Michał Seweryn

Dr. Michał Seweryn

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
1 November 2016 in Journal of Clinical Epidemiology
Verified
Journal Article
Closed access
BJBradley Johnston
Bradley Johnston
PMPatricia A. Miller
Patricia A. Miller
AAArnav Agarwal
Arnav Agarwal
SMSohail Mulla
Sohail Mulla
RKRabia Khokhar
Rabia Khokhar
GGGordon H. Guyatt
Gordon H. Guyatt

1 September 2025 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
ALAgnieszka Leszczyńska
Agnieszka Leszczyńska
Rafał ObuchowiczRafał Obuchowicz
Rafał Obuchowicz
Michał StrzeleckiMichał Strzelecki
Michał Strzelecki
MSMichał Seweryn
Michał Seweryn
Background/Objectives: This systematic review aims to synthesize recent studies on the integration of artificial intelligence (AI) into robotic surgery for oncological patients. It focuses on studies using real patient data and AI tools in robotic oncologic surgery. Methods: This systematic review followed PRISMA guidelines to ensure a robust methodology. A comprehensive search was conducted in June 2025 across Embase, Medline, Web of Science, medRxiv, Google Scholar, and IEEE databases, using MeSH terms, relevant keywords, and Boolean logic. Eligible studies were original research articles published in English between 2024 and 2025, focusing on AI applications in robotic cancer surgery using real patient data. Studies were excluded if they were non-peer-reviewed, used synthetic/preclinical data, addressed non-oncologic indications, or explored non-robotic AI applications. This approach ensured the selection of studies with practical clinical relevance. Results: The search identified 989 articles, with 17 duplicates removed. After screening, 921 were excluded, and 37 others were eliminated for reasons such as misalignment with inclusion criteria or lack of full text. Ultimately, 14 articles were included, with 8 using a retrospective design and 6 based on prospective data. These included articles that varied significantly in terms of the number of participants, ranging from several dozen to several thousand. These studies explored the application of AI across various stages of robotic oncologic surgery, including preoperative planning, intraoperative support, and postoperative predictions. The quality of 11 included studies was very good and good. Conclusions: AI significantly supports robotic oncologic surgery at various stages. In preoperative planning, it helps estimate the risk of conversion from minimally invasive to open colectomy in colon cancer. During surgery, AI enables precise tumor and vascular structure localization, enhancing resection accuracy, preserving healthy tissue, and reducing warm ischemia time. Postoperatively, AI’s flexibility in predicting functional and oncological outcomes through context-specific models demonstrates its value in improving patient care. Due to the relatively small number of cases analyzed, further analysis of the issues presented in this review is necessary.

1 June 2022 in Combinatorica
Verified
Journal Article
Closed access
PDF file
THTony Huynh
Tony Huynh
GJGwenaël Joret
Gwenaël Joret
PMPiotr Micek
Piotr Micek
MSMichał Seweryn
Michał Seweryn
PWPaul Wollan
Paul Wollan

MSMichał Seweryn
Michał Seweryn
TBTomasz Banas
Tomasz Banas
JAJoanna Augustynska
Joanna Augustynska
OLOla Lorenc
Ola Lorenc
JKJustyna Kopel
Justyna Kopel
TSTomasz Skóra
Tomasz Skóra
Background: In Poland, breast cancer (BC) is the most frequently diagnosed cancer in women and the second most common cause of death after lung cancer. This disease has important economic implications for patients, public payers, and the whole Polish economy. This study aimed to estimate the total National Health Fund (NHF) expenditures on the diagnosis and treatment of patients with breast cancer. In addition, the costs of productivity losses were also calculated. Methods: Cost estimation was prepared using a top-down approach. Direct cost calculations were based on data reported by NHF for patients with the diagnosis of breast cancer. Medical care costs included the following components: screening program, oncological package, surgical treatment, hospitalization, drug program, chemotherapy, radiotherapy, and outpatient care. Indirect costs in the form of absenteeism costs were calculated based on data from Statistics Poland (gross domestic product, number of employees) and the Social Insurance Institution database (the number of sick leave days). Results: Total expenditures for BC including direct costs and indirect costs amounted to EUR 305,371, EUR 332,998, and EUR 344,649, respectively in 2017, 2018, and 2019. Total healthcare costs in 2019 were EUR 4114 lower than in 2018, which resulted from the reduction in expenditure on the drug program (decrease of EUR 13,527), despite the observed increase in all remaining resources. From direct costs, the highest expense was spent on the drug program (nearly 50% of total direct costs), but this expense dropped significantly in 2019. For the remaining parameters, the costs increased year by year, of which the most expensive were surgical treatment (15%), radiotherapy (12%), and the screening program (10%). BC generated over EUR 120 thousand of social costs in 2019 and compared to 2017, there was an increase in productivity loss by 26%. Conclusions: Our results from 2017–2019 demonstrated that total expenditure for BC in Poland increased from year to year. Breast cancer generated almost EUR 345 thousand expenses in 2019, which translates into a significant burden on the public payer’s budget and the society in Poland.

