Providing insights into health data science education through artificial intelligence.

BACKGROUND: Health Data Science (HDS) is a novel interdisciplinary field that integrates biological, clinical, and computational sciences with the aim of analysing clinical and biological data through the utilisation of computational methods. Training healthcare specialists who are knowledgeable in both health and data sciences is highly required, important, and challenging. Therefore, it is essential to analyse students' learning experiences through artificial intelligence techniques in order to provide both teachers and learners with insights about effective learning strategies and to improve existing HDS course designs. METHODS: We applied artificial intelligence methods to uncover learning tactics and strategies employed by students in an HDS massive open online course with over 3,000 students enrolled. We also used statistical tests to explore students' engagement with different resources (such as reading materials and lecture videos) and their level of engagement with various HDS topics. RESULTS: We found that students in HDS employed four learning tactics, such as actively connecting new information to their prior knowledge, taking assessments and practising programming to evaluate their understanding, collaborating with their classmates, and repeating information to memorise. Based on the employed tactics, we also found three types of learning strategies, including low engagement (Surface learners), moderate engagement (Strategic learners), and high engagement (Deep learners), which are in line with well-known educational theories. The results indicate that successful students allocate more time to practical topics, such as projects and discussions, make connections among concepts, and employ peer learning. CONCLUSIONS: We applied artificial intelligence techniques to provide new insights into HDS education. Based on the findings, we provide pedagogical suggestions not only for course designers but also for teachers and learners that have the potential to improve the learning experience of HDS students.

Treatment seeking behaviours, antibiotic use and relationships to multi-drug resistance: A study of urinary tract infection patients in Kenya, Tanzania and Uganda.

Antibacterial resistance (ABR) is a major public health threat. An important accelerating factor is treatment-seeking behaviour, including inappropriate antibiotic (AB) use. In many low- and middle-income countries (LMICs) this includes taking ABs with and without prescription sourced from various providers, including health facilities and community drug sellers. However, investigations of complex treatment-seeking, AB use and drug resistance in LMICs are scarce. The Holistic Approach to Unravel Antibacterial Resistance in East Africa (HATUA) Consortium collected questionnaire and microbiological data from adult outpatients with urinary tract infection (UTI)-like symptoms presenting at healthcare facilities in Kenya, Tanzania and Uganda. Using data from 6,388 patients, we analysed patterns of self-reported treatment seeking behaviours ('patient pathways') using process mining and single-channel sequence analysis. Among those with microbiologically confirmed UTI (n = 1,946), we used logistic regression to assess the relationship between treatment seeking behaviour, AB use, and the likelihood of having a multi-drug resistant (MDR) UTI. The most common treatment pathway for UTI-like symptoms in this sample involved attending health facilities, rather than other providers like drug sellers. Patients from sites in Tanzania and Uganda, where over 50% of patients had an MDR UTI, were more likely to report treatment failures, and have repeat visits to providers than those from Kenyan sites, where MDR UTI proportions were lower (33%). There was no strong or consistent relationship between individual AB use and likelihood of MDR UTI, after accounting for country context. The results highlight the hurdles East African patients face in accessing effective UTI care. These challenges are exacerbated by high rates of MDR UTI, suggesting a vicious cycle of failed treatment attempts and sustained selection for drug resistance. Whilst individual AB use may contribute to the risk of MDR UTI, our data show that factors related to context are stronger drivers of variations in ABR.

Challenges and Opportunities in Data Visualization Education: A Call to Action.

This paper is a call to action for research and discussion on data visualization education. As visualization evolves and spreads through our professional and personal lives, we need to understand how to support and empower a broad and diverse community of learners in visualization. Data Visualization is a diverse and dynamic discipline that combines knowledge from different fields, is tailored to suit diverse audiences and contexts, and frequently incorporates tacit knowledge. This complex nature leads to a series of interrelated challenges for data visualization education. Driven by a lack of consolidated knowledge, overview, and orientation for visualization education, the 21 authors of this paper-educators and researchers in data visualization-identify and describe 19 challenges informed by our collective practical experience. We organize these challenges around seven themes People, Goals & Assessment, Environment, Motivation, Methods, Materials, and Change. Across these themes, we formulate 43 research questions to address these challenges. As part of our call to action, we then conclude with 5 cross-cutting opportunities and respective action items: embrace DIVERSITY+INCLUSION, build COMMUNITIES, conduct RESEARCH, act AGILE, and relish RESPONSIBILITY. We aim to inspire researchers, educators and learners to drive visualization education forward and discuss why, how, who and where we educate, as we learn to use visualization to address challenges across many scales and many domains in a rapidly changing world: viseducationchallenges.github.io.

Treatment seeking behaviours, antibiotic use and relationships to multi-drug resistance: A study of urinary tract infection patients in Kenya, Tanzania and Uganda.

