Daily Workflows Research Articles

Dosimetric differences between online adapt-to-position and offline adapt-to-shape plans for adaptive radiotherapy in cervical cancer

Radiation therapy plays a significant role in the treatment of cervical cancer. Additionally, more adaptive workflows using ATP are being implemented in the daily radiotherapy of our organization. Herein, we aimed to investigate the dosimetric differences between online ATP and offline ATS plans for magnetic resonance (MR)-guided adaptive radiotherapy in patients with cervical cancer and determine radiotherapy modalities that address clinical requirements. In total, 25 patients with cervical cancer were enrolled in this study, with 13 in the radical radiotherapy group and 12 in post-operative radiotherapy group. We aimed for the clinical target volume (CTV) to be covered by 95 – 100% of the prescribed dose (50 Gy/25 sessions/5 weeks). MR-Linac was performed daily during treatment, and the images were rigidly aligned with the local computed tomography to generate an online ATP plan. MR images acquired during the first three sessions were selected to recontour the CTV and organs at risk (OAR). Furthermore, an offline ATS plan was generated. In the radical radiotherapy group, the CTV, D98, D95 (5024.65 ± 23.34 vs. 4995.50 ± 14.99 cGy), and Dmean of the ATS were superior compared with those of the ATP. The Dmax was lower in the ATS plan than in the ATP plan. In the post-operative radiotherapy group, the CTV, Dmean, D98, and D95 (5052.61 ± 67.87 vs. 5014.41 ± 24.68 cGy) were better in the ATS plan than in the ATP plan. When evaluating the OAR in the radical radiotherapy group, the minimum doses to the bladder and rectum were greater in the ATS plan than in the ATP plan. In the post-operative radiotherapy group, the V20 of the bladder and rectum were lower in the ATS plan than in the ATP plan. Therefore, ATS is well suited for post-operative radiotherapy, whereas ATP is better suited for radical radiotherapy. Furthermore, ATP can effectively address the clinical requirements of daily workflows.

Assessing Artificial Intelligence (AI) Implementation for Assisting Gene Linking (at the National Library of Medicine).

The National Library of Medicine (NLM) currently indexes close to a million articles each year pertaining to more than 5300 medicine and life sciences journals. Of these, a significant number of articles contain critical information about the structure, genetics, and function of genes and proteins in normal and disease states. These articles are identified by the NLM curators, and a manual link is created between these articles and the corresponding gene records at the NCBI Gene database. Thus, the information is interconnected with all the NLM resources, services which bring considerable value to life sciences. National Library of Medicine aims to provide timely access to all metadata, and this necessitates that the article indexing scales to the volume of the published literature. On the other hand, although automatic information extraction methods have been shown to achieve accurate results in biomedical text mining research, it remains difficult to evaluate them on established pipelines and integrate them within the daily workflows. Here, we demonstrate how our machine learning model, GNorm2, which achieved state-of-the art performance on identifying genes and their corresponding species at the same time handling innate textual ambiguities, could be integrated with the established daily workflow at the NLM and evaluated for its performance in this new environment. We worked with 8 biomedical curator experts and evaluated the integration using these parameters: (1) gene identification accuracy, (2) interannotator agreement with and without GNorm2, (3) GNorm2 potential bias, and (4) indexing consistency and efficiency. We identified key interface changes that significantly helped the curators to maximize the GNorm2 benefit, and further improved the GNorm2 algorithm to cover 135 species of genes including viral and bacterial genes, based on the biocurator expert survey. GNorm2 is currently in the process of being fully integrated into the regular curator's workflow.

Automatic Vessel Segmentation and Reformation of Non-contrast Coronary Magnetic Resonance Angiography Using Transfer Learning-based 3D U-net with Attention Mechanism

