İsMail Dilli
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
İsMail Dilli has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Engin Eren Kavak
Ankara Etlik City hospital
7 shared publications - Esra Zeynelgil
Department of Medical Oncology, Ankara Etlik City Hospital, Ankara 06170, Turkey
4 shared publications - Efe Cem Erdat
Ankara Gulhane Training and Research Hospital
2 shared publications - Goksen Inanc Imamoglu
Ankara Etlik Şehir Hastanesi
2 shared publications - Mehmetcan Atak
Department of Medical Oncology, Etlik City Hospital, 06170 Ankara, Turkey
2 shared publications - Salih Karatlı
Department of Medical Oncology, Ankara Etlik City Hospital, 06010 Ankara, Türkiye
2 shared publications
Latest Publications
- Open Access
- 8 October 2026
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 15 (19) , 7750
Real-World Evaluation of the Immune Checkpoint Inhibitor Score (IChIS) in Advanced Non-Small Cell Lung Cancer Treated with Immunotherapy
Background: The Immune Checkpoint Inhibitor Score (IChIS), an inflammation-based biomarker incorporating neutrophil and immature granulocyte counts, was recently developed to predict outcomes in patients with advanced non-small cell lung cancer (NSCLC) receiving immune checkpoint inhibitors (ICIs). However, evidence regarding its prognostic performance in independent real-world populations remains limited. We aimed to evaluate the prognostic significance of IChIS in a real-world cohort of patients with advanced NSCLC treated with immunotherapy. Methods: This retrospective single-center cohort study included 169 patients with advanced, recurrent, or metastatic NSCLC who received ICIs with palliative intent between September 2022 and December 2025. IChIS ranged from 0 to 2 and was analyzed as a categorical variable, with IChIS 0 as the reference category. The primary endpoint was progression-free survival (PFS), while overall survival (OS) was evaluated as a secondary exploratory endpoint. Survival outcomes were estimated using the Kaplan–Meier method and evaluated using Cox proportional hazards regression. Multivariable models included ICI treatment line as a clinically relevant potential confounder. Results: A total of 169 patients were included. The median follow-up was 14.1 months. IChIS 0, 1, and 2 were observed in 105 (62.1%), 33 (19.5%), and 31 (18.4%) patients, respectively. Median PFS decreased across increasing IChIS categories. In multivariable Cox regression analysis, compared with IChIS 0, both IChIS 1 (adjusted HR 1.61, 95% CI 1.00–2.59; p = 0.04) and IChIS 2 (adjusted HR 3.63, 95% CI 2.22–5.92; p < 0.001) were independently associated with shorter PFS. For OS, IChIS 1 was not significantly associated with outcome (adjusted HR 1.51, 95% CI 0.86–2.64; p = 0.15), whereas IChIS 2 was independently associated with shorter OS (adjusted HR 4.40, 95% CI 2.53–7.64; p < 0.001). Conclusions: Higher IChIS was independently associated with shorter PFS in patients with advanced NSCLC receiving ICIs, supporting its potential role as a simple and readily available prognostic biomarker. The association with OS was primarily observed in patients with IChIS 2 and should be interpreted cautiously given the relatively short follow-up. Prospective multicenter validation is warranted.
