Hilmi Erdem Sumbul

Prof. Dr. Hilmi Erdem Sumbul

Internal Medicine, Health Sciences University, Adana City Training and Research Hospital, Department of Neurosurgery, Adana, Turkey (Türkiye)
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
23 May 2024 in Briefings in Bioinformatics
Verified
Journal Article
Open access
PDF file
OTOnder Tutsoy
Onder Tutsoy
Hilmi Erdem SumbulHilmi Erdem Sumbul
Hilmi Erdem Sumbul
Thyroid cancer incidences endure to increase even though a large number of inspection tools have been developed recently. Since there is no standard and certain procedure to follow for the thyroid cancer diagnoses, clinicians require conducting various tests. This scrutiny process yields multi-dimensional big data and lack of a common approach leads to randomly distributed missing (sparse) data, which are both formidable challenges for the machine learning algorithms. This paper aims to develop an accurate and computationally efficient deep learning algorithm to diagnose the thyroid cancer. In this respect, randomly distributed missing data stemmed singularity in learning problems is treated and dimensionality reduction with inner and target similarity approaches are developed to select the most informative input datasets. In addition, size reduction with the hierarchical clustering algorithm is performed to eliminate the considerably similar data samples. Four machine learning algorithms are trained and also tested with the unseen data to validate their generalization and robustness abilities. The results yield 100% training and 83% testing preciseness for the unseen data. Computational time efficiencies of the algorithms are also examined under the equal conditions.

10 January 2022 in Ultrasound Quarterly
Verified
Journal Article
Closed access
Hilmi Erdem SumbulHilmi Erdem Sumbul
Hilmi Erdem Sumbul
BAbegüm şeyda Avci
begüm şeyda Avci
MBMehmet Bankir
Mehmet Bankir
BPBurcak Cakir Pekoz
Burcak Cakir Pekoz
EGErdinc Gulumsek
Erdinc Gulumsek
AKAyse Selcan Koc
Ayse Selcan Koc
Objectives: Parenchymal stiffness obtained by point shear-wave elastography (pSWE) in solid organs is used as a sign of damage in these organs. However, its clinical use and whether patients with polycystic ovary syndrome (PCOS) have increased ovarian tissue stiffness are still unclear. The aim of this study is to determine the parameters related to ovarian stiffness and whether there is an increase in ovarian stiffness in patients with PCOS compared with healthy controls. Methods: Forty-five women who were followed up regularly with the diagnosis of PCOS and 30 healthy controls similar to age and sex were included in this study. In addition to the routine follow-up parameters for PCOS, serum homeostatic model assessment of insulin resistance and anti-Mullerian hormone (AMH) levels were examined in all patients, and pSWE examination was performed with pelvic ultrasound (US) and ElastPQ technique. Results: Serum dehydroepiandrosterone sulfate, luteinizing hormone/follicle-stimulating hormone, testosterone, homeostatic model assessment of insulin resistance, and AMH were higher in PCOS compared with healthy controls (P < 0.001). Right, left, and mean ovary stiffness and volumes were significantly higher in PCOS group than healthy controls (P < 0.001). Correlation analysis was performed between mean ovary stiffness and dehydroepiandrosterone sulfate, luteinizing hormone/follicle-stimulating hormone, testosterone, homeostatic model assessment, and AMH and ovary volumes (P < 0.01 for each one). In linear regression analysis, only AMH was found to be related to mean ovary stiffness (P < 0.001 and β = 0.734). Conclusions: Ovarian stiffness value obtained by ElastPQ technique and pSWE method increases in PCOS patients compared with healthy controls and is closely related to serum AMH levels. In patients with PCOS, in addition to the conventional US, ovarian stiffness measured by pSWE may be an auxiliary examination in the follow-up of the disease. However, it was concluded that the ovarian stiffness measurement obtained in our current study should be supported by studies involving more patients and the transvaginal US method.

