Expert Feedback Research Articles

Evaluating a Reference Model for SAV in Urban Areas

Previous work presented a reference model for shared autonomous vehicles in urban areas supported by a systematic literature review and topic modeling. The proposed reference model was then evaluated with two real-world demonstrations: the service provided by Waymo in Phoenix and another offered by Baidu in Beijing. In this paper, we present another evaluation based on a survey conducted with a group of potential stakeholders belonging to the mobility industry who were asked about their agreement with each of the concepts in the reference model. The resulting artifact is stronger and more reliable because it reflects the feedback of mobility experts.

The Oncology QCARD Initiative: Fostering efficient evaluation of initial real-world data proposals.

The oncology quality, characterization, and assessment of real-world data (Oncology QCARD) Initiative was formed to develop a set of minimum study design and data elements needed to evaluate the fitness of the real-world data (RWD) source(s) proposed in an initial study concept as part of early interaction with scientific reviewers. A multidisciplinary executive committee (EC) was established to guide the Oncology QCARD Initiative. The EC conducted a landscape review of published literature, guidances, and guidelines to evaluate relevant dimensions of data quality measurement. Guided by the review and informed by expert feedback, the Oncology QCARD Initial Protocol Characterization (IPC) provides a summary of minimum elements needed to adequately describe an initial clinical study concept that involves RWD and is intended to support decision-making. Fit-for-use data and fit-for-purpose design emerged as themes from the landscape analysis. Data that are fit-for-use are both relevant (sufficiently capturing exposure, outcomes, and covariates) and reliable (understanding data accrual and quality control and whether the data represent the underlying concepts they are intended to represent) to answer a specific research question. A fit-for-purpose design takes appropriate steps to ensure internal and external validity and allows for transparency in reporting. The QCARD-IPC focuses on high-level characteristics of RWD sources and study design domains including data temporality, population, medical product exposure, comparators, and covariates, endpoints, statistical analysis, and data quality assurance plans. Evaluation of studies including RWD requires understanding the data source, study design, and potential biases to preliminarily evaluate whether selected RWD are fit-for-use for the research question. The Oncology QCARD-IPC provides a structured, transparent approach to facilitate early review and enhanced communication between study sponsors and scientific reviewers of initial study proposals including RWD.

Transformation of Traditional Corporate Tax Planning into AI-Driven Corporate Tax Planning

Corporate tax planning has traditionally relied on manual processes and expert judgment to minimize tax liabilities. However, the rise of artificial intelligence (AI) presents new opportunities to transform these practices through automation, real-time analysis, and predictive capabilities. To conduct this research, a comprehensive review of academic literature, case studies, and existing AI tools in tax planning was carried out. The proposed AI-based tax planning model was developed based on these findings and validated through simulations and expert feedback. The study also examined the process of integrating AI systems with existing corporate tax structures to assess the feasibility and effectiveness of implementation. Results show that AI-driven corporate tax planning significantly enhances accuracy and efficiency compared to traditional methods. The AI model provides real-time analysis and predictive insights, enabling businesses to optimize tax strategies while ensuring compliance with evolving regulations. Tax authorities also benefit from AI implementation, gaining more transparent and equitable tax structures, along with stronger supervision capabilities. The proposed model can be developed into customized software tailored to individual companies, seamlessly integrating with existing corporate systems. These findings indicate that AI has the potential to revolutionize corporate tax planning by streamlining tax management and optimizing outcomes. For businesses, AI enables personalized tax strategies that adapt to specific data and regulations, improving both compliance and long-term tax optimization.

Expert consensus on the clinical application of cortical bone trajectory for lumbar pedicle screws: results from a modified Delphi study.

