John Milkovich

Mr. John Milkovich

McMaster University

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2020 in Canadian Medical Association Journal
Verified
Journal Article
Closed access
PDF file
JWJonathan Wang
Jonathan Wang
SVSaba Vahid
Saba Vahid
MEMaria Eberg
Maria Eberg
SMShannon Milroy
Shannon Milroy
JMJohn Milkovich
John Milkovich
JIJonathan C. Irish
Jonathan C. Irish
Background: To mitigate the effects of coronavirus disease 2019 (COVID-19), jurisdictions worldwide ramped down nonemergent surgeries, creating a global surgical backlog. We sought to estimate the size of the nonemergent surgical backlog during COVID-19 in Ontario, Canada, and the time and resources required to clear the backlog. Methods: We used 6 Ontario or Canadian population administrative sources to obtain data covering part or all of the period between Jan. 1, 2017, and June 13, 2020, on historical volumes and operating room throughput distributions by surgery type and region, and lengths of stay in ward and intensive care unit (ICU) beds. We used time series forecasting, queuing models and probabilistic sensitivity analysis to estimate the size of the backlog and clearance time for a +10% (+1 day per week at 50% capacity) surge scenario. Results: Between Mar. 15 and June 13, 2020, the estimated backlog in Ontario was 148 364 surgeries (95% prediction interval 124 508–174 589), an average weekly increase of 11 413 surgeries. Estimated backlog clearance time is 84 weeks (95% confidence interval [CI] 46–145), with an estimated weekly throughput of 717 patients (95% CI 326–1367) requiring 719 operating room hours (95% CI 431–1038), 265 ward beds (95% CI 87–678) and 9 ICU beds (95% CI 4–20) per week. Interpretation: The magnitude of the surgical backlog from COVID-19 raises serious implications for the recovery phase in Ontario. Our framework for modelling surgical backlog recovery can be adapted to other jurisdictions, using local data to assist with planning.

7 February 2022 in Journal of Oral and Maxillofacial Surgery
Verified
Journal Article
Closed access
WBWilmar Xavier Briceno
Wilmar Xavier Briceno
JMJohn Milkovich
John Milkovich
MEMohamed El-Rabbany
Mohamed El-Rabbany
MCMarco F. Caminiti
Marco F. Caminiti
DPDavid J. Psutka
David J. Psutka

18 February 2025 in Plastic Surgery
Verified
Journal Article
Open access
JPJonah W. Perlmutter
Jonah W. Perlmutter
JMJohn Milkovich
John Milkovich
SFSierra Fremont
Sierra Fremont
SDShaishav Datta
Shaishav Datta
AMAdam Mosa
Adam Mosa
Introduction: Self-examinations for skin cancer detection are limited by sensitivity. ChatGPT-4 has image recognition capabilities that can be a useful adjunct for screening cancers and tele-health applications. This study investigated the efficacy of ChatGPT-4 in identifying skin lesions. Methods: Dermoscopic images were retrospectively selected from the PH 2 dataset, categorized by clinical diagnosis, and uploaded to ChatGPT-4 with a predesigned prompt. Responses were compared against clinical diagnoses. Confidence intervals were calculated using the bootstrap method assessing precision and significance was calculated using McNemar's test. Analyses were performed using Jupyter Notebook and Python. Results: The GPT-4 model showed moderate performance in melanoma detection with 68.5% accuracy, 52.5% sensitivity, and 72.5% specificity, significantly differing from the clinical standard ( P = .002). For suspicious lesion detection, it performed better with 68.0% accuracy, 78.0% precision, and 70.0% F-measure, still not closely matching clinical diagnosis for atypical nevi and melanoma ( P = .0169). Conclusion: The statistical difference between ChatGPT-4 diagnosis of melanoma and suspicious lesions compared with clinical diagnoses and other AI models suggests the need for improvement in ChatGPT-4 algorithms. This study's limitations included the use of a secondary care database with a higher melanoma incidence, high-quality dermoscopic images that limit generalizability, a small sample size lacking diversity, and the need for larger datasets to validate findings in broader contexts.

12 March 2021 in Current Oncology
Verified
Journal Article
Open access
PDF file
JMJohn Milkovich
John Milkovich
THTimothy Hanna
Timothy Hanna
Carolyn NessimCarolyn Nessim
Carolyn Nessim
TPTeresa M. Petrella
Teresa M. Petrella
LWLouis Weatherhead
Louis Weatherhead
TCthe Ontario Skin Cancer Advisory Committee
the Ontario Skin Cancer Advisory Committee
There is a global rise in skin cancer incidence, resulting in an increase in patient care needs and healthcare costs. To optimize health care planning, costs, and patient care, Ontario Health developed a provincial skin cancer plan to streamline the quality of care. We conducted a systematic review and a grey literature search to evaluate the definitions and management of skin cancer within other jurisdictions, as well as a provincial survey of skin cancer care practices, to identify care gaps. The systematic review did not identify any published comprehensive skin cancer management plans. The grey literature search revealed skin cancer plans in isolated regions of the United Kingdom (U.K.), National Institute for Health and Care Excellence (NICE) guidelines for skin cancer quality indicators and regional skin cancer biopsy clinics, and wait time guidelines in Australia and the U.K. With the input of the Ontario Cancer Advisory Committee (CAC), unique definitions for complex and non-complex skin cancers and the appropriate cancer services were created. A provincial survey of skin cancer care yielded 44 responses and demonstrated gaps in biopsy access. A skin cancer pathway map was created and a recommendation was made for regional skin cancer biopsy clinics. We have created unique definitions for complex and non-complex skin cancer and a skin cancer pathways map, which will allow for the implementation of both process and performance metrics to address identified gaps in care.