- 8 October 2026
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 15 (19) , 7750
Open AccessReal-World Evaluation of the Immune Checkpoint Inhibitor Score (IChIS) in Advanced Non-Small Cell Lung Cancer Treated with Immunotherapy
Background: The Immune Checkpoint Inhibitor Score (IChIS), an inflammation-based biomarker incorporating neutrophil and immature granulocyte counts, was recently developed to predict outcomes in patients with advanced non-small cell lung cancer (NSCLC) receiving immune checkpoint inhibitors (ICIs). However, evidence regarding its prognostic performance in independent real-world populations remains limited. We aimed to evaluate the prognostic significance of IChIS in a real-world cohort of patients with advanced NSCLC treated with immunotherapy. Methods: This retrospective single-center cohort study included 169 patients with advanced, recurrent, or metastatic NSCLC who received ICIs with palliative intent between September 2022 and December 2025. IChIS ranged from 0 to 2 and was analyzed as a categorical variable, with IChIS 0 as the reference category. The primary endpoint was progression-free survival (PFS), while overall survival (OS) was evaluated as a secondary exploratory endpoint. Survival outcomes were estimated using the Kaplan–Meier method and evaluated using Cox proportional hazards regression. Multivariable models included ICI treatment line as a clinically relevant potential confounder. Results: A total of 169 patients were included. The median follow-up was 14.1 months. IChIS 0, 1, and 2 were observed in 105 (62.1%), 33 (19.5%), and 31 (18.4%) patients, respectively. Median PFS decreased across increasing IChIS categories. In multivariable Cox regression analysis, compared with IChIS 0, both IChIS 1 (adjusted HR 1.61, 95% CI 1.00–2.59; p = 0.04) and IChIS 2 (adjusted HR 3.63, 95% CI 2.22–5.92; p < 0.001) were independently associated with shorter PFS. For OS, IChIS 1 was not significantly associated with outcome (adjusted HR 1.51, 95% CI 0.86–2.64; p = 0.15), whereas IChIS 2 was independently associated with shorter OS (adjusted HR 4.40, 95% CI 2.53–7.64; p < 0.001). Conclusions: Higher IChIS was independently associated with shorter PFS in patients with advanced NSCLC receiving ICIs, supporting its potential role as a simple and readily available prognostic biomarker. The association with OS was primarily observed in patients with IChIS 2 and should be interpreted cautiously given the relatively short follow-up. Prospective multicenter validation is warranted.
- Open Access
- 1 September 2026
- Published by T.C. Sağlık Bakanlığı Ankara Atatürk Sanatoryum Eğitim ve Araştırma Hastanesi in Sanatorium Medical Journal
- Vol. 2 (3) , 110-116
Febrile Neutropenia Information on YouTube: A Multilingual Cross-Sectional Quality and Reliability Assessment Using DISCERN, JAMA, and GQS
Background: Febrile neutropenia (FN) is a potentially life-threatening complication of cancer treatment requiring prompt recognition and management. As patients increasingly seek health information online, YouTube has become a widely used platform; however, the reliability and quality of FN-related content remain unclear.Objective: This study aimed to evaluate the reliability, transparency, and educational quality of multilingual YouTube videos on febrile neutropenia using DISCERN, JAMA benchmark criteria, and the Global Quality Score (GQS).Methods: In this cross-sectional study, YouTube videos were identified using predefined keywords in English, Turkish, and German. Videos providing structured educational content on febrile neutropenia were included. Two independent medical oncologists evaluated videos using DISCERN (reliability; 16–80), JAMA (transparency; 0–4), and GQS (educational quality; 1–5). Interrater reliability was assessed using intraclass correlation coefficients (ICC), and correlations between video duration and quality metrics were analyzed using Spearman’s rank correlation.Results: Thirty videos were included (English: 25/30, 83%; Turkish: 4/30, 13%; German: 1/30, 3%). Median DISCERN score was 57 (IQR 40–66), median GQS was 3 (IQR 3–4), and median JAMA score was 3 (IQR 2–4), indicating overall moderate reliability and quality. Interrater reliability was excellent for DISCERN (ICC=0.98) and GQS (ICC=0.95), and good for JAMA (ICC=0.86). Video duration showed strong correlations with DISCERN (ρ=0.80, P
- 1 September 2026
- Published by T.C. Sağlık Bakanlığı Ankara Atatürk Sanatoryum Eğitim ve Araştırma Hastanesi in Sanatorium Medical Journal
- Vol. 2 (3) , 110-116
