Quality Assurance Activities Research Articles

Quality Management of Prehospital Airway Programs: An NAEMSP Position Statement and Resource Document

Prehospital airway management encompasses a multitude of complex decision-making processes, techniques, and interventions. Quality management (encompassing quality assurance and quality improvement activities) in EMS is dynamic, evidence-based, and most of all, patient-centric. Long a mainstay of the EMS clinician skillset, airway management deserves specific focus and attention and dedicated quality management processes to ensure the delivery of high-quality clinical care. It is the position of NAEMSP that: All EMS agencies should dedicate sufficient resources to patient-centric, comprehensive prehospital airway quality management program. These quality management programs should consist of prospective, concurrent, and retrospective activities. Quality management programs should be developed and operated with the close involvement of the medical director. Quality improvement and quality assurance efforts should operate in an educational, non-disciplinary, non-punitive, evidence-based medicine culture focused on patient safety. The highest quality of care is only achieved when the quality management program rewards those who identify and seek to prevent errors before they occur. Information evaluated in prehospital airway quality management programs should include both subjective and objective data elements with uniform reporting and operational definitions. EMS systems should regularly measure and report process, outcome, and balancing airway management measures. Quality management activities require large-scale bidirectional information sharing between EMS agencies and receiving facilities. Hospital outcome information should be shared with agencies and the involved EMS clinicians. Findings from quality management programs should be used to guide and develop initial education and continued training. Quality improvement programs must continually undergo evaluation and assessment to identify strengths and shortcomings with a focus on continuous improvement.

System Performance Monitoring in Clinical Liquid Chromatography-Tandem Mass Spectrometry (LC-MS/MS).

Quality assurance (QA) activities enable continuous improvement through ongoing post-implementation monitoring to identify, evaluate, and correct problems. QA for clinical liquid chromatography tandem mass spectrometry (LC-MS/MS) assays should include specific components that address the unique aspects of these methods. This chapter briefly describes approaches for clinical LC-MS/MS system performance monitoring using batch and peak review metrics, largely following CLSI-C62A guidance. Though routine checks ensure the quality of results reported for each run, there is also a need to evaluate metrics between runs over time. Post-implementation performance monitoring of LC-MS/MS methods is typically focused on calibration curves, retention times, peak intensities, and ion ratios.

A Systematic Review of Ensemble Techniques for Software Defect and Change Prediction

Background: The use of ensemble techniques have steadily gained popularity in several software quality assurance activities. These aggregated classifiers have proven to be superior than their constituent base models. Though ensemble techniques have been widely used in key areas such as Software Defect Prediction (SDP) and Software Change Prediction (SCP), the current state-of-the-art concerning the use of these techniques needs scrutinization. Aim: The study aims to assess, evaluate and uncover possible research gaps with respect to the use of ensemble techniques in SDP and SCP. Method: This study conducts an extensive literature review of 77 primary studies on the basis of the category, application, rules of formulation, performance, and possible threats of the proposed/utilized ensemble techniques. Results: Ensemble techniques were primarily categorized on the basis of similarity, aggregation, relationship, diversity, and dependency of their base models. They were also found effective in several applications such as their use as a learning algorithm for developing SDP/SCP models and for addressing the class imbalance issue. Conclusion: The results of the review ascertain the need of more studies to propose, assess, validate, and compare various categories of ensemble techniques for diverse applications in SDP/SCP such as transfer learning and online learning.

Impact of Accreditation Policy on Quality Assurance Activities of Public and Private Universities in Vietnam

Impact of Accreditation Policy on Quality Assurance Activities of Public and Private Universities in Vietnam

SQrum: An Improved Method of Scrum

Software systems are having a major impact on many aspects of personal and professional life. Safety-critical applications, such as production line controls, automotive operations, and process industry controls, rely significantly on software systems. In these applications, software failure may result in bodily damage or death. The proper operation of software is essential to the safety and well-being of individuals and businesses. Therefore, software quality assurance is of paramount relevance in the software business today. In recent years, Agile Project Management and particularly Scrum, have gained popularity as a method of dealing with "vuca" business environments, which are characterized by rising Volatility, Uncertainty, Complexity, and Ambiguity. This paper contributes to the software development body of knowledge by proposing a metamodel of Scrum quality assurance, named SQrum (‘SQ’ of Software Quality and ‘rum’ of Scrum). Our objective is to make Scrum more efficient and reliable and to assist enterprises in undertaking quality assurance activities while considering agile practices and values.