28 April 2024 in Plastic Surgery
Verified
Journal Article
Open access
JMJohn Milkovich
John Milkovich
ICIsabella F. Churchill
Isabella F. Churchill
LGLucas Gallo
Lucas Gallo
PKPatrick Kim
Patrick Kim
MGMatteo Gallo
Matteo Gallo
CCChristopher J. Coroneos
Christopher J. Coroneos
Introduction: Admitted patients with burn injuries require prompt treatment and shorter hospital stays to avoid hospital-acquired infections and associated complications. This study aimed to determine the impact of time to the first surgery, and total length of hospital stay on the incidence of BWI and associated complications in adult patients with moderate burn injuries at a single tertiary hospital burn center. Methods: A retrospective chart review identified burn patients admitted to the Burn Unit between January 2011 and January 2021. The incidences of BWI and complications were documented. Univariate logistic regressions were performed, with significance set at P < .05. Results: A total of 171 patients were included in the study. The mean age was 50.8 years (range, 94-18 years), with 64 (37.4%) females. The mean wait time for surgery and total hospital stay was 2.6 days (SD = 2.5; 1-15 days) and 18.6 days (SD = 16.0; 1-125 days), respectively. Precisely, 47 patients (27.5%) were associated with positive burn wound cultures, with 23 patients (13.5%) experiencing clinical burn wound complications. Wait time to surgery did not significantly impact the incidence of BWI (OR = 0.97, P = .72) or related complications (OR = 0.97, P = .61). Total hospital stay was significantly associated with the incidence of BWI (OR = 1.05, P < .001) and related complications (OR = 1.02, P = .03). Conclusions: Delay to surgery may not be a significant risk factor of BWI and related complications in patients with burn injuries. Half of positive burn wound cultures are associated with objective clinical infection and subsequent complications. However, total hospital stay may be clinically important.

11 January 2021 in Canadian Medical Association Journal
Verified
Journal Article
Open access
PDF file
JWJonathan Wang
Jonathan Wang
SVSaba Vahid
Saba Vahid
MEMaria Eberg
Maria Eberg
SMShannon Milroy
Shannon Milroy
JMJohn Milkovich
John Milkovich
JIJonathan C. Irish
Jonathan C. Irish
CONTEXTE: Pour limiter la propagation de la maladie à coronavirus 2019 (COVID-19), de nombreux pays ont décidé de réduire le nombre d’interventions chirurgicales non urgentes, ce qui a créé des retards en chirurgie partout dans le monde. Notre objectif était d’évaluer l’ampleur du retard pour ce type d’interventions en Ontario, au Canada, ainsi que le temps et les ressources nécessaires pour y remédier. MÉTHODES: Nous avons consulté 6 bases de données administratives décrivant la population ontarienne et canadienne pour dégager la distribution du volume chirurgical et de la cadence des salles d’opération pour chaque type d’interventions et chaque région, et connaître la durée d’occupation d’un lit d’hôpital et d’un lit de soins intensifs. Les données utilisées concernent l’ensemble ou une partie de la période du 1er janvier 2017 au 13 juin 2020. Nous avons estimé l’ampleur du retard accumulé et prédit le temps nécessaire pour le reprendre dans un scénario avec capacité d’appoint de + 10 % (ajout d’un jour à 50 % de la capacité par semaine) à l’aide de modèles de séries chronologiques, de modèles de files d’attente et d’une analyse de sensibilité probabiliste. RÉSULTATS: Entre le 15 mars et le 13 juin 2020, le retard en chirurgie à l’échelle de l’Ontario s’est accru de 148 364 opérations (intervalle de prévision à 95 % 124 508–174 589) au total, et en moyenne de 11 413 opérations par semaine. Pour reprendre le retard accumulé, il faudra environ 84 semaines (intervalle de confiance [IC] à 95 % 46–145) et une cadence hebdomadaire de 717 patients (IC à 95 % 326–1367), qui elle demande 719 heures passées au bloc opératoire (IC à 95 % 431–1038), 265 lits d’hôpital (IC à 95 % 87–678) et 9 lits de soins intensifs (IC à 95 % 4–20) par semaine. INTERPRÉTATION: L’ampleur du retard en chirurgie dû à la COVID-19 laisse entrevoir de graves conséquences pour la phase de reprise en Ontario. Le cadre qui nous a servi à modéliser la reprise du retard peut être adapté ailleurs, avec des données locales, pour faciliter la planification.