Ağrıda yapay zekâ: Kapsamlı bir derleme

Öz

Ağrı, yüksek yaygınlığı ve yaşam kalitesi üzerindeki önemli olumsuz etkisi nedeniyle dünya çapında büyük bir halk sağlığı sorunudur. Yapay zekâ (YZ) tabanlı sohbet robotları, sağlıkla ilgili bilgilere erişmek için giderek daha fazla kullanılmaktadır; ancak, bu sistemler tarafından sağlanan ağrı ile ilgili bilgilerin okunabilirliği, kalitesi, güvenilirliği ve klinik uygulama kılavuzlarıyla uyumu hakkındaki kanıtlar sınırlı ve heterojendir. Bu derleme, ağrı alanında YZ tabanlı sohbet robotları tarafından üretilen yanıtları okunabilirlik, bilgi kalitesi, güvenilirlik ve klinik uygulama kılavuzlarına uyum açısından değerlendiren mevcut literatürü kapsamlı bir şekilde incelemeyi amaçlamıştır. 2024 ve 2025 yılları arasında yayınlanan ve YZ sohbet robotlarının ağrı ile ilgili sorulara verdiği yanıtları değerlendiren çalışmalar analiz edildi. ChatGPT, Gemini, Perplexity, DeepSeek ve diğer büyük dil modelleri değerlendirildi. Okunabilirlik, Flesch Okuma Kolaylığı, Flesch-Kincaid Sınıf Düzeyi ve SMOG endeksleri kullanılarak değerlendirilirken, bilgi kalitesi ve güvenilirliği DISCERN, JAMA Kriterleri, EQIP ve Küresel Kalite Puanı kullanılarak değerlendirildi. Klinik kılavuzlara uyum, ilgili ulusal ve uluslararası önerilerle karşılaştırmalar yoluyla incelendi. İncelenen çalışmalar, yapay zekâ modellerinin genel olarak ağrı hakkında doğru temel bilgiler sağladığını göstermiştir. Bununla birlikte, çoğu yanıt, hasta eğitim materyalleri için önerilen okunabilirlik seviyelerini aşmıştır. Bilgi kalitesi ve güvenilirliği genellikle orta düzeyde olarak değerlendirilmiş olup, tedavi riskleri, alternatif seçenekler ve kaynak şeffaflığı tartışmalarında eksiklikler bildirilmiştir. Klinik kılavuzlara uyum genel prensipler düzeyinde kabul edilebilir olsa da, tanısal ayrıntılarda ve tedavi sıralamasında tutarsızlıklar tespit edilmiştir. Yapay zekâ tabanlı sohbet robotları, ağrı ile ilgili bilgiler için destekleyici araçlar olarak potansiyel gösterse de, klinik karar verme veya birincil hasta eğitimi için bağımsız kaynaklar olarak mevcut kullanımları sınırlıdır. Bu sistemlerin güvenli kullanımı için insan gözetimi ve sağlık okuryazarlığına uygun içerik üretimi şarttır.

Anahtar Kelimeler

• Ağrı
• yapay zekâ
• sohbet botları
• sağlık okuryazarlığı
• okunabilirlik
• kalite değerlendirmesi