Quality Assurance of Education in Senior High School during Covid-19 Pandemic

During the Covid-19 pandemic, SMA Nurul Jadid, Probolinggo, East Java created a quality assurance system to survive and win the rivalry between educational institutions. This study aims to understand the meaning behind quality assurance activities at SMA Nurul Jadid, Probolinggo using a qualitative case study approach. Researchers conducted interviews with committees, principals, vice-principals, teachers, and observations and documentation were carried out in this research. Data gathering, data reduction, display, and conclusion are steps in the data analysis process. The findings revealed that SMA Nurul Jadid's quality assurance system was implemented and evaluated through systematic planning, including numerous school members and the community, quality assurance implementation, and evaluation. This study has implications for the significance of educational institutions maintaining excellence to sustain the public trust built up over the years.

Disrupted, but not derailed: A year of scholarship in health professions education.

The commitment of health care professionals over the last year is unparalleled. In a time of crisis, going on for longer than anyone could have imagined, health care providers demonstrated an ability to rise higher, work harder and care even more deeply. Astoundingly, education did not get lost in the mix, as evidenced by the recently held Annual Scientific Meeting (ASM) of the Association for the Study of Medical Education. Ironically, the theme of 2020's (cancelled) meeting was to be “Disrupting medical education.” As COVID forced the concept from a rallying cry into an imposed necessity, this year's ASM, “Disrupted medical education,” was a shining light coming at what we hope is the end of an all too long tunnel. In parallel sessions, plenaries and workshops, we listened to stories of scholarship, creativity and an unwillingness to let a pandemic get in the way of educational progress. Learners, in particular, led the way in education design, creating opportunities for near peer teaching, mentoring and leadership. While technology took centre stage in education delivery this year, the ASM made it abundantly clear that it was the engagement of educators and learners in this rapid evolution, and their ability to “adapt, improvise and overcome” educational challenges that enabled successful continuation of education programmes. And somehow, through it all, education scholars managed to largely keep their research programmes and quality assurance activities afloat. To be sure, many adaptations were required with time-limited studies (e.g., MSc projects) being particularly impacted by issues of recruitment, availability of ethics committees and challenges in data collection like conducting focus groups in virtual environments. However, in the main, many appear to have successfully found workarounds, adapting protocols to ensure feasibility, without compromising their study's integrity. Context, as always, was critical, and scholars at the ASM offered compelling insights into how they grappled with the nuances of their situation, recognising how observations and experiences might have been different in different environments including different points in time. We are aware that those who were able to present at the ASM are likely a select sample as others undoubtedly had projects irretrievably derailed through no fault of their own. We think the strategies and transformations (both curricular and methodological) presented at the meeting offer keys to unlocking adaptations elsewhere and came away from the ASM excited to see that the future of health professions education scholarship is looking very bright. Our field has always been one of committed researchers, academics, educators and learners who prioritise and maintain a strong sense of community, a practice of paying it forward, and a desire to continue pushing the boundaries of methodology and education science. In efforts to replicate that history, it was comforting to see more than one workshop that focused on careers in health professions education, with learners and trainees keen to strategically develop educational scholarship and leadership opportunities alongside their clinical training and practice. The challenge now is to consider and evaluate how the countless crisis-time adaptations can be adapted further to maintain their best qualities while overcoming concessions that needed to be made throughout the past year. The pandemic, therefore, creates vast opportunities to shape the next era of education design and delivery as we begin to grapple with the question of “what will we do when we have the time to actually shape change instead of reacting to disruptions forced upon us?” We do not claim perfect clarity in this regard but are reassured by our attendance at the ASM that the question is in good hands and we look forward to hearing the answers delegates have generated at next year's (in person?) ASM.

ROLE OF STUDENTS’ RESEARCH ACTIITY IN FOSTERING PROFESSIONAL COMPETENCE AT THE DEPARTMENT OF PATHOPHYSIOLOGY OF POLTAVA STATE MEDICAL UNIVERSITY

