Jennifer M. Siu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jennifer M. Siu has a total of 82 co-authors. Here are the top co-authors by number of shared publications:
Evan J. Propst
Department of Otolaryngology—Head & Neck Surgery The Hospital for Sick Children Toronto Ontario Canada
14 shared publications- Nikolaus Ernst Wolter
Department of Otolaryngology – Head & Neck Surgery, Hospital for Sick Children University of Toronto Toronto Ontario Canada
11 shared publications Nikolaus E. Wolter
Department of Otolaryngology—Head & Neck Surgery The Hospital for Sick Children Toronto Ontario Canada
5 shared publications- Evan Jon Propst
Department of Otolaryngology – Head & Neck Surgery, Hospital for Sick Children University of Toronto Toronto Ontario Canada
2 shared publications Jackie Chiang
Division of Respiratory Medicine, Department of Paediatrics, The Hospital for Sick Children, University of Toronto, Toronto, ON, Canada
2 shared publications- Jenny B. Xiao
Faculty of Medicine University of British Columbia Vancouver British Columbia Canada
2 shared publications
Latest Publications
- Open Access
- 19 June 2026
- Published by Wiley in Pediatric Anesthesia
- Vol. 36 (9) , 1159-1161
Respiratory Events and Procedure Interruptions During Pediatric Bronchoscopy and Suspension Laryngoscopy: A Secondary Analysis Comparing Dexmedetomidine and Remifentanil‐Based Anesthesia
- 19 June 2026
- Published by Wiley in Pediatric Anesthesia
- Vol. 36 (9) , 1159-1161
Open AccessRespiratory Events and Procedure Interruptions During Pediatric Bronchoscopy and Suspension Laryngoscopy: A Secondary Analysis Comparing Dexmedetomidine and Remifentanil‐Based Anesthesia
- 16 February 2026
- Published by Wiley in The Laryngoscope
- Vol. 136 (7) , 3229-3236
Computer Vision Model to Detect and Classify Laryngomalacia From Pediatric Video Nasolaryngoscopy
Objective: Laryngomalacia diagnosis and subtype classification is typically based on flexible nasolaryngoscopy, but this can be challenging, particularly for clinicians who see it infrequently. Infant movement may also prolong the procedure. Automated computer vision (CV) assessment of video nasolaryngoscopy may improve diagnostic accuracy, shorten procedure time, and reduce infant discomfort. The aim was to develop a CV model to segment laryngeal anatomy, differentiate between normal and laryngomalacia cases, and classify laryngomalacia type (1, 2, or 3). Methods: A total of 241 pediatric nasolaryngoscopy videos were obtained from The Hospital for Sick Children between August 2023 and March 2025 from participants < 1 year old. Videos were annotated and randomly assigned to a training set [192 (80%)] and testing set [49 (20%)]. Three binary classification models (fine‐tuned for feature extraction) were developed to predict laryngomalacia and classify its type. CV predictions were compared with diagnoses made by three staff otolaryngologists. Results: The CV model's Dice similarity coefficient for laryngeal anatomy segmentation was 0.86 (95% CI: 0.85–0.88). The model differentiated normal from laryngomalacia cases with an accuracy of 0.90 and predicted type 1 and type 2 laryngomalacia with accuracies of 0.86 and 0.90, respectively. A type 3 model was not developed due to insufficient cases. Conclusion: The CV model successfully segmented laryngeal anatomy, differentiated normal from laryngomalacia cases, and classified type 1 and 2 laryngomalacia from pediatric video nasolaryngoscopy. With dataset expansion, further algorithm refinement, and external validation, this model may serve as a clinical decision support tool in the future. Level of Evidence: 3.