2 March 2026 in Cancers
Verified
Journal Article
Open access
PDF file
ALAgnieszka Leszczyńska
Agnieszka Leszczyńska
MSMichał Seweryn
Michał Seweryn
Rafał ObuchowiczRafał Obuchowicz
Rafał Obuchowicz
Michał StrzeleckiMichał Strzelecki
Michał Strzelecki
Adam PiórkowskiAdam Piórkowski
Adam Piórkowski
PPPaweł Michał Potocki
Paweł Michał Potocki
Background/Objectives: To systematically review and critically appraise AI methods for RECIST-based radiologic treatment response assessment in solid tumors, comparing image-derived and report-derived approaches and summarizing their performance, agreement with reference standards, and validation quality. Methods: This systematic review followed PRISMA guidelines. We searched Embase, MEDLINE, Web of Science, Scopus, and the Cochrane Library on 6 December 2025. We included English-language original studies (2015–2025) in solid tumors where AI directly assigned RECIST response categories and was validated against a reference standard; studies without RECIST-based response endpoints or non–solid tumor populations were excluded. We distinguished image-based techniques that assign RECIST categories from direct analysis of imaging data from report-based techniques that infer RECIST categories from radiology reports using natural language processing. Results: Evidence remains sparse; we identified four eligible studies (two image-based and two report-based). DeepSeek-V3-0324 and GatorTron, both report-based approaches, achieved high accuracy (96.5% and 89%, respectively) in treatment response evaluation, with DeepSeek demonstrating higher expert agreement (κ 0.85–0.90). The nnU-Net and 3D U-Net pipelines, both image-based, showed high segmentation performance (DSC 0.85, VS 0.89) and treatment response classification accuracy of 0.77 for R1, with moderate agreement with the manual reference (κ = 0.60); nnU-Net also achieved moderate to almost perfect agreement (Cohen’s κ 0.67–0.81) in RECIST 1.1 measurements. Conclusions: AI-based RECIST-oriented response assessment is feasible and potentially beneficial for standardization, efficiency, and scalability, but current evidence is limited and heterogeneous, requiring larger multi-center studies with rigorous external validation before clinical adoption. Key limitations include data source variability, reference standard inconsistencies, and lack of robust external validation.

10 July 2024 in Oncology in Clinical Practice
Verified
Journal Article
Open access
PDF file
MSMichał Seweryn
Michał Seweryn
ALAgnieszka Leszczyńska
Agnieszka Leszczyńska
JJJerzy Jakubowicz
Jerzy Jakubowicz
TBTomasz Banas
Tomasz Banas
Introduction. Cervical cancer in Poland has a higher incidence and mortality rates, and lower 5-year survival rates compared to Western Europe. The Polish government has initiated screening and vaccination programs to improve outcomes. This study reviews cervical cancer epidemiology in Poland and assesses adherence to preventative measures. Additionally, we tried to assess the potential for improving the epidemiological situation in the future. Material and methods. Data were collected from the Polish National Cancer Registry and the National Health Fund. We performed desk research using international databases and peer-reviewed publications to contextualize Poland’s situation within Europe. Results. The incidence rate of cervical cancer in Poland is gradually decreasing, with an annual percent change of -3.3 (95% CI from –5.2 to –1.4; p < 0.05). The age-standardized incidence rate of 18.9 ranks Poland 20th of 27 European countries, while the mortality rate of 10.5 is twice as high as the European average. With only 55.1% of diagnosed women surviving 5 years, Poland ranks near the bottom in Europe. Additionally, only 10% of Poles have received anti-HPV immunization, and cytology screening coverage does not exceed 25%. Conclusions. Cervical cancer outcomes in Poland remain significantly below the European average. There is a pressing need for enhanced preventative measures and education in women’s health. Keywords: cervical cancer epidemiology prophylaxis adherence polish patients screening programs vaccination health outcomes