Open AccessFebrile Neutropenia Information on YouTube: A Multilingual Cross-Sectional Quality and Reliability Assessment Using DISCERN, JAMA, and GQS
Background: Febrile neutropenia (FN) is a potentially life-threatening complication of cancer treatment requiring prompt recognition and management. As patients increasingly seek health information online, YouTube has become a widely used platform; however, the reliability and quality of FN-related content remain unclear.Objective: This study aimed to evaluate the reliability, transparency, and educational quality of multilingual YouTube videos on febrile neutropenia using DISCERN, JAMA benchmark criteria, and the Global Quality Score (GQS).Methods: In this cross-sectional study, YouTube videos were identified using predefined keywords in English, Turkish, and German. Videos providing structured educational content on febrile neutropenia were included. Two independent medical oncologists evaluated videos using DISCERN (reliability; 16–80), JAMA (transparency; 0–4), and GQS (educational quality; 1–5). Interrater reliability was assessed using intraclass correlation coefficients (ICC), and correlations between video duration and quality metrics were analyzed using Spearman’s rank correlation.Results: Thirty videos were included (English: 25/30, 83%; Turkish: 4/30, 13%; German: 1/30, 3%). Median DISCERN score was 57 (IQR 40–66), median GQS was 3 (IQR 3–4), and median JAMA score was 3 (IQR 2–4), indicating overall moderate reliability and quality. Interrater reliability was excellent for DISCERN (ICC=0.98) and GQS (ICC=0.95), and good for JAMA (ICC=0.86). Video duration showed strong correlations with DISCERN (ρ=0.80, P
- Open Access
- 29 July 2026
- Published by Galenos Yayinevi in Acta Haematologica Oncologica Turcica
Quantifying the Survival Benefit of Trimodality Therapy in Esophageal Squamous Cell Carcinoma: An IPTW-adjusted Retrospective Analysis
Quantifying the Survival Benefit of Trimodality Therapy in Esophageal Squamous Cell Carcinoma: An IPTW-adjusted Retrospective Analysis - Acta Haematologica Oncologica Turcica
- 29 July 2026
- Published by Galenos Yayinevi in Acta Haematologica Oncologica Turcica
Open AccessQuantifying the Survival Benefit of Trimodality Therapy in Esophageal Squamous Cell Carcinoma: An IPTW-adjusted Retrospective Analysis
Quantifying the Survival Benefit of Trimodality Therapy in Esophageal Squamous Cell Carcinoma: An IPTW-adjusted Retrospective Analysis - Acta Haematologica Oncologica Turcica
- Open Access
- 24 March 2026
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 15 (7) , 2475
Impact of Prior mRNA COVID-19 Vaccination on PFS2 in NSCLC Patients Receiving Second-Line Immune Checkpoint Inhibitors: A Real-World Analysis
Background: Immune checkpoint inhibitors (ICIs) targeting the PD-1 axis represent standard second-line therapy for metastatic non-small cell lung cancer (NSCLC). Emerging data suggest that SARS-CoV-2 mRNA vaccines may enhance antitumor immunity through innate immune activation and type I interferon signaling, potentially sensitizing tumors to PD-1 blockade. The clinical impact of patients initiating second-line nivolumab remains unclear. Methods: In this retrospective single-center cohort study, 88 patients with recurrent stage IV NSCLC who received second-line nivolumab between 1 January 2023 and 1 January 2026 were analyzed. Vaccination exposure was defined using a 6-month pre-treatment window prior to nivolumab initiation (T0). Patients were stratified according to receipt of ≥2 versus 0–1 mRNA COVID-19 vaccine doses within the 6 months preceding T0 (n = 45 and n = 43, respectively). The primary endpoint was progression-free survival from nivolumab initiation (PFS2). Survival outcomes were estimated using the Kaplan–Meier method and evaluated using Cox regression models. Results: With a median follow-up of 22.4 months, median PFS2 for the overall cohort was 11.1 months (95% CI, 9.4–15.1). Patients receiving ≥2 mRNA doses had significantly longer PFS2 than those receiving 0–1 dose (14.0 vs. 9.6 months; p = 0.04). In multivariable analysis, ≥2 doses were independently associated with reduced risk of progression or death (aHR 0.52, 95% CI 0.31–0.88; p = 0.01). Non-adenocarcinoma histology and baseline brain metastasis were independently associated with shorter PFS2. Conclusions: Receipt of ≥2 mRNA vaccine doses within 6 months before nivolumab initiation was independently associated with prolonged PFS2 in metastatic NSCLC. Prospective multicenter validation is warranted.
