Finding discriminative and interpretable patterns in sequences of surgical activities

Germain Forestier, François Petitjean, Pavel Senin, Laurent Riffaud, Pierre Louis Henaux, Pierre Jannin

Research output: Contribution to journalArticleResearchpeer-review

4 Citations (Scopus)

Abstract

Objective: Surgery is one of the riskiest and most important medical acts that is performed today. Understanding the ways in which surgeries are similar or different from each other is of major interest to understand and analyze surgical behaviors. This article addresses the issue of identifying discriminative patterns of surgical practice from recordings of surgeries. These recordings are sequences of low-level surgical activities representing the actions performed by surgeons during surgeries. Materials and method: To discover patterns that are specific to a group of surgeries, we use the vector space model (VSM) which is originally an algebraic model for representing text documents. We split long sequences of surgical activities into subsequences of consecutive activities. We then compute the relative frequencies of these subsequences using the tf*. idf framework and we use the Cosine similarity to classify the sequences. This process makes it possible to discover which patterns discriminate one set of surgeries recordings from another set. Results: Experiments were performed on 40 neurosurgeries of anterior cervical discectomy (ACD). The results demonstrate that our method accurately identifies patterns that can discriminate between (1) locations where the surgery took place, (2) levels of expertise of surgeons (i.e., expert vs. intermediate) and even (3) individual surgeons who performed the intervention. We also show how the tf*. idf weight vector can be used to both visualize the most interesting patterns and to highlight the parts of a given surgery that are the most interesting. Conclusions: Identifying patterns that discriminate groups of surgeon is a very important step in improving the understanding of surgical processes. The proposed method finds discriminative and interpretable patterns in sequences of surgical activities. Our approach provides intuitive results, as it identifies automatically the set of patterns explaining the differences between the groups.

Original languageEnglish
Pages (from-to)11-19
Number of pages9
JournalArtificial Intelligence in Medicine
Volume82
DOIs
Publication statusPublished - Oct 2017

Keywords

  • Bag of words
  • Surgery
  • Surgical process modelling
  • Surgical technical skills
  • Temporal analysis
  • Vector space model

Cite this

Forestier, Germain ; Petitjean, François ; Senin, Pavel ; Riffaud, Laurent ; Henaux, Pierre Louis ; Jannin, Pierre. / Finding discriminative and interpretable patterns in sequences of surgical activities. In: Artificial Intelligence in Medicine. 2017 ; Vol. 82. pp. 11-19.
@article{35c49634fcbf423d818780cff85a33a2,
title = "Finding discriminative and interpretable patterns in sequences of surgical activities",
abstract = "Objective: Surgery is one of the riskiest and most important medical acts that is performed today. Understanding the ways in which surgeries are similar or different from each other is of major interest to understand and analyze surgical behaviors. This article addresses the issue of identifying discriminative patterns of surgical practice from recordings of surgeries. These recordings are sequences of low-level surgical activities representing the actions performed by surgeons during surgeries. Materials and method: To discover patterns that are specific to a group of surgeries, we use the vector space model (VSM) which is originally an algebraic model for representing text documents. We split long sequences of surgical activities into subsequences of consecutive activities. We then compute the relative frequencies of these subsequences using the tf*. idf framework and we use the Cosine similarity to classify the sequences. This process makes it possible to discover which patterns discriminate one set of surgeries recordings from another set. Results: Experiments were performed on 40 neurosurgeries of anterior cervical discectomy (ACD). The results demonstrate that our method accurately identifies patterns that can discriminate between (1) locations where the surgery took place, (2) levels of expertise of surgeons (i.e., expert vs. intermediate) and even (3) individual surgeons who performed the intervention. We also show how the tf*. idf weight vector can be used to both visualize the most interesting patterns and to highlight the parts of a given surgery that are the most interesting. Conclusions: Identifying patterns that discriminate groups of surgeon is a very important step in improving the understanding of surgical processes. The proposed method finds discriminative and interpretable patterns in sequences of surgical activities. Our approach provides intuitive results, as it identifies automatically the set of patterns explaining the differences between the groups.",
keywords = "Bag of words, Surgery, Surgical process modelling, Surgical technical skills, Temporal analysis, Vector space model",
author = "Germain Forestier and Fran{\cc}ois Petitjean and Pavel Senin and Laurent Riffaud and Henaux, {Pierre Louis} and Pierre Jannin",
year = "2017",
month = "10",
doi = "10.1016/j.artmed.2017.09.002",
language = "English",
volume = "82",
pages = "11--19",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",

}

Finding discriminative and interpretable patterns in sequences of surgical activities. / Forestier, Germain; Petitjean, François; Senin, Pavel; Riffaud, Laurent; Henaux, Pierre Louis; Jannin, Pierre.