Artificial intelligence in pain: A comprehensive review

Öz

Pain is a major public health problem worldwide due to its high prevalence and substantial negative impact on quality of life. Artificial intelligence (AI)-based chatbots are increasingly used to access health-related information; however, evidence regarding the readability, quality, reliability, and alignment of pain-related information provided by these systems with clinical practice guidelines remains limited and heterogeneous. This review aimed to comprehensively examine the existing literature evaluating responses generated by AI-based chatbots in the field of pain with respect to readability, information quality, reliability, and adherence to clinical practice guidelines. Studies published between 2024 and 2025 that assessed AI chatbot responses to pain-related questions were analyzed. ChatGPT, Gemini, Perplexity, DeepSeek, and other large language models were evaluated. Readability was assessed using the Flesch Reading Ease, Flesch-Kincaid Grade Level, and SMOG indices, while information quality and reliability were evaluated using DISCERN, the JAMA Benchmark Criteria, EQIP, and the Global Quality Score. Adherence to clinical guidelines was examined through comparisons with relevant national and international recommendations. The reviewed studies demonstrated that AI models generally provide accurate basic information about pain. However, most responses exceeded the recommended readability levels for patient education materials. Information quality and reliability were typically rated as moderate, with reported deficiencies in the discussion of treatment risks, alternative options, and source transparency. Although adherence to clinical guidelines was acceptable at the level of general principles, inconsistencies were identified in diagnostic details and treatment sequencing. While AI-based chatbots show potential as supportive tools for pain-related information, their current use as independent sources for clinical decision-making or primary patient education is limited. Human oversight and the generation of health literacy-appropriate content are essential for the safe use of these systems.

Anahtar Kelimeler

• Pain
• artificial intelligence
• chatbots
• health literacy
• readability
• quality assessment

Kaynakça

1. Zimmer Z, Fraser K, Grol-Prokopczyk H, Zajacova A. A global study of pain prevalence across 52 countries: examining the role of country-level contextual factors. Pain. 2022;163(9):1740-1750. https://doi.org/10.1097/j.pain.0000000000002557
2. Breivik H, Eisenberg E, O’Brien T; OPENMinds. The individual and societal burden of chronic pain in Europe: the case for strategic prioritisation and action to improve knowledge and availability of appropriate care. BMC Public Health. 2013 Dec 24;13:1229. https://doi.org/10.1186/1471-2458-13-1229.
3. Rice ASC, Smith BH, Blyth FM. Pain and the global burden of disease. Pain. 2016;157(4):791-6. https://doi.org/10.1097/j.pain.0000000000000454.
4. Yong RJ, Mullins PM, Bhattacharyya N. Prevalence of chronic pain among adults in the United States.  Pain. 2022;163(2):e328-e332. https://doi.org/10.1097/j.pain.0000000000002291
5. Eti Aslan F, Çınar F. Prevalence of pain in adult population in Türkiye. Agri. 2023;35(2):83-95. https://doi.org/10.14744/agri.2022.26086
6. Özbek İC. Evaluation of the Quality, Reliability, and Popularity of YouTube Videos on Thoracic Outlet Syndrome: A Critical Analysis. Journal of Physical Medicine and Rehabilitation Sciences. 2025;28(3):207-17
7. Ozduran E, Hanci V, Erkin Y. Evaluating the readability, quality and reliability of online patient education materials on chronic low back pain. Natl Med J India. 2024;37(3):124-130. https://doi.org/10.25259/NMJI_327_2022
8. Özbek İC. Evaluation of Artificial Intelligence-Supported Osteoarthritis Information Texts: Content Quality and Readability Analysis. Journal of Physical Medicine and Rehabilitation Sciences. 2025;28(1):21-9.

