Data Science Methods Research Articles

Assessing the Impact and Cost-Effectiveness of Exposome Interventions on Alzheimer’s Disease: A Review of Agent-Based Modeling and Other Data Science Methods for Causal Inference

Background: The exposome (e.g., totality of environmental exposures) and its role in Alzheimer’s Disease and Alzheimer’s Disease and Related Dementias (AD/ADRD) are increasingly critical areas of study. However, little is known about how interventions on the exposome, including personal behavioral modification or policy-level interventions, may impact AD/ADRD disease burden at the population level in real-world settings and the cost-effectiveness of interventions. Methods: We performed a critical review to discuss the challenges in modeling exposome interventions on population-level AD/ADRD burden and the potential of using agent-based modeling (ABM) and other advanced data science methods for causal inference to achieve this. Results: We describe how ABM can be used for empirical causal inference modeling and provide a virtual laboratory for simulating the impacts of personal and policy-level interventions. These hypothetical experiments can provide insight into the optimal timing, targeting, and duration of interventions, identifying optimal combinations of interventions, and can be augmented with economic analyses to evaluate the cost-effectiveness of interventions. We also discuss other data science methods, including structural equation modeling and Mendelian randomization. Lastly, we discuss challenges in modeling the complex exposome, including high dimensional and sparse data, the need to account for dynamic changes over time and over the life course, and the role of exposome burden scores developed using item response theory models and artificial intelligence to address these challenges. Conclusions: This critical review highlights opportunities and challenges in modeling exposome interventions on population-level AD/ADRD disease burden while considering the cost-effectiveness of different interventions, which can be used to aid data-driven policy decisions.

Analysis methods for large-scale neuronal recordings.

Simultaneous recordings from hundreds or thousands of neurons are becoming routine because of innovations in instrumentation, molecular tools, and data processing software. Such recordings can be analyzed with data science methods, but it is not immediately clear what methods to use or how to adapt them for neuroscience applications. We review, categorize, and illustrate diverse analysis methods for neural population recordings and describe how these methods have been used to make progress on longstanding questions in neuroscience. We review a variety of approaches, ranging from the mathematically simple to the complex, from exploratory to hypothesis-driven, and from recently developed to more established methods. We also illustrate some of the common statistical pitfalls in analyzing large-scale neural data.

METHODS AND PRACTICES OF TRAINING AND APPLICATION OF CONVOLUTIONAL NEURAL NETWORKS FOR DETECTING VARIOUS DEFECTS ON THE SURFACES OF BUILDING STRUCTURES

The subject of research in this article is the practice of implementing and applying types of artificial intelligence – convolutional neural networks and data science - to detect various defects on the surfaces of building structures. The purpose of the study is to identify the advantages and disadvantages of implementing and using convolutional neural network technologies together with other software and hardware components to automate traditional methods of monitoring the technical condition of the external surfaces of buildings and structures. The article solves the following tasks: to substantiate the effectiveness of implementation of convolutional neural network technologies and data science methods; to apply them in practice with software and hardware technologies to automate traditional methods of performing work on detecting various defects on the surfaces of building structures in the construction and operation of buildings and structures; to show the problems and shortcomings of these methods and technologies. To solve the tasks, an integrated approach was used with the use of general scientific and special research methods (analysis, explanation, generalisation, comparison). The following results have been obtained: the features that affect the accuracy of the analysis of the collected data used by neural convolutional network technologies to detect various defects on the surfaces of building structures have been identified; practices and methods for more efficient and accurate application of this technology have been reflected. Conclusions: the study allowed to identify the practical opportunities and problems that exist in this technology; recommendations for the effective use of this technology were developed; factors influencing the more efficient use of this technology in industry were identified.