BackgroundCoronary Magnetic Resonance Angiography (CMRA) presents distinct advantages, but its reliance on manual image post-processing is labor-intensive and requires specialized knowledge. This study aims to design and test an efficient artificial intelligence (AI) model capable of automating coronary artery segmentation and reformation from CMRA images for coronary artery disease (CAD) diagnosis. MethodsBy leveraging transfer learning from a pre-existing coronary CT angiography model, a 3D attention-aware U-Net was established, trained, and validated on a dataset of 104 subjects’ CMRA. Furthermore, an independent clinical evaluation was conducted on an additional cohort of 70 patients. The AI model's performance in segmenting coronary arteries was assessed using the Dice Similarity Coefficient (DSC) and Recall. The comparison between the AI model and manual processing by experienced radiologists on vessel reformation was based on reformatted image quality (rIQ) scoring, post-processing time, and the number of necessary user interactions. The diagnostic performance of AI-segmented CMRA for significant stenosis (≥50% diameter reduction) was evaluated using conventional coronary angiography (CAG) as a reference in sub-set data. ResultsThe DSC of the AI model achieved on the training and validation sets were 0.952 and 0.944, with recalls of 0.936 and 0.923, respectively. In the clinical evaluation, the model outperformed manual processes by reducing vessel post-processing time, from 632.6±17.0seconds to 77.4±8.9seconds, and the number of user interactions from 221±59 to 8±2. The AI postprocessed images maintained high rIQ scores comparable to those processed manually (2.7±0.8 vs 2.7±0.6; P=0.4806). In subjects with CAG, the prevalence of CAD was 71%. The sensitivity, specificity, and accuracy at patient-based analysis were 94%, 71%, and 88%, respectively, by AI post-processed whole-heart CMRA. ConclusionThe AI auto-segmentation system can effectively facilitate CMRA vessel reformation and reduce the time consumption for radiologists. It has the potential to become a standard component of daily workflows, optimizing the clinical application of CMRA in the future.

Perceptions of AI Integration in the UAE’s Creative Sector

This study explores the perceptions of artificial intelligence (AI) within the creative sector of the United Arab Emirates (UAE) based on 13 semi-structured interviews and a survey with 224 participants among media professionals and their stakeholders. The findings indicate considerable enthusiasm surrounding AI’s potential to augment creativity and drive operational efficiency, a perspective that the study’s participants share. However, there are also apprehensions regarding job displacement and the necessity for strategic upskilling. Participants generally regard AI as an unavoidable technological influence that demands adaptation and seamless integration into daily workflows. The study underscores the disparity between the UAE’s government-led digital transformation objectives and the actual implementation within organizations, underscoring the urgent need for cohesive strategic alignment. The findings caution that the absence of clear directives and strategic planning may precipitate a new digital schism, impeding progress in the sector.

Integrating telemedicine in European healthcare settings: Key enablers for healthcare professionals

Abstract Background Conducted as part of WP4 (Sustainability) of the eCAN Joint Action (JA), we aimed to understand the facilitating factors for the use of telemedicine services in healthcare organisations (HCOs) involved in cancer care, such as comprehensive cancer centres and hospitals. eCAN JA runs pilot studies in 18 HCOs across 10 EU Member States (MS) to test the integration of telemedicine into the daily practice of healthcare professionals. Methods Based on a literature review, we identified 26 facilitators to implement telemedicine services at the organisational level; these were integrated to an online survey and sent to healthcare professionals working in cancer care. Next, they were invited to a foresight workshop to complement the quantitative survey data with qualitative insights. Results 24 healthcare professionals across 12 EU MS, predominantly from the pilot sites of the eCAN JA, responded to the survey. They advocate for trainings on telemedicine, emphasising the importance of user-friendly and interoperable platforms, alongside sufficient technological support, time, and financial resources to effectively implement telemedicine in HCOs. Trial periods for both healthcare professionals and patients should offer first-hand experience, while harmonising telemedicine protocols ensure consistency. In addition, promoting digital literacy among physicians and providing IT education from an early age could facilitate adoption. These strategies, coupled with awareness campaigns and infrastructure investments in HCOs, can pave the way for telemedicine adoption. Conclusions Based on the quantitative and qualitative outcomes, it can be concluded that policies should establish telemedicine training for healthcare professionals, support interoperability and user-friendliness of these services in HCOs. They should also address hospital workload challenges, create harmonised protocols, provide incentives, and invest in digital infrastructure in HCOs for telemedicine adoption. Key messages • Telemedicine implementation in HCOs requires equipping healthcare professionals with the necessary skills, ensuring system compatibility, and addressing resource constraints in HCOs for success. • Financial and infrastructural support to HCOs is crucial for the seamless integration of telemedicine services into the daily workflows of healthcare professionals, enhancing health service delivery.

Self-Management Systems for Patients and Clinicians in Parkinson's Disease Care: A Scoping Review.