Student research activity is one of the most important forms of the education and the driving force of quality assurance activities. Ukraine has developed a regulatory and legal framework that ensures high-quality research work, which should meet the needs of future specialists in intellectual and professional development and increase their professional competence. The involvement in research work requires, first of all, gaining deep theoretical and practical knowledge in medicine, well-designed extra-curricular activities to guide students in their mastering methodology of scientific research and developing research skills, and university promotion. The experience of Poltava State Medical University convincingly proves that the most effective means of improving the quality of training is the regular active involvement of students in research activity. The role of scientific knowledge in higher education is decisive, since the active participation of the teaching staff in fostering research skills makes it possible to demonstrate the latest scientific achievements and their practical application. Structured research activities, woven into the medical school curriculum provide an opportunity to evince the intellectual potential of both students and educators, to contribute to deeper investigation of medical problems, to master the methods of scientific investigation, and to realize the importance of such activity in increasing one's competitiveness in the labour market. This approach also contributes to better comprehension of professional information, to develop mindset associated with high professionalism.
 Pathophysiology as a discipline is at the junction of theoretical and clinical disciplines that serves as a wide background to meet the diversity of students’ scientific demands and interests. Involving students into structured research activities not only promotes gaining special knowledge, but also builds up ethical and deontological foundations of future successful medical research career; enhances team spirit and cooperation between students and educators. This interaction enables in clearly stating their focus and research question, engaging in an adequate critical discussion of the strengths and weaknesses of the study methods, and offering conclusions that are properly qualified in the scope given the evidence gathered and analyzed. This department is proud to maintain a high university rank on student research results performance among the non-clinical departments. The culmination of knowledge in this developmental trajectory can reinforced and extend other aspects of high quality training.

The "Shut the f**k up" Phenomenon: Characterizing Incivility in Open Source Code Review Discussions

Code review is an important quality assurance activity for software development. Code review discussions among developers and maintainers can be heated and sometimes involve personal attacks and unnecessary disrespectful comments, demonstrating, therefore, incivility. Although incivility in public discussions has received increasing attention from researchers in different domains, the knowledge about the characteristics, causes, and consequences of uncivil communication is still very limited in the context of software development, and more specifically, code review. To address this gap in the literature, we leverage the mature social construct of incivility as a lens to understand confrontational conflicts in open source code review discussions. For that, we conducted a qualitative analysis on 1,545 emails from the Linux Kernel Mailing List (LKML) that were associated with rejected changes. We found that more than half (66.66%) of the non-technical emails included uncivil features. Particularly, frustration, name calling, and impatience are the most frequent features in uncivil emails. We also found that there are civil alternatives to address arguments, while uncivil comments can potentially be made by any people when discussing any topic. Finally, we identified various causes and consequences of such uncivil communication. Our work serves as the first study about the phenomenon of in(civility) in open source software development, paving the road for a new field of research about collaboration and communication in the context of software engineering activities.

User Involvement and Performance of Enterprise Resource Planning System Implementation in Multi-national Organizations in Kenya. A Case of Un-Habitat in Kenya

Most multi-national organizations in Kenya are adopting an entire suite of enterprise resource planning Software and customize them to fit the business processes. Despite the continued review of the enterprise resource planning suite, the realization of a successful enterprise resource planning implementation for multi-national organizations is becoming difficult, owing to user involvement issues. This research, therefore, addressed this by assessing the effect of user involvement on enterprise resource planning implementation for multi-national organizations in Kenya. The study used a descriptive research design, where it obtained a sample size of 70 respondents and selected the respondents from 85 subjects using stratified proportionate sampling. The data for the study was gathered from primary sources using a questionnaire. Data was evaluated using quantitative analysis to provide descriptive statistics accompanied by inferential analysis to estimate the model. Guided by the study findings, it was concluded that; there is a positive and significant relationship between users’ functional requirements activities and enterprise resource planning implementation; users’ presentation requirement activities positively significantly influence enterprise resource planning implementation, users’ quality assurance activities has a significant moderate influence on its enterprise resource planning implementation, and users’ project management activities have a significant moderate influence on enterprise resource planning implementation. The study recommends that these organizations should; develop users’ functional requirements activities policy, review policies on business processes to accommodate different system implementation practices; review current quality assurance activities by consumers to satisfy the planned enterprise resource planning system demand of the provider, and acquire as well as retain the appropriate users’ project management.

Human factor associations with safety events in radiation therapy.

