Repository logo
  • English
  • Srpski (lat)
  • Српски
Log In
Have you forgotten your password?
  1. Home
  2. Browse by Author

Browsing by Author "Marković, Ivan (7004033833)"

Filter results by typing the first few letters
Now showing 1 - 4 of 4
  • Results Per Page
  • Sort Options
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Publication
    Prediction of Cervical Lymph Node Metastasis in Clinically Node-Negative T1 and T2 Papillary Thyroid Carcinoma Using Supervised Machine Learning Approach
    (2023)
    Popović Krneta, Marina (57428070900)
    ;
    Šobić Šaranović, Dragana (57202567582)
    ;
    Mijatović Teodorović, Ljiljana (57221447343)
    ;
    Krajčinović, Nemanja (57221706004)
    ;
    Avramović, Nataša (23134505800)
    ;
    Bojović, Živko (36498994400)
    ;
    Bukumirić, Zoran (36600111200)
    ;
    Marković, Ivan (7004033833)
    ;
    Rajšić, Saša (57196448260)
    ;
    Djorović, Biljana Bazić (58307921300)
    ;
    Artiko, Vera (55887737000)
    ;
    Karličić, Mihajlo (57259714400)
    ;
    Tanić, Miljana (54584546700)
    Papillary thyroid carcinoma (PTC) is generally considered an indolent cancer. However, patients with cervical lymph node metastasis (LNM) have a higher risk of local recurrence. This study evaluated and compared four machine learning (ML)-based classifiers to predict the presence of cervical LNM in clinically node-negative (cN0) T1 and T2 PTC patients. The algorithm was developed using clinicopathological data from 288 patients who underwent total thyroidectomy and prophylactic central neck dissection, with sentinel lymph node biopsy performed to identify lateral LNM. The final ML classifier was selected based on the highest specificity and the lowest degree of overfitting while maintaining a sensitivity of 95%. Among the models evaluated, the k-Nearest Neighbor (k-NN) classifier was found to be the best fit, with an area under the receiver operating characteristic curve of 0.72, and sensitivity, specificity, positive and negative predictive values, F1 and F2 scores of 98%, 27%, 56%, 93%, 72%, and 85%, respectively. A web application based on a sensitivity-optimized kNN classifier was also created to predict the potential of cervical LNM, allowing users to explore and potentially build upon the model. These findings suggest that ML can improve the prediction of LNM in cN0 T1 and T2 PTC patients, thereby aiding in individual treatment planning. © 2023 by the authors.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Publication
    Public trust and media influence on anxiety and depression levels among skilled workers during the COVID-19 outbreak in Serbia; [Uticaj poverenja javnosti i medija na nivoe anksioznosti i depresije medu stručnim radnicima tokom COVID-19 epidemije u Srbiji]
    (2020)
    Marković, Ivan (7004033833)
    ;
    Nikolovski, Srdjan (57191440233)
    ;
    Milojević, Stefan (57221306057)
    ;
    Živković, Dragan (57221311483)
    ;
    Knežević, Snežana (54892565300)
    ;
    Mitrović, Aleksandra (57221305057)
    ;
    Fišer, Zlatko (55055385800)
    ;
    Djurdjević, Dragan (58704698000)
    Background/Aim. Along with the great impact of 2019 coronavirus disease (COVID-19) on physical health, social functioning, and economy, this public health emergency has significant impact on mental health of people as well. The aim of this study was to assess the impact of outbreak-related information and public trust in the health system and preventive measures during the COVID-19 outbreak in Serbia in 2020 on levels of anxiety and depression in education, army and healthcare professionals. Methods. An anonymous questionnaire was disseminated to skilled professionals working in fields of education, army, and healthcare. The questionnaire included the Beck Anxiety Inventory, Zung Self-Rating Depression Scale, as well as the section assessing the perceived disturbance by the outbreak-related information and the trust of participants in healthcare system and preventive measures proposed by the crisis team. Results. Out of 110 subjects enrolled in this study (mean age 35.25 ± 9.23 years), 59.1% were women. Among healthcare workers, the frequency of perceiving outbreak-related information available in public media as disturbing, as well as the average level of anxiety, were higher compared to the group of army professionals (p < 0.05). Women also perceived outbreak-related information available in public media as disturbing in a higher percentage compared to men (p < 0.01), and had higher levels of anxiety (p = 0.01) and depression (p < 0.05). The lack of public trust was associated with higher levels of depression, and the perception of outbreak-related information as disturbing with higher levels of both anxiety and depression. Conclusion. Significant perception of outbreak-related information as disturbing among healthcare workers, as well as the lack of trust in healthcare system and preventive measures proposed by the crisis team are important factors influencing the mental state. This finding has the guiding purpose for competent institutions to make efforts to increase public trust, as one of the important preventive measures, in order to preserve and improve the mental well-being of the population in outbreak conditions. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Publication