- 24 March 2026
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 15 (7) , 2475
Open AccessImpact of Prior mRNA COVID-19 Vaccination on PFS2 in NSCLC Patients Receiving Second-Line Immune Checkpoint Inhibitors: A Real-World Analysis
Background: Immune checkpoint inhibitors (ICIs) targeting the PD-1 axis represent standard second-line therapy for metastatic non-small cell lung cancer (NSCLC). Emerging data suggest that SARS-CoV-2 mRNA vaccines may enhance antitumor immunity through innate immune activation and type I interferon signaling, potentially sensitizing tumors to PD-1 blockade. The clinical impact of patients initiating second-line nivolumab remains unclear. Methods: In this retrospective single-center cohort study, 88 patients with recurrent stage IV NSCLC who received second-line nivolumab between 1 January 2023 and 1 January 2026 were analyzed. Vaccination exposure was defined using a 6-month pre-treatment window prior to nivolumab initiation (T0). Patients were stratified according to receipt of ≥2 versus 0–1 mRNA COVID-19 vaccine doses within the 6 months preceding T0 (n = 45 and n = 43, respectively). The primary endpoint was progression-free survival from nivolumab initiation (PFS2). Survival outcomes were estimated using the Kaplan–Meier method and evaluated using Cox regression models. Results: With a median follow-up of 22.4 months, median PFS2 for the overall cohort was 11.1 months (95% CI, 9.4–15.1). Patients receiving ≥2 mRNA doses had significantly longer PFS2 than those receiving 0–1 dose (14.0 vs. 9.6 months; p = 0.04). In multivariable analysis, ≥2 doses were independently associated with reduced risk of progression or death (aHR 0.52, 95% CI 0.31–0.88; p = 0.01). Non-adenocarcinoma histology and baseline brain metastasis were independently associated with shorter PFS2. Conclusions: Receipt of ≥2 mRNA vaccine doses within 6 months before nivolumab initiation was independently associated with prolonged PFS2 in metastatic NSCLC. Prospective multicenter validation is warranted.
- Open Access
- 13 January 2026
- Published by MDPI AG in Current Oncology
- Vol. 33 (1) , 43
Prognostic Significance of Lung Immune Prognostic Index at Diagnosis in Stage III Non-Small Cell Lung Cancer
Objective: The aim of this study was to assess the association between the Lung Immune Prognostic Index (LIPI) measured at diagnosis and both event-free survival (EFS) and overall survival (OS) in patients with stage III non-small cell lung cancer (NSCLC). Methods: This retrospective cohort included patients diagnosed with stage III NSCLC between September 2022 and July 2024, all of whom had a minimum follow-up duration of six months. LIPI was calculated using the derived neutrophil-to-lymphocyte ratio (dNLR) and lactate dehydrogenase levels at diagnosis. Clinical, demographic, and treatment-related data were systematically collected. Survival outcomes were estimated using the Kaplan–Meier approach, while factors associated with prognosis were examined through Cox proportional hazards models. Results: The study population consisted of 68 patients, predominantly male (86.8%), with a mean age of 63.4 ± 8.7 years. According to the Lung Immune Prognostic Index classification, 29 patients (42.6%) were categorized as having a good score, 27 (39.7%) as intermediate, and 12 (17.6%) as poor. During a median follow-up of 15.4 months, a total of 40 progressions and 22 deaths occurred. Median EFS was 17.7, 9.4, and 5.8 months for good, intermediate, and poor LIPI groups, respectively (p < 0.001). Median OS was 25.7 months in the good LIPI group, was not reached in the intermediate group due to insufficient events, and was 6.7 months in the poor group (p < 0.001). In multivariate Cox analysis, poor LIPI was independently associated with inferior survival (EFS: HR = 2.87, 95% CI: 1.85–4.46, p < 0.001; OS: HR = 2.59, 95% CI: 1.40–4.78, p = 0.002). Conclusions: LIPI calculated at diagnosis is an independent prognostic factor for both EFS and OS in stage III NSCLC. Validation in larger, prospective cohorts is warranted to further define its prognostic role in stage III NSCLC.
- 13 January 2026
- Published by MDPI AG in Current Oncology
- Vol. 33 (1) , 43
Open AccessPrognostic Significance of Lung Immune Prognostic Index at Diagnosis in Stage III Non-Small Cell Lung Cancer
Objective: The aim of this study was to assess the association between the Lung Immune Prognostic Index (LIPI) measured at diagnosis and both event-free survival (EFS) and overall survival (OS) in patients with stage III non-small cell lung cancer (NSCLC). Methods: This retrospective cohort included patients diagnosed with stage III NSCLC between September 2022 and July 2024, all of whom had a minimum follow-up duration of six months. LIPI was calculated using the derived neutrophil-to-lymphocyte ratio (dNLR) and lactate dehydrogenase levels at diagnosis. Clinical, demographic, and treatment-related data were systematically collected. Survival outcomes were estimated using the Kaplan–Meier approach, while factors associated with prognosis were examined through Cox proportional hazards models. Results: The study population consisted of 68 patients, predominantly male (86.8%), with a mean age of 63.4 ± 8.7 years. According to the Lung Immune Prognostic Index classification, 29 patients (42.6%) were categorized as having a good score, 27 (39.7%) as intermediate, and 12 (17.6%) as poor. During a median follow-up of 15.4 months, a total of 40 progressions and 22 deaths occurred. Median EFS was 17.7, 9.4, and 5.8 months for good, intermediate, and poor LIPI groups, respectively (p < 0.001). Median OS was 25.7 months in the good LIPI group, was not reached in the intermediate group due to insufficient events, and was 6.7 months in the poor group (p < 0.001). In multivariate Cox analysis, poor LIPI was independently associated with inferior survival (EFS: HR = 2.87, 95% CI: 1.85–4.46, p < 0.001; OS: HR = 2.59, 95% CI: 1.40–4.78, p = 0.002). Conclusions: LIPI calculated at diagnosis is an independent prognostic factor for both EFS and OS in stage III NSCLC. Validation in larger, prospective cohorts is warranted to further define its prognostic role in stage III NSCLC.
