Iterative Improvement Research Articles

Developing a design thinking artificial intelligence driven auto-marking/grading system for assessments to reduce the workload of lecturers at a higher learning institution in South Africa

This study explores the development and implementation of a design thinking Artificial Intelligence (AI)-driven auto-marking/grading system for practical assessments and accurate feedback aimed at alleviating the workload of lecturers at an Online Distance eLearning (ODeL) institution in South Africa. The study adopts an iterative approach to designing and prototyping the system, ensuring alignment with the unique needs and challenges at an ODeL higher learning institution (HLI). The study outlines a Design thinking framework for developing the AI system, emphasizing empathy with user needs, clear problem definition, ideation, prototyping, testing, and iterative improvements. Integrating such a system promises to enhance operational efficiency, ensure fair and unbiased grading for assessments, and provide students with consistent, timely, personalized feedback. Tapping on theorists such as Michael Foucault and Joseph Schumpeter, this study contributes to the ongoing discourse on innovative solutions for educational challenges in South Africa by employing a design thinking framework and qualitative research methods. It provides insights for developing and implementing AI-driven auto-marking/grading systems in higher education settings. Cognizant of data privacy laws, the study will highlight the essential adherence to ethical guidelines in automated assessment processes and the successful implementation of AI-driven auto-marking/grading systems in ODeL. Additionally, this study aligns with several Sustainable Development Goals (SDGs), such as Good Health and Wellbeing (SDG 3), Quality Education (SDG 4), Decent Work and Economic Growth (SDG 8), Industry, Innovation, and Infrastructure (SDG 9). The study will have a follow-up article that will report on the data collected, and we will conduct another study where we seek the users’ feedback regarding the system.

Exploratory Analysis of Skin Cancer Dermatoscopic Image Datasets and Classification Methods

Skin cancer is a critical global health issue, where early detection significantly improves treatment outcomes. In this review paper, titled Exploratory Analysis of Skin Cancer Dermatoscopic Image Datasets and Classification Methods, we systematically explore the intersection of artificial intelligence (AI) and skin cancer diagnosis. Our approach began with a detailed literature survey of 40 research studies, providing insights into advancements and challenges in AI-based classification methods. This survey emphasizes the role of machine learning algorithms, particularly convolutional neural networks (CNNs), and datasets such as HAM10000, ISIC 2019, and ISIC 2024 in improving diagnostic performance. Next, we conducted exploratory data analysis (EDA) on the HAM10000, ISIC 2019, and ISIC 2024 datasets, uncovering critical patterns related to lesion distribution, anatomical sites, and demographic factors. These analyses highlight biases and imbalances in the datasets, which are crucial to address for robust model training. Finally, we discuss the creation and evaluation of a machine learning model trained on a separate dataset. Initial experiments revealed challenges such as overfitting and class imbalance. Through advanced data augmentation techniques and the integration of an Augmentor pipeline, we mitigated these issues, achieving improved accuracy and generalizability. This paper provides a comprehensive framework for integrating literature insights, dataset analysis, and iterative model improvement to develop effective AI-based solutions for skin cancer detection. It underscores the importance of addressing dataset biases, adopting diverse datasets, and refining methodologies to advance AI applications in dermatology.

Development of a remote implementation support strategy to enhance integration of depression treatment into primary care settings in rural India

IntroductionContextually responsive implementation support strategies are needed to enhance the integration of mental health services into primary health care. Technical assistance is widely used as a core “capacity building” strategy, primarily for increasing the motivation and capacity of individuals (e.g., frontline workers) to adopt evidence-based interventions in healthcare settings. This article documents the systematic design of a technical assistance strategy for supporting primary care staff (e.g., nurses) in integrating depression care, from screening to treatment, aligned with a non-communicable disease program across seven health facilities in the Sehore District of Madhya Pradesh, India.MethodsWe conducted a mapping exercise of local health facilities with dedicated staff and a literature review to inform the development of the technical assistance strategy.ResultsReporting guidelines guided the structure of the strategy protocol. The evidence-supported strategy, called Remote Coaching Support, is tailored to the local setting. It uses quality improvement methods like the Plan-Do-Act-Study cycle and training materials to help coaches deliver support remotely via video/phone-based calls and WhatsApp messaging with the overall goal of increasing uptake and fidelity of depression screening and referral among primary care staff in alignment with an existing non-communicable diseases program.ConclusionThe development of Remote Coaching Support involved iterative improvements through team meetings and practice-training feedback, though limitations exist due to a lack of systematic implementation standards, especially in this setting. This strategy will be tested in increasing scales to refine its application, with effectiveness and acceptability results to be evaluated in a randomized control trial.