- 16 February 2026
- Published by Wiley in The Laryngoscope
- Vol. 136 (7) , 3229-3236
Computer Vision Model to Detect and Classify Laryngomalacia From Pediatric Video Nasolaryngoscopy
Objective: Laryngomalacia diagnosis and subtype classification is typically based on flexible nasolaryngoscopy, but this can be challenging, particularly for clinicians who see it infrequently. Infant movement may also prolong the procedure. Automated computer vision (CV) assessment of video nasolaryngoscopy may improve diagnostic accuracy, shorten procedure time, and reduce infant discomfort. The aim was to develop a CV model to segment laryngeal anatomy, differentiate between normal and laryngomalacia cases, and classify laryngomalacia type (1, 2, or 3). Methods: A total of 241 pediatric nasolaryngoscopy videos were obtained from The Hospital for Sick Children between August 2023 and March 2025 from participants < 1 year old. Videos were annotated and randomly assigned to a training set [192 (80%)] and testing set [49 (20%)]. Three binary classification models (fine‐tuned for feature extraction) were developed to predict laryngomalacia and classify its type. CV predictions were compared with diagnoses made by three staff otolaryngologists. Results: The CV model's Dice similarity coefficient for laryngeal anatomy segmentation was 0.86 (95% CI: 0.85–0.88). The model differentiated normal from laryngomalacia cases with an accuracy of 0.90 and predicted type 1 and type 2 laryngomalacia with accuracies of 0.86 and 0.90, respectively. A type 3 model was not developed due to insufficient cases. Conclusion: The CV model successfully segmented laryngeal anatomy, differentiated normal from laryngomalacia cases, and classified type 1 and 2 laryngomalacia from pediatric video nasolaryngoscopy. With dataset expansion, further algorithm refinement, and external validation, this model may serve as a clinical decision support tool in the future. Level of Evidence: 3.
- 27 January 2026
- Published by Wiley in Journal of Paediatrics and Child Health
- Vol. 62 (4) , 551-563
Foreign Concepts in Paediatric Oesophageal Foreign Bodies: A Health Knowledge Study
Aim: Non‐food object ingestion and resulting oesophageal foreign body (EFB) impactions are a common problem in children, with potentially severe consequences requiring urgent management. This study aimed to assess public knowledge of paediatric EFBs, including prevention, risks and management to inform future primary prevention efforts: Methods: Members of the public were surveyed between January and May 2024. The pretested, electronic survey was distributed via social media and printed notices. Collected data included demographics, preventative household safety measures, recognition, perceptions of object danger and knowledge of EFB management. Responses were analysed using descriptive statistics. Results: Overall, 516 respondents completed the survey, including 444 (86%) with children in their home or workplace. Rated on a Likert‐type scale from 1 (not dangerous) to 10 (most dangerous), button batteries were perceived as most dangerous EFBs (mean ± standard deviation [SD]: 8.7 ± 2.1), followed by high‐powered magnets (8.3 ± 2.4). However, only 33% of participants with children at home reported storing dangerous objects away, most commonly sharp objects (94%), small toys (72%) and coins (69%). Despite being perceived as most dangerous, only 59% of participants stored button batteries and 34% stored high‐powered magnets away from children. Upon survey completion, 84% of respondents indicated they would like to learn more about EFBs in children. Conclusions: Paediatric EFBs represent a significant public health concern, and this study highlights substantial gaps in public knowledge regarding safety and preventative measures. By focusing public health initiatives on addressing these knowledge gaps, there is potential to significantly reduce the prevalence and impact of ingestion incidents in children.
- 27 January 2026
- Published by Wiley in Journal of Paediatrics and Child Health
- Vol. 62 (4) , 551-563
Foreign Concepts in Paediatric Oesophageal Foreign Bodies: A Health Knowledge Study
Aim: Non‐food object ingestion and resulting oesophageal foreign body (EFB) impactions are a common problem in children, with potentially severe consequences requiring urgent management. This study aimed to assess public knowledge of paediatric EFBs, including prevention, risks and management to inform future primary prevention efforts: Methods: Members of the public were surveyed between January and May 2024. The pretested, electronic survey was distributed via social media and printed notices. Collected data included demographics, preventative household safety measures, recognition, perceptions of object danger and knowledge of EFB management. Responses were analysed using descriptive statistics. Results: Overall, 516 respondents completed the survey, including 444 (86%) with children in their home or workplace. Rated on a Likert‐type scale from 1 (not dangerous) to 10 (most dangerous), button batteries were perceived as most dangerous EFBs (mean ± standard deviation [SD]: 8.7 ± 2.1), followed by high‐powered magnets (8.3 ± 2.4). However, only 33% of participants with children at home reported storing dangerous objects away, most commonly sharp objects (94%), small toys (72%) and coins (69%). Despite being perceived as most dangerous, only 59% of participants stored button batteries and 34% stored high‐powered magnets away from children. Upon survey completion, 84% of respondents indicated they would like to learn more about EFBs in children. Conclusions: Paediatric EFBs represent a significant public health concern, and this study highlights substantial gaps in public knowledge regarding safety and preventative measures. By focusing public health initiatives on addressing these knowledge gaps, there is potential to significantly reduce the prevalence and impact of ingestion incidents in children.