9. Ensari E, Onder ENA, Ertan P. A Comparative Assessment of Large Language Models in Pediatric Dialysis: Reliability, Quality and Readability. Ther Apher Dial. 2025 Oct;29(5):739-746. https://doi.org/10.1111/1744-9987.70058.
10. Hamet P, Tremblay J. Artificial intelligence in medicine. Metabolism. 2017;69S:S36-S40. https://doi.org/10.1016/j.metabol.2017.01.011
11. Bashah A, Salem A, Al-Waqeerah A, Ghaleb E, Wahan N, Awad A,, et al. Evaluation of deepseek, gemini, ChatGPT-4o, and perplexity in responding to salivary gland cancer. BMC Oral Health. 2025;25(1):1358. https://doi.org/10.1186/s12903-025-06726-4
12. Özbek İC, Hancı V, Özduran E. Digital Guidance: Quality and Readability Analysis of Artificial Intelligence-Generated Spondyloarthropathy Texts. Turk J Osteoporos. 2025;31(1):12-18. https://doi.org/10.4274/tod.galenos.2024.76743
13. Anıl H, Kayra MV. The digital dialogue on premature ejaculation: evaluating the efficacy of artificial intelligence-driven responses. Int Urol Nephrol. 2025 Sep;57(9):2829-2836. https://doi.org/10.1007/s11255-025-04461-x.
14. Hopkins AM, Logan JM, Kichenadasse G, Sorich MJ. Artificial intelligence chatbots will revolutionize how cancer patients access information: ChatGPT represents a paradigm-shift. JNCI Cancer Spectr. 2023;7(2):pkad010. https://doi.org/10.1093/jncics/pkad010
15. Özbek İC, Özduran E. Digital Rehabilitation in Parkinson’s Disease: The Role of Artificial Intelligence-Assisted Exercise Training. Turk J Osteoporos. Published online Sep 12, 2025. https://doi.org/10.4274/tod.galenos.2025.66664
16. Topan H, Baydoğan GM, Sürme Y. Revolutionizing patient care: assessing ai-created discharge education for total hip replacement patients. BMC Med Educ. 2025 Nov 24;25(1):1636. https://doi.org/10.1186/s12909-025-08186-4.
17. Shiferaw MW, Zheng T, Winter A, Mike LA, Chan LN. Assessing the accuracy and quality of artificial intelligence (AI) chatbot-generated responses in making patient-specific drug-therapy and healthcare-related decisions. BMC Med Inform Decis Mak. 2024;24(1):404. https://doi.org/10.1186/s12911-024-02824-5
18. Kara M, Ozduran E, Kara MM, Özbek İC, Hancı V. Evaluating the readability, quality, and reliability of responses generated by ChatGPT, Gemini, and Perplexity on the most commonly asked questions about Ankylosing spondylitis. PLoS One. 2025 Jun 18;20(6):e0326351. https://doi.org/10.1371/journal.pone.0326351.
19. Abeo ANA, Armstrong S, Scriney M, Goss H. Artificial Intelligence Techniques and Health Literacy: A Systematic Review. Mayo Clin Proc Digit Health. 2025;3(4):100269. https://doi.org/10.1016/j.mcpdig.2025.100269
20. Gokalp MG, Yucel SC. Comparative analysis of nursing care plans produced by artificial intelligence models (ChatGPT, Gemini, and DeepSeek) in terms of readability, reliability, and quality. BMC Nurs. 2026 Jan 12. https://doi.org/10.1186/s12912-026-04295-7.
21. Ozduran E, Akkoc I, Büyükçoban S, Erkin Y, Hanci V. Readability, reliability and quality of responses generated by ChatGPT, Gemini, and Perplexity for the most frequently asked questions about pain. Medicine (Baltimore). 2025;104(11):e41780. https://doi.org/10.1097/MD.0000000000041780.
22. Ozduran E, Hancı V, Erkin Y, Özbek İC, Abdulkerimov V. Assessing the readability, quality and reliability of responses produced by ChatGPT, Gemini, and Perplexity regarding most frequently asked keywords about low back pain. PeerJ. 2025;13:e18847. https://doi.org/10.7717/peerj.18847.
23. Scaff SPS, Reis FJJ, Ferreira GE, Jacob MF, Saragiotto BT. Assessing the performance of AI chatbots in answering patients’ common questions about low back pain. Ann Rheum Dis. 2025;84(1):143-149. https://doi.org/10.1136/ard-2024-226202.