A modified Delphi study. This study sought to establish expert consensus on the use of cortical bone trajectory (CBT) for lumbar pedicle screws. The CBT technique is widely used in the treatment of various degenerative lumbar diseases because it reduces surgical time, soft tissue exposure, and blood loss; improves biomechanical stability; and allows for faster patient recovery. However, as an emerging surgical technique, CBT remains controversial in terms of preoperative evaluation methods, key surgical techniques, complication prevention and treatment, postoperative follow-up, and other aspects, resulting in unclear indications and contraindications for some doctors and posing great challenges to the steady promotion of this technique. From May 2021 to August 2021, panelists were chosen to collect expert feedback using the modified Delphi method, and 74 spine surgeons from across China agreed to participate. Four rounds were conducted: one in-person meeting and three subsequent survey rounds. Each question received at least 70.0% agreement, indicating a consensus. The grade A, B, and C recommendation were defined as having ≥90.0%, 80.0%-89.9%, and 70.0%-79.9% agreement on each question, respectively. The panelist group consisted of 74 experts, and 72, 70, and 69 questionnaires were collected in three rounds, respectively. In total, 24 questions with 59 options reached consensus after the Delphi rounds, including indications (adjacent vertebral diseases after lumbar internal fixation) and contraindications (previous surgery or bone destructive diseases lead to the destruction or absence of bone in the lamina or isthmus); advantages (intraoperative traction of paravertebral soft tissue is small) and disadvantages (not three-column fixation.); preoperative evaluation; complications; and postoperative follow-up evaluation, of CBT. The modified Delphi method achieved expert consensus on the clinical use of CBT for lumbar pedicle screws. This consensus document establishes clear guidelines for indications, contraindications, surgical techniques, and postoperative management, thereby enhancing clinical decision-making and promoting the safe and effective use of CBT. While the initial study focused on Chinese surgeons, future research will seek to validate and expand these findings from a broader international perspective.

FSscore: A Personalized Machine Learning‐Based Synthetic Feasibility Score

AbstractDetermining whether a molecule can be synthesized is crucial in chemistry and drug discovery, as it guides experimental prioritization and molecule ranking in de novo design tasks. Existing scoring approaches to assess synthetic feasibility struggle to extrapolate to new chemical spaces or fail to discriminate based on subtle differences such as chirality. This work addresses these limitations by introducing the Focused Synthesizability score (FSscore), which uses machine learning to rank structures based on their relative ease of synthesis. First, a baseline trained on an extensive set of reactant‐product pairs is established, which is then refined with expert human feedback tailored to specific chemical spaces. This targeted fine‐tuning improves performance on these chemical scopes, enabling more accurate differentiation between molecules that are hard and easy to synthesize. The FSscore showcases how a human‐in‐the‐loop framework can be utilized to optimize the assessment of synthetic feasibility for various chemical applications.

Exploring global perspectives on the use of computer-based simulation in pharmacy education: a survey of students and educators.

: Increasing student numbers and logistical challenges in pharmacy education limit patient counselling and clinical placement opportunities. Computer-based simulation (CBS) offers scalable, interactive learning but faces integration barriers. : To explore global perceptions of CBS implementation in pharmacy education among educators and students. Methods: An online cross-sectional survey was developed based on literature review and expert feedback. The survey was distributed globally through academic pharmacy organisations, social media, and the authors' networks. It included 20 questions targeting pharmacy educators and students. : Responses from 152 educators across 38 countries and 392 students from 46 countries, spanning six WHO regions (AFRO, AMRO, EMRO, EURO, SEARO, and WPRO) were analysed using descriptive and inferential statistics. The majority of educators (90.1%, n = 137) and students (84.2%, n = 330) expressed comfort with using CBS and implementing it in their curriculum. Despite this, CBS was perceived as underutilised by 53.5% (n = 81) of educators and 63.7% (n = 250) of students. Students valued CBS for enhancing communication and problem-solving skills, while educators highlighted its relevance to community pharmacy practice. Both groups supported CBS use in assessments. All educators (100%) identified workload reduction as a key priority, hoped CBS could assist in this area. Educators also reported barriers such as financial constraints (56.6%, n = 86) and insufficient technical support (53.3%, n = 81). On the other hand, students were less optimistic about institutional support, with only a few (7.4%, n = 29) believed institutional leaders would actively support CBS adoption. Regional differences emerged, with SEARO (Southeast Asia) and AFRO (Africa) showing the lowest CBS usage rates. Educators in SEARO, AFRO, and EMRO (Eastern Mediterranean) raised concerns about technical support, while those in SEARO, AFRO, and WPRO (Western Pacific, including Australia, New Zealand, and Singapore) expressed financial concerns. Educators in AFRO and WPRO, however, reported being 100% comfortable with using CBS. : Both students and educators recognised the potential of CBS in pharmacy education, with strong support for its integration. Addressing barriers such as educator workload, financial constraints, and technical support is crucial for broader adoption. Improved resource allocation and targeted training for educators are essential to effectively incorporate CBS into the pharmacy curriculum.