Digital self-management tools including mobile apps and wearables can enhance personalized care in Parkinson's disease, and incorporating patient and clinician feedback into their evaluation can empower users and nurture patient-clinician relationships, necessitating a review to assess the state of the art and refine their use. This review aimed to summarize the state of the art of self-management systems used in Parkinson's disease management, detailing the application of self-management techniques and the integration of clinicians. It also aimed to provide a concise synthesis on the acceptance and usability of these systems from the clinicians' standpoint, reflecting both patient engagement and clinician experience. The review was organized following the PRISMA extension for Scoping Reviews and PICOS frameworks. Studies were retrieved from PubMed, CINAHL, Scopus, ACM Digital Library, and IEEE Xplore. Data was collected using a predefined form and then analyzed descriptively. Of the 15,231 studies retrieved, 33 were included. Five technology types were identified, with systems combining technologies being the most evaluated. Common self-management strategies included educational material and symptom journals. Only 11 studies gathered data from clinicians or reported evidence of clinician integration; out of those, six studies point out the importance of raw data availability, data visualization, and integrated data summaries. While self-management systems for Parkinson's disease are well-received by patients, the studies underscore the urgency for more research into their usability for clinicians and integration into daily medical workflows to enhance overall care quality.

Artificial Intelligence Revolutionizing Cancer Care: A Comprehensive Overview

Artificial intelligence (AI) is rapidly developing in the field of healthcare. It is expected to play a key role in oncology, in the areas of diagnosis, treatment, but also screening and cancer research. AI has evolved from a specialized resource to a readily accessible tool for practitioners and cancer researchers. AI can thus facilitate the screening, early and accurate diagnosis of cancers. Thus, the computer analysis of medical images in particular, radiological (radiomics), or anatomo-pathological (pathomics), has shown many very interesting results for the prediction of prognosis and response of patients with cancer. Thanks to deep learning algorithms, AI can identify subtle patterns on medical images, such as X-rays, MRIs or CT scans, that are likely to escape the human eye. In terms of treatment, AI can contribute to the development of personalized treatment plans. By analyzing large datasets, which can predict tumor response to certain treatments. AI also plays a key role in patient monitoring. AI-based systems can continuously monitor patients' health status, detecting any recurrences or complications. In the field of cancer research, AI-based tools can boost research productivity in daily workflows, but they can also extract hidden information from existing data, enabling new scientific discoveries. Researchers working in traditional biological sciences can use AI-based tools through commercially available software, while those who are more inclined to computer science can develop their own AI-based software pipelines. In this article, we will provide an update on the contribution of AI in the field of oncology, the practical applications already validated and the perspectives of this tool.

Re-Envisioning Electronic Health Records to Optimize Patient-Centered Cancer Care, Quality, Surveillance, and Research.

Electronic health records (EHRs) are a significant advancement over paper records. However, the full potential of EHRs for improving care quality, patient outcomes, surveillance, and research in cancer care is yet to be realized. The organic evolution of EHRs has resulted in a number of unanticipated consequences including increased time spent by clinicians interfacing with the EHR for daily workflows. Patient access to clinicians and their records has been an important advancement in patient-centered care; however, this has brought to light additional gaps and challenges in EHRs meeting these needs. A significant challenge for EHR design and physician workflows is how best to meet the complex goals and priorities of various stakeholders including providers, researchers, patients, health systems, payors, and regulatory agencies. The National Cancer Policy Forum convened a 2022 workshop, "Innovations in Electronic Health Records for Oncology Care, Research and Surveillance," to address these challenges and to facilitate collaboration across all user groups with the goal of re-envisioning EHRs that will better support shared goals of improving patient outcomes and advancing cancer care and research without overburdening clinicians with administrative tasks. Here, we summarize the current EHR ecosystem as discussed at the workshop and highlight opportunities to improve EHR contributions to oncology evidence and care.

Unveiling the heterogeneous utilisation of the same digital patient management platform: case studies in primary healthcare in Sweden

