Visualization of Patient Behavior from Natural Language

Jonathan Siddle, Alan Lindsay, Joao Ferreira, Julie Porteous, Jonathon Read, Fred Charles, Marc Cavazza, Gersende Georg

Research output: Contribution to conferencePaper

Abstract

The visualization of procedural knowledge from textual documents using 3D animation may be a way to improve understanding. We are interested in applying this approach to documents relating to patient education for bariatric surgery: a domain with challenging textual documents describing behavior recommendations that contain few procedural steps and leave much commonsense knowledge unspecified. In this work we look at how to automatically capture knowledge from a range of differently phrased recommendations and use that with implicit knowledge about compliance and violation, such that the recommendations can be visualized using 3D animations. Our solution is an end-to-end system that automates this process via: analysis of input recommendations to uncover their conditional structure; the use of commonsense knowledge and deontic logic to generate compliance and violation rules; and mapping of this knowledge to update a default knowledge base, which is used to generate appropriate sequences of visualizations. In this paper we overview this approach and demonstrate its potential.
Original languageEnglish
Publication statusPublished - 2017
Event9th International Conference on Knowledge Capture 2017 - Austin, United States
Duration: 4 Dec 20176 Dec 2017

Conference

Conference9th International Conference on Knowledge Capture 2017
Abbreviated titleK-CAP 2017
CountryUnited States
CityAustin
Period4/12/176/12/17

Fingerprint

Animation
Visualization
Surgery
Education
Compliance

Cite this

Siddle, J., Lindsay, A., Ferreira, J., Porteous, J., Read, J., Charles, F., ... Georg, G. (2017). Visualization of Patient Behavior from Natural Language. Paper presented at 9th International Conference on Knowledge Capture 2017, Austin, United States.
Siddle, Jonathan ; Lindsay, Alan ; Ferreira, Joao ; Porteous, Julie ; Read, Jonathon ; Charles, Fred ; Cavazza, Marc ; Georg, Gersende. / Visualization of Patient Behavior from Natural Language. Paper presented at 9th International Conference on Knowledge Capture 2017, Austin, United States.
@conference{d040bd4da1d84057bed6522953bc4e94,
title = "Visualization of Patient Behavior from Natural Language",
abstract = "The visualization of procedural knowledge from textual documents using 3D animation may be a way to improve understanding. We are interested in applying this approach to documents relating to patient education for bariatric surgery: a domain with challenging textual documents describing behavior recommendations that contain few procedural steps and leave much commonsense knowledge unspecified. In this work we look at how to automatically capture knowledge from a range of differently phrased recommendations and use that with implicit knowledge about compliance and violation, such that the recommendations can be visualized using 3D animations. Our solution is an end-to-end system that automates this process via: analysis of input recommendations to uncover their conditional structure; the use of commonsense knowledge and deontic logic to generate compliance and violation rules; and mapping of this knowledge to update a default knowledge base, which is used to generate appropriate sequences of visualizations. In this paper we overview this approach and demonstrate its potential.",
author = "Jonathan Siddle and Alan Lindsay and Joao Ferreira and Julie Porteous and Jonathon Read and Fred Charles and Marc Cavazza and Gersende Georg",
year = "2017",
language = "English",
note = "9th International Conference on Knowledge Capture 2017, K-CAP 2017 ; Conference date: 04-12-2017 Through 06-12-2017",

}

Siddle, J, Lindsay, A, Ferreira, J, Porteous, J, Read, J, Charles, F, Cavazza, M & Georg, G 2017, 'Visualization of Patient Behavior from Natural Language' Paper presented at 9th International Conference on Knowledge Capture 2017, Austin, United States, 4/12/17 - 6/12/17, .

Visualization of Patient Behavior from Natural Language. / Siddle, Jonathan; Lindsay, Alan; Ferreira, Joao; Porteous, Julie; Read, Jonathon; Charles, Fred; Cavazza, Marc; Georg, Gersende.

2017. Paper presented at 9th International Conference on Knowledge Capture 2017, Austin, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Visualization of Patient Behavior from Natural Language

AU - Siddle, Jonathan

AU - Lindsay, Alan

AU - Ferreira, Joao

AU - Porteous, Julie

AU - Read, Jonathon

AU - Charles, Fred

AU - Cavazza, Marc

AU - Georg, Gersende

PY - 2017

Y1 - 2017

N2 - The visualization of procedural knowledge from textual documents using 3D animation may be a way to improve understanding. We are interested in applying this approach to documents relating to patient education for bariatric surgery: a domain with challenging textual documents describing behavior recommendations that contain few procedural steps and leave much commonsense knowledge unspecified. In this work we look at how to automatically capture knowledge from a range of differently phrased recommendations and use that with implicit knowledge about compliance and violation, such that the recommendations can be visualized using 3D animations. Our solution is an end-to-end system that automates this process via: analysis of input recommendations to uncover their conditional structure; the use of commonsense knowledge and deontic logic to generate compliance and violation rules; and mapping of this knowledge to update a default knowledge base, which is used to generate appropriate sequences of visualizations. In this paper we overview this approach and demonstrate its potential.

AB - The visualization of procedural knowledge from textual documents using 3D animation may be a way to improve understanding. We are interested in applying this approach to documents relating to patient education for bariatric surgery: a domain with challenging textual documents describing behavior recommendations that contain few procedural steps and leave much commonsense knowledge unspecified. In this work we look at how to automatically capture knowledge from a range of differently phrased recommendations and use that with implicit knowledge about compliance and violation, such that the recommendations can be visualized using 3D animations. Our solution is an end-to-end system that automates this process via: analysis of input recommendations to uncover their conditional structure; the use of commonsense knowledge and deontic logic to generate compliance and violation rules; and mapping of this knowledge to update a default knowledge base, which is used to generate appropriate sequences of visualizations. In this paper we overview this approach and demonstrate its potential.

M3 - Paper

ER -

Siddle J, Lindsay A, Ferreira J, Porteous J, Read J, Charles F et al. Visualization of Patient Behavior from Natural Language. 2017. Paper presented at 9th International Conference on Knowledge Capture 2017, Austin, United States.