Yazar "Sari, Nagehan Didem" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Assisting the Diagnosis of Cirrhosis in Chronic Hepatitis C Patients Based on Machine Learning Algorithms: A Novel Non-Invasive Approach
    (Wiley, 2025) Dirican, Emre; Bal, Tayibe; Onlen, Yusuf; Sarigul, Figen; User, Ulku; Sari, Nagehan Didem; Kurtaran, Behice
    Aim: This study aimed to determine the important features and cut-off values after demonstrating the detectability of cirrhosis using routine laboratory test results of chronic hepatitis C (CHC) patients in machine learning (ML) algorithms. Methods: This retrospective multicenter (37 referral centers) study included the data obtained from the Hepatitis C Turkey registry of 1164 patients with biopsy-proven CHC. Three different ML algorithms were used to classify the presence/absence of cirrhosis with the determined features. Results: The highest performance in the prediction of cirrhosis (Accuracy = 0.89, AUC = 0.87) was obtained from the Random Forest (RF) method. The five most important features that contributed to the classification were platelet, alpha lpha-feto protein (AFP), age, gamma-glutamyl transferase (GGT), and prothrombin time (PT). The cut-off values of these features were obtained as platelet < 182.000/mm3, AFP > 5.49 ng/mL, age > 52 years, GGT > 39.9 U/L, and PT > 12.35 s. Using cut-off values, the risk coefficients were AOR = 4.82 for platelet, AOR = 3.49 for AFP, AOR = 4.32 for age, AOR = 3.04 for GGT, and AOR = 2.20 for PT. Conclusion: These findings indicated that the RF-based ML algorithm could classify cirrhosis with high accuracy. Thus, crucial features and cut-off values for physicians in the detection of cirrhosis were determined. In addition, although AFP is not included in non-invasive indexes, it had a remarkable contribution in predicting cirrhosis. Trial Registration: Clinicaltrials.gov identifier: NCT03145844
  • Küçük Resim
    Öğe
    In a Real-Life Setting, Direct-Acting Antivirals to People Who Inject Drugs with Chronic Hepatitis C in Turkey
    (Aves, 2022) Yıldırım, Figen Sarıgül; User, Ülkü; Sari, Nagehan Didem; Kurtaran, Behice; Onlen, Yusuf; Şenateş, Ebubekir; Gündüz, Alper
    Background: People who inject drugs (PWID) should be treated in order to eliminate hepatitis C virus in the world. The aim of this study was to compare direct-acting antivirals treatment of hepatitis C virus for PWID and non-PWID in a real-life setting. Methods: We performed a prospective, non-randomized, observational multicenter cohort study in 37 centers. All patients treated with direct-acting antivirals between April 1, 2017, and February 28, 2019, were included. In total, 2713 patients were included in the study among which 250 were PWID and 2463 were non-PWID. Besides patient characteristics, treatment response, follow-up, and side effects of treatment were also analyzed. Results: Genotype 1a and 3 were more prevalent in PWID-infected patients (20.4% vs 9.9% and 46.8% vs 5.3%). The number of naive patients was higher in PWID (90.7% vs 60.0%), while the number of patients with cirrhosis was higher in non-PWID (14.1% vs 3.7%). The loss of follow-up was higher in PWID (29.6% vs 13.6%). There was no difference in the sustained virologic response at 12 weeks after treatment (98.3% vs 98.4%), but the end of treatment response was lower in PWID (96.2% vs 99.0%). In addition, the rate of treatment completion was lower in PWID (74% vs 94.4%). Conclusion: Direct-acting antivirals were safe and effective in PWID. Primary measures should be taken to prevent the loss of follow-up and poor adherence in PWID patients in order to achieve World Health Organization's objective of eliminating viral hepatitis.