Matching Items (30)

132761-Thumbnail Image.png

AI in Radiology: How the Adoption of an Accountability Framework can Impact Technology Integration in the Expert-Decision-Making Job Space

Description

Rapid advancements in Artificial Intelligence (AI), Machine Learning, and Deep Learning technologies are widening the playing field for automated decision assistants in healthcare. The field of radiology offers a unique platform for this technology due to its repetitive work structure,

Rapid advancements in Artificial Intelligence (AI), Machine Learning, and Deep Learning technologies are widening the playing field for automated decision assistants in healthcare. The field of radiology offers a unique platform for this technology due to its repetitive work structure, ability to leverage large data sets, and high position for clinical and social impact. Several technologies in cancer screening, such as Computer Aided Detection (CAD), have broken the barrier of research into reality through successful outcomes with patient data (Morton, Whaley, Brandt, & Amrami, 2006; Patel et al, 2018). Technologies, such as the IBM Medical Sieve, are growing excitement with the potential for increased impact through the addition of medical record information ("Medical Sieve Radiology Grand Challenge", 2018). As the capabilities of automation increase and become a part of expert-decision-making jobs, however, the careful consideration of its integration into human systems is often overlooked. This paper aims to identify how healthcare professionals and system engineers implementing and interacting with automated decision-making aids in Radiology should take bureaucratic, legal, professional, and political accountability concerns into consideration. This Accountability Framework is modeled after Romzek and Dubnick’s (1987) public administration framework and expanded on through an analysis of literature on accountability definitions and examples in military, healthcare, and research sectors. A cohesive understanding of this framework and the human concerns it raises helps drive the questions that, if fully addressed, create the potential for a successful integration and adoption of AI in radiology and ultimately the care environment.

Contributors

Agent

Created

Date Created
2019-05

131772-Thumbnail Image.png

A Look into Measuring Trust in Medical Devices

Description

The purpose of this review is to determine how to measure and assess human trust in medical technology. A systematic literature review was selected as the path to understand the landscape for measuring trust up to this point. I started

The purpose of this review is to determine how to measure and assess human trust in medical technology. A systematic literature review was selected as the path to understand the landscape for measuring trust up to this point. I started by creating a method of systematically reading through related studies in databases before summarizing results and concluding with a recommended design for the upcoming study. This required searching several databases and learning each advanced search methods for each in order to determine which databases provided the most relevant results. From there, the reader examined the results, keeping track in a spreadsheet. The first pass through filtered out the results which did not include detailed methods of measuring trust. The second pass took detailed notes on the remaining studies, keeping track of authors, participants, subjects, methods, instruments, issues, limitations, analytics, and validation. After summarizing the results, discussing trends in the results, and mentioning limitations a conclusion was devised. The recommendation is to use an uncompressed self-reported questionnaire with 4-10 questions on a six-point-Likert scale with reversing scales throughout. Though the studies analyzed were specific to medical settings, this method can work outside of the medical setting for measuring human trust.

Contributors

Agent

Created

Date Created
2020-05

The Need for Contextual Design when Creating Electronic Health Records

Description

Electronic Health Records (EHRs) began to be introduced in the 1960s. Government-run hospitals were the primary adopters of technology. The rate of adoption continually rose from there, doubling from 2007 to 2012 from 34.8% to about 71%. Most of the

Electronic Health Records (EHRs) began to be introduced in the 1960s. Government-run hospitals were the primary adopters of technology. The rate of adoption continually rose from there, doubling from 2007 to 2012 from 34.8% to about 71%. Most of the growth seen from 2007 to 2012 is a result of the passage of the Health Information Technology for Economic and Clinical Health (HITECH) Act as part of the American Reinvestment and Recovery (ARRA) Act. $19 billion dollars were made available as part of these two acts to increase the rate of Health Information Technology (HIT), of which EHRs are a large part. A national health information network is envisioned for the end stages of HITECH which will enable health information to be exchanged immediately from one health network to another. While the ability to exchange data quickly appears to be an achievable goal, it might come with the cost of loss of usability and functionality for providers who interact with the EHRs and often enter health data into an EHR. The loss of usability can be attributed to how the EHR was designed.

Contributors

Agent

Created

Date Created
2020-05

147586-Thumbnail Image.png

Diabetes Education/Management Needs for Chinese Americans with Type 2 Diabetes: Opportunities and Implications for Design

Description

Diabetes education has shown to improve diabetes health markers but there is a need for it to be more accessible Diabetes education in the form of Diabetes Self Education and Management (DSMES) could potentially utilize IT technologies, which have shown

Diabetes education has shown to improve diabetes health markers but there is a need for it to be more accessible Diabetes education in the form of Diabetes Self Education and Management (DSMES) could potentially utilize IT technologies, which have shown promise as a more accessible way to access healthcare and manage health. However, both these methods have not been optimized for the diverse population in the US. In particular, Chinese Americans are a growing minority group in America whose health needs such as diabetes type 2 are growing. As a cultural group, Chinese Americans have cultural characteristics that have been identified in the literature, which should be accounted for in the design of a technology-enabled DSMES program. This qualitative study aims to understand what ways Chinese Americans with type 2 diabetes are learning about and managing diabetes, as well as their technology usage. Themes such as cultural food importance, family roles, information acquisition, and attitudes and motivation emerged. Themes motivated the design implications and recommendations such as creating a more specified, culturally tailored Chinese food menu, integrated family features, and trackers with increased feedback. More research should be conducted to test the effectiveness of including these features in a technology-enabled DSMES program.