Equity-Focused Interventions Improve Interpreter Use in the Pediatric Intensive Care Unit.

Federal guidelines and equitable care mandate that patients who use a language other than English receive interpretation in their preferred language. Substantial variability exists in interpreter use in intensive care settings. We aimed to increase the rate of interpretations in our pediatric intensive care unit (PICU) through a series of targeted interventions. A multidisciplinary team developed a key driver diagram to identify areas for focused intervention. Each plan-do-study-act cycle informed the next cycle of interventions, targeting increasing interpreter (video, phone, and in-person) use. Interventions included standardizing technology, standardizing placement of interpretation devices in patient rooms, provider education, and creating accountability systems of interpreter use by care providers. We reviewed data from PICU encounters between January 2018 and January 2022 and used summary statistics and statistical process control methods to measure the impact of our interventions. We analyzed 882 patient encounters over the 4-year study period. Demographic characteristics were similar in the preintervention and postintervention periods. The total interpretation rate increased to 2.7 interpretations per patient per day from a baseline rate of 1.4. Each individual interpretation modality demonstrated increases in use. Average time spent interpreting via phone increased from 8 to 10.5 minutes per patient per day, and average time spent interpreting via video went from 9.5 to 22 minutes per patient per day. Iterative quality improvement methodology effectively identified barriers to equitable care, guided development of focused interventions, and improved interpreter use among pediatric patients who were critically ill.

Furniture App using Augmented Reality (AR)

Abstract: In recent years, augmented reality (AR) has revolutionized various industries, including retail and e-commerce. This paper presents the development methodology of a cross-platform furniture application utilizing Flutter and an AR plugin to enhance user experience in visualizingfurniture in real-world environments. The app aims to bridge the gap between online shopping and physical interaction with furniture by allowing users to place and view virtual furniture in their homes through their mobile devices. Key features include a comprehensive furniture catalogue, detailed product views, and intuitive AR interactions. This project highlights the integration of AR technology into a mobile app,the design and implementation process, and the challenges encountered during development. User feedback and iterative improvements play a crucial role in refining the app for better performance and user satisfaction.

“My Back Exercise App”—mHealth for Low Back Pain: Development and Usability Testing

Abstract Effective management of chronic low back pain (LBP) often relies on maintaining a healthy lifestyle. Mobile health (mHealth) applications provide a unique opportunity to support LBP sufferers by integrating evidence-based health education into daily routines. However, many existing mHealth apps lack scientific rigour in their development, limiting their impact. This study reports on developing and usability testing My Back Exercise, an mHealth app designed to support individuals managing chronic LBP through a user-centred, theory-based approach. The development followed the Double Diamond framework and Software Development Life Cycle (SDLC) model, focusing on behaviour change theory to promote healthy lifestyle habits. Usability testing involved ten users and employed the System Usability Scale (SUS) and Mobile App Rating Scale (MARS) to assess engagement, functionality, aesthetics, and information quality. Additionally, a think-aloud approach captured real-time feedback and guided iterative improvements. Results showed that the app was well-received, achieving a SUS mean score of 79 (total score of 100) and a MARS mean score of 3.7 (out of 5.0). Key intervention components included exercises, sleep management, diet, and pain education, contributing to a holistic self-management tool. This study provides a transparent roadmap for the development of evidence-based digital health tools. The My Back Exercise app offers an innovative, holistic approach to help people self-manage chronic LBP using evidence-based methods.

Trade-offs, control conditions, and alternative designs in the experimental study of cultural evolution.