- Open Access
- 12 December 2025
- Published by SAGE Publications in Journal of Otolaryngology - Head & Neck Surgery
- Vol. 54
Risk Factors for Postoperative Respiratory Events After Pediatric Microlaryngoscopy and Bronchoscopy
Importance: Preoperative risk factors can guide appropriate postoperative disposition location to a ward bed, intermediate care, or intensive care unit after pediatric microlaryngoscopy and bronchoscopy (MLB), resulting in optimization of resource use and costs. Objective: Identify risk factors associated with postoperative respiratory events requiring escalation of care after MLB to identify a subpopulation of high-risk patients. Design: Retrospective cohort study. Setting: Tertiary pediatric center. Participants: Patients undergoing MLB alone or with intervention from 2017 to 2023. Intervention: MLB alone or with intervention. Main Outcome Measures: Primary outcome was postoperative respiratory events requiring escalation of nursing care: escalation of oxygen supplementation for >2 hours, laryngospasm, bronchospasm, unplanned escalation of care to ICU, O 2 desaturation 5. Multivariate logistic regression was performed to identify risk factors for postoperative respiratory events. Results: 420 patients were included. The mean age was 39.4 months and 41% were female. Overall, 229 patients (54.5%) had events that required escalation of care. Five patients (1.2%) had laryngospasm, 5 (1.2%) desaturated below 80%, and 15 (3.6%) required an unplanned escalation of care to the ICU. 157 (37.4%) required escalation of care based on a PEW score >5, and 148 (35.2%) required supplemental O2 for >2 hours. Multivariate analysis identified independent risk factors for postoperative respiratory events including age 1 to 2 years (OR 2.47, P = .037), cardiovascular disease (OR 2.96, P = .0066), GERD (OR 1.89, P = .042), ASA IV (OR 5.76, P = .0032), MLB with supraglottoplasty (OR 4.34, P = .0081), inpatient surgery (OR 4.68, P < .0001), and operative time ≥180 minutes (OR 2.16, P = .05). Conclusion: Risk factors for postoperative respiratory events after MLB include age 1 to 2 years, CVD, GERD, ASA 4, MLB with supraglottoplasty, inpatient emergency, OR time >180 minutes. Tailoring postoperative disposition based on these preoperative risk factors may result in a reduction in ICU utilization while ensuring patients are safely monitored in an appropriate setting. Level of Evidence: Level 3
- 12 December 2025
- Published by SAGE Publications in Journal of Otolaryngology - Head & Neck Surgery
- Vol. 54
Open AccessRisk Factors for Postoperative Respiratory Events After Pediatric Microlaryngoscopy and Bronchoscopy
Importance: Preoperative risk factors can guide appropriate postoperative disposition location to a ward bed, intermediate care, or intensive care unit after pediatric microlaryngoscopy and bronchoscopy (MLB), resulting in optimization of resource use and costs. Objective: Identify risk factors associated with postoperative respiratory events requiring escalation of care after MLB to identify a subpopulation of high-risk patients. Design: Retrospective cohort study. Setting: Tertiary pediatric center. Participants: Patients undergoing MLB alone or with intervention from 2017 to 2023. Intervention: MLB alone or with intervention. Main Outcome Measures: Primary outcome was postoperative respiratory events requiring escalation of nursing care: escalation of oxygen supplementation for >2 hours, laryngospasm, bronchospasm, unplanned escalation of care to ICU, O 2 desaturation 5. Multivariate logistic regression was performed to identify risk factors for postoperative respiratory events. Results: 420 patients were included. The mean age was 39.4 months and 41% were female. Overall, 229 patients (54.5%) had events that required escalation of care. Five patients (1.2%) had laryngospasm, 5 (1.2%) desaturated below 80%, and 15 (3.6%) required an unplanned escalation of care to the ICU. 157 (37.4%) required