Background and purposeIncident learning can reveal important opportunities for safety improvement, yet learning from error is challenged by a number of human factors. In this study, incident learning reports have been analyzed with the human factors analysis classification system (HFACS) to uncover predictive patterns of human contributing factors.Materials and methodsSixteen hundred reports from the Safety in Radiation Oncology incident learning system were filtered for inclusion ultimately yielding 141 reports. A radiotherapy‐specific error type was assigned to each event as were all reported human contributing factors. An analysis of associations between human contributing factors and error types was performed.ResultsMultiple associations between human factors were found. Relationships between leadership and risk were demonstrated with supervision failures. Skill‐based errors (those done without much thought while performing familiar tasks) were found to pose a significant safety risk to the treatment planning process. Errors made during quality assurance (QA) activities were associated with decision‐based errors which indicate lacking knowledge or skills.ConclusionAn application of the HFACS to incident learning reports revealed relationships between human contributing factors and radiotherapy errors. Safety improvement efforts should include supervisory influences as they affect risk and error. An association between skill‐based and treatment planning errors showed a need for more mindfulness in this increasingly automated process. An association between decision and QA errors revealed a need for improved education in this area. These and other findings can be used to strategically advance safety.

Bayesian Modeling for the Detection of Adverse Events Underreporting in Clinical Trials.

IntroductionSafety underreporting is a recurrent issue in clinical trials that can impact patient safety and data integrity. Clinical quality assurance (QA) practices used to detect underreporting rely on on-site audits; however, adverse events (AEs) underreporting remains a recurrent issue. In a recent project, we developed a predictive model that enables oversight of AE reporting for clinical quality program leads (QPLs). However, there were limitations to using solely a machine learning model.ObjectiveOur primary objective was to propose a robust method to compute the probability of AE underreporting that could complement our machine learning model. Our model was developed to enhance patients’ safety while reducing the need for on-site and manual QA activities in clinical trials.MethodsWe used a Bayesian hierarchical model to estimate the site reporting rates and assess the risk of underreporting. We designed the model with Project Data Sphere clinical trial data that are public and anonymized.ResultsWe built a model that infers the site reporting behavior from patient-level observations and compares them across a study to enable a robust detection of outliers between clinical sites.ConclusionThe new model will be integrated into the current dashboard designed for clinical QPLs. This approach reduces the need for on-site audits, shifting focus from source data verification to pre-identified, higher risk areas. It will enhance further QA activities for safety reporting from clinical trials and generate quality evidence during pre-approval inspections.Supplementary InformationThe online version contains supplementary material available at 10.1007/s40264-021-01094-8.

Investigation of the higher education students’ participation in quality assurance processes based on the theory of planned behaviour: a case of Turkey

ABSTRACT This study aims to investigate Turkish higher education students’ participation behaviours in quality assurance systems. The data were collected from 113 students through a semi-structured qualitative questionnaire developed based on the theory of planned behaviour. The data were analysed under three main themes: feelings, subjective norms and perceived behavioural control. According to the results, students generally had positive opinions concerning their feelings about the quality assurance system and had positive subjective norms. However, the results for these two aspects indicated implementation-based passive participation rather than decision-based active participation. Challenges in behavioural control and ways of coping with these challenges were observed. The overall results has revealed the behavioural basis of student participation in quality assurance processes. In addition, the results can contribute to policy improvement processes in the higher education system and quality assurance activities for higher education institutions.

Understanding shared links and their intentions to meet information needs in modern code review:

Code reviews serve as a quality assurance activity for software teams. Especially for Modern Code Review, sharing a link during a review discussion serves as an effective awareness mechanism where “Code reviews are good FYIs [for your information].”. Although prior work has explored link sharing and the information needs of a code review, the extent to which links are used to properly conduct a review is unknown. In this study, we performed a mixed-method approach to investigate the practice of link sharing and their intentions. First, through a quantitative study of the OpenStack and Qt projects, we identify 19,268 reviews that have 39,686 links to explore the extent to which the links are shared, and analyze a correlation between link sharing and review time. Then in a qualitative study, we manually analyze 1,378 links to understand the role and usefulness of link sharing. Results indicate that internal links are more widely referred to (93% and 80% for the two projects). Importantly, although the majority of the internal links are referencing to reviews, bug reports and source code are also shared in review discussions. The statistical models show that the number of internal links as an explanatory factor does have an increasing relationship with the review time. Finally, we present seven intentions of link sharing, with providing context being the most common intention for sharing links. Based on the findings and a developer survey, we encourage the patch author to provide clear context and explore both internal and external resources, while the review team should continue link sharing activities. Future research directions include the investigation of causality between sharing links and the review process, as well as the potential for tool support.

Adverse Event Trends Within a Large-Scale, Routine, Voluntary Medical Male Circumcision Program in Zimbabwe, 2014-2019.