BackgroundThe utilisation of digital technology in primary healthcare, particularly digital patient management platforms, has gained prominence, notably due to the global pandemic. These platforms are positioned as substitutes for face-to-face consultations and telephone triage. They are seen as a potential solution to the escalating costs associated with an aging population, increasing chronic conditions, and a shrinking healthcare workforce. However, a significant knowledge gap exists concerning the practical aspects of their implementation and their effect on the utilisation of digital patient management in primary healthcare.MethodsThis study addresses this gap by conducting a comprehensive analysis of three case studies involving the implementation of a specific digital patient management platform. Over a period of three years, we examine how the practicalities of implementation shape the adoption and utilisation of a digital patient management platform in three different clinics.ResultsOur findings revealed that differences in implementation strategies directly influenced variations in utilisation. The successful utilisation of the platform was achieved through a bottom-up decision-making process that involved the employees of the primary healthcare clinics. Onsite training, close collaboration with the eHealth provider, and a structured patient onboarding process played crucial roles in this utilisation. In contrast, a top-down approach at two of the primary healthcare clinics led to limited utilisation of the platform into daily workflows. Furthermore, making the platform a part of everyday work meant putting accessibility, by working as a team of physicians, at the forefront of continuity of care, with patients being managed by their designated physician. Additionally, it was observed that digital patient management proved most effective for addressing simple patient issues such as skin rashes, rather than complex cases, and did not reduce the demand for phone triage.ConclusionOnly one of the three clinics studied effectively integrated digital patient management into its daily operations, and did so by aligning objectives among management and all categories of healthcare professionals, employing a bottom-up decision-making process, collaborating with the eHealth service provider for regular platform adjustments to clinic needs, and implementing active patient onboarding. This sociotechnical integration resulted in high platform utilisation. In contrast, the other two clinics faced challenges due to incoherent objectives among diverse healthcare professional employees and top management, a top-down decision-making approach during implementation, limited collaboration with the eHealth service provider, and passive patient onboarding. The findings indicate that these factors negatively affected utilisation and led to low platform adoption as well as disrupted the sociotechnical balance.

A guide to artificial intelligence for cancer researchers.

Artificial intelligence (AI) has been commoditized. It has evolved from a specialty resource to a readily accessible tool for cancer researchers. AI-based tools can boost research productivity in daily workflows, but can also extract hidden information from existing data, thereby enabling new scientific discoveries. Building a basic literacy in these tools is useful for every cancer researcher. Researchers with a traditional biological science focus can use AI-based tools through off-the-shelf software, whereas those who are more computationally inclined can develop their own AI-based software pipelines. In this article, we provide a practical guide for non-computational cancer researchers to understand how AI-based tools can benefit them. We convey general principles of AI for applications in image analysis, natural language processing and drug discovery. In addition, we give examples of how non-computational researchers can get started on the journey to productively use AI in their own work.

Understanding the Technology-Mediated Home Phlebotomy Ecosystem in India

The increasing platformization of healthcare services in India, in the wake of COVID-19, has resulted in huge demand for home phlebotomy. However, there is a limited understanding of the impact of digitization on home phlebotomists' workflows. To address this gap, we conducted 26 semi-structured interviews with home phlebotomists, riders, and patients, supplemented by observations of the entire workday of 3 phlebotomists. We found that home phlebotomists' technology-mediated workflows are organized in ways that enable them to build strong support networks of human infrastructure, helping them negotiate and optimize their daily workflows. Moreover, while the digitization of their workflows resulted in continued surveillance, it empowered them to justify their decisions and present evidence of work when needed. Based on our findings, we discuss implications for equitable platform work and the future of platformized health and conclude with design recommendations for telehealth platforms offering home phlebotomy services.

Lessons Learned from a National Hospital Antibiotic Stewardship Implementation Project

BackgroundThe goal of antibiotic stewardship programs (ASPs) is to ensure patients receive effective therapy while minimizing adverse events. To overcome barriers commonly faced in implementing successful ASPs, AHRQ established a multifaceted, nationwide Safety Program for Improving Antibiotic Use in 2018. This report summarizes the lessons learned from the implementation of this initiative based on structured interviews with ASP leaders. MethodsAt the completion of the one-year initiative, semi-structured exit interviews were conducted with site leaders at 151 of the 402 hospitals that participated. These interviews consisted of open-ended questions about the perceived effectiveness of components of the Safety Program. Qualitative analyses incorporated both deductive coding themes (based on existing literature) and an iteratively developed inductive coding framework (based on salient themes that emerged from a subset of interviews). ResultsSeveral components of the Safety Program were identified as effective in expanding local stewardship activities, including techniques and strategies to implement sustainable ASPs, access to Implementation Advisors to keep sites engaged, provision of local benchmarked antibiotic use data to compare to similar hospitals, and Safety Program materials such as the antibiotic time-out tool to integrate stewardship techniques into daily work flows. The biggest challenges to greater effectiveness were suboptimal frontline staff engagement and difficulty changing antibiotic prescribing culture. Some approaches used to overcome these barriers (i.e., peer-to-peer communication and education through team huddles, identifying physician champions, informal rounds to enhance collegiality and buy-in, and engagement of hospital leadership) were also identified. ConclusionsLessons learned from the Safety Program can be applied by other teams looking to promote an effective ASP at their hospital or system. The themes that emerged in this study likely also have relevance across a wide range of large-scale quality improvement initiatives.