Although the theoretical foundations of the modern field of cultural evolution have been in place for over 50 y, laboratory experiments specifically designed to test cultural evolutionary theory have only existed for the last two decades. Here, we review the main experimental designs used in the field of cultural evolution, as well as major findings related to the generation of cultural variation, content- and model-based biases, cumulative cultural evolution, and nonhuman culture. We then identify methodological advances that demonstrate the iterative improvement of cultural evolution experimental methods. Finally, we focus on one common critique of cultural evolution experiments, the appropriate individual learning control condition needed to demonstrate cumulative culture, and present an original experimental investigation relevant to this critique. Participants completed a combinatorial innovation task allowing for cumulative improvement over time in one of four commonly used experimental designs/conditions: social learners in chains, social learners in groups, individual learners experiencing an extended session lasting the same accumulated time as an entire chain or group, and individual learners experiencing repeated sessions adding up to the same total time. We found that repeated individual learning resulted in superior performance to any other condition. We discuss these findings in light of the relevance of the specific criticism of previous experimental studies that purport to have demonstrated cumulative culture. We also use our findings to discuss the broad trade-offs that participants face when learning individually and socially in different contexts, including variable acquisition costs, redundancy of effort in groups, and cognitive and motivational fatigue.

Development of an operational trap for collection, killing, and preservation of triatomines (Hemiptera: Reduviidae): the kissing bug kill trap.

Surveillance of triatomines or kissing bugs (Hemiptera: Reduviidae: Triatominae), the insect vectors of Trypanosoma cruzi, a Chagas disease agent, is hindered by the lack of an effective trap. To develop a kissing bug trap, we made iterative improvements over 3 years on a basic design resulting in 7 trap prototypes deployed across field sites in Texas, United States and Northern Mexico, yielding the capture of 325 triatomines of 4 species (Triatoma gerstaeckeri [Stål], T. sanguisuga [LeConte], T. neotomae [Neiva], and T. rubida [Uhler]). We began in 2019 with vertical transparent tarpaulin panel traps illuminated with artificial light powered by AC current, which were successful in autonomous trapping of flying triatomines, but were expensive, labor-intensive, and fragile. In 2020, we switched to white LED lights powered by a solar cell. We tested a scaled-down version of the vertical panel traps, a commercial cross-vane trap, and a multiple-funnel trap. The multiple-funnel traps captured 2.6× more kissing bugs per trap-day than cross-vane traps and approached the performance of the vertical panel traps in number of triatomines captured, number of triatomines per trap-day and triatomines per arthropod bycatch. Multiple-funnel traps required the least labor, were more durable, and had the highest triatomines per day per cost. Propylene glycol in the collection cups effectively preserved captured triatomines allowing for molecular detection of T. cruzi. The trapping experiments established dispersal patterns for the captured species. We conclude that multiple-funnel traps with solar-powered LED lights should be considered for adoption as surveillance and potentially mass-trapping management tools for triatomines.

An interactive dashboard for analyzing user interaction patterns in the i2b2 clinical data warehouse

BackgroundClinical data warehouses provide harmonized access to healthcare data for medical researchers. Informatics for Integrating Biology and the Bedside (i2b2) is a well-established open-source solution with the major benefit that data representations can be tailored to support specific use cases. These data representations can be defined and improved via an iterative approach together with domain experts and the medical researchers using the platform. To facilitate these discussions, it is important to understand how users interact with the system.ObjectiveThe objective of this work was to develop metrics for describing user interactions with clinical data warehouses in general and i2b2 in particular. Moreover, we aimed to develop a dashboard featuring interactive visualizations that inform data engineers and data stewards about potential improvements.MethodsWe first identified metrics for different data usage dimensions and extracted the relevant metadata about previous user queries from the i2b2 database schema for further analysis. We then implemented associated visualizations in Python and integrated the results into an interactive dashboard using Dash.ResultsThe identified categories of metrics include frequency of use, session duration, and use of functionality and features. We created a dashboard that extends our local i2b2 data warehouse platform, focusing on the latter category, further broken down into the number of queries, frequently queried concepts, and query complexity. The implementation is available as open-source software.ConclusionA range of metrics can be derived from metadata logged in the i2b2 database schema to provide data engineers and data stewards with a comprehensive understanding of how users interact with the platform. This can help to identify the strengths and limitations of specific instances of the platform for specific use cases and aid their iterative improvement.