МЕТОДИ І ПРАКТИКИ ВПРОВАДЖЕННЯ ТА ЗАСТОСУВАННЯ РІЗНИХ ТИПІВ ШТУЧНОГО ІНТЕЛЕКТУ І НАУКИ ПРО ДАНІ ДЛЯ РІШЕННЯ ПРОБЛЕМ У ВОДНІЙ ІНФРАСТРУКТУРІ

The subject of the study in this article was the practice of implementing and applying various types of artificial intelligence and data science to detect leaks from water supply networks, to monitor freshwater conditions and to detect pollution, clean freshwater bodies from waste from industrial and mining enterprises, control freshwater flow and develop more efficient water filtration methods. The article identifies the advantages and disadvantages of the practice of introducing and applying various types of artificial intelligence and data science technologies to automate traditional methods of monitoring, control and related work in the water industry. The article addresses the following objectives: to substantiate the effectiveness of implementation of various types of artificial intelligence technologies and data science methods and their practical application with software and hardware technologies to automate traditional methods of performing work in the water industry. To solve the tasks set, the methodology used was based on general scientific and special research methods, such as theoretical methods (analysis, explanation, generalisation, comparison). The use of this approach allowed us to obtain the following results: the features that affect the accuracy of the analysis of collected data used by technologies of various types of artificial intelligence and data science methods were identified. Practices and methods for more efficient and accurate application of this technology are reflected. Scientific data are analysed. The study allowed identifying the practical opportunities and problems of this technology. Recommendations for the effective use of this technology have been developed. The factors that influence the effective use of this technology in industry are identified.

Application of multiparametric methods of data science for the classification of Russian subjects on the basis of subsidisation

The relevance of the study is justified by the importance of monitoring and forecasting the subsidisation of the Russian regions in order to identify the main criteria for classifying subjects on the basis of subsidisation. In a brief review of the literature, mathematical models used to model the subsidisation of the Russian regions are considered. They have mainly fixed socio-economic indicators that need to be given attention while applying, and also regression models are used, but mathematically sound recommendations for the withdrawal of regions from clusters of subsidisation are not provided. The paper analyses the socio-economic and demographic indicators of the Russian regions applying methods that identify patterns in a multiparametric dataset. The methods of traditional statistical analysis and machine learning, including the author’s ones, are used. Statistically significant patterns have been identified, reflecting the relationship of subsidisation with such indicators as investments in fixed capital, fixed assets, average per capita income and average size of assigned pensions, unemployment rate, etc. The performed logical and statistical analysis strongly supports the use of machine learning (Data Science) methods in identifying statistically significant relationships between various indicators characterising the development of the regions of the Russian Federation.

Context-dependent agricultural intensification pathways to increase rice production in India

Yield gap analysis is used to characterize the untapped production potential of cropping systems. With emerging large-n agronomic datasets and data science methods, pathways for narrowing yield gaps can be identified that provide actionable insights into where and how cropping systems can be sustainably intensified. Here we characterize the contributing factors to rice yield gaps across seven Indian states, with a case study region used to assess the power of intervention targeting. Primary yield constraints in the case study region were nitrogen and irrigation, but scenario analysis suggests modest average yield gains with universal adoption of higher nitrogen rates. When nitrogen limited fields are targeted for practice change (47% of the sample), yield gains are predicted to double. When nitrogen and irrigation co-limitations are targeted (20% of the sample), yield gains more than tripled. Results suggest that analytics-led strategies for crop intensification can generate transformative advances in productivity, profitability, and environmental outcomes.

Study path analyses for quality assurance and support of study planning

AbstractUtilizing student lifecycle data provided by campus management systems yields the opportunity to conduct study path analyses. Methods of artificial intelligence (AI) and data science can be used to analyze study paths, identify indicators for success, and gain insights into problems and issues of student cohorts following different study paths. Meanwhile, AI can also be used to support students through informed study planning. This article presents the project AIStudyBuddy with its focus on utilizing rule-based AI and process mining to support study planning and cohort monitoring. The concept of a reference architecture and data model for study path analytics as well as details on the development of the two user applications, StudyBuddy for students and BuddyAnalytics for study program designers, are presented. By exploring how AI and process mining can be applied in the scope of the two applications, the article addresses the question of how AI can be used for quality assurance in study planning and student cohort monitoring.

Some Aspects and Convergence of Human and Veterinary Drug Repositioning.