escalation of care based on a PEW score >5, and 148 (35.2%) required supplemental O2 for >2 hours. Multivariate analysis identified independent risk factors for postoperative respiratory events including age 1 to 2 years (OR 2.47, P = .037), cardiovascular disease (OR 2.96, P = .0066), GERD (OR 1.89, P = .042), ASA IV (OR 5.76, P = .0032), MLB with supraglottoplasty (OR 4.34, P = .0081), inpatient surgery (OR 4.68, P < .0001), and operative time ≥180 minutes (OR 2.16, P = .05). Conclusion: Risk factors for postoperative respiratory events after MLB include age 1 to 2 years, CVD, GERD, ASA 4, MLB with supraglottoplasty, inpatient emergency, OR time >180 minutes. Tailoring postoperative disposition based on these preoperative risk factors may result in a reduction in ICU utilization while ensuring patients are safely monitored in an appropriate setting. Level of Evidence: Level 3
- Open Access
- 30 October 2025
- Published by SAGE Publications in Journal of Otolaryngology - Head & Neck Surgery
- Vol. 54
COVID Croup: Pediatric Croup Due to Severe Acute Respiratory Syndrome Coronavirus 2 Infection (SARS-CoV-2; Covid-19)
Importance: During the COVID-19 [severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)] pandemic, reports emerged of croup secondary to SARS-CoV-2 in the pediatric population. Children with croup and concurrent SARS-CoV-2 infection seemed to require a greater number of doses of dexamethasone and nebulized epinephrine and were more likely to need hospitalization and intensive care unit (ICU) admission compared to pre-SARS-CoV-2 croup. Objective: This study aimed to compare the outcomes of children presenting with SARS-CoV-2-associated croup and those with conventional croup. Design: Observational, retrospective review. Setting: Tertiary care pediatric hospital. Participants: Children (age P < .001) patients, and were more often admitted (30%) to hospital than SARS-CoV-2-negative (3.4%) patients (OR: 12; 95% CI 4.4-37.7, P < .001). ICU admission was required for 3 SARS-CoV-2-negative patients, but none of the SARS-CoV-2-positive patients. Length of stay was similar across groups. Conclusion: Patients with croup and SARS-CoV-2 infection were found to have an increased need for nebulized epinephrine and an increased frequency of admission to the hospital. However, there was no increased need for ICU admission or longer length of stay in the hospital. Level of Evidence: III.
- 30 October 2025
- Published by SAGE Publications in Journal of Otolaryngology - Head & Neck Surgery
- Vol. 54
Open AccessCOVID Croup: Pediatric Croup Due to Severe Acute Respiratory Syndrome Coronavirus 2 Infection (SARS-CoV-2; Covid-19)
Importance: During the COVID-19 [severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)] pandemic, reports emerged of croup secondary to SARS-CoV-2 in the pediatric population. Children with croup and concurrent SARS-CoV-2 infection seemed to require a greater number of doses of dexamethasone and nebulized epinephrine and were more likely to need hospitalization and intensive care unit (ICU) admission compared to pre-SARS-CoV-2 croup. Objective: This study aimed to compare the outcomes of children presenting with SARS-CoV-2-associated croup and those with conventional croup. Design: Observational, retrospective review. Setting: Tertiary care pediatric hospital. Participants: Children (age P < .001) patients, and were more often admitted (30%) to hospital than SARS-CoV-2-negative (3.4%) patients (OR: 12; 95% CI 4.4-37.7, P < .001). ICU admission was required for 3 SARS-CoV-2-negative patients, but none of the SARS-CoV-2-positive patients. Length of stay was similar across groups. Conclusion: Patients with croup and SARS-CoV-2 infection were found to have an increased need for nebulized epinephrine and an increased frequency of admission to the hospital. However, there was no increased need for ICU admission or longer length of stay in the hospital. Level of Evidence: III.