Numerical study on a new adjustable multi-hole throttling device for natural gas flooding

Natural gas flooding represents a significant technique for the enhancement of oil recovery, thereby facilitating the efficient utilization of oil and gas resources. In the injection and production system, the throttling gas nozzle is a key component that adjust the injection pressure according to the reservoir’s pressure. However, current throttling gas nozzles utilize a fixed structure, which presents a challenge in achieving online control of flow rate and pressure drop. Therefore, a new adjustable multi-hole throttling device was proposed in this paper, allowing for the regulation of pressure loss by changing the number of flowing holes. In order to gain insight into the operational principles and pressure drop characteristics of this new throttling device, the SST k-ω turbulence model and the NIST physical property model were employed to simulate the supercritical natural gas flow in the nozzle. The results demonstrate that there is an uneven distribution of velocity between the channels of the downhole multi-hole throttling device. The velocity in a single nozzle channel exhibits a trend of initially increasing rapidly and then decreasing, while the pressure exhibits an initial decrease, which is then followed by a slight increase. The pressure drops of the nozzle under different flow rates and flowing hole numbers were acquired, revealing that the pressure drop of the multi-hole throttling device is inversely proportional to the number of holes. The adjustment accuracy of pressure drop and flow rate is higher when the number of holes is between 4 and 6. However, a significant increase in pressure drop occurs when the number of holes is less than 3, resulting in poorer regulation accuracy. Furthermore, a pressure drop prediction model was developed based on the numerical results, which provides guidance for the application and design of the throttling device. In this study, a new natural gas flooding throttling device is proposed, offering a new approach for downhole equipment development. Additionally, this research provides guidance for the practical application and iterative improvement of this throttling device in future use.

A Web-Based Intervention to Support a Growth Mindset and Well-Being in Unemployed Young Adults: Development Study.

Engaging young adults in the labor market is vital for economic growth and well-being. However, the path to employment often presents setbacks that impact motivation and psychological functioning. Research suggests exploring positive psychology interventions in job-seeking and scaling the delivery of these using technology. However, dropout rates are high for self-administered psychological interventions on digital platforms. This challenge needs to be addressed for such platforms to be effective conveyors of psychological interventions. This study addresses this challenge by exploring user-oriented methods and proposes persuasive features for the design and development of a new web-based intervention targeting young unemployed adults. This study aims to provide an overview of a new positive psychology wise intervention, including its theoretical underpinnings and human-centered design methodology, targeting young, unemployed adults. Researchers collaborated with designers, developers, and stakeholders to design a web-based positive psychology intervention that leverages evidence-based wise interventions. Key improvements and adaptations were explored through formative usability testing with 13 unemployed young adults aged between 18 and 25 years (the target population). Qualitative usability testing data were collected, analyzed, and integrated into the ongoing design process as iterative improvements. The result of this study is a modular intervention web application named RØST, designed to align with the user needs and the preferences of the specific end-user group of unemployed young adults. During the project, this application evolved from early concept sketches and prototypes into a developed solution ready for further testing and use. Insights from both end-user feedback and rich user observation gained in the study were used to refine the content and the design. To increase targeted end users' motivation, persuasive design features including praise, rewards, and reminders were added. The web application was designed primarily to be used on mobile phones using text messaging for reminders. The development process included technical and data protection considerations. This study offers valuable insights into developing psychological or behavioral interventions to support unemployed young adults by documenting the design process and the adaptation and combination of diverse theoretical and empirical foundations. Involving stakeholders and end users in the development enabled relatable content development and resolved potential usability problems. An essential implication is the finding that end-user feedback and insights are crucial in shaping interventions. However, we experienced tensions between the evidence-based interventions and the human-centered design approaches. These tensions were not resolved and highlighted a need for ongoing user motivation support through monetary rewards, which were incorporated into the final web app design.

Shadow Testing in Autonomous Vehicles : A Novel Approach to Validating Full Self-Driving AI Systems

As autonomous vehicles progress towards widespread deployment, ensuring the reliability and safety of Full Self-Driving (FSD) AI systems remains a critical challenge. This article presents a comprehensive analysis of shadow testing, an innovative approach to validating new FSD AI models in real-world conditions without compromising user safety. We examine the methodology of deploying new AI models in "shadow mode," where they process live sensory data alongside the operational system but do not control the vehicle. This approach enables the collection of valuable performance metrics and the identification of edge cases while mitigating risks associated with direct deployment. Our study demonstrates how shadow testing facilitates a continuous feedback loop for iterative improvement, enhancing model reliability through data-driven refinement. We further explore the challenges of implementing shadow testing at scale, including data processing requirements and ethical considerations. Our findings suggest that shadow testing not only accelerates the development of robust FSD systems but also plays a crucial role in building public trust in autonomous vehicle technology. This article contributes to the growing body of knowledge on AI safety validation techniques and provides insights for standardizing testing protocols in the autonomous vehicle industry.