Contributors

Agent

Created

Date Created
2021-05

Certainty, Severity, and Low Latency Deception

Description

There has been an ongoing debate between the relative deterrent power of certainty and severity on deceptive and criminal activity, certainty being the likelihood of capture and severity being the magnitude of the potential punishment. This paper is a review

There has been an ongoing debate between the relative deterrent power of certainty and severity on deceptive and criminal activity, certainty being the likelihood of capture and severity being the magnitude of the potential punishment. This paper is a review of the current body of research regarding risk assessment and deception in games, specifically regarding certainty and severity. The topics of game theoretical foundations, balance, and design were covered, as were heuristics and individual differences in deceptive behavior. Using this background knowledge, this study implemented a methodology through which the risk assessments of certainty and severity can be compared behaviorally in a repeated conflict context. It was found that certainty had a significant effect on a person’s likelihood to lie, while severity did not. Exploratory data was collected using the dark triad personality quiz, though it did not ultimately show a pattern.

Contributors

Agent

Created

Date Created
2019

161525-Thumbnail Image.png

Executive Function (Anticipation) Differences Between Soccer Players With and Without a History of Traumatic Brain Injury

Description

The present study sought to understand traumatic brain injuries (TBI) impact on executive function (EF) in terms of anticipation amongst individuals with a background in soccer; along with other contributing factors of EF curtailments that inhibit athletes. Within this study

The present study sought to understand traumatic brain injuries (TBI) impact on executive function (EF) in terms of anticipation amongst individuals with a background in soccer; along with other contributing factors of EF curtailments that inhibit athletes. Within this study 57 participants, with a background in soccer (high school, collegiate, and semi-professional), completed five EF tasks: working memory, cognitive flexibility, attentional control, and anticipation; pattern detection and athletic cues (temporal occlusion). The results of this study concluded that when TBI history, gender, and soccer athletic level are factors, athletes with a soccer level of collegiate and semi-professional had decrements related to pattern detection anticipation; meaning athletes at higher levels had lower average scores on the Brixton Spatial Anticipation Test (BSAT). Additionally, female athletes showed more anticipation decrements related to athletic cues, especially those that are reliant on the initiation of judgment. Overall undiagnosed TBIs and limited understanding on how to approach rehabilitation to mitigate EF decrements, continue to impede individual autonomy amongst athletes. Keywords: Traumatic brain injury, executive function, anticipation, soccer, temporal occlusion, Brixton Spatial Anticipation Test (BSAT), collegiate, semi-professional, pattern detection, rehabilitation

Contributors

Agent

Created

Date Created
2021

161760-Thumbnail Image.png

EHR-mediated Workflow Analysis and Optimization Framework in PreOp Settings

Description

Perioperative care has a direct and crucial impact on patient safety and patient outcomes, as well as the financial viability of the healthcare facility. The time pressure and workload of caring patients facing surgery are heavier than caring inpatients of

Perioperative care has a direct and crucial impact on patient safety and patient outcomes, as well as the financial viability of the healthcare facility. The time pressure and workload of caring patients facing surgery are heavier than caring inpatients of other departments. This workload raises requirements for PreOp nurses, the primary PreOp caregiver, to complete information gathering, screening, and verification tasks accurately and efficiently. EHRs (Electronic Health Record System) have evolved continuously with increasing features to meet newly raised needs and expectations. Many healthcare institutions have undergone EHR conversion since the introduction of first-generation EHRs. Thus, the need for a systematic evaluation of changed information system workflow following conversion is becoming more and more manifest. There are a growing number of methods for analyzing health information technology use. However, few studies provide and apply a standard method to understand the impact of EHR transition and inspire opportunities for improvement.
This dissertation focuses on PreOp nurse’s EHR use in PreOp settings. The goals of this dissertation are to: (a) introduce a systematic framework to evaluate EHR-mediated workflow and the impact of the EHR transition; (b) understand the impact of different EHR systems on PreOp nurse’s workflow and preoperative care efficiency; (c) transform the evaluation results into practical user-centered EHR designs. This research draws on computational ethnography, cognitive engineering process and user-centered design concepts to build a practical approach for EHR transition-related workflow evaluation and optimization.
Observational data were collected before and after a large-scale EHR conversion throughout Mayo Clinic’s different regional health systems. For a structured computational evaluation framework, the time-efficiency of PreOp nurses’ work were compared quantitatively by means of coding and segmenting nurses’ tasks. Interview data provided contextual information, reflecting practical challenges and opportunities before and after the EHR transition.
The total case time, the time spent on EHR, and the task fragmentation were improved after converting to the new EHR system. A trend of standardization of information-related workflow and EHR transition was observed. Notably, the approach helped to identify current new system challenges and pointed out potential optimization solutions.