Developing a Comprehensive Inventory to Define Harm Reduction Housing.

Background The City of Boston has faced unprecedented challenges with substance use amidst changes to the illicit drug supply and increased visibility of homelessness. Among its responses, Boston developed six low threshold harm reduction housing (HRH) sites geared towards supporting the housing needs of people who use drugs (PWUD) and addressing health and safety concerns around geographically concentrated tent encampments. HRH sites are transitional supportive housing that adhere to a "housing first" approach where abstinence is not required and harm reduction services and supports are co-located. Despite the importance of HRH, the specific characteristics and operations of these sites are not well understood. This study sought to address this gap by cataloging the common features of Boston's HRH sites to generate a comprehensive inventory tool for evaluating implementation of harm reduction strategies at transitional housing locations. Methods We collected data between June and September 2023 and included semi-structured qualitative interviews with HRH staff (n = 19), ethnographic observations and photos at six HRH sites. Candidate inventory components were derived through triangulation of the data. Two expert medical staff unaffiliated with data collection reviewed a draft inventory measuring awareness and utility of HRH inventory components. We then pilot tested the inventory with 3 HRH residents across two sites for readability and reliability. Inventory performance was further tested in a survey of 106 residents. Results HRH staff identified best practices, resources, and policies in HRH sites that were further contextualized with ethnographic field notes. Common to all were overdose prevention protocols, behavioral policies, security measures, and harm reduction supplies distribution. The initial 44-item inventory of services, policies and site best practices was further refined with expert and participant feedback and application, then finalized to generate a 32-item inventory. Residents identified and valued harm reduction services; medical supports were highly valued but less utilized. Conclusion The HRH inventory comprehensively assesses harm reduction provision and residents' awareness and perceived helpfulness of HRH operational components. Characterizing the critical components of HRH through this tool will aid in standardizing the concept and practice of HRH for PWUD and may assist other cities in planning and implementing HRH.

Regaining focus: Promoting attentional literacy in digital higher education

The attentional demands placed on digital learners have grown, with online and blended education increasingly impacted by hyperconnectivity and digital disarray. In this context, it is essential for educators to help learners develop attentional literacy (AL). Building on past research on AL which fused insights from the fields of digital literacies and contemplative pedagogy (CP), this Delphi study examined the concept of AL and associated practices in higher education. Starting with a working definition of AL, expert feedback was invited from a global panel of experienced CP practitioners across academic disciplines. Through three Delphi rounds, the AL definition was validated and refined, before an abbreviated version was produced to facilitate operationalisation by digital educators who may not have a CP background. The study further explored how AL can be integrated into online higher education curricula, identifying strategies for educators and students to develop AL practices and address barriers to these practices. Despite systemic and structural constraints, cultivating AL allows educators and students to exercise a greater degree of individual and collective agency over their own attention in a digital world. Implications for practice or policy: Students can be guided in developing AL through a series of stages involving awareness and noticing, focus and intentional choice, openness and curiosity, and consideration of the wider attentional ecosystem. Educators should develop their own AL first, approaching it holistically by integrating personal, pedagogical and professional development-related practices, along with complementary offline activities. Institutions can maximise scope for AL development by increasing technological support and, especially, reducing curricular time pressure on educators and students.