- Open Access
- 3 October 2025
- Published by Wiley in The Laryngoscope
- Vol. 136 (2) , 528-530
Roadmap for Representative Artificial Intelligence Models for Thyroid Cancer
Artificial intelligence (AI) models in thyroid cancer are often not generalizable due to biased or non-representative training and validation datasets. We propose a four-stage roadmap emphasizing representative data collection, inclusion of contextual variables, robust training/validation design, and post-deployment monitoring to improve fairness and clinical utility.
- 3 October 2025
- Published by Wiley in The Laryngoscope
- Vol. 136 (2) , 528-530
Open AccessRoadmap for Representative Artificial Intelligence Models for Thyroid Cancer
Artificial intelligence (AI) models in thyroid cancer are often not generalizable due to biased or non-representative training and validation datasets. We propose a four-stage roadmap emphasizing representative data collection, inclusion of contextual variables, robust training/validation design, and post-deployment monitoring to improve fairness and clinical utility.
- Open Access
- 8 August 2025
- Published by SAGE Publications in Journal of Otolaryngology - Head & Neck Surgery
- Vol. 54
Outcomes After Tonsillectomy in Children With Angelman Syndrome
Importance: Angelman syndrome is a rare genetic disorder characterized by developmental delay, sleep disturbances, and a happy demeanor. Tonsillectomies are common procedures for individuals with Angelman syndrome, and their postoperative recovery may be complicated by challenging pain assessments, respiratory complications, or feeding difficulties. Inappropriate laughing may mask perioperative pain and anxiety. Objective: The objective of this study is to review postoperative outcomes and complications of children with Angelman syndrome undergoing tonsillectomy. Methods (Design, Setting, Participants, Intervention, Measures): We conducted a retrospective review of patients with Angelman syndrome undergoing tonsillectomies from 2000 to 2024 in a quaternary pediatric hospital. Demographic, clinical, and surgical outcome variables were collected. Results: Twelve children with Angelman syndrome underwent tonsillectomy: 7 for sleep-disordered breathing, 4 for sialorrhea, and 1 for recurrent tonsillitis. Median (IQR) duration of stay was 4.0 (3.0-5.3) days. The most common reason for prolonged hospital stay was inadequate oral intake. Nine (75.0%) children experienced postoperative complications, most frequently pooling of secretions and oxygen desaturations. Three children (25.0%) experienced severe postoperative complications, including 1 opioid overdose, 1 respiratory distress, and 1 aspiration pneumonia. Two patients were readmitted to the hospital: 1 for irregular breathing and poor pain control, and 1 for epistaxis. Conclusion: The postoperative course following tonsillectomy in children with Angelman syndrome can be complicated by a prolonged recovery, inadequate pain control, opioid toxicity, respiratory complications, and poor oral intake. Caregiver input on pain behavior is critical to develop an effective postoperative management strategy. Relevance: Based on our results and a literature review, we have created recommendations for post-tonsillectomy care in children with Angelman syndrome.
- 8 August 2025
- Published by SAGE Publications in Journal of Otolaryngology - Head & Neck Surgery
- Vol. 54
Open AccessOutcomes After Tonsillectomy in Children With Angelman Syndrome
Importance: Angelman syndrome is a rare genetic disorder characterized by developmental delay, sleep disturbances, and a happy demeanor. Tonsillectomies are common procedures for individuals with Angelman syndrome, and their postoperative recovery may be complicated by challenging pain assessments, respiratory complications, or feeding difficulties. Inappropriate laughing may mask perioperative pain and anxiety. Objective: The objective of this study is to review postoperative outcomes and complications of children with Angelman syndrome undergoing tonsillectomy. Methods (Design, Setting, Participants, Intervention, Measures): We conducted a retrospective review of patients with Angelman syndrome undergoing tonsillectomies from 2000 to 2024 in a quaternary pediatric hospital. Demographic, clinical, and surgical outcome variables were collected. Results: Twelve children with Angelman syndrome underwent tonsillectomy: 7 for sleep-disordered breathing, 4 for sialorrhea, and 1 for recurrent tonsillitis. Median (IQR) duration of stay was 4.0 (3.0-5.3) days. The most common reason for prolonged hospital stay was inadequate oral intake. Nine (75.0%) children experienced postoperative complications, most frequently pooling of secretions and oxygen desaturations. Three children (25.0%) experienced severe postoperative complications, including 1 opioid overdose, 1 respiratory distress, and 1 aspiration pneumonia. Two patients were readmitted to the hospital: 1 for irregular breathing and poor pain control, and 1 for epistaxis. Conclusion: The postoperative course following tonsillectomy in children with Angelman syndrome can be complicated by a prolonged recovery, inadequate pain control, opioid toxicity, respiratory complications, and poor oral intake. Caregiver input on pain behavior is critical to develop an effective postoperative management strategy. Relevance: Based on our results and a literature review, we have created recommendations for post-tonsillectomy care in children with Angelman syndrome.