Antibacterial resistance (ABR) is a major public health threat. An important accelerating factor is treatment-seeking behaviours, including inappropriate antibiotic (AB) use. In many low- and middle-income countries (LMICs) this includes taking ABs with and without prescription sourced from various providers, including health facilities and community drug sellers. However, investigations of complex treatment-seeking, AB use and drug resistance in LMICs are scarce. The Holistic Approach to Unravel Antibacterial Resistance in East Africa (HATUA) Consortium collected questionnaire and microbiological data from 6,827 adult outpatients with urinary tract infection (UTI)-like symptoms presenting at healthcare facilities in Kenya, Tanzania and Uganda. Among 6,388 patients we analysed patterns of self-reported treatment seeking behaviours ('patient pathways') using process mining and single-channel sequence analysis. Of those with microbiologically confirmed UTI (n=1,946), we used logistic regression to assessed the relationship between treatment seeking behaviour, AB use, and likelihood of having a multi-drug resistant (MDR) UTI. The most common treatment pathways for UTI-like symptoms included attending health facilities, rather than other providers (e.g. drug sellers). Patients from the sites sampled in Tanzania and Uganda, where prevalence of MDR UTI was over 50%, were more likely to report treatment failures, and have repeated visits to clinics/other providers, than those from Kenyan sites, where MDR UTI rates were lower (33%). There was no strong or consistent relationship between individual AB use and risk of MDR UTI, after accounting for country context. The results highlight challenges East African patients face in accessing effective UTI treatment. These challenges increase where rates of MDR UTI are higher, suggesting a reinforcing circle of failed treatment attempts and sustained selection for drug resistance. Whilst individual behaviours may contribute to the risk of MDR UTI, our data show that factors related to context are stronger drivers of ABR.

Data science in undergraduate medicine: Course overview and student perspectives.

BACKGROUND: Despite the growing interest in health data science education, it is not embedded in undergraduate medical curricula and little is known about best teaching practices. This paper presents a highly innovative course in a UK university that introduces undergraduate medical students to data science. It also discusses a study on student perspectives on the learning and teaching of health data science. METHODS: The pedagogical design elements of the Data Science in Medicine course are discussed, along with its syllabus, assessment methodology and flipped classroom delivery. The course has been offered to approximately 630 students over three years. Student perspectives were investigated through three focus groups with the participation of 19 students across different study years in medicine. An experiment was conducted regarding instructor-led vs. video-based modalities of online programming labs, with the participation of 8 students. RESULTS: The course has led to improved data competency among medical students and to a positive change in their opinions about data science. Motivating the course and showing relevance to clinical practice was one of the biggest challenges. Statistics was perceived by focus group participants as an essential data skill. Including data science in the medical curriculum was perceived as important by Year 1 students, while opinions varied between Year 4/5 participants. Video-based online labs were preferred over instructor-led online labs, and they were found to be more useful and enjoyable, without leading to any significant difference in academic performance. CONCLUSIONS: Teaching data science to undergraduate medicine students is highly desirable and feasible. We recommend including statistics in the curriculum and practical skill development through simple and clinically-relevant data science tasks, supported through video-based online labs. Further reporting on similar courses is needed, as well as larger-scale studies on student perspectives.

Multi-Method Study of Electronic Health Records Workflows.

EHRs transform work practices in ways that enhance or impede the quality of care. There is a need for in-depth analysis of EHR workflows, particularly in complex clinical environments. We investigated EHR-basedpre-operative workflows by combining findings from 18 interviews, 7 days of observations, and process mining of EHR interactions from 31 personnel caring for 375 patients at one tertiary referral center. We provided high-definition descriptions of workflows and personnel roles. One third (32.2%) of the time with each patient was spent interacting with the EHR and 4.2% using paper-based artifacts. We also mined personnel social networks validating observed personnel's EHR-interactions. When comparing workflows between two similar pre-operative settings at different hospitals, we found significant differences in physical organization, patient workflow, roles, use of EHR, social networks and time efficiency. This study informs Mayo Clinic's enterprise-wide conversion to a single EHR and will guide before and after workflow comparisons.

A Workflow-Driven Formal Methods Approach to the Generation of Structured Checklists for Intrahospital Patient Transfers.

Intrahospital transfers are a common but hazardous aspect of hospital care, with a large number of incidents posing a threat to patient safety. A growing body of work advocates the use of checklists for minimizing intrahospital transfer risk, but the majority of existing checklists are not guaranteed to be error-free and are difficult to adapt to different clinical settings or changing hospital policies. This paper details an approach that addresses these challenges through the employment of workflow technologies and formal methods for generating structured checklists. A three-phased methodology is proposed, where intrahospital transfer processes are first conceptualized, then rigorously composed into workflows that are mechanically verified, and finally, translated into a set of checklists that support hospital staff while maintaining the dependencies between different transfer tasks. A case study is presented, highlighting the feasibility of this approach, and the correctness and maintainability benefits brought by the logical underpinning of this methodology. A checklist evaluation is discussed, with promising results regarding their usefulness.