    Serum DPPIV activity and CD26 expression on lymphocytes in patients with benign or malignant breast tumors
    (2011)
    Erić-Nikolić, Aleksandra (36859387500)
    ;
    Matić, Ivana Z. (36572349500)
    ;
    Dordević, Milica (43760989500)
    ;
    Milovanović, Zorka (25228841900)
    ;
    Marković, Ivan (7004033833)
    ;
    Džodić, Radan (6602410321)
    ;
    Inić, Momčilo (6507618262)
    ;
    Srdić-Rajić, Tatjana (58116313000)
    ;
    Jevrić, Marko (43761174500)
    ;
    Gavrilović, Dušica (8849698200)
    ;
    Cordero, Oscar J. (7004437937)
    ;
    Juranić, Zorica D. (7003932917)
    The aim of this work was to determine serum DPPIV activity as well as the percentage of CD26+ white blood cells and of CD26+ lymphocytes and the mean fluorescence intensity (MFI) of CD26 expression on lymphocytes in groups of patients with benign or malignant breast tumors and in healthy control people. Serum DPPIV activity was determined by colorimetric test, while CD26+ cells were counted using flow cytometer. Results of this study show that there is no statistically significant difference in serum DPPIV activity between examined groups of patients and healthy controls. However, two times higher frequency of patients with breast cancers had the enhanced DPPIV enzymatic activity in comparison to controls. Significant decrease in the percentage of CD26+ total white blood cells was found in the group of breast cancer patients and in patients with benign breast tumors compared to that found for healthy people. Although there was decrease in the percentage of lymphocytes in patients with breast tumors it was not statistically significant. The MFI of CD26 expression on these cells was significantly lower for cancer patients in comparison to healthy controls.In conclusion, this work showed the enhanced frequency of breast cancer patients with higher serum DPPIV activity. Decreased percentage of CD26+ white blood cells and decreased CD26 expression on lymphocytes are also characteristics of this group of patients.Determination of the clinical outcome of analyzed patients, 1 and 2 years after the surgical resection of the tumor, would clarify potential prognostic values of examined parameters for breast cancer. © 2011 Elsevier GmbH.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Publication
    Serum DPPIV activity and CD26 expression on lymphocytes in patients with benign or malignant breast tumors
    (2011)
    Erić-Nikolić, Aleksandra (36859387500)
    ;
    Matić, Ivana Z. (36572349500)
    ;
    Dordević, Milica (43760989500)
    ;
    Milovanović, Zorka (25228841900)
    ;
    Marković, Ivan (7004033833)
    ;
    Džodić, Radan (6602410321)
    ;
    Inić, Momčilo (6507618262)
    ;
    Srdić-Rajić, Tatjana (58116313000)
    ;
    Jevrić, Marko (43761174500)
    ;
    Gavrilović, Dušica (8849698200)
    ;
    Cordero, Oscar J. (7004437937)
    ;
    Juranić, Zorica D. (7003932917)
    The aim of this work was to determine serum DPPIV activity as well as the percentage of CD26+ white blood cells and of CD26+ lymphocytes and the mean fluorescence intensity (MFI) of CD26 expression on lymphocytes in groups of patients with benign or malignant breast tumors and in healthy control people. Serum DPPIV activity was determined by colorimetric test, while CD26+ cells were counted using flow cytometer. Results of this study show that there is no statistically significant difference in serum DPPIV activity between examined groups of patients and healthy controls. However, two times higher frequency of patients with breast cancers had the enhanced DPPIV enzymatic activity in comparison to controls. Significant decrease in the percentage of CD26+ total white blood cells was found in the group of breast cancer patients and in patients with benign breast tumors compared to that found for healthy people. Although there was decrease in the percentage of lymphocytes in patients with breast tumors it was not statistically significant. The MFI of CD26 expression on these cells was significantly lower for cancer patients in comparison to healthy controls.In conclusion, this work showed the enhanced frequency of breast cancer patients with higher serum DPPIV activity. Decreased percentage of CD26+ white blood cells and decreased CD26 expression on lymphocytes are also characteristics of this group of patients.Determination of the clinical outcome of analyzed patients, 1 and 2 years after the surgical resection of the tumor, would clarify potential prognostic values of examined parameters for breast cancer. © 2011 Elsevier GmbH.

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science

  • Privacy policy
  • End User Agreement
  • Send Feedback