Limes (the Roman Frontier): Developing a Video Game for History Learning

The use of gaming technologies in education holds great promise to provide engaging learning experiences. Whereas video games have been successfully used to foster learning in several school subjects, the current understanding of the potential of video games for history learning is still limited. This paper details the development of Limes, a 2D top-down educational game created in Unity and rendered in pixel art. The game targets 5th/6th grade secondary school students and is set in the third century AD in southern Germany, a period characterized by political and social instabilities. Limes digs into the complex relations between the Roman Empire and the Alemanni tribe, one of the most powerful Germanic tribes of this period. The player can experience this pixelated world through the eyes of an Alemanni child, who forms a friendship with a Roman centurion. The unfolding narrative places the young protagonist in the precarious balance of peace and conflict, and the player needs to navigate the diplomatic tensions of the era. The gameplay consists of five levels, including primary missions and optional secondary missions which unlock special features (e.g., puzzles, quizzes). Limes incorporates a variety of game mechanics, ranging from running and interacting with characters to stealth missions, throwing rocks, and horse racing. These dynamics are integrated into the historical narrative of the game, enriching the player's experience. The game development process combined insights and methods from multiple disciplines, including game-based learning, educational, social, and cultural psychology, education sciences and pedagogy, and history education. Moreover, the game capitalizes on Unity’s wide array of development tools, which provide extensive customization possibilities, and employs pixel art, facilitating an engaging environment while maintaining a cost-conscious development process. Initial tests and expert feedback highlight the promise of Limes as a game that leverages historical accuracy and innovative educational tools to foster a deeper understanding of Roman history. Next steps include empirical studies with students to test the game's effectiveness (e.g., in improving interest in and knowledge of Roman history).

Adapting and Validating a Patient Prompt List to Assist Localized Prostate Cancer Patients with Treatment Decision Making.

Effective communication between patients and healthcare providers is essential for informed decision making in cancer care. Communication aids that can help prostate cancer patients optimize their involvement in treatment care planning are not widely used in the U.S. This research details the adaptation and validation process of a patient prompt list for localized prostate cancer patients undergoing treatment decisions. This process occurred in three steps: Step 1 involved gathering usable questions from the literature; in Step 2, we evaluated the tool's content via expert (N = 6) feedback; and in Step 3, we assessed the usefulness of the prompt list with patients (N = 30). Sixty percent of candidate questions (20/33) were retained for inclusion after achieving acceptable item-level content validity index (range: 0.83-1.00) and scale-level content validity index (S-CVI = 0.96) scores. The final 20 questions were classified into 5 domains (1: Treatment Options and Information, 2: Side Effects, Risks, and Recovery, 3: Emotional and Social Support, 4: Logistical and Practical Concerns, and 5: Future Health Considerations) through a card sorting exercise with a subset of patients (N = 3) and providers (N = 2). Most patients rated the prompt list as "useful or very useful" both to themselves (80%, N = 24) and to other men presenting with prostate cancer (83%, N = 25). The participatory process used to develop and validate the prompt list offers insights for the development of similar tools.

Expert-Guided Large Language Models for Clinical Decision Support in Precision Oncology.

Rapidly expanding medical literature challenges oncologists seeking targeted cancer therapies. General-purpose large language models (LLMs) lack domain-specific knowledge, limiting their clinical utility. This study introduces the LLM system Medical Evidence Retrieval and Data Integration for Tailored Healthcare (MEREDITH), designed to support treatment recommendations in precision oncology. Built on Google's Gemini Pro LLM, MEREDITH uses retrieval-augmented generation and chain of thought. We evaluated MEREDITH on 10 publicly available fictional oncology cases with iterative feedback from a molecular tumor board (MTB) at a major German cancer center. Initially limited to PubMed-indexed literature (draft system), MEREDITH was enhanced to incorporate clinical studies on drug response within the specific tumor type, trial databases, drug approval status, and oncologic guidelines. The MTB provided a benchmark with manually curated treatment recommendations and assessed the clinical relevance of LLM-generated options (qualitative assessment). We measured semantic cosine similarity between LLM suggestions and clinician responses (quantitative assessment). MEREDITH identified a broader range of treatment options (median 4) compared with MTB experts (median 2). These options included therapies on the basis of preclinical data and combination treatments, expanding the treatment possibilities for consideration by the MTB. This broader approach was achieved by incorporating a curated medical data set that contextualized molecular targetability. Mirroring the approach MTB experts use to evaluate MTB cases improved the LLM's ability to generate relevant suggestions. This is supported by high concordance between LLM suggestions and expert recommendations (94.7% for the enhanced system) and a significant increase in semantic similarity from the draft to the enhanced system (from 0.71 to 0.76, P = .01). Expert feedback and domain-specific data augment LLM performance. Future research should investigate responsible LLM integration into real-world clinical workflows.