24 August 2018 in Clinical and Experimental Hypertension
Verified
Journal Article
Closed access
Hilmi Erdem SumbulHilmi Erdem Sumbul
Hilmi Erdem Sumbul
AKAyse Selcan Koc
Ayse Selcan Koc
DDDerya Demirtas
Derya Demirtas
Background: Increased carotid-femoral pulse wave velocity (CF-PWV) and increased carotid intima-media thickness (IMT) in hypertension (HT) patients are indicators of asymptomatic organ damage. The relationship between carotid IMT and CF-PWV has been shown; studies comparing CF-PWV and IMT values within different vascular regions are limited. We aimed to investigate the relationship between IMT value measured from different anatomical regions and CF-PWV, and the localization of IMT that determines increased CF-PWV best. Methods: This study included 312 patients with HT. CF-PWV measurements with Doppler ultrasonography (USG). Vascular IMTs were measurements of common-internal carotid, brachial, and femoral arteries with B-mode USG (CC-IMT, IC-IMT, B-IMT, and F-IMT, respectively). Patients were divided into two groups according to their CF-PWV value (Increased CF-PWV >10 m/s and normal CF-PWV ≤10m/s). Results: Increased CF-PWV was detected in 54 (17.3%) of HT patients. The patient group with increased CF-PWV was older, and their CC-IMT, IC-IMT and F-IMT values were found to be higher. The other 3 IMT increases excluding B-IMT were closely related to the CF-PWV increase. Only age and CC-IMT values were found to be most closely related to CF-PWV. CC-IMT and age were found to be independently associated with increased CF-PWV. CC-IMT (each-0.1 mm) and age (each year) were found to augment the development of increased CF-PWV by 50.3% and 14.6%, respectively. Conclusion: There is a close relationship between CC-IMT and CF-PWV increase in HT. It was thought that it would still be more useful to look at the increase of CC-IMT compared to other vascular regions for screening asymptomatic organ damage.

12 June 2018 in Cardiovascular Ultrasound
Verified
Journal Article
Open access
PDF file
AKAyse Selcan Koc
Ayse Selcan Koc
Hilmi Erdem SumbulHilmi Erdem Sumbul
Hilmi Erdem Sumbul
Carotid intima media thickness (C-IMT) and aortic IMT (A-IMT) increase in adult and pediatric patients with diabetes mellitus (DM), respectively. In both age groups IMT is used for early detection of macrovascular complications. In adult DM patients, A-IMT is still not a routine examination and is not used frequently. We aimed to determine whether there is an increase in A-IMT values measured from abdominal aorta besides traditional C-IMT in patients with type II DM and to determine parameters closely related to A-IMT in the same patient group. We included 114 type II DM patients and 100 healthy control subjects similar in age and sex in our study. Bilateral C-IMT and A-IMT values were measured by B-mode ultrasonography (USG) in addition to anamnesis, physical examination and routine examinations of all patients. When the clinical, demographic and laboratory data of patients with and without DM were compared, there was a high level of glucose and HbA1c and low hemoglobin levels in the DM patient group. All other parameters were found to be similar between the two groups. When the B-mode USG findings were examined, it was found that C-IMT and A-IMT were increased in patients with DM, with the A-IMT increase being more prominent. A-IMT values were found to be strongly and positively correlated with age, systolic blood pressure, blood urea nitrogen, DM onset time and HbA1c levels, and a negatively and significantly correlated with hemoglobin levels (p < 0.05, for each). In the regression model, the parameters correlating most closely with A-IMT were DM diagnosis onset time, HbA1c and hemoglobin levels (p = 0.001 and β = 0.353, p = 0.014 and β = 0.247 and p < 0.001 and β = − 0.406). As in pediatric DM patients also in adult DM patients A-IMT can easily be measured with new model USG devices. A-IMT must be measured during abdominal USG which is routine in adult DM patients. A-IMT is an easy, reproducible and non-invasive parameter that may be used in the diagnosis of macrovascular complications of adult type II DM.

1 January 2025 in Journal of Korean Medical Science
Verified
Journal Article
Open access
PDF file
RORamazan Azim Azim Okyay
Ramazan Azim Azim Okyay
BKBurhan Koçyiğit
Burhan Koçyiğit
AKAinur Kumar
Ainur Kumar
MYMarlen Yessirkepov
Marlen Yessirkepov
Hilmi Erdem SumbulHilmi Erdem Sumbul
Hilmi Erdem Sumbul
Okyay RA, et al. J Korean Med Sci. 2025 Oct;40:e300. https://doi.org/10.3346/jkms.2025.40.e300

1 June 2019 in Abdominal Radiology
Verified
Journal Article
Closed access
PDF file
ADAbdullah Orhan Orhan Demirtas
Abdullah Orhan Orhan Demirtas
AKAyse Selcan Koc
Ayse Selcan Koc
Hilmi Erdem SumbulHilmi Erdem Sumbul
Hilmi Erdem Sumbul
HKHasan Koca
Hasan Koca
YIYahya Kemal Icen
Yahya Kemal Icen
MKMehmet Kucukosmanoglu
Mehmet Kucukosmanoglu