Between 2008 and 2020, over 22.6 million male circumcisions (MCs) were performed among men ≥10 years in 15 priority countries of East and Southern Africa. Few studies from routine MC programs operating at scale describe trends of adverse events (AEs) or AE rates over time. Routine program data from a large MC program in Zimbabwe. χ2 compared characteristics of patients with AEs. Univariable and multivariable logistic models examined factors associated with AE severity. Cochran-Armitage trend tests compared AE rate trends by year (2014-2019), age, and MC method (2017-2019). From 2014 to 2019, 469,000 men were circumcised; of the total men circumcised, 38%, 27%, and 35% were conducted among individuals aged 10-14; 15-19; and ≥20 years, respectively. Most MCs (95%) used surgical (dorsal slit or forceps-guided) methods; 5% were device based (PrePex). AEs were reported among 632 (0.13%) MCs; 0.05% were severe. From 2015 to 2019, overall AE rates declined from 34/10,000 to 5/10,000 (P-value <0.001). Severe AE rates also decreased over this period from 12/10,000 to 2/10,000 (P-value <0.001). AE rates among younger clients, aged 10-14 (18/10,000) were higher than among older age men (9/10,000) aged ≥20 years (P < 0.001); however, there was no significant association between age and AE severity. AE rates each year and over time were lower than the World Health Organization acceptable maximum (2% AEs). ZAZIC quality assurance activities ensured guideline adherence, mentored clinicians to MC competency, promoted quality client education and counseling, and improved AE reporting over time. Decreases in AE rates are likely attributed to safety gains and increasing provider experience.

Assessments of the quality systems of pharmaceutical distributors: a remote approach to be applied in times of COVID-19 and beyond

BackgroundAdequate quality systems throughout pharmaceutical supply chains are crucial to protect individuals and communities from substandard and falsified medical products. Thus, pharmaceutical distributors are regularly assessed by qualified experts. Since the COVID-19 pandemic has forced a suspension of normal activities, remote assessments via videoconferencing may represent a temporary alternative to on-site audits. We exploratorily evaluated the feasibility of remote assessments of pharmaceutical distributors, located in a low- or middle-income country hard-to reach during the COVID-19 pandemic.MethodsWe conducted pilot remote assessments of four conveniently selected distributors. The expert was remotely connected via videoconference, and supported by an in-country assessment facilitator (ICAF), who had received ad hoc training and was present at the assessed facility. First, the remote expert assessed the quality assurance (QA) activities and rated their compliance with the standards of the World Health Organization Good Storage & Distribution Practices (GSDP), as per routine practice. Second, s/he assessed the completeness, clarity and accuracy of data collected remotely, first per distributor, and then in aggregated form.ResultsData completeness was assessed by the expert as excellent, while clarity and accuracy were good. Overall data quality (a combination of completeness, clarity and accuracy) was good, with no major differences across QA activities, nor across distributors. Contextual limitations included poor internet connection, language barriers, and distributors’ lack of familiarity with QA terminology.ConclusionsOur findings are exploratory and cannot be extrapolated to other contexts, nor to other types of audits. Nonetheless, this pilot experience suggests that a well-planned remote assessment of pharmaceutical distributors, conducted with the support of a well-trained onsite ICAF, can provide data of acceptable quality, allowing to assess GSDP-compliance and to make temporary decisions about licensing or purchasing. Purchasers and policy makers should read the results of remote assessments in light of their intrinsic limitations. At the moment, onsite assessments remain the gold standards, but this could change in the longer term, with improved information technology and in light of the need to avoid unnecessary travels. Furthermore, remote assessments could be considered for routine pre-screening candidates for on-site assessments, and for targeted follow-up of on-site assessment.

Perceived Influence of Financial Disbursement on School Quality Assurance in Nyamagana District, Tanzania

This study sought to investigate on the perceived influence of financial disbursement on school quality assurance in Nyamagana District. The study used a mixed study approach that involves the use of both qualitative and quantitative data in a single study. The study population comprised of 198 selected school stakeholders and the sample was 78 school stakeholders. A single interview guide and a questionnaire were used during data collection. Quantitative data was analyzed through descriptive statistics using the Statistical Package for Social Science (Version 21.0) while qualitative data was analyzed through the thematic approach. The findings of the study showed that adequate funds are important for school quality assurance officers to function effectively. Furthermore, the adequate supply of funds for quality assurance purposes have added advantages like increasing the quality of students’ and teachers’ performance, propelling teachers’ professional development as well as enhancing the confidence of teachers in the process of teaching and learning. The study recommends that the government should disburse adequate funds to support Quality assurance activities in schools, recruit more qualified quality assurers and offer regular training to enable them to effectively perform all activities which are required when they visit schools. Quality assurers should do their job effectively to make sure schools have good environment to enhance quality learning for big results.