Drug innovation traditionally follows a de novo approach with new molecules through a complex preclinical and clinical pathway. In addition to this strategy, drug repositioning has also become an important complementary approach, which can be shorter, cheaper, and less risky. This review provides an overview of drug innovation in both human and veterinary medicine, with a focus on drug repositioning. The evolution of drug repositioning and the effectiveness of this approach are presented, including the growing role of data science and computational modeling methods in identifying drugs with potential for repositioning. Certain business aspects of drug innovation, especially the relevant factors of market exclusivity, are also discussed. Despite the promising potential of drug repositioning for innovation, it remains underutilized, especially in veterinary applications. To change this landscape for mutual benefits of human and veterinary drug innovation, further exploitation of the potency of drug repositioning is necessary through closer cooperation between all stakeholders, academia, industry, pharmaceutical authorities, and innovation policy makers, and the integration of human and veterinary repositioning into a unified innovation space. For this purpose, the establishment of the conceptually new "One Health Drug Repositioning Platform" is proposed. Oncology is one of the disease areas where this platform can significantly support the development of new drugs for human and dog (or other companion animals) anticancer therapies. As an example of the utilization of human and veterinary drugs for veterinary repositioning, the use of COX inhibitors to treat dog cancers is reviewed.

Fixed points of regular set-valued mappings in quasi-metric spaces

Metric fixed point theory is becoming increasingly significant across various fields, including data science and iterative methods for solving optimization problems. This paper aims to introduce new fixed point theorems for set-valued mappings under novel regularity conditions, such as orbital regularity and orbital pseudo-Lipschitzness. Instead of traditional metric spaces, we adopt the framework of quasi-metric spaces, motivated by the need to address problems in spaces that are not necessarily metric, such as function spaces of homogeneous type. We also explore the stability of the set of fixed points under variations of the set-valued mapping. Additionally, we provide estimates for the distances from a given point to the set of fixed points and between two sets of fixed points. Building on these findings, we extend the discussion to similar problems involving fixed, coincidence, and cyclic/double fixed points within this framework. Our results generalize recent findings from the literature, including those in Ait Mansour M, Bahraoui MA, El Bekkali A. [Metric regularity and Lyusternik-Graves theorem via approximate fixed points of set-valued maps in noncomplete metric spaces. Set-Valued Var Anal. 2022;30(1):233–256. doi: 10.1007/s11228-020-00553-1], Dontchev AL, Rockafellar RT. [Implicit functions and solution mappings. a view from variational analysis. Dordrecht: Springer; 2009. Springer Monographs in Mathematics], Ioffe AD. [Variational analysis of regular mappings. Springer, Cham; 2017. Springer Monographs in Mathematics; theory and applications. doi: 10.1007/978-3-319-64277-2], Lim TC. [On fixed point stability for set-valued contractive mappings with applications to generalized differential equations. J Math Anal Appl. 1985;110(2):436–441. doi: 10.1016/0022-247X(85)90306-3] and Tron NH. [Coincidence and fixed points of set-valued mappings via regularity in metric spaces. Set-Valued Var Anal. 2023;31(2):22. Paper No. 17. doi: 10.1007/s11228-023-00680-5].

Frank–Wolfe and friends: a journey into projection-free first-order optimization methods

AbstractInvented some 65 years ago in a seminal paper by Marguerite Straus-Frank and Philip Wolfe, the Frank–Wolfe method recently enjoys a remarkable revival, fuelled by the need of fast and reliable first-order optimization methods in Data Science and other relevant application areas. This review tries to explain the success of this approach by illustrating versatility and applicability in a wide range of contexts, combined with an account on recent progress in variants, both improving on the speed and efficiency of this surprisingly simple principle of first-order optimization.

The application of deterministic and probabilistic methods of data linkage methods to link population and health data in western Uganda

IntroductionThere is increasing interest in record linkage between population-level data and health facility records to support epidemiological research in Africa. However, there is a lack of unique and ubiquitous identification systems for linkage. We applied two common data linkage approaches between population-level data from a health and demographic surveillance system and hospital records in Western Uganda. MethodologyWe established a data linkage system using deterministic and probabilistic linkage on population level data collected from 23 villages with hospital records. Deterministic linkage entails connecting a pair of records from the clinic and census data using a common identifier. Probabilistic linkage classifies a pair of records from two data sources as belonging to the same individual based on the statistical probability that a common set of identifiers drawn from the two data sources belong to the same individual. The preliminary results are on the deterministic approaches. ResultsUsing deterministic linkage, we fully linked 1061 records from 12/23 villages. Further updates of linkage with characteristics of the linked patients will be summarized in the next two months. Probabilistic linkage data will be presented with the characteristics of participants after the completion of the study, and the agreement between the two methods will be compared. Note to the results: Presentations during the conference will be done using finalized data. ConclusionPreliminary findings show that the linkage of population and health data is feasible. Findings could be used by researchers to design data linkage studies and answer different types of health and population research questions using innovative data science methods.