Patient experiences with a smartphone application dedicated to postoperative recovery after elective arthroplasty

IntroductionIn the rapidly evolving landscape of digital health technologies, the widespread use of smartphones has paved the way for innovative applications designed to enhance healthcare experiences. This introduction underscores the global prevalence of smartphone users and their potential in healthcare, particularly exemplified by therapeutic apps such as the ‘Post Op’ smartphone application. Focused on postoperative support, this app prioritises user-friendly design, data recording, and adherence to national standards. The study aims to evaluate the app's success in achieving these objectives, highlighting its continuous improvement based on real user feedback and its potential impact on improving patient experiences and recovery processes. Methods and materialsA cohort of elective joint arthroplasty procedure patients at Kettering General Hospital (KGH), spanning a timeframe of one to 12 months post-surgery were surveyed over the telephone regarding their experience of the ‘Post Op’ smartphone utilising a custom, well-structured standardised questionnaire. ResultsThe study surveyed 42 consecutive patients who had undergone elective joint arthroplasty procedures at Kettering General Hospital, including 22 total hip replacement (THR) and 20 total knee replacement (TKR) patients. The respondents, with a median age of 66 years, provided overwhelmingly positive feedback about the ‘Post Op’ smartphone application. On a scale of 1–6, the mean ease-of-use score was 5.31, with only two THR patients providing lower scores due to difficulties with photography. However, the app's overall functionality, particularly in uploading photos, received a mean score of 4.78. Despite some technical issues, 97.6 % of respondents would recommend the app, emphasising its positive impact on confidence in the recovery and reducing unnecessary healthcare visits. Narrative responses highlighted the app's simplicity, support, and prompt communication with healthcare teams. Overall, the feedback indicates a high level of satisfaction with the ‘Post Op’ application among elective arthroplasty patients, showcasing its potential benefits for postoperative care. ConclusionThe study provides valuable insights into the impact of the ‘Post Op’ smartphone application on postoperative care, acknowledging both its successes and areas for enhancement. Further research and iterative improvements are crucial for optimising patient experiences and ensuring the app aligns effectively with healthcare needs.

Evaluating a novel clinical reasoning tool for physical therapy students: A pilot study.

This paper explores the use of the Anticipate-Plan-Pause Clinical Reasoning (APP CR) Tool to enhance clinical reasoning (CR) in Doctor of Physical Therapy (DPT) students. Current pedagogical methods often inadequately integrate CR abilities in a manner that is both engaging and effective. Drawing on several theoretical frameworks, the APP CR Tool was integrated into an interactive module for DPT students, aiming to improve CR abilities while reducing cognitive load and stress during high-stakes simulations. A randomised controlled trial was conducted with nine DPT students, divided into a control group (n = 5) and an intervention group (n = 4). Both groups used an interactive module with case-based scenarios, but only the intervention group used the APP CR Tool. Improvements in CR abilities and reduced stress and cognitive load were observed in both groups. However, statistical analysis revealed no significant differences between the groups. Despite this, a trend toward greater improvements in CR abilities was noted in the intervention group (p = 0.084). Further research is needed to validate these findings and refine the tool. The APP CR Tool shows potential for enhancing CR in DPT students, although its current application may require refinement to achieve statistically significant results. Educators should consider iterative improvements to the tool and its curriculum integration to better support CR development.