Contributors

Agent

Created

Date Created
2021

161714-Thumbnail Image.png

A Study of Explainable Decision Support for Longitudinal Sequential Decision Making

Description

Decision support systems aid the human-in-the-loop by enhancing the quality of decisions and the ease of making them in complex decision-making scenarios. In the recent years, such systems have been empowered with automated techniques for sequential decision making or planning

Decision support systems aid the human-in-the-loop by enhancing the quality of decisions and the ease of making them in complex decision-making scenarios. In the recent years, such systems have been empowered with automated techniques for sequential decision making or planning tasks to effectively assist and cooperate with the human-in-the-loop. This has received significant recognition in the planning as well as human computer interaction communities as such systems connect the key elements of automated planning in decision support to principles of naturalistic decision making in the HCI community. A decision support system, in addition to providing planning support, must be able to provide intuitive explanations based on specific user queries for proposed decisions to its end users. Using this as motivation, I consider scenarios where the user questions the system's suggestion by providing alternatives (referred to as foils). In response, I empower existing decision support technologies to engage in an interactive explanatory dialogue with the user and provide contrastive explanations based on user-specified foils to reach a consensus on proposed decisions. Furthermore, the foils specified by the user can be indicative of the latent preferences of the user. I use this interpretation to equip existing decision support technologies with three different interaction strategies that utilize the foil to provide revised plan suggestions. Finally, as part of my Master's thesis, I present RADAR-X, an extension of RADAR, a proactive decision support system, that showcases the above mentioned capabilities. Further, I present a user-study evaluation that emphasizes the need for contrastive explanations and a computational evaluation of the mentioned interaction strategies.

Contributors

Agent

Created

Date Created
2021

157313-Thumbnail Image.png

Decision Support for Crew Scheduling using Automated Planning

Description

Allocating tasks for a day's or week's schedule is known to be a challenging and difficult problem. The problem intensifies by many folds in multi-agent settings. A planner or group of planners who decide such kind of task association schedule

Allocating tasks for a day's or week's schedule is known to be a challenging and difficult problem. The problem intensifies by many folds in multi-agent settings. A planner or group of planners who decide such kind of task association schedule must have a comprehensive perspective on (1) the entire array of tasks to be scheduled (2) idea on constraints like importance cum order of tasks and (3) the individual abilities of the operators. One example of such kind of scheduling is the crew scheduling done for astronauts who will spend time at International Space Station (ISS). The schedule for the crew of ISS is decided before the mission starts. Human planners take part in the decision-making process to determine the timing of activities for multiple days for multiple crew members at ISS. Given the unpredictability of individual assignments and limitations identified with the various operators, deciding upon a satisfactory timetable is a challenging task. The objective of the current work is to develop an automated decision assistant that would assist human planners in coming up with an acceptable task schedule for the crew. At the same time, the decision assistant will also ensure that human planners are always in the driver's seat throughout this process of decision-making.

The decision assistant will make use of automated planning technology to assist human planners. The guidelines of Naturalistic Decision Making (NDM) and the Human-In-The -Loop decision making were followed to make sure that the human is always in the driver's seat. The use cases considered are standard situations which come up during decision-making in crew-scheduling. The effectiveness of automated decision assistance was evaluated by setting it up for domain experts on a comparable domain of scheduling courses for master students. The results of the user study evaluating the effectiveness of automated decision support were subsequently published.

Contributors

Agent

Created

Date Created
2019

157345-Thumbnail Image.png

Communicating intent in autonomous vehicles

Description

The prospects of commercially available autonomous vehicles are surely tantalizing, however the implementation of these vehicles and their strain on the social dynamics between motorists and pedestrians remains unknown. Questions concerning how autonomous vehicles will communicate safety and intent to

The prospects of commercially available autonomous vehicles are surely tantalizing, however the implementation of these vehicles and their strain on the social dynamics between motorists and pedestrians remains unknown. Questions concerning how autonomous vehicles will communicate safety and intent to pedestrians remain largely unanswered. This study examines the efficacy of various proposed technologies for bridging the communication gap between self-driving cars and pedestrians. Displays utilizing words like “safe” and “danger” seem to be effective in communicating with pedestrians and other road users. Future research should attempt to study different external notification interfaces in real-life settings to more accurately gauge pedestrian responses.

Contributors

Agent

Created

Date Created
2019