Devon Energy and Software Partners Enable Automatic Bottomhole Pressure Calculations

_ More than a decade ago, Devon Energy made it a priority to enhance its digital infrastructure which has led to a step change in internal data access along with how the company securely works with its third-party vendors. Easy access to relevant, trustworthy, and value-adding data has become the norm, not the exception, for the US oil and gas producer’s subsurface engineering teams. The upside extends beyond mere convenience, however, and translates directly into faster decision making which is one of the keys to success in the dynamic landscape of unconventional developments. When data is seamlessly connected for daily consumption, engineers engage with it regularly, integrating it into their daily workflows. Additionally, we see that the frequency of use is directly correlated with accessibility. The emphasis on accessibility reflects Devon’s proactive efforts to treat its data more and more as a valuable asset. By democratizing data and analysis tools, business-impacting insights are more readily available to engineers and decision-makers throughout the organization. This case study outlines one of the most recent and tangible outcomes of this collaborative philosophy: automatic calculation of bottomhole pressure (BHP). Solving for Bottomhole Pressures As shown in Fig. 1, accurate and reliable flowing BHP data is a critical input for a number of important engineering applications in both conventional and unconventional settings: reservoir simulation, production diagnostics, nodal analysis, rate transient analysis, pressure transient analysis, and material balance. The list goes on, but the overarching point is that BHP data allows engineers to make informed decisions, i.e., high-confidence estimations on future well production, reservoir management, and optimization strategies. The rub is that acquiring accurate BHP measurements has historically been a luxury service that is too costly to scale up beyond a few science projects. Operators that desire such critical data often turn to BHP gauges, which are positioned down in the wellbore to measure pressure at a specific depth. But given an average cost of $50,000 per installation, it is estimated that less than 5% of all horizontal wells drilled during the North American shale revolution have benefited from the use of downhole gauges. Without a downhole gauge, operators must calculate the pressures from surface pressure. The problem here is again one of scale. Using surface pressure has traditionally required the manual gathering of the proper data sets and calculating BHP. From there, the process is not only time consuming but considered to be error prone. Applying any of the published methods may take a reasonably experienced engineer half an hour to complete a BHP calculation and the odds of a miscalculation rise as the data set grows in size and complexity.

Satisfaction of adult and pediatric neurologists and neurosurgeons using telehealth during the COVID-19 pandemic in Saudi Arabia: a cross-sectional study.

Telehealth has become increasingly important in achieving universal health coverage. It offers doctors and their patients' convenience, including providing quality care at reduced costs. During the coronavirus disease (COVID)-19 pandemic, telehealth has been a vital tool for remote healthcare services. This study aimed to assess the satisfaction of adult and pediatric neurologists and neurosurgeons using telehealth, during the COVID-19 pandemic in Saudi Arabia. This study had 348 participants. It was conducted among adult and pediatric neurologists and neurosurgeons using telehealth technology at their clinics between February and June 2021. The self-administered questionnaire included sociodemographic data, behavior in using telehealth, and an assessment of satisfaction with telehealth; the SPSS Windows software version 26 was used to analyze the data. The most common age group was 25-34 years (42.8%), with men dominating (68.4%). The mean satisfaction score was 25.9 (SD 3.91) out of 33 points, with 90.2% of respondents satisfied with telehealth and 9.8% dissatisfied. Working in an academic center or private hospital, being a first-time telehealth user, using messages as a telehealth method, and using telehealth daily were associated with increased satisfaction with telehealth use. The satisfaction of adult and pediatric neurologists and neurosurgeons with telehealth was high. Although physicians still preferred face-to-face interviews, they recognized the benefits of telehealth in strengthening the patient-provider relationship, improving productivity, and integrating into daily workflows. The satisfaction levels align with past studies, but physical examination needs should be considered. Telehealth is suitable for follow-up visits and varies across subspecialties.

A checklist to publish collections as data in GLAM institutions

PurposeThe purpose of this study is to offer a checklist that can be used for both creating and evaluating digital collections, which are also sometimes referred to as data sets as part of the collections as data movement, suitable for computational use.Design/methodology/approachThe checklist was built by synthesising and analysing the results of relevant research literature, articles and studies and the issues and needs obtained in an observational study. The checklist was tested and applied both as a tool for assessing a selection of digital collections made available by galleries, libraries, archives and museums (GLAM) institutions as proof of concept and as a supporting tool for creating collections as data.FindingsOver the past few years, there has been a growing interest in making available digital collections published by GLAM organisations for computational use. Based on previous work, the authors defined a methodology to build a checklist for the publication of Collections as data. The authors’ evaluation showed several examples of applications that can be useful to encourage other institutions to publish their digital collections for computational use.Originality/valueWhile some work on making available digital collections suitable for computational use exists, giving particular attention to data quality, planning and experimentation, to the best of the authors’ knowledge, none of the work to date provides an easy-to-follow and robust checklist to publish collection data sets in GLAM institutions. This checklist intends to encourage small- and medium-sized institutions to adopt the collection as data principles in daily workflows following best practices and guidelines.