Flood impact assessment in remote areas using machine learning, SAR, and GIS: a case study of Ngabang District, Indonesia

ABSTRACT Flooding in remote regions presents significant challenges due to data scarcity, complicating impact assessment and mitigation efforts. This research delineates an integrated methodology for quantifying flood impacts in such contexts. By leveraging machine-learning algorithms, Sentinel-1 synthetic aperture radar (SAR) imagery was combined with digital elevation model data and river proximity metrics to predict and accurately demarcate flood extents. Geographic information systems overlay techniques were then employed for spatial analysis of the floods’ impacts on population and infrastructural assets. The methodology was applied in a case study in Ngabang District, Indonesia, demonstrating its utility. Analysis using decision tree, random forest (RF), and gradient boosting machine models provided critical insights into flood prediction factors. The RF model was chosen as the best, successfully identified flood-prone regions, achieving an accuracy of 0.94 and a Kappa of 0.87 on the testing data, demonstrating its robustness. The flood map showed significant impacts, affecting 373.81 hectares, 10,706 people, 1,500 buildings, and 15 km of roads. This study highlights the importance of proximity, elevation, SAR imagery, and iterative model improvements in flood prediction, offering valuable insights for flood management and mitigation efforts in data-scarce regions.

Enhancing Aerosol Mitigation in Medical Procedures: A CFD-Informed Respiratory Barrier Enclosure.

The COVID-19 pandemic has highlighted the significant infection risks posed by aerosol-generating procedures (AGPs), such as intubation and cardiopulmonary resuscitation (CPR). Despite existing protective measures, high-risk environments like these require more effective safety solutions. In response, our research team has focused on developing a novel respiratory barrier enclosure designed to enhance the safety of healthcare workers and patients during AGPs. We developed a hood that covers the patient's respiratory area, incorporating a negative pressure system to contain aerosols. Using computational fluid dynamics (CFD) analysis, we optimized the hood's design and adjusted the negative pressure levels based on simulations of droplet dispersion. To test the design, Polyalphaolefin (PAO) particles were generated inside the hood, and leakage was measured every 10 s for 90 s. The open side of the hood was divided into nine sections for consistent leakage measurements, and a standardized structure was implemented to ensure accuracy. Our target was to maintain a leakage rate of less than 0.3%, in line with established filter-testing criteria. Through iterative improvements based on leakage rates and intubation efficiency, we achieved significant results. Despite reducing the hood's size, the redesigned enclosure showed a 36.2% reduction in leakage rates and an approximately 3204.6% increase in aerosol extraction efficiency in simulations. The modified hood, even in an open configuration, maintained a droplet leakage rate of less than 0.3%. These findings demonstrate the potential of a CFD-guided design in developing respiratory barriers that effectively reduce aerosol transmission risks during high-risk medical procedures. This approach not only improves the safety of both patients and healthcare providers but also provides a scalable solution for safer execution of AGPs in various healthcare settings.

Evaluation of a public health workplace staff psychosocial risk assessment and wellbeing initiative

Abstract Adverse psychosocial work environments can have a detrimental effect on staff wellbeing causing chronic stress leading to burnout. Despite legislation mandating regular risk assessments, only one third of workplaces assess psychosocial risks. A 2020 European report identified one of the main barriers being a reluctance to talk openly about psychosocial issues. This paper describes an evaluation of a staff psychosocial risk assessment and wellbeing initiative in a Public Health Department in Ireland. The initiative commenced in October 2022 during a period of major health service organisational change. Informed by positive organisational psychology conceptual frameworks, guided by the European Psychosocial risk assessment framework (PRIMA-EF) and utilising the HSE Work Positive (CI) survey tool it was possible to constructively identify and categorise psychosocial risks across the Public Health team. In the evaluation, a mixed methods approach was used based on Donabedian’s structures, processes and outcomes overarching framework and Nielsen’s Model of Process Evaluation Framework. The first three iterative quality improvement cycles of the intervention were reviewed. The evaluation demonstrated that all of Nielson’s three indicators for a successful organisational level staff wellbeing intervention had been met: there was evidence of improvement in both working conditions and staff wellbeing; iterative quality improvement cycles including appreciative inquiry staff collaborative engagement ensured staff views and key learning was captured; new organisational structures within the Department enabled the sustainability of this process. The evaluation indicates that the staff psychosocial risk assessment process is beneficial for staff wellbeing and that the methods used are appropriate. The resources used in this process continue to be readily available within the health service organisation. The evaluation supports continuation of this process in its present form. Key messages • This evaluation supports staff psychosocial risk assessment and mitigation processes and provides a framework for healthcare managers to implement such processes and comply with legislation. • This evaluation indicates that effective and sustainable collaborative staff engagement can be achieved using a positive focus which builds on team strengths and harnesses collective wisdom.

