has highlighted the role of collection of data and biological samples, thus raising legal and ethical concerns regarding its use and dissemination. Further, the expansion of biobanking, from the basic collection of frozen specimens to the virtual biobanks of specimens and associated data that exist today, has given a revolutionary potential on healthcare systems, particularly in the field of neurological diseases, due to the inaccessibility of central nervous system and the need of non-invasive investigation approaches. Informed Consent (IC) is considered mandatory in all research studies and specimen collections, and must specifically take into account the ethical respect to the individuals to whom the used biological material and data belong. METHODS: We evaluated the attitudes of patients with neurological diseases (NP) and healthy volunteers (HV) towards the donation of biological samples to a biobank for future research studies on neurological diseases, and limitations on the use of data, related to the requirements set by the General Data Protection Regulation (GDPR). The study involved a total of 1454 subjects, including 502 HVs and 952 NPs, recruited at Santa Lucia Foundation IRCCS, Rome, from 2020 to 2024. RESULTS: We found that (i) almost all subjects agreed with the participation in biobanking (ii) and authorization to genetic studies (HV = 99.1%; NP = 98.3%); Regarding the return of results, (iii) we found a statistically significant difference between NP and HV, the latter preferring not to be informed of potential results (HV = 43%; NP = 11.3%; p < 0.0001); (iv) a small number limited the sharing inside European Union (EU) (HV = 4.6%; NP = 6.6%), whereas patients were more likely to refuse transfer outside EU (HV = 7.4%; NP = 10.7% p = 0.05); (v) nearly all patients agreed with the use of additional health data from EMR for research purposes (98.9%). CONCLUSIONS: Consent for the donation of material for research purposes is crucial for biobanking and biomedical research studies that use biological material of human origin. Here, we have shown that choices regarding participation in a neurological biobank can be different between HVs and NPs, even if the benefit for research and scientific progress is recognized. NP have a strong interest in being informed of possible results but limit sharing of samples, highlighting a perception of greater individual or relative benefit, while HV prefer a wide dissemination and sharing of data but not to have the return of the results, favoring a possible benefit for society and knowledge. The results underline the need to carefully manage biological material and data collected in biobanks, in compliance with the GDPR and the specific requests of donors.

Uncovering individualised treatment effects for educational trials.

Large-scale Randomised Controlled Trials (RCTs) are widely regarded as "the gold standard" for testing the causal effects of school-based interventions. RCTs typically present the statistical significance of the average treatment effect (ATE), which captures the effect an intervention has had on average for a given population. However, key decisions in child health and education are often about individuals who may be very different from those averages. One way to identify heterogeneous treatment effects across different individuals, not captured by the ATE, is to conduct subgroup analyses. For example, free school meal (FSM) pupils as required for projects funded by the Education Endowment Foundation (EEF) in England. These subgroup analyses, as we demonstrate in 48 EEF-funded RCTs involving over 200,000 students, are usually not standardised across studies and offer flexible degrees of freedom to researchers, potentially leading to mixed, if not misleading, results. Here, we develop and deploy an alternative to ATE and subgroup analysis, a machine-learning and regression-based framework to predict individualised treatment effects (ITEs). ITEs could show where an intervention worked, for which individuals, and to what extent. Our findings have implications for decision-makers in fields like education, healthcare, law, and clinical practices concerning children and adolescents.

Massive detection of cryptic recessive genetic defects in dairy cattle mining millions of life histories.

BACKGROUND: Dairy cattle breeds are populations of limited effective size, subject to recurrent outbreaks of recessive defects that are commonly studied using positional cloning. However, this strategy, based on the observation of animals with characteristic features, may overlook a number of conditions, such as immune or metabolic genetic disorders, which may be confused with pathologies of environmental etiology. RESULTS: We present a data mining framework specifically designed to detect recessive defects in livestock that have been previously missed due to a lack of specific signs, incomplete penetrance, or incomplete linkage disequilibrium. This approach leverages the massive data generated by genomic selection. Its basic principle is to compare the observed and expected numbers of homozygotes for sliding haplotypes in animals with different life histories. Within three cattle breeds, we report 33 new loci responsible for increased risk of juvenile mortality and present a series of validations based on large-scale genotyping, clinical examination, and functional studies for candidate variants affecting the NOA1, RFC5, and ITGB7 genes. In particular, we describe disorders associated with NOA1 and RFC5 mutations for the first time in vertebrates. CONCLUSIONS: The discovery of these many new defects will help to characterize the genetic basis of inbreeding depression, while their management will improve animal welfare and reduce losses to the industry.

Kinase Drug Discovery: Impact of Open Science and Artificial Intelligence.

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.

A Digital Intervention for Capturing the Real-Time Health Data Needed for Epilepsy Seizure Forecasting: Protocol for a Formative Co-Design and Usability Study (The ATMOSPHERE Study).

