{"id":{"repo_id":"mcmaster","oai_identifier":"oai:macsphere.mcmaster.ca:11375/13353"},"canonical_url":"https://search.ndltd.org/etd/mcmaster/oai:macsphere.mcmaster.ca:11375/13353","repository":{"repo_id":"mcmaster","name":"McMaster University","base_url":"https://macsphere.mcmaster.ca/server/oai/request"},"display":{"title":"Surgical Skills and Ergonomics Evaluation for Laparoscopic Surgery Training","abstract":"<p>Training and ergonomics evaluation for laparoscopic surgery is an important tool for the assessment of trainees. Timely and objective assessment helps surgeons improve hand dexterity and movement precision, and perform surgery in an ergonomic manner. Traditionally, skill is evaluated by expert surgeons observing trainees, but this approach is both expensive and subjective. The approach proposed by this research employs an Ascension 3DGuidance trakSTAR system that captures the positions and orientations of hand and laparoscopic tool trajectories. Recorded trajectories are automatically analysed to extract meaningful feedback for training evaluation using statistical and machine learning methods.</p> <p>The data are acquired while a subject performs a standardized task such as peg transfer or suturing. The system records laproscopic instrument positions, hand, forearms, elbows trajectories, as well as wrist angles. We propose several metrics that attempt to objectively quantify the skill level or ergonomics of the procedure. The metrics for surgical skills are based on surgical instrument tip trajectories, whereas the ergonomics metric uses wrist angles. These metrics have been developed using statistical and machine learning methods.</p> <p>The metrics have been experimentally evaluated by using a population of seven first year postgraduate urology residents, one general surgery resident, and eight fourth year postgraduate urology residents and fellows. The machine learning approach discriminated correctly in 73% of cases between experts and novices. The machine learning approach applied to ergonomics data correctly discriminates between experts and novices in 88% of the cases for the peg transfer task and 75% for the suturing task. We also propose a method to derive a competency-based score using either statistical or machine learning derived metrics.</p> <p>Initial experimental data show that the proposed methods discriminate between the skills and ergonomics of expert and novice surgeons. The proposed system can be a valuable tool for research and training evaluation in laparoscopic surgery.</p>","abstract_html":"&lt;p&gt;Training and ergonomics evaluation for laparoscopic surgery is an important tool for the assessment of trainees. Timely and objective assessment helps surgeons improve hand dexterity and movement precision, and perform surgery in an ergonomic manner. Traditionally, skill is evaluated by expert surgeons observing trainees, but this approach is both expensive and subjective. The approach proposed by this research employs an Ascension 3DGuidance trakSTAR system that captures the positions and orientations of hand and laparoscopic tool trajectories. Recorded trajectories are automatically analysed to extract meaningful feedback for training evaluation using statistical and machine learning methods.&lt;/p&gt; &lt;p&gt;The data are acquired while a subject performs a standardized task such as peg transfer or suturing. The system records laproscopic instrument positions, hand, forearms, elbows trajectories, as well as wrist angles. We propose several metrics that attempt to objectively quantify the skill level or ergonomics of the procedure. The metrics for surgical skills are based on surgical instrument tip trajectories, whereas the ergonomics metric uses wrist angles. These metrics have been developed using statistical and machine learning methods.&lt;/p&gt; &lt;p&gt;The metrics have been experimentally evaluated by using a population of seven first year postgraduate urology residents, one general surgery resident, and eight fourth year postgraduate urology residents and fellows. The machine learning approach discriminated correctly in 73% of cases between experts and novices. The machine learning approach applied to ergonomics data correctly discriminates between experts and novices in 88% of the cases for the peg transfer task and 75% for the suturing task. We also propose a method to derive a competency-based score using either statistical or machine learning derived metrics.&lt;/p&gt; &lt;p&gt;Initial experimental data show that the proposed methods discriminate between the skills and ergonomics of expert and novice surgeons. The proposed system can be a valuable tool for research and training evaluation in laparoscopic surgery.&lt;/p&gt;","abstract_has_math":false,"creators":["Kyaw, Thu Zar"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Electrical and Computer Engineering","school":null,"contributors":[],"advisors":["Reilly, Jim","Patriciu, Alexandru","I. Bruce and A. Jeremic"],"committee_chairs":[],"committee_members":[],"year":2013,"date_issued":"2013-10","date_published":"2013-10","updated_at":"2026-11-18T19:37:54Z","subjects":["Surgical Skills Evaluation","Surgical Ergonomics Evaluation","Machine Learning","ANOVA1","Laparoscopic Surgery","Statistical Analysis","Biomedical Engineering and Bioengineering","Computer Engineering","Electrical and Computer Engineering","Medicine and Health Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.71548/19589"],"render_values":[{"text":"https://doi.org/10.71548/19589","href":"https://doi.org/10.71548/19589","code":true}]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["opendissertations/8174","9305","4600871"],"render_values":[{"text":"opendissertations/8174","href":null,"code":true},{"text":"9305","href":null,"code":true},{"text":"4600871","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11375/13353","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"http://hdl.handle.net/11375/13353","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://macsphere.mcmaster.ca/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Amacsphere.mcmaster.ca%3A11375%2F13353","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Reilly, Jim","Patriciu, Alexandru","I. Bruce and A. Jeremic"]},{"key":"dc:contributor.department","label":"Department","values":["Electrical and Computer Engineering"]},{"key":"dc:creator","label":"Author","values":["Kyaw, Thu