- Open Access
- 15 December 2025
- Published by Springer Nature in BMC Cancer
- Vol. 25 (1) , 1869
BMI and PNI as predictors of treatment completion and survival in locally advanced HNSCC receiving sequential chemoradiotherapy
This study aimed to evaluate the clinical and laboratory factors affecting treatment response and treatment tolerance in patients diagnosed with head and n
- 15 December 2025
- Published by Springer Nature in BMC Cancer
- Vol. 25 (1) , 1869
Open AccessBMI and PNI as predictors of treatment completion and survival in locally advanced HNSCC receiving sequential chemoradiotherapy
This study aimed to evaluate the clinical and laboratory factors affecting treatment response and treatment tolerance in patients diagnosed with head and n
- Open Access
- 16 September 2025
- Published by Journal of Health Sciences and Medicine in Journal of Health Sciences and Medicine
- Vol. 8 (5) , 747-753
Prognostic value of Systemic Immune-Inflammation Index in head and neck cancer
Aims: This study aimed to evaluate the prognostic value of the Systemic Immune-Inflammation Index (SII) in patients with head and neck cancer and its association with survival outcomes including disease-free survival (DFS) and overall survival (OS). Methods: The patients diagnosed with head and neck cancer were retrospectively analyzed. Patients were stratified into two groups based on the SII cut-off value (796): low SII (L-SII) and high SII (H-SII). Clinical, demographic, and treatment-related parameters were compared between the groups. Kaplan-Meier survival analysis and Cox regression were used for univariate and multivariate analyses of DFS and OS. Results: Of the total number of patients included in the study (n=184), 67 with high SII (≥796) exhibited significantly higher recurrence rates (43.3% vs. 8.5%, p
- 16 September 2025
- Published by Journal of Health Sciences and Medicine in Journal of Health Sciences and Medicine
- Vol. 8 (5) , 747-753
Open AccessPrognostic value of Systemic Immune-Inflammation Index in head and neck cancer
Aims: This study aimed to evaluate the prognostic value of the Systemic Immune-Inflammation Index (SII) in patients with head and neck cancer and its association with survival outcomes including disease-free survival (DFS) and overall survival (OS). Methods: The patients diagnosed with head and neck cancer were retrospectively analyzed. Patients were stratified into two groups based on the SII cut-off value (796): low SII (L-SII) and high SII (H-SII). Clinical, demographic, and treatment-related parameters were compared between the groups. Kaplan-Meier survival analysis and Cox regression were used for univariate and multivariate analyses of DFS and OS. Results: Of the total number of patients included in the study (n=184), 67 with high SII (≥796) exhibited significantly higher recurrence rates (43.3% vs. 8.5%, p
- Open Access
- 28 July 2025
- Published by Anatolian Current Medical Journal in Anatolian Current Medical Journal
- Vol. 7 (4) , 513-517
Prognostic value of the CALLY index in De Novo metastatic colorectal cancer: a retrospective study
Aims: The CALLY index, integrating C-reactive protein (CRP), albumin, and lymphocyte count, has been identified as a promising prognostic biomarker in various cancers. The present study aims to evaluate its prognostic significance in De Novo metastatic colorectal cancer (mCRC). Methods: A retrospective analysis was conducted on 108 patients diagnosed with de novo mCRC at Ankara Etlik City Hospital (2021–2024). The CALLY index was calculated from baseline laboratory values and dichotomized at the median (0.2018). Progression-free survival (PFS) and overall survival (OS) were compared between low and high CALLY groups using the Kaplan–Meier method and log-rank test. The associations between the CALLY index and tumour location, as well as RAS/BRAF mutation status, were evaluated using the chi-square test. Cox regression analyses were also performed to determine independent prognostic factors. Results: Patients with elevated CALLY scores exhibited significantly prolonged median PFS (24.0 vs. 13.0 months; p
- 28 July 2025
- Published by Anatolian Current Medical Journal in Anatolian Current Medical Journal
- Vol. 7 (4) , 513-517
Open AccessPrognostic value of the CALLY index in De Novo metastatic colorectal cancer: a retrospective study