Development of an evaluation system for rational drug use in patients with chronic kidney disease using the Delphi method.

Chronic kidney disease (CKD) stages 3-4 present a significant clinical challenge due to the absence of a systematic approach to managing associated medication-related problems (MRPs). This lack of a structured framework hinders the timely identification and effective intervention for these complications, potentially compromising patient safety and prognosis. This study aims to leverage the Delphi method to establish an evaluation index for a rational drug use evaluation system dedicated to CKD patients in stages 3-4. This system will function as a platform for the continuous identification and management of MRPs, ultimately contributing to improved medication safety and patient outcomes. This research uses the modified Delphi technique to develop an evaluation system for rational drug use in patients with chronic kidney disease. The initial questionnaire was developed by literature review for patients with chronic kidney disease. Twenty-six senior experts formed a panel in order to evaluate items across two Delphi rounds. Consensus was defined as at least 95% agreement (first round) and 85% agreement (second round), agreeing with an average score of at least 4.5 (first round) and 4.0 (second round). Items that fulfill the stipulated criteria are eligible for inclusion in the consensus list. All experts participated in both rounds (100% response rate). Consensus was achieved on three patient-related items in the first round of 34 items. Based on expert feedback, 18 revised items were included in the second round after refining, restructuring, and removing some elements. Following two rounds of consultation, 20 items achieved consensus, encompassing aspects such as drug selection, dosage assessment, treatment duration, prescription and dispensing practices, patient-related factors, and other relevant considerations. This study has successfully identified 20 key evaluation indicators for a rational drug use evaluation system specifically designed for CKD patients in stages 3 and 4. This system will serve as a tool for continuous MRP identification and timely intervention, ultimately enhancing medication safety and patient prognosis.

Innovating Nephrology Point-of-Care Ultrasonography Education: Artificial Intelligence-Assisted Curriculum Integration with Human Expert Feedback Loops

Innovating Nephrology Point-of-Care Ultrasonography Education: Artificial Intelligence-Assisted Curriculum Integration with Human Expert Feedback Loops

Development of a Pancasila Education Teaching Module with Integration of Mattabe' Culture for Strengthening Student Character Values

This study aims to develop and analyze a Pancasila education teaching module that incorporates the local Bugis-Makassar culture for elementary schools. It using the ADDIE development model, the research findings indicate that the Pancasila education teaching module meets the established criteria. The content effectively reflects Pancasila values integrated with Mattabe' culture, aligns with the Merdeka curriculum, and expert feedback confirms that the module is relevant and ready for use in teaching. The study concludes that the Pancasila education module presents accurate and authentic content, uses simple language, and employs interactive, engaging, and contextual teaching methods. Expert validation confirms that the module is ready for implementation in educational settings.Pancasila Education Teaching Module

Learning to Score: A Coding System for Constructed Response Items via Interactive Clustering

Constructed response items that require the student to give more detailed and elaborate responses are widely applied in large-scale assessments. However, the hand-craft scoring with a rubric for massive responses is labor-intensive and impractical due to rater subjectivity and answer variability. The automatic response coding method, such as the automatic scoring of short answers, has become a critical component of the learning and assessment system. In this paper, we propose an interactive coding system called ASSIST to efficiently score student responses with expert knowledge and then generate an automatic score classifier. First, the ungraded responses are clustered to generate specific codes, representative responses, and indicator words. The constraint set based on feedback from experts is taken as training data in metric learning to compensate for machine bias. Meanwhile, the classifier from responses to code is trained according to the clustering results. Second, the experts review each coded cluster with the representative responses and indicator words to score a rating. The coded cluster and score pairs will be validated to ensure inter-rater reliability. Finally, the classifier is available for scoring a new response with out-of-distribution detection, which is based on the similarity between response representation and class proxy, i.e., the weight of class in the last linear layer of the classifier. The originality of the system developed stems from the interactive response clustering procedure, which involves expert feedback and an adaptive automatic classifier that can identify new response classes. The proposed system is evaluated on our real-world assessment dataset. The results of the experiments demonstrate the effectiveness of the proposed system in saving human effort and improving scoring performance. The average improvements in clustering quality and scoring accuracy are 14.48% and 18.94%, respectively. Additionally, we reported the inter-rater reliability, out-of-distribution rate, and cluster statistics, before and after interaction.