Mathematical Data Science with Applications in Business, Industry, and Medicine

Mathematical data science is a field that combines mathematical techniques with data science methods to extract insights and knowledge from data [...]

Data Science, Simulation, and Experimental Methods for Exploration and Design of Superconducting Materials

Data Science, Simulation, and Experimental Methods for Exploration and Design of Superconducting Materials

Current Status and Future Perspective of the Utilization of Data Science Methods in the Development of Fabrication Processes for Superconducting Materials

Current Status and Future Perspective of the Utilization of Data Science Methods in the Development of Fabrication Processes for Superconducting Materials

Special Issue on Informatics Education: Teaching Data Science through an Interactive, Hands-On Workshop with Clinically-Relevant Case Studies.

In this case report, we describe the development of an innovative workshop to bridge the gap in data science education for practicing clinicians (and particularly nurses). In the workshop, we emphasize the core concepts of machine learning and predictive modeling to increase understanding among clinicians. Addressing the limited exposure of healthcare providers to leverage and critique data science methods, this interactive workshop aims to provide clinicians with foundational knowledge in data science, enabling them to contribute effectively to teams focused on improving care quality. The workshop focuses on meaningful topics for clinicians, such as model performance evaluation and introduces machine learning through hands-on exercises using free, interactive python notebooks. Clinical case studies on sepsis recognition and opioid overdose death provide relatable contexts for applying data science concepts. Positive feedback from over 300 participants across various settings highlights the workshop's effectiveness in making complex topics accessible to clinicians. Our approach prioritizes engaging content delivery and practical application over extensive programming instruction, aligning with adult learning principles. This initiative underscores the importance of equipping clinicians with data science knowledge to navigate today's data-driven healthcare landscape, offering a template for integrating data science education into healthcare informatics programs or continuing professional development.

Importance of alternative pathways to STEM through analysis of longitudinal student dataset

Using a longitudinal national educational dataset, data science methods were applied to explain students’ educational trajectories and determine the most predictive variables in STEM degree attainment. Challenging the notion of the STEM pipeline, an Alternative Pathways to STEM (APS) model was proposed. Using a foundation of Social Cognitive Career Theory, academic, demographic, and economic variables were selected for analysis and Imbalanced dataset and random forest data analytic techniques were implemented. Results supported the consideration of the Alternate Pathways to STEM model given the varied educational pathways identified throughout STEM matriculation. Additionally, multiple academic variables, except for career interest, were found to be most predictive of STEM graduation, while demographic and economic variables were not significant. These findings have important implications for recruiting STEM students and increasing STEM graduation rates. Additional research is recommended using these data extraction and analysis methodologies on other datasets to further test the efficacy of the Alternative Pathways to STEM model.

Data Science Methods for Real-World Evidence Generation in Real-World Data.

In the healthcare landscape, data science (DS) methods have emerged as indispensable tools to harness real-world data (RWD) from various data sources such as electronic health records, claim and registry data, and data gathered from digital health technologies. Real-world evidence (RWE) generated from RWD empowers researchers, clinicians, and policymakers with a more comprehensive understanding of real-world patient outcomes. Nevertheless, persistent challenges in RWD (e.g., messiness, voluminousness, heterogeneity, multimodality) and a growing awareness of the need for trustworthy and reliable RWE demand innovative, robust, and valid DS methods for analyzing RWD. In this article, I review some common current DS methods for extracting RWE and valuable insights from complex and diverse RWD. This article encompasses the entire RWE-generation pipeline, from study design with RWD to data preprocessing, exploratory analysis, methods for analyzing RWD, and trustworthiness and reliability guarantees, along with data ethics considerations and open-source tools. This review, tailored for an audience that may not be experts in DS, aspires to offer a systematic review of DS methods and assists readers in selecting suitable DS methods and enhancing the process of RWE generation for addressing their specific challenges.

