A transdisciplinary systems approach to the design of an artificial intelligence (AI) decision support system can more effectively address the limitations of AI systems. By incorporating stakeholder input early in the process, the final product is more likely to improve decision-making and effectively reduce kidney discard.
Kidney discard is a complex problem that will require increased coordination between transplant stakeholders. An AI decision support system has significant potential, but there are challenges associated with overfitting, poor explainability, and inadequate trust. A transdisciplinary approach provides a holistic perspective that incorporates expertise from engineering, social science, and transplant healthcare. A systems approach leverages techniques for visualizing the system architecture to support solution design from multiple perspectives.
Developing a systems-based approach to AI decision support involves engaging in a cycle of documenting the system architecture, identifying pain points, developing prototypes, and validating the system. Early efforts have focused on describing process issues to prioritize tasks that would benefit from AI support.
- NSF-PAR ID:
- 10306424
- Publisher / Repository:
- Springer Science + Business Media
- Date Published:
- Journal Name:
- Current Transplantation Reports
- Volume:
- 8
- Issue:
- 4
- ISSN:
- 2196-3029
- Page Range / eLocation ID:
- p. 263-271
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
null (Ed.)Purpose of Review: A transdisciplinary systems approach to the design of an artificial intelligence (AI) decision support system can more effectively address the limitations of AI systems. By incorporating stakeholder input early in the process, the final product is more likely to improve decision-making and effectively reduce kidney discard. Recent Findings: Kidney discard is a complex problem that will require increased coordination between transplant stakeholders. An AI decision support system has significant potential, but there are challenges associated with overfitting, poor explainability, and inadequate trust. A transdisciplinary approach provides a holistic perspective that incorporates expertise from engineering, social science, and transplant healthcare. A systems approach leverages techniques for visualizing the system architecture to support solution design from multiple perspectives. Summary: Developing a systems-based approach to AI decision support involves engaging in a cycle of documenting the system architecture, identifying pain points, developing prototypes, and validating the system. Early efforts have focused on describing process issues to prioritize tasks that would benefit from AI support.more » « less
-
Abstract This paper provides an experience report on a co‐design approach with teachers to co‐create learning analytics‐based technology to support problem‐based learning in middle school science classrooms. We have mapped out a workflow for such applications and developed design narratives to investigate the implementation, modifications and temporal roles of the participants in the design process. Our results provide precedent knowledge on co‐designing with experienced and novice teachers and co‐constructing actionable insight that can help teachers engage more effectively with their students' learning and problem‐solving processes during classroom PBL implementations.
Practitioner notes What is already known about this topic
Success of educational technology depends in large part on the technology's alignment with teachers' goals for their students, teaching strategies and classroom context.
Teacher and researcher co‐design of educational technology and supporting curricula has proven to be an effective way for integrating teacher insight and supporting their implementation needs.
Co‐designing learning analytics and support technologies with teachers is difficult due to differences in design and development goals, workplace norms, and AI‐literacy and learning analytics background of teachers.
What this paper adds
We provide a co‐design workflow for middle school teachers that centres on co‐designing and developing actionable insights to support problem‐based learning (PBL) by systematic development of responsive teaching practices using AI‐generated learning analytics.
We adapt established human‐computer interaction (HCI) methods to tackle the complex task of classroom PBL implementation, working with experienced and novice teachers to create a learning analytics dashboard for a PBL curriculum.
We demonstrate researcher and teacher roles and needs in ensuring co‐design collaboration and the co‐construction of actionable insight to support middle school PBL.
Implications for practice and/or policy
Learning analytics researchers will be able to use the workflow as a tool to support their PBL co‐design processes.
Learning analytics researchers will be able to apply adapted HCI methods for effective co‐design processes.
Co‐design teams will be able to pre‐emptively prepare for the difficulties and needs of teachers when integrating middle school teacher feedback during the co‐design process in support of PBL technologies.