Delphi method investigation and research on the revision of Diagnosis of Occupational Arsenic Poisoning (GBZ 83-2013)

Objective: To explore the expert opinions on the revision of the Diagnosis of Occupational Arsenic Poisoning (GBZ 83-2013) . Methods: In March 2023, the improved Delphi expert consultation method was adopted, in the first round of consultation, a pre-survey was conducted on 20 experts, and the questionnaire was improved according to the experts' opinions. Then, a second round of expert consultation questionnaire was formed to conduct a questionnaire survey and consultation of 50 experts engaged in occupational disease diagnosis and related work. The feedback of experts was collected and analyzed. Results: The average score for the scientificity and progressiveness of the main technical content of the original standard was 3.33, and the average score for the rationality and operability of the main technical content of the original standard was 3.25. The importance of individual indicators with specific connotations were ranged from 4.20 to 4.45, with coefficients of variation <0.25, and the experts' opinions were relatively concentrated. The experts have provided feedback indicating that the original standard had issues such as lack of continuity in diagnostic gradation, the need to integrate biomarkers with urinary and hair arsenic levels, a scarcity of objective diagnostic indicators, the removal of exposure response from the main text, and a low level of consistency in standard usage. These issues need to be revised urgently. Conclusion: The Diagnosis of Occupational Arsenic Poisoning (GBZ 83-2013) should be revised based on experts' feedback and suggestions to meet the current real demand for occupational arsenic poisoning diagnosis.

Development and Validation of an Evaluation Questionnaire for the Healthy Early Life Moments in Singapore (HELMS) Program.

Global fertility rates are declining due to metabolic and mental health challenges in women trying to conceive. The Healthy Early Life Moments in Singapore (HELMS) program aims to address these challenges through mobile health (mHealth)-enabled lifestyle interventions. However, the lack of validated evaluation tools for such programs makes it difficult to assess their feasibility and acceptability. To tackle this, a comprehensive evaluation questionnaire was developed and validated to determine if the HELMS preconception program's implementation outcomes were achieved. The questionnaire development process included a literature review and a two-step validation process: content validation by five content experts and face validation by 20 HELMS participants. Content validation was assessed using the scale content validity index (S-CVI) based on relevance, clarity, simplicity, and ambiguity. Face validation with participants evaluated these criteria and the ease of completing the questionnaire. Internal consistency was assessed using Cronbach's alpha among 49 participants. The questionnaire achieved good S-CVI values for relevance (0.93), clarity (0.91), simplicity (0.94), and ambiguity (0.71). After expert feedback, the revised version scored highly among HELMS participants for relevance (100%), clarity (95%), simplicity (95%), and non-ambiguity (90%). A Cronbach's alpha of 0.93 indicated good internal consistency. The HELMS evaluation questionnaire shows promise for evaluating similar mHealth-based lifestyle intervention programs globally.