24. Tabanli A, Demirkiran ND. Comparing ChatGPT 3.5 and 4.0 in low back pain patient education: addressing strengths, limitations, and psychosocial challenges. World Neurosurg. 2025;196:123755. https://doi.org/10.1016/j.wneu.2025.123755.
25. Rossettini G, Bargeri S, Cook C, Guida S, Palese A, Rodeghiero L, et al. Accuracy of ChatGPT-3.5, ChatGPT-4o, Copilot, Gemini, Claude, and Perplexity in advising on lumbosacral radicular pain against clinical practice guidelines. Front Digit Health. 2025;7:1574287. https://doi.org/10.3389/fdgth.2025.1574287.
26. Gianola S, Bargeri S, Castellini G, Cook C, Palese A, Pillastrini P, et al. Performance of ChatGPT compared to clinical practice guidelines in making informed decisions for lumbosacral radicular pain. J Orthop Sports Phys Ther. 2024;54(3):222-228. https://doi.org/10.2519/jospt.2024.12151.
27. Deng J, Qiu X, Dong C, Xu L, Dong X, Yang S, et al. Evaluating ChatGPT and DeepSeek in postdural puncture headache management: a comparative study with international consensus guidelines. BMC Neurol. 2025;25(1):264. https://doi.org/10.1186/s12883-025-04280-8.
28. Lo Bianco G, Cascella M, Natoli S, D’Angelo FP, Sinagra E, Marchesini M, et al. Assessing artificial intelligence-powered responses to common patient questions on radiofrequency ablation and cryoanalgesia for chronic pain. J Clin Med. 2025;14(19):6814. https://doi.org/10.3390/jcm14196814.
29. Yücel K, Sutcuoglu O, Yazıcı O, Ozet A, Ozdemir N. Can artificial intelligence provide accurate and reliable answers to cancer patients’ questions about cancer pain? Comparison of chatbots based on ESMO cancer pain guideline. memo. 2024;17(4):302-306.
30. García-Rudolph A, Sanchez-Pinsach D, Opisso E, Soler MD. Exploring new educational approaches in neuropathic pain: assessing accuracy and consistency of artificial intelligence responses from GPT-3.5 and GPT-4. Pain Med. 2025;26(1):48-50. https://doi.org/10.1093/pm/pnae094.
31. Ateş Demiroglu SB, Özpolat Bulut Ö, Bağcier F. AI-powered insights: analyzing ChatGPT’s responses on myofascial pain syndrome. J Bodyw Mov Ther. 2025;44:558-563. https://doi.org/10.1016/j.jbmt.2025.05.043. PMID:40954629.
32. Brant-Zawadzki G, Klapthor B, Ryba C, Youngquist DC, Burton B, Palatinus H, et al. The performance of ChatGPT-4 and Gemini Ultra 1.0 for quality assurance review in emergency medical services chest pain calls. Prehosp Emerg Care. 2025;29(3):210-217. https://doi.org/10.1080/10903127.2024.2376757.
33. Aljamani S, Hassona Y, Fansa HA, M Saadeh H, Dafi Jamani K.. Evaluating large language models in addressing patient questions on endodontic pain. J Endod. 2025;51(11):1617-1624. https://doi.org/10.1016/j.joen.2025.04.015.
34. Mohammad-Rahimi H, Ourang SA, Pourhoseingholi MA, Dianat O, Dummer PMH, Nosrat A. Validity and reliability of artificial intelligence chatbots as public sources of information on endodontics. Int Endod J. 2024;57(3):305-314. https://doi.org/10.1111/iej.14014.
35. Degirmencioglu D, Temel AN. Evaluation of the quality and readability of ChatGPT responses to toothache queries. Cureus. 2025;17(11):e96436. https://doi.org/10.7759/cureus.96436.
36. Gondode P, Duggal S, Garg N, Sethupathy S, Asai O, Lohakare P. Comparing patient education tools for chronic pain medications: artificial intelligence chatbot versus traditional patient information leaflets. Indian J Anaesth. 2024;68(7):631-636.
37. Basharat A, Shah R, Wilcox N, Tur G, Tripati S, Kansal P, et al. ChatGPT and low back pain - Evaluating AI-driven patient education in the context of interventional pain medicine. Interv Pain Med. 2025 Sep 2;4(3):100636. https://doi.org/10.1016/j.inpm.2025.100636.
38. Dong C, Qiu X, Deng J, Xu L, Dong X, Chen S, et al. Comparative evaluation of large language models in delivering guideline-compliant recommendations for topical NSAID use in musculoskeletal pain: a multidimensional analysis. Clin