-
Abstract Systems engineers regularly rely on analysis of early design artifacts like system architecture representations to predict system performance, lifecycle costs, and development schedules, and to support design decision‐making. Recent recognition of challenges in this type of measurement has led to a heightened focus on developing better metrics. Less attention has been paid to the system representations upon which all subsequent analysis is performed. With this study, we demonstrate that choices about how to represent the system can explain variation in measurement, even holding metrics constant. This is important because most of these representation choices remain unarticulated in current practice. To do this, we conduct a controlled experiment where we experimentally manipulated the Design Structure Matrix (DSM) architecture representation of nine crowdsourced robotic arm designs and compared the value and relative ranks of their modularity and complexity. We found statistically significant changes in both value and rank, attributable to differences in choices in the system representation. The direction and magnitude of these changes also differed across modularity and complexity. In addition, some underlying designs seemed to be more robust to representation changes. This suggests an interaction between representation, design, and lifecycle properties. These results emphasize the importance of developing standard guidelines for how to represent system architectures and better documenting their use.
-
Artificial Intelligence (AI) systems for mental healthcare (MHCare) have been ever-growing after realizing the importance of early interventions for patients with chronic mental health (MH) conditions. Social media (SocMedia) emerged as the go-to platform for supporting patients seeking MHCare. The creation of peer-support groups without social stigma has resulted in patients transitioning from clinical settings to SocMedia supported interactions for quick help. Researchers started exploring SocMedia content in search of cues that showcase correlation or causation between different MH conditions to design better interventional strategies. User-level Classification-based AI systems were designed to leverage diverse SocMedia data from various MH conditions, to predict MH conditions. Subsequently, researchers created classification schemes to measure the severity of each MH condition. Such ad-hoc schemes, engineered features, and models not only require a large amount of data but fail to allow clinically acceptable and explainable reasoning over the outcomes. To improve Neural-AI for MHCare, infusion of clinical symbolic knowledge that clinicans use in decision making is required. An impactful use case of Neural-AI systems in MH is conversational systems. These systems require coordination between classification and generation to facilitate humanistic conversation in conversational agents (CA). Current CAs with deep language models lack factual correctness, medical relevance, and safety in their generations, which intertwine with unexplainable statistical classification techniques. This lecture-style tutorial will demonstrate our investigations into Neuro-symbolic methods of infusing clinical knowledge to improve the outcomes of Neural-AI systems to improve interventions for MHCare:(a) We will discuss the use of diverse clinical knowledge in creating specialized datasets to train Neural-AI systems effectively. (b) Patients with cardiovascular disease express MH symptoms differently based on gender differences. We will show that knowledge-infused Neural-AI systems can identify gender-specific MH symptoms in such patients. (c) We will describe strategies for infusing clinical process knowledge as heuristics and constraints to improve language models in generating relevant questions and responses.more » « less
-
Abstract This paper describes a Human‐Centred Learning Analytics (HCLA) design approach for developing learning analytics (LA) dashboards for K‐12 classrooms that maintain both contextual relevance and scalability—two goals that are often in competition. Using mixed methods, we collected observational and interview data from teacher partners and assessment data from their students' engagement with the lesson materials. This DBR‐based, human‐centred design process resulted in a dashboard that supported teachers in addressing their students' learning needs. To develop the dashboard features that could support teachers, we found that a design refinement process that drew on the insights of teachers with varying teaching experience, philosophies and teaching contexts strengthened the resulting outcome. The versatile nature of the approach, in terms of student learning outcomes, makes it useful for HCLA design efforts across diverse K‐12 educational contexts.
Practitioner notes What is already known about this topic
Learning analytics that are aligned to both a learning theory and learning design support student learning.
LA dashboards that support users to understand the associated learning analytics data provide actionable insight.
Design‐based research is a promising methodology for Human‐Centred Learning Analytics design, particularly in the K‐12 educational context.
What this paper adds
Leveraging a longstanding, yet fluid, research‐practice partnership is an effective design‐based research adaptation for addressing the high variation in instructional practices that characterize K‐12 education.
Using both quantitative and qualitative data that reflects students' developing knowledge effectively supports teachers' inquiry into student learning.
Teachers' use of learning analytics dashboards is heavily influenced by their perspectives on teaching and learning.
Implications for practice and/or policy
Impact on student learning outcomes, alongside usability and feasibility, should be included as a necessary metric for the effectiveness of LA design.
LA dashboard developers should both leverage learning data that reflect students' developing knowledge and position teachers to take responsive pedagogical action to support student learning.
LA researchers and developers should utilize a long‐term, yet fluid, research‐practice partnership to form a multi‐stakeholder, multidisciplinary design team for Human‐Centred Learning Analytics design.