BACKGROUND: Epilepsy is a chronic neurological disorder affecting individuals globally, marked by recurrent and apparently unpredictable seizures that pose significant challenges, including increased mortality, injuries, and diminished quality of life. Despite advancements in treatments, a significant proportion of people with epilepsy continue to experience uncontrolled seizures. The apparent unpredictability of these events has been identified as a major concern for people with epilepsy, highlighting the need for innovative seizure forecasting technologies. OBJECTIVE: The ATMOSPHERE study aimed to develop and evaluate a digital intervention, using wearable technology and data science, that provides real-time, individualized seizure forecasting for individuals living with epilepsy. This paper reports the protocol for one of the workstreams focusing on the design and testing of a prototype to capture real-time input data needed for predictive modeling. The first aim was to collaboratively design the prototype (work completed). The second aim is to conduct an "in-the-wild" study to assess usability and refine the prototype (planned research). METHODS: This study uses a person-based approach to design and test the usability of a prototype for real-time seizure precipitant data capture. Phase 1 (work completed) involved co-design with individuals living with epilepsy and health care professionals. Sessions explored users' requirements for the prototype, followed by iterative design of low-fidelity, static prototypes. Phase 2 (planned research) will be an "in-the-wild" usability study involving the deployment of a mid-fidelity, functional prototype for 4 weeks, with the collection of mixed methods usability data to assess the prototype's real-world application, feasibility, acceptability, and engagement. This phase involves primary participants (adults diagnosed with epilepsy) and, optionally, their nominated significant other. The usability study will run in 3 rounds of deployment and data collection, aiming to recruit 5 participants per round, with prototype refinement between rounds. RESULTS: The phase-1 co-design study engaged 22 individuals, resulting in the development of a mid-fidelity, functional prototype based on identified requirements, including the tracking of evidence-based and personalized seizure precipitants. The upcoming phase-2 usability study is expected to provide insights into the prototype's real-world usability, identify areas for improvement, and refine the technology for future development. The estimated completion date of phase 2 is the last quarter of 2024. CONCLUSIONS: The ATMOSPHERE study aims to make a significant step forward in epilepsy management, focusing on the development of a user-centered, noninvasive wearable device for seizure forecasting. Through a collaborative design process and comprehensive usability testing, this research aims to address the critical need for predictive seizure forecasting technologies, offering a promising approach to improving the lives of individuals with epilepsy. By leveraging predictive analytics and personalized machine learning models, this technology seeks to offer a novel approach to managing epilepsy, potentially improving clinical outcomes, including quality of life, through increased predictability and seizure management. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/60129.

A Perspective on Neuroscience Data Standardization with Neurodata Without Borders.

Neuroscience research has evolved to generate increasingly large and complex experimental data sets, and advanced data science tools are taking on central roles in neuroscience research. Neurodata Without Borders (NWB), a standard language for neurophysiology data, has recently emerged as a powerful solution for data management, analysis, and sharing. We here discuss our labs' efforts to implement NWB data science pipelines. We describe general principles and specific use cases that illustrate successes, challenges, and non-trivial decisions in software engineering. We hope that our experience can provide guidance for the neuroscience community and help bridge the gap between experimental neuroscience and data science. Key takeaways from this article are that (1) standardization with NWB requires non-trivial design choices; (2) the general practice of standardization in the lab promotes data awareness and literacy, and improves transparency, rigor, and reproducibility in our science; (3) we offer several feature suggestions to ease the extensibility, publishing/sharing, and usability for NWB standard and users of NWB data.

Assessing the Capacity of High-resolution Commercial Satellite Imagery for Grapevine Downy Mildew Detection and Surveillance in New York state.

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.

A data science-based analysis of socioeconomic determinants impacting pediatric diagnostic radiology utilization during the COVID-19 pandemic.

BACKGROUND: Research on healthcare disparities in pediatric radiology is limited, leading to the persistence of missed care opportunities (MCO). We hypothesize that the COVID-19 pandemic exacerbated existing health disparities in access to pediatric radiology services. OBJECTIVE: Evaluate the social determinants of health and sociodemographic factors related to pediatric radiology MCO before, during, and after the COVID-19 pandemic. MATERIALS AND METHODS: The study examined all outpatient pediatric radiology exams at a pediatric medical center and its affiliate centers from 03/08/19 to 06/07/21 to identify missed care opportunities. Logistic regression with the least absolute shrinkage and selection operator (LASSO) method and classification and regression tree (CART) analysis were used to explore factors and visualize relationships between social determinants and missed care opportunities. RESULTS: A total of 62,009 orders were analyzed: 30,567 pre-pandemic, 3,205 pandemic, and 28,237 initial recovery phase. Median age was 11.34 years (IQR 5.24-15.02), with 50.8% females (31,513/62,009). MCO increased during the pandemic (1,075/3,205; 33.5%) compared to pre-pandemic (5,235/30,567; 17.1%) and initial recovery phase (4,664/28,237; 16.5%). The CART analysis identified changing predictors of missed care opportunities across different periods. Pre-pandemic, these were driven by exam-specific factors and patient age. During the pandemic, social determinants like income, distance, and ethnicity became key. In the initial recovery phase, the focus returned to exam-specific factors and age, but ethnicity continued to influence missed care, particularly in neurological exams for Hispanic patients. Logistic regression revealed similar results: during the pandemic, increased distance from the examination site (OR 1.1), residing outside the state (OR 1.57), Hispanic (OR 1.45), lower household income ($25,000-50,000 (OR 3.660) and $50,000-75,000 (OR 1.866)), orders for infants (OR 1.43), and fluoroscopy (OR 2.3) had higher odds. In the initial recovery phase, factors such as living outside the state (OR 1.19), orders for children (OR 0.79), and being Hispanic (OR 1.15) correlate with higher odds of MCO. CONCLUSION: The application of basic data science techniques is a valuable tool in uncovering complex relationships between sociodemographic factors and disparities in pediatric radiology, offering crucial insights into addressing inequalities in care.