- 5 July 2025
- Published by Elsevier in International Journal of Pediatric Otorhinolaryngology
- Vol. 196, 112455
Developing age-specific protocols for pediatric voice databases in artificial intelligence research
- 5 July 2025
- Published by Elsevier in International Journal of Pediatric Otorhinolaryngology
- Vol. 196, 112455
Developing age-specific protocols for pediatric voice databases in artificial intelligence research
- 15 May 2025
- Published by Wiley in The Laryngoscope
- Vol. 135 (10) , 3520-3534
Artificial Intelligence in Surgical Training and Applications to Otolaryngology: A Scoping Review
Objective: Traditional evaluations of surgical skills in otolaryngology rely heavily on subjective assessments, which are prone to variability and bias. This study aims to examine advancements in artificial intelligence (AI) applications for surgical skills evaluation with a focus on their potential to enhance otolaryngology education.Data Sources: A systematic search of MEDLINE, Embase, Cochrane Database of Systematic Reviews, and Google Scholar was conducted using search terms related to AI and surgical skills evaluation.Review Methods: A structured review of the literature up to November 2024 was performed. Two independent reviewers identified and analyzed relevant studies. Reference lists of selected articles were also screened to ensure comprehensiveness.Results: A total of 34 studies met inclusion criteria. Of these, 56% (19/34) evaluated basic surgical tasks, such as hand‐tying, open suturing, and robotic or laparoscopic procedures using bench‐top simulators, while 44% (15/34) focused on specific surgical procedures across specialties, including otolaryngology (mastoidectomy, septoplasty, endoscopic sinus surgery, endoscopic carotid injury management), neurosurgery, urology, and general surgery. AI methods applied included deep learning, machine learning, and computer vision techniques. Classification accuracy ranged from 66% to 100% for kinematic, motion, and force data, and from 60% to 96% for video‐based analyses of surgical skills.Conclusion: AI‐driven assessment tools hold significant promise for otolaryngology surgical education. Automated feedback mechanisms can provide trainees with objective, data‐driven insights into their performance, enabling enhanced benchmarking and accelerating learning curves. By adopting AI, otolaryngology has the potential to advance its training methodologies and improve outcomes for both trainees and patients.Level of Evidence: N/A.
- 15 May 2025
- Published by Wiley in The Laryngoscope
- Vol. 135 (10) , 3520-3534
Artificial Intelligence in Surgical Training and Applications to Otolaryngology: A Scoping Review
Objective: Traditional evaluations of surgical skills in otolaryngology rely heavily on subjective assessments, which are prone to variability and bias. This study aims to examine advancements in artificial intelligence (AI) applications for surgical skills evaluation with a focus on their potential to enhance otolaryngology education.Data Sources: A systematic search of MEDLINE, Embase, Cochrane Database of Systematic Reviews, and Google Scholar was conducted using search terms related to AI and surgical skills evaluation.Review Methods: A structured review of the literature up to November 2024 was performed. Two independent reviewers identified and analyzed relevant studies. Reference lists of selected articles were also screened to ensure comprehensiveness.Results: A total of 34 studies met inclusion criteria. Of these, 56% (19/34) evaluated basic surgical tasks, such as hand‐tying, open suturing, and robotic or laparoscopic procedures using bench‐top simulators, while 44% (15/34) focused on specific surgical procedures across specialties, including otolaryngology (mastoidectomy, septoplasty, endoscopic sinus surgery, endoscopic carotid injury management), neurosurgery, urology, and general surgery. AI methods applied included deep learning, machine learning, and computer vision techniques. Classification accuracy ranged from 66% to 100% for kinematic, motion, and force data, and from 60% to 96% for video‐based analyses of surgical skills.Conclusion: AI‐driven assessment tools hold significant promise for otolaryngology surgical education. Automated feedback mechanisms can provide trainees with objective, data‐driven insights into their performance, enabling enhanced benchmarking and accelerating learning curves. By adopting AI, otolaryngology has the potential to advance its training methodologies and improve outcomes for both trainees and patients.Level of Evidence: N/A.