In: Artificial Intelligence in Medicine, Vol. 82, 10.2017, p. 11-19.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Finding discriminative and interpretable patterns in sequences of surgical activities

AU - Forestier, Germain

AU - Petitjean, François

AU - Senin, Pavel

AU - Riffaud, Laurent

AU - Henaux, Pierre Louis

AU - Jannin, Pierre

PY - 2017/10

Y1 - 2017/10

N2 - Objective: Surgery is one of the riskiest and most important medical acts that is performed today. Understanding the ways in which surgeries are similar or different from each other is of major interest to understand and analyze surgical behaviors. This article addresses the issue of identifying discriminative patterns of surgical practice from recordings of surgeries. These recordings are sequences of low-level surgical activities representing the actions performed by surgeons during surgeries. Materials and method: To discover patterns that are specific to a group of surgeries, we use the vector space model (VSM) which is originally an algebraic model for representing text documents. We split long sequences of surgical activities into subsequences of consecutive activities. We then compute the relative frequencies of these subsequences using the tf*. idf framework and we use the Cosine similarity to classify the sequences. This process makes it possible to discover which patterns discriminate one set of surgeries recordings from another set. Results: Experiments were performed on 40 neurosurgeries of anterior cervical discectomy (ACD). The results demonstrate that our method accurately identifies patterns that can discriminate between (1) locations where the surgery took place, (2) levels of expertise of surgeons (i.e., expert vs. intermediate) and even (3) individual surgeons who performed the intervention. We also show how the tf*. idf weight vector can be used to both visualize the most interesting patterns and to highlight the parts of a given surgery that are the most interesting. Conclusions: Identifying patterns that discriminate groups of surgeon is a very important step in improving the understanding of surgical processes. The proposed method finds discriminative and interpretable patterns in sequences of surgical activities. Our approach provides intuitive results, as it identifies automatically the set of patterns explaining the differences between the groups.

AB - Objective: Surgery is one of the riskiest and most important medical acts that is performed today. Understanding the ways in which surgeries are similar or different from each other is of major interest to understand and analyze surgical behaviors. This article addresses the issue of identifying discriminative patterns of surgical practice from recordings of surgeries. These recordings are sequences of low-level surgical activities representing the actions performed by surgeons during surgeries. Materials and method: To discover patterns that are specific to a group of surgeries, we use the vector space model (VSM) which is originally an algebraic model for representing text documents. We split long sequences of surgical activities into subsequences of consecutive activities. We then compute the relative frequencies of these subsequences using the tf*. idf framework and we use the Cosine similarity to classify the sequences. This process makes it possible to discover which patterns discriminate one set of surgeries recordings from another set. Results: Experiments were performed on 40 neurosurgeries of anterior cervical discectomy (ACD). The results demonstrate that our method accurately identifies patterns that can discriminate between (1) locations where the surgery took place, (2) levels of expertise of surgeons (i.e., expert vs. intermediate) and even (3) individual surgeons who performed the intervention. We also show how the tf*. idf weight vector can be used to both visualize the most interesting patterns and to highlight the parts of a given surgery that are the most interesting. Conclusions: Identifying patterns that discriminate groups of surgeon is a very important step in improving the understanding of surgical processes. The proposed method finds discriminative and interpretable patterns in sequences of surgical activities. Our approach provides intuitive results, as it identifies automatically the set of patterns explaining the differences between the groups.

KW - Bag of words

KW - Surgery

KW - Surgical process modelling

KW - Surgical technical skills

KW - Temporal analysis

KW - Vector space model

UR - http://www.scopus.com/inward/record.url?scp=85029649393&partnerID=8YFLogxK

U2 - 10.1016/j.artmed.2017.09.002

DO - 10.1016/j.artmed.2017.09.002

M3 - Article

AN - SCOPUS:85029649393

VL - 82

SP - 11

EP - 19

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

ER -