Aims: The CALLY index, integrating C-reactive protein (CRP), albumin, and lymphocyte count, has been identified as a promising prognostic biomarker in various cancers. The present study aims to evaluate its prognostic significance in De Novo metastatic colorectal cancer (mCRC). Methods: A retrospective analysis was conducted on 108 patients diagnosed with de novo mCRC at Ankara Etlik City Hospital (2021–2024). The CALLY index was calculated from baseline laboratory values and dichotomized at the median (0.2018). Progression-free survival (PFS) and overall survival (OS) were compared between low and high CALLY groups using the Kaplan–Meier method and log-rank test. The associations between the CALLY index and tumour location, as well as RAS/BRAF mutation status, were evaluated using the chi-square test. Cox regression analyses were also performed to determine independent prognostic factors. Results: Patients with elevated CALLY scores exhibited significantly prolonged median PFS (24.0 vs. 13.0 months; p
- Open Access
- 1 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-12
Comparison of AI chatbot predicted and realworld survival outcomes in hepatocellular carcinoma
This study compares survival predictions made by an artificial intelligence (AI) based chatbot with real-world data in hepatocellular carcinoma (HCC) patients. It aims to evaluate the reliability and accuracy of AI technologies in HCC prognosis. A retrospective analysis was conducted on patients diagnosed with HCC. The estimated survival times for each patient were calculated using an artificial intelligence chatbot. The follow-up periods and mortality data for the patients were used to obtain real-life survival data. The predicted and actual survival times were statistically compared. ChatGPT-4o consistently overestimated the overall survival (OS) times compared to real-world outcomes.A statistically significant discrepancy was observed between the predicted and actual survival times (p < 0.05). Nevertheless, while the survival predictions of AI were more accurate in patients with advanced-stage HCC, the predictions differed significantly in patients with early-stage HCC. AI has the potential to play an important role in the prognosis of complex diseases such as HCC. However, this study’s findings indicate that AI’s predictions are not entirely consistent with real-world data, particularly in the context of early-stage diseases. Further large-scale studies may enhance the dependability of incorporating AI into clinical decision-support systems. The use of AI-assisted predictions may prove to be a valuable tool for the prediction of survival in patients with HCC. Nevertheless, further studies are required to substantiate the accuracy and reliability of these systems before they can be implemented in clinical practice.
- 1 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-12
Open AccessComparison of AI chatbot predicted and realworld survival outcomes in hepatocellular carcinoma
This study compares survival predictions made by an artificial intelligence (AI) based chatbot with real-world data in hepatocellular carcinoma (HCC) patients. It aims to evaluate the reliability and accuracy of AI technologies in HCC prognosis. A retrospective analysis was conducted on patients diagnosed with HCC. The estimated survival times for each patient were calculated using an artificial intelligence chatbot. The follow-up periods and mortality data for the patients were used to obtain real-life survival data. The predicted and actual survival times were statistically compared. ChatGPT-4o consistently overestimated the overall survival (OS) times compared to real-world outcomes.A statistically significant discrepancy was observed between the predicted and actual survival times (p < 0.05). Nevertheless, while the survival predictions of AI were more accurate in patients with advanced-stage HCC, the predictions differed significantly in patients with early-stage HCC. AI has the potential to play an important role in the prognosis of complex diseases such as HCC. However, this study’s findings indicate that AI’s predictions are not entirely consistent with real-world data, particularly in the context of early-stage diseases. Further large-scale studies may enhance the dependability of incorporating AI into clinical decision-support systems. The use of AI-assisted predictions may prove to be a valuable tool for the prediction of survival in patients with HCC. Nevertheless, further studies are required to substantiate the accuracy and reliability of these systems before they can be implemented in clinical practice.