A natural language intelligent tutoring system for training pathologists: implementation and evaluation

Saadawi, Gilan M.; Tseytlin, Eugene; Legowski, Elizabeth; Jukic, D.M.; Castine, Melissa; Fine, Jeffrey L.; Gormley, Robert; Crowley, Rebecca S.

doi:10.1007/s10459-007-9081-3

Cited by 39 publications

(32 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…No significant differences in learning gains were observed between groups. These findings replicate results demonstrated in previous studies of our tutoring system (Crowley et al, 2007; El Saadawi et al, 2008; El Saadawi et al, 2010). …”

Section: Resultssupporting

confidence: 92%

“…ITSs support “leaning-by-doing,” and provide individualized support, point out errors, and organize content to cater to the needs of the individual when the teacher has limited time to spend (Corbett, Koedinger, & Hadley, 2002; Koedinger & Aleven, 2007; VanLehn, 2006, 2011). Although there is a great potential for the use of medical ITS, few of these systems have been fully developed (e.g., Azevedo & Lajoie, 1998; Clancey, 1987; Crowley & Medvedeva, 2006; Lajoie & Azevedo, 2006; Lajoie, 2009; Maries & Kumar, 2008; Obradovich et al, 2000; Rogers, 1995; Sharples et al, 2000; Smith et al, 1998), a smaller number of which have been empirically evaluated (Crowley et al, 2007; El Saadawi et al, 2008; Woo et al, 2006). …”

Section: Introductionmentioning

confidence: 99%

“…The system analyzes diagnostic reports written by pathology residents in real-time, and highlights errors they make in their slide review and report writing. Participants who used the system experienced a four-fold improvement in their ability to write accurate and complete diagnostic reports (El Saadawi et al, 2008). …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Metacognitive scaffolds improve self-judgments of accuracy in a medical intelligent tutoring system

et al. 2013

Self Cite

View full text Add to dashboard Cite

In this study, we examined the effect of two metacognitive scaffolds on the accuracy of confidence judgments made while diagnosing dermatopathology slides in SlideTutor. Thirty-one (N = 31) first- to fourth-year pathology and dermatology residents were randomly assigned to one of the two scaffolding conditions. The cases used in this study were selected from the domain of Nodular and Diffuse Dermatitides. Both groups worked with a version of SlideTutor that provided immediate feedback on their actions for two hours before proceeding to solve cases in either the Considering Alternatives or Playback condition. No immediate feedback was provided on actions performed by participants in the scaffolding mode. Measurements included learning gains (pre-test and post-test), as well as metacognitive performance, including Goodman-Kruskal Gamma correlation, bias, and discrimination. Results showed that participants in both conditions improved significantly in terms of their diagnostic scores from pre-test to post-test. More importantly, participants in the Considering Alternatives condition outperformed those in the Playback condition in the accuracy of their confidence judgments and the discrimination of the correctness of their assertions while solving cases. The results suggested that presenting participants with their diagnostic decision paths and highlighting correct and incorrect paths helps them to become more metacognitively accurate in their confidence judgments.

show abstract

Section: Resultssupporting

confidence: 92%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Metacognitive scaffolds improve self-judgments of accuracy in a medical intelligent tutoring system

et al. 2013

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another research field with similar needs is the development of Intelligent Tutoring Systems (ITS) based on natural language interaction [D' Mello et al 2007]. In this area several systems have been developed to support students in their study activities; for example in reading and speaking a first or second language [Ferreira and Atkinson 2009; Amaral and Meurers 2011], in providing feedback on misconceptions regarding several topics, like physics [Litman et al 2004], and medicine [El Saadawi et al 2008]. However, in this field the research is more focused on providing appropriate feedback to students and the challenge is to provide detailed topic models [Griffiths and Steyvers 2007].…”

Section: Related Workmentioning

confidence: 99%

An easy to author dialogue management system for serious games

Mori

Berta

Gloria

et al. 2013

J. Comput. Cult. Herit.

View full text Add to dashboard Cite

This article describes an architecture for a dialogue management system to be employed in serious games for natural language interaction with nonplayer characters. The aim of this work is to improve the learning experience by enhancing the immersiveness felt by the player. The system is implemented in a Service Oriented Architecture perspective and it exposes its functionalities through Web services. It also provides an easy to use authoring tool, which allows cultural heritage experts to define the character's knowledge without the need for learning a scripting language. We tested the system by embedding it in a simple serious game, where the user could interact with the virtual representation of a XVI century Geneoese artist, Luca Cambiaso, in order to acquire knowledge about his life and artworks. These early lab test results showed a high level of appreciation for the usability of the system and for the user engagement. Tests also showed that the system is a good didactic tool, since players demonstrated a similar level of knowledge acquisition to that achieved by reading a text.

show abstract

“…The combination of these properties suggests that computers are a technology platform that will provide valuable resources for neuroanatomy instruction. Recent generations of computer systems display graphical material particularly well (LONI, 2013; Surgical Planning Laboratory, 2013), and the capabilities of computers for information management should provide good support for self-study (Saadawi et al, 2008; Koedinger & Corbett, 2006). Despite this promise, most reviews of computer-based instructional applications in the biomedical sciences are not enthusiastic about the progress that has been made (J.…”

mentioning

confidence: 99%

Learning with interactive computer graphics in the undergraduate neuroscience classroom

Pani

Chariker

Naaz

et al. 2014

Adv in Health Sci Educ

View full text Add to dashboard Cite

Instruction of neuroanatomy depends on graphical representation and extended self-study. As a consequence, computer-based learning environments that incorporate interactive graphics should facilitate instruction in this area. The present study evaluated such a system in the undergraduate neuroscience classroom. The system used the method of adaptive exploration, in which exploration in a high fidelity graphical environment is integrated with immediate testing and feedback in repeated cycles of learning. The results of this study were that students considered the graphical learning environment to be superior to typical classroom materials used for learning neuroanatomy. Students managed the frequency and duration of study, test, and feedback in an efficient and adaptive manner. For example, the number of tests taken before reaching a minimum test performance of 90% correct closely approximated the values seen in more regimented experimental studies. There was a wide range of student opinion regarding the choice between a simpler and a more graphically compelling program for learning sectional anatomy. Course outcomes were predicted by individual differences in the use of the software that reflected general work habits of the students, such as the amount of time committed to testing. The results of this introduction into the classroom are highly encouraging for development of computer-based instruction in biomedical disciplines.

show abstract

A natural language intelligent tutoring system for training pathologists: implementation and evaluation

Cited by 39 publications

References 21 publications

Metacognitive scaffolds improve self-judgments of accuracy in a medical intelligent tutoring system

Metacognitive scaffolds improve self-judgments of accuracy in a medical intelligent tutoring system

An easy to author dialogue management system for serious games

Learning with interactive computer graphics in the undergraduate neuroscience classroom

Contact Info

Product

Resources

About