- Open Access
- 14 April 2025
- Published by Wiley in The Laryngoscope
- Vol. 135 (10) , 3570-3578
Generative AI in Otolaryngology Residency Personal Statement Writing: A Mixed‐Methods Analysis
Objective: Generative Artificial Intelligence (GAI) interfaces have rapidly integrated into various societal domains. Widespread accessibility of GAI for drafting personal statements poses challenges for evaluators to gauge writing ability and personal insight. This study aims to compare the quality of GAI‐generated personal statements to those written by successful applicants in OHNS residency programs, via integration of statistical and qualitative thematic analyses.Methods: Personal statements were collected from successful OHNS residency applicants. Characteristic extraction from submitted statements was used to generate GAI‐written personal statements using ChatGPT 4.0. All statements were blindly reviewed by 21 experienced evaluators on a 10‐point Likert scale of authenticity, readability, personability, and overall quality. Thematic analysis of qualitative reviewer comments was conducted to extract deeper insights into evaluators' perceptions. Quantitative results were compared using independent t‐tests, while thematic coding was performed inductively using NVivo software.Results: GAI‐generated personal statements significantly outperformed applicant‐written statements in all assessed domains, including authenticity (7.67 vs. 7.05, p = 0.002), readability (8.03 vs. 7.49, p = 0.002), personability (7.33 vs. 6.72, p = 0.004), and overall score (7.49 vs. 6.90, p = 0.005). Thematic analysis revealed that GAI statements were seen as “well‐constructed but generic,” while applicant statements were often “verbose and lacked focus.” Additionally, reviewers noted concerns regarding personal insight and engagement in AI‐generated statements.Conclusion: GAI‐generated personal statements were rated more favorably across all domains, raising critical questions about the future of personal statements in the residency application process. While AI in medical education continues to evolve, clear guidelines on its ethical use in residency applications are essential.Level of Evidence: N/A
- 14 April 2025
- Published by Wiley in The Laryngoscope
- Vol. 135 (10) , 3570-3578
Open AccessGenerative AI in Otolaryngology Residency Personal Statement Writing: A Mixed‐Methods Analysis
Objective: Generative Artificial Intelligence (GAI) interfaces have rapidly integrated into various societal domains. Widespread accessibility of GAI for drafting personal statements poses challenges for evaluators to gauge writing ability and personal insight. This study aims to compare the quality of GAI‐generated personal statements to those written by successful applicants in OHNS residency programs, via integration of statistical and qualitative thematic analyses.Methods: Personal statements were collected from successful OHNS residency applicants. Characteristic extraction from submitted statements was used to generate GAI‐written personal statements using ChatGPT 4.0. All statements were blindly reviewed by 21 experienced evaluators on a 10‐point Likert scale of authenticity, readability, personability, and overall quality. Thematic analysis of qualitative reviewer comments was conducted to extract deeper insights into evaluators' perceptions. Quantitative results were compared using independent t‐tests, while thematic coding was performed inductively using NVivo software.Results: GAI‐generated personal statements significantly outperformed applicant‐written statements in all assessed domains, including authenticity (7.67 vs. 7.05, p = 0.002), readability (8.03 vs. 7.49, p = 0.002), personability (7.33 vs. 6.72, p = 0.004), and overall score (7.49 vs. 6.90, p = 0.005). Thematic analysis revealed that GAI statements were seen as “well‐constructed but generic,” while applicant statements were often “verbose and lacked focus.” Additionally, reviewers noted concerns regarding personal insight and engagement in AI‐generated statements.Conclusion: GAI‐generated personal statements were rated more favorably across all domains, raising critical questions about the future of personal statements in the residency application process. While AI in medical education continues to evolve, clear guidelines on its ethical use in residency applications are essential.Level of Evidence: N/A