Kabak, Mehmet

Profile Picture
Profile URL
https://hdl.handle.net/20.500.12514/7724
Name Variants
Job Title
Doç. Dr.
Email Address
mehmetkabak@artuklu.edu.tr
Main Affiliation
Department of Internal Medical Sciences / Dahili Tıp Bilimleri Bölümü
Status
Current Staff
Website
ORCID ID
0000-0003-4781-1751
Scopus Author ID
57210705197
Turkish CoHE Profile ID
150585
Google Scholar ID
rmc3fYIAAAAJ
WoS Researcher ID
LRB-6648-2024
Files
cv_A-1621_ingilizce.pdf (398.47 KB)
cv_A-1621_turkce.pdf (402.94 KB)

Sustainable Development Goals

3

GOOD HEALTH AND WELL-BEING
GOOD HEALTH AND WELL-BEING Logo

1

Research Products
Documents

18

Citations

61

h-index

5

Go to Scopus profile
Documents

13

Citations

52

Go to WoS profile
Scholarly Output

3

Articles

3

Views / Downloads

5/0

Supervised MSc Theses

0

Supervised PhD Theses

0

WoS Citation Count

0

Scopus Citation Count

1

WoS h-index

0

Scopus h-index

1

Patents

0

Projects

0

WoS Citations per Publication

0.00

Scopus Citations per Publication

0.33

Open Access Source

3

Supervised Theses

0

Google Analytics Visitor Traffic

JournalCount
Annals of Thoracic Medicine1
Frontiers in Public Health1
Tuberk Toraks1
Current Page: 1 / 1

Scopus Quartile Distribution

Competency Cloud

GCRIS Competency Cloud

Filters

2025220241
Reset filters

Settings

Scholarly Output Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Article
    Predicting the Severity of Obstructive Sleep Apnea Using Artificial Intelligence Tools
    (Wolters Kluwer Medknow Publications, 2025) Cil, Baris; Irmak, Halit; Kabak, Mehmet
    BACKGROUND:We developed an artificial intelligence (AI) model to predict the severity of obstructive sleep apnea syndrome (OSAS).METHODS:We used data from 750 inpatients at a research hospital between 2021 and 2023. The dataset comprises 20 attributes, including demographic information, medical history, anthropometric measurements, and polysomnography (PSG) data. The target attribute was the apnea-hypopnea Index (AHI), from which OSAS severity was determined. Data preprocessing included min-max scaling for normalization and the Synthetic Minority Over-sampling Technique algorithm to address the class imbalance, increasing the dataset size to 1250. We invented and further developed a multilayer artificial neural network (ANN) model to predict OSAS severity and evaluated its performance using k-fold cross-validation. We also performed an information gain analysis to rank the features by importance.RESULTS:The ANN model accurately predicted OSAS severity (area under the receiver operating characteristic curve: 0.966, CA: 0.880). Information gain analysis revealed strong associations between OSAS severity and the Epworth Sleepiness Scale, lowest nighttime oxygen saturation, percentage of sleep time with oxygen saturation between 80% and 90% during the night, and neck thickness. These identified features represent important risk factors for early OSAS diagnosis and treatment.CONCLUSION:Our findings suggest that AI-based models can effectively predict OSAS severity. This research may contribute to the development of next-generation diagnostic tools for OSAS diagnosis and risk assessment. AI can readily determine OSAS severity from overnight pulse oximetry recordings, combined with other risk factors, in patients with suspected OSAS.
  • Thumbnail Image
    Article
    Syrian Civil War and Assessment of Tuberculosis Among Syrian Refugees and Local Citizens in Mardin
    (Frontiers Media SA, 2025) Cil, Baris; Kabak, Mehmet; Bodur, Mehmet Sinan; Sanmak, Erkan; Gunes, Guldan; Alakas, Yusuf; Oktay, Hamza
    Background: We compared tuberculosis (TB) characteristics and outcomes between Syrian refugees and local citizens in Mardin, Turkey (2016-2023), a border province with substantial population mobility. Methods: Retrospective, registry-based cross-sectional analysis of 491 patients (locals n = 456; refugees n = 35). Descriptive comparisons used chi(2)/Fisher (categorical) and Mann-Whitney U (age). Annual incidence per 100,000 used mid-year denominators (locals: ABPRS/NVI; refugees: DGMM/PMM and UNHCR). For outcomes with significant crude differences (treatment success, BCG scar, transferred-out), age- and sex-adjusted bias-reduced (Firth) logistic regression was applied; p-values from penalized likelihood-ratio (PLR) tests. Results: BCG-scar positivity was lower in refugees than locals (62.9% vs. 93.2%, p < 0.001). Microbiological confirmation remained below WHO targets in both groups. Crude treatment success was lower in refugees (68.6%) than locals (90.4%, p = 0.03), while transferred-out was higher (25.7% vs. 5.3%, p = 0.001). In adjusted Firth models including all cases, refugee status was associated with lower odds of success (aOR 0.224, 95% CI 0.103-0.488; PLR p < 0.001); after excluding transferred-out cases the association attenuated and was not significant (aOR 0.562, 95% CI 0.121-2.605; PLR p = 0.42). In pulmonary-only analyses, the association persisted (aOR 0.216, 95% CI 0.083-0.567; PLR p = 0.002). Refugee incidence dipped in 2020-2021 and rebounded in 2022-2023. Conclusion: Differences likely reflect operational barriers-especially transfers disrupting continuity-rather than intrinsic factors. Refugee-inclusive TB services with robust inter-provincial transfer tracking, patient navigation, and expanded bacteriological testing (notably for extrapulmonary disease) should be prioritized. Given the small refugee subgroup and denominator uncertainties, findings are hypothesis-generating.
  • Thumbnail Image
    Article
    Citation - Scopus: 1
    Radiologic Severity Index Can Be Used To Predict Mortality Risk in Patients With Covid-19
    (Turkish Assoc Tuberculosis & Thorax, 2024) Sahutoglu, Elif; Kabak, Mehmet; Cil, Baris; Atay, Kadri; Peker, Ahmet; Guler, Suekran; Sahutoglu, Tuncay
    Introduction: Pneumonia is a common symptom of coronavirus disease-2019 (COVID-19), and this study aimed to determine how analyzing initial thoracic computerized-tomography (CT) scans using semi-quantitative methods could be used to predict the outcomes for hospitalized patients. Materials and Methods: This study looked at previously collected data from adult patients who were hospitalized with a positive test for severe acute respiratory syndrome coronavirus-2 and had CT scans of their thorax at the time of presentation. The CT scans were evaluated for the extent of lung involvement using a semi-quantitative scoring system ranging from 0 to 72. The researchers then analyzed whether CT score could be used to predict outcomes. Results: The study included 124 patients, 55 being females, with a mean age of 46.13 years and an average duration of hospitalization of 11.69 days. Twelve patients (9.6%) died within an average of 17.2 days. The non-surviving patients were significantly older, had more underlying health conditions, and higher CT scores than the surviving patients. After taking age and comorbidities into account, each increase in CT score was associated with a 1.048 increase in the risk of mortality. CT score had a good ability to predict mortality, with an area under the curve of 0.857 and a sensitivity of 75% and specificity of 85.7% at a cut-off point of 25.5. Conclusion: Radiologic severity index, which is calculated using a semi-quantitative CT scoring system, can be used to predict the mortality of COVID-19 patients at the time of their initial hospitalization.