Development of an automated process for monitoring of amiodarone treatment

Abstract Background Amiodarone treatment requires repeated laboratory evaluations of thyroid and liver function due to risk of side effects during long-term administration. Robotic process automation (RPA) represents the use of software robots to automate repetitive and routine tasks typically performed by humans. Purpose We aimed to develop an RPA using a diagnostic classification algorithm and clinical support system for follow-up of amiodarone treatment. Methods Based on international guidelines and clinical specialist advisory we constructed an RPA which was studied in a test environment in parallel with routine amiodarone treatment. Expert advice was integrated through a series of collaborative workshops, ensuring alignment of the algorithm with current best practices in thyroid and liver disease management. The RPA provided recommendations on the time interval to next laboratory testing and suggestions for patient management to the physician, who was serving as a human-in-the-loop responsible for clinical decisions. Results After iterative improvements the RPA was evaluated against physician orders (n=390 paired orders) without technical failures. The recommended time interval to next follow-up was (mean ± SD) 4.5 ± 2.4 vs. 3.1 ± 1.4 months for RPA vs. physician (p<0.0001). While normal laboratory findings resulted in recommended follow-up in 6 months by the RPA (72.2%) this was only ordered in 9.9% by the physician (Figure). Physicians’ orders clustered between 3-4 months (58.5%). All patients diagnosed with new side effects (n=12) were detected and communicated correctly by the RPA, whereas only 8 were correctly detected and responded to by the physician (Table). Conclusions An automated process constitutes a reliable alternative to the current fully manual management of amiodarone follow-up. It may reduce manual labour, frequency of laboratory testing and detect side effects with increased precision, thereby reducing costs and enhancing patient value. While the RPA shows promise, further research is needed to explore its adaptability to other treatment scenarios.

Developing Methods for Assessing the Impact of Digital Innovations on the Economic Efficiency of Enterprises: Methodology for Measuring ROI of Digital Projects

This study aims to develop methodologies for assessing the return on investment (ROI) of digital projects, crucial for understanding the economic impact of digital innovations on enterprises. Traditional ROI metrics often fail to capture the comprehensive value generated by digital projects. The proposed integrative framework employs advanced analytical methods, including cost-benefit analysis, real options analysis, and predictive analytics, to evaluate both tangible and intangible benefits. It incorporates dynamic risk management and scenario planning to address uncertainties and future challenges. Continuous feedback and iterative improvements ensure the framework's accuracy and relevance, enabling enterprises to optimize economic efficiency and strategic decision-making. This holistic approach offers an understanding of the multifaceted value of digital innovations.

Development and Evaluation of an AI-Based Chatbot for Preventing Social Media Addiction: A Waterfall Model Approach

The rapid growth of social media has transformed interaction and communication patterns, but it has also led to the rise of social media addiction, particularly among teenagers and young adults. This addiction, marked by compulsive usage and negative impacts on mental health and daily life, necessitates effective interventions. This research explores the development and evaluation of an AI-based chatbot designed to mitigate social media addiction by employing cognitive and behavioural strategies. The study utilizes the Waterfall model—a structured, sequential approach—in the chatbot’s development, encompassing stages from needs analysis to maintenance. The chatbot’s effectiveness was assessed through rigorous testing and user feedback. The methodology included problem analysis, system design, implementation, testing, and iterative improvements. A comprehensive needs analysis identified the psychological and behavioural factors contributing to social media addiction, leading to the design of a prototype chatbot integrated with AI for dynamic content adaptation and real-time feedback. The implementation phase focused on coding and system integration, followed by rigorous testing using Black Box Testing and the System Usability Scale (SUS) to ensure functionality and user-friendliness. Results indicate that the chatbot significantly reduced social media addiction scores, with a mean decrease from 55.21 to 50.17, supported by a highly significant p-value of <0.0001. User satisfaction was high, particularly regarding ease of use and information quality. However, user engagement declined over time, highlighting the need for ongoing content updates and feature enhancements. This study contributes to the field by providing insights into the application of the Waterfall model in AI chatbot development and offers a scalable solution for addressing social media addiction, with implications for future digital interventions in mental health.