Interactive visual formula composition of multidimensional data classifiers

Understanding how a classification result is generated and what role individual features play in the classification is crucial in many applications and, in particular, in medical contexts such as the translation of diagnosis biomarkers into clinical practice. The goal is to find (ideally simple) relationships between the features in multi-dimensional data and the classification for an explanation of the underlying phenomenon. Mathematical formulas allow for the expression of these relationships and can serve as classifiers. However, there are infinitely many mathematical formulas for the given features and they bear an inherent trade-off between complexity and accuracy. We present an interactive visual approach that supports domain experts to mitigate the trade-off issue. Core to our approach is a novel feature selection method, from which formulas are composed using symbolic regression and where state-of-the-art classifiers serve as a reference. To evaluate our approach and compare the achieved classification performance to the performance achieved by other state-of-the-art feature selection techniques, we test our methods with well-known machine learning data sets. Our evaluation shows that our feature selection method performs better than randomly selecting features for data sets with many features or when a low number of generations in the symbolic regression is required. Moreover, it consistently matches or outperforms state-of-the-art methods. Moreover, we apply our approach in a case study to a hemodynamic cohort data set, where we report our findings and domain expert feedback. Our approach was able to find formulas containing features that are in agreement with literature. Also, we could find formulas that performed better in the micro-averaged F1 score when compared to established histological indices.

A model for investment type recommender system based on the potential investors based on investors and experts feedback using ANFIS and MNN

This article presents an investment recommender system based on an Adaptive Neuro-Fuzzy Inference System (ANFIS) and pre-trained weights from a Multimodal Neural Network (MNN). The model is designed to support the investment process for the customers and takes into consideration seven factors to implement the proposed investment system model through the customer or potential investor data set. The system takes input from a web-based questionnaire that collects data on investors' preferences and investment goals. The data is then preprocessed and clustered using ETL tools, JMP, MATLAB, and Python. The ANFIS-based recommender system is designed with three inputs and one output and trained using a hybrid approach over three epochs with 188 data pairs and 18 fuzzy rules. The system's performance is evaluated using metrics such as RMSE, accuracy, precision, recall, and F1-score. The system is also designed to incorporate expert feedback and opinions from investors to customize and improve investment recommendations. The article concludes that the proposed ANFIS-based investment recommender system is effective and accurate in generating investment recommendations that meet investors' preferences and goals.Graphical abstract

The evaluation of daily activity questionnaire for stroke survivors: cross-cultural adaptation, content validity and digitisation

ObjectiveThe study's objective was to culturally adapt and digitise the Evaluation of Daily Activity Questionnaire (EDAQ), originally designed for rheumatoid arthritis and various other musculoskeletal conditions, creating a version for stroke survivors (EDAQ-SS). This adaptation also aimed to develop a comprehensive electronic Patient Reported Outcome Measure (ePROM) intended to refine stroke survivors' self-assessment of their daily activity limitations. Materials and methodsCross-cultural adaptation of the EDAQ was completed by a review of expert panel, which included healthcare professionals to increase the clarity and relevancy of the items, followed by cognitive debriefing interviews with British stroke survivors to rate their understanding of the questionnaire items. After developing the paper version of the questionnaire, this was digitised (eEDAQ-SS) and disseminated online via the Stroke Survivors Hub (SSHUB). Content validity of the EDAQ-SS was evaluated using the International Classification of Functioning (ICF) Core Set for Stroke. ResultsThe expert panel meeting (n:11) and cognitive debriefing interviews with stroke survivors (n:10) resulted in an EDAQ-SS with 160 items across 15 domains, which was understandable and relevant to stroke survivors. The SSHUB was deemed to be a user-friendly platform, providing easy access to eEDAQ-SS and aid self-assessment of daily activities of stroke survivors. Mapping the EDAQ-SS items to the ICF Core Set for Stroke demonstrated good content validity with 44/55 matching categories. ConclusionThe EDAQ-SS offers a comprehensive measure for self-assessment, which may serve to guide stroke survivors’ self-management by overcoming limitations of existing PROMs. Further psychometric testing of the EDAQ-SS and wider testing of the digital version is recommended. Contribution of the Paper•The Evaluation of daily activity questionnaire for stroke survivors (EDAQ-SS) is a culturally adapted, comprehensive PROM for British stroke survivors, enhancing self-assessment of daily activities.•Methodically developed using guidelines, expert feedback, and stroke survivor interviews, the EDAQ-SS ensures relevance and clarity.•The EDAQ-SS demonstrates good content validity against the International Classification of Functioning Core Set for Stroke, with potential to improve clinical practice by providing a detailed, sensitive measure to help stroke survivors and healthcare professionals identify and manage daily activity limitations more effectively.