Letter: The Urgency of Neurosurgical Leadership in the Era of Artificial Intelligence.

Letter: The Urgency of Neurosurgical Leadership in the Era of Artificial Intelligence.

Nangibotide for precision immunomodulation in septic shock and COVID-19

Nangibotide for precision immunomodulation in septic shock and COVID-19

Intensive Care Unit Physicians’ Perspectives on Artificial Intelligence–Based Clinical Decision Support Tools: Preimplementation Survey Study

Artificial intelligence-based clinical decision support (AI-CDS) tools have great potential to benefit intensive care unit (ICU) patients and physicians. There is a gap between the development and implementation of these tools. We aimed to investigate physicians' perspectives and their current decision-making behavior before implementing a discharge AI-CDS tool for predicting readmission and mortality risk after ICU discharge. We conducted a survey of physicians involved in decision-making on discharge of patients at two Dutch academic ICUs between July and November 2021. Questions were divided into four domains: (1) physicians' current decision-making behavior with respect to discharging ICU patients, (2) perspectives on the use of AI-CDS tools in general, (3) willingness to incorporate a discharge AI-CDS tool into daily clinical practice, and (4) preferences for using a discharge AI-CDS tool in daily workflows. Most of the 64 respondents (of 93 contacted, 69%) were familiar with AI (62/64, 97%) and had positive expectations of AI, with 55 of 64 (86%) believing that AI could support them in their work as a physician. The respondents disagreed on whether the decision to discharge a patient was complex (23/64, 36% agreed and 22/64, 34% disagreed); nonetheless, most (59/64, 92%) agreed that a discharge AI-CDS tool could be of value. Significant differences were observed between physicians from the 2 academic sites, which may be related to different levels of involvement in the development of the discharge AI-CDS tool. ICU physicians showed a favorable attitude toward the integration of AI-CDS tools into the ICU setting in general, and in particular toward a tool to predict a patient's risk of readmission and mortality within 7 days after discharge. The findings of this questionnaire will be used to improve the implementation process and training of end users.

Consolidation of quality control material improves patient safety and supports sustainability

Abstract Objectives Quality control measurements are a keystone in daily routine laboratory workflows. This study evaluated the use of a consolidated quality control material for increasing efficiency while also reducing costs. Methods Quality control materials from two different manufacturers were chosen to evaluate efficiency in a test setting. A total of 23 clinical chemistry tests and 15 immunoassays were performed twice each day under routine conditions over a 10-day time period using an Abbott Alinity system. Results The data obtained showed a saving of between 40 and 100% depending on test criteria. The cost savings in waste reduction ranges between a factor of 5.4 for dead volume to 19.8 for consumables. No difference in quality performance were found. Conclusions Choosing a consolidated quality control material resulted in a higher efficiency, greater cost savings and higher sustainability while maintaining the same level of performance.

On Sense Making and the Generation of Knowledge in Visual Analytics

Interactive visual tools and related visualization technologies, built to support explorative data analysis, ultimately lead to sense making and knowledge discovery from large volumes of raw data. These processes namely rely on human visual perception and cognition, in which human analysts perceive external representations (system structure, dataset, integral data visualizations) and form respective internal representations (internal cognitive imprints of external systems) that enable deeper comprehension of the employed system and the underlying data features. These internal representations further evolve through continuous interaction with external representations. They also depend on the individual’s own cognitive pathways. Currently, there has been insufficient work on understanding how these internal cognitive mechanisms form and function. Hence, we aim to offer our own interpretations of such processes observed through our daily data exploration workflows. This is accomplished by following specific explorative data science tasks while working with diverse interactive visual systems and related notebook style environments that have different organizational structures and thus may entail different approaches to thinking and shaping sense making and knowledge generation. In this paper, we deliberate on the cognitive implications for human analysists when interacting with such a diverse organizational structure of tools and approaches when performing the essential steps of an explorative visual analysis.