Quality of care assessment for non-small cell lung cancer patients: transforming routine care data into a continuous improvement system.

The complexity of cancer care requires planning and analysis to achieve the highest level of quality. We aim to measure the quality of care provided to patients with non-small cell lung cancer (NSCLC) using the data contained in the hospital's information systems, in order to establish a system of continuous quality improvement. Retrospective observational cohort study conducted in a university hospital in Spain, consecutively including all patients with NSCLC treated between 2016 and 2020. A total of 34 quality indicators were selected based on a literature review and clinical practice guideline recommendations, covering care processes, timeliness, and outcomes. Applying data science methods, an analysis algorithm, based on clinical guideline recommendations, was set up to integrate activity and administrative data extracted from the Electronic Patient Record along with clinical data from a lung cancer registry. Through data generated in routine practice, it has been feasible to reconstruct the therapeutic trajectory and automatically calculate quality indicators using an algorithm based on clinical practice guidelines. Process indicators revealed high adherence to guideline recommendations, and outcome indicators showed favorable survival rates compared to previous data. Our study proposes a methodology to take advantage of the data contained in hospital information sources, allowing feedback and repeated measurement over time, developing a tool to understand quality metrics in accordance with evidence-based recommendations, ultimately seeking a system of continuous improvement of the quality of health care.

Knowledge Leaks in Data-Driven Business Models? Exploring Different Types of Knowledge Risks and Protection Measures

Data-driven business models imply the inter-organisational exchange of data or similar value objects. Data science methods enable organisations to discover patterns and eventually knowledge from data. Further, by training machine learning models, knowledge is materialised in those models. Thus, organisations might risk the exposure of competitive knowledge by sharing data-related value objects, such as data, models or predictions. Although knowledge risks have been studied in traditional business models, little research has been conducted in the direction of data-driven business models. In this explorative qualitative study, we conducted 28 expert interviews in three rounds (two exploratory and one evaluatory) and identified five types of risks along the three basic types of value objects: data, models and predictions. These risks depend on the context, i.e., when competitive knowledge could be discovered from shared value objects. We found that those risks can be mitigated by technology, contractual regulations, trusted relationships, and adjusting the business model design. In this study, we show that the risk of knowledge leakage is a relevant risk factor in data-driven business models. Overall, knowledge risks should be considered already during business model design, and their management requires an interdisciplinary approach via a balanced assessment. The level of knowledge protection from a technology perspective highly depends on computer science innovations and thus is a moving target. As an outlook, we suggest that knowledge risk will become even more relevant with the extensive usage of machine learning and artificial intelligence in data-driven business models.

Machine learning in drug delivery

For decades, drug delivery scientists have been performing trial-and-error experimentation to manually sample parameter spaces and optimize release profiles through rational design. To enable this approach, scientists spend much of their career learning nuanced drug-material interactions that drive system behavior. In relatively simple systems, rational design criteria allow us to fine tune release profiles and enable efficacious therapies. However, as materials and drugs become increasingly sophisticated and their interactions have non-linear and compounding effects, the field is suffering the Curse of Dimensionality which prevents us from comprehending complex structure-function relationships. In the past, we have embraced this complexity by implementing high-throughput screens to increase the probability of finding ideal compositions. However, this brute force method was inefficient and led many to abandon these fishing expeditions. Fortunately, methods in data science including artificial intelligence / machine learning (AI/ML) are providing ideal analytical tools to model this complex data and ascertain quantitative structure-function relationships. In this Oration, I speak to the potential value of data science in drug delivery with particular focus on polymeric delivery systems. Here, I do not suggest that AI/ML will simply replace mechanistic understanding of complex systems. Rather, I propose that AI/ML should be yet another useful tool in the lab to navigate complex parameter spaces. The recent hype around AI/ML is breathtaking and potentially over inflated, but the value of these methods is poised to revolutionize how we perform science. Therefore, I encourage readers to consider adopting these skills and applying data science methods to their own problems. If done successfully, I believe we will all realize a paradigm shift in our approach to drug delivery.