Cardiac Arrest and Complications after Spinal Anesthesia: The Perioperative and Anesthetic Adverse Event in Thailand (PAAd Thai) Incident Report Study

Background: Spinal anesthesia is one of most common anesthetic techniques in Thailand. The Perioperative and Anesthetic Adverse Events in Thailand (PAAd Thai) Study was a multicentered project among 22 hospitals across the country to investigate the incidence of anesthesia related complications. Objective: To study the incidences of cardiac arrest and complication after spinal anesthesia including the contributing factors and suggested corrective strategies. Materials and Methods: This prospective descriptive study of the incident reports that occurred regarding spinal anesthesia collected from 22 participating hospital in the data collection between January and December of 2015 was completed. Three senior anesthesiologists reviewed the data and descriptive statistics were used. Results: Among 62,120 spinal anesthesia, there were 127 incidents (5.8%) among 2,206 incident reports related to anesthesia. There were seven cases of intraoperative cardiac arrest with an incidence of 1.13:10,000 spinal anesthesia (95% CI 0.55 to 2.33). Other complications were bradycardia with less than 40 beats per minute (50.4%), anaphylaxis or anaphylactoid reaction or drug allergy (14.2%), drug error (8.4%), coma or CVA or convulsion (3.9%), and suspected pulmonary embolism (3.9%). Adverse events occurred frequently with specialties or surgeries of orthopedics (44.1%), cesarean delivery (17.3%), urosurgery (17.3%), general surgery (14.2%), and gynecological surgery (4.7%), respectively. Conclusion: Contributing factors were inexperience, inappropriate decision making, haste, and inappropriate pre-anesthetic evaluation or preparation while factors minimizing incidents were vigilance, having experience, and experienced assistants. Suggested corrective strategies were quality assurance activity, guidelines especially monitoring, improvement of supervision, and additional training. Keywords: Spinal anesthesia, Adverse events, Incidents, Complications, Neuraxial anesthesia, Cardiac arrest

Effort-Aware Just-in-Time Bug Prediction for Mobile Apps Via Cross-Triplet Deep Feature Embedding

Just-in-time (JIT) bug prediction is an effective quality assurance activity that identifies whether a code commit will introduce bugs into the mobile app, aiming to provide prompt feedback to practitioners for priority review. Since collecting sufficient labeled bug data is not always feasible for some mobile apps, one possible approach is to leverage cross-app models. In this work, we propose a new cross-triplet deep feature embedding method, called CDFE, for cross-app JIT bug prediction task. The CDFE method incorporates a state-of-the-art cross-triplet loss function into a deep neural network to learn high-level feature representation for the cross-app data. This loss function adapts to the cross-app feature learning task and aims to learn a new feature space to shorten the distance of commit instances with the same label and enlarge the distance of commit instances with different labels. In addition, this loss function assigns higher weights to losses caused by cross-app instance pairs than that by intra-app instance pairs, aiming to narrow the discrepancy of cross-app bug data. We evaluate our CDFE method on a benchmark bug dataset from 19 mobile apps with two effort-aware indicators. The experimental results on 342 cross-app pairs show that our proposed CDFE method performs better than 14 baseline methods.

Reinforcement Learning for Test Case Prioritization

Continuous Integration (CI) significantly reduces integration problems, speeds up development time, and shortens release time. However, it also introduces new challenges for quality assurance activities, including regression testing, which is the focus of this work. Though various approaches for test case prioritization have shown to be very promising in the context of regression testing, specific techniques must be designed to deal with the dynamic nature and timing constraints of CI. Recently, Reinforcement Learning (RL) has shown great potential in various challenging scenarios that require continuous adaptation, such as game playing, real-time ads bidding, and recommender systems. Inspired by this line of work and building on initial efforts in supporting test case prioritization with RL techniques, we perform here a comprehensive investigation of RL-based test case prioritization in a CI context. To this end, taking test case prioritization as a ranking problem, we model the sequential interactions between the CI environment and a test case prioritization agent as an RL problem, using three alternative ranking models. We then rely on carefully selected and tailored state-of-the-art RL techniques to automatically and continuously learn a test case prioritization strategy, whose objective is to be as close as possible to the optimal one. Our extensive experimental analysis shows that the best RL solutions provide a significant accuracy improvement over previous RL-based work, with prioritization strategies getting close to being optimal, thus paving the way for using RL to prioritize test cases in a CI context.