Zar"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2014-06-18T17:03:42Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2014-06-18T17:03:42Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2013-09-19"]},{"key":"dc:date.issued","label":"Date","values":["2013-10"]},{"key":"dc:type","label":"Dc Type","values":["thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Surgical Skills Evaluation","Surgical Ergonomics Evaluation","Machine Learning","ANOVA1","Laparoscopic Surgery","Statistical Analysis","Biomedical Engineering and Bioengineering","Computer Engineering","Electrical and Computer Engineering","Medicine and Health Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["opendissertations/8174","9305","4600871"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/11375/13353","https://doi.org/10.71548/19589"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["<p>Training and ergonomics evaluation for laparoscopic surgery is an important tool for the assessment of trainees. Timely and objective assessment helps surgeons improve hand dexterity and movement precision, and perform surgery in an ergonomic manner. Traditionally, skill is evaluated by expert surgeons observing trainees, but this approach is both expensive and subjective. The approach proposed by this research employs an Ascension 3DGuidance trakSTAR system that captures the positions and orientations of hand and laparoscopic tool trajectories. Recorded trajectories are automatically analysed to extract meaningful feedback for training evaluation using statistical and machine learning methods.</p> <p>The data are acquired while a subject performs a standardized task such as peg transfer or suturing. The system records laproscopic instrument positions, hand, forearms, elbows trajectories, as well as wrist angles. We propose several metrics that attempt to objectively quantify the skill level or ergonomics of the procedure. The metrics for surgical skills are based on surgical instrument tip trajectories, whereas the ergonomics metric uses wrist angles. These metrics have been developed using statistical and machine learning methods.</p> <p>The metrics have been experimentally evaluated by using a population of seven first year postgraduate urology residents, one general surgery resident, and eight fourth year postgraduate urology residents and fellows. The machine learning approach discriminated correctly in 73% of cases between experts and novices. The machine learning approach applied to ergonomics data correctly discriminates between experts and novices in 88% of the cases for the peg transfer task and 75% for the suturing task. We also propose a method to derive a competency-based score using either statistical or machine learning derived metrics.</p> <p>Initial experimental data show that the proposed methods discriminate between the skills and ergonomics of expert and novice surgeons. The proposed system can be a valuable tool for research and training evaluation in laparoscopic surgery.</p>"]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Applied Science (MASc)"]},{"key":"dc:title","label":"Title","values":["Surgical Skills and Ergonomics Evaluation for Laparoscopic Surgery Training"]},{"key":"others:access_status","label":"Others Access Status","values":["open.access"]}]}],"canonical_facts":{"dc:contributor.advisor":["Reilly, Jim","Patriciu, Alexandru","I. Bruce and A. Jeremic"],"dc:contributor.department":["Electrical and Computer Engineering"],"dc:creator":["Kyaw, Thu Zar"],"dc:date.accessioned":["2014-06-18T17:03:42Z"],"dc:date.available":["2014-06-18T17:03:42Z"],"dc:date.created":["2013-09-19"],"dc:date.issued":["2013-10"],"dc:description.abstract":["<p>Training and ergonomics evaluation for laparoscopic surgery is an important tool for the assessment of trainees. Timely and objective assessment helps surgeons improve hand dexterity and movement precision, and perform surgery in an ergonomic manner. Traditionally, skill is evaluated by expert surgeons observing trainees, but this approach is both expensive and subjective. The approach proposed by this research employs an Ascension 3DGuidance trakSTAR system that captures the positions and orientations of hand and laparoscopic tool trajectories. Recorded trajectories are automatically analysed to extract meaningful feedback for training evaluation using statistical and machine learning methods.</p> <p>The data are acquired while a subject performs a standardized task such as peg transfer or suturing. The system records laproscopic instrument positions, hand, forearms, elbows trajectories, as well as wrist angles. We propose several metrics that attempt to objectively quantify the skill level or ergonomics of the procedure. The metrics for surgical skills are based on surgical instrument tip trajectories, whereas the ergonomics metric uses wrist angles. These metrics have been developed using statistical and machine learning methods.</p> <p>The metrics have been experimentally evaluated by using a population of seven first year postgraduate urology residents, one general surgery resident, and eight fourth year postgraduate urology residents and fellows. The machine learning approach discriminated correctly in 73% of cases between experts and novices. The machine learning approach applied to ergonomics data correctly discriminates between experts and novices in 88% of the cases for the peg transfer task and 75% for the suturing task. We also propose a method to derive a competency-based score using either statistical or machine learning derived metrics.</p> <p>Initial experimental data show that the proposed methods discriminate between the skills and ergonomics of expert and novice surgeons. The proposed system can be a valuable tool for research and training evaluation in laparoscopic surgery.</p>"],"dc:description.degree":["Master of Applied Science (MASc)"],"dc:identifier.other":["opendissertations/8174","9305","4600871"],"dc:identifier.uri":["http://hdl.handle.net/11375/13353","https://doi.org/10.71548/19589"],"dc:subject":["Surgical Skills Evaluation","Surgical Ergonomics Evaluation","Machine Learning","ANOVA1","Laparoscopic Surgery","Statistical Analysis","Biomedical Engineering and Bioengineering","Computer Engineering","Electrical and Computer Engineering","Medicine and Health Sciences"],"dc:title":["Surgical Skills and Ergonomics Evaluation for Laparoscopic Surgery Training"],"dc:type":["thesis"],"others:access_status":["open.access"]},"updated_at":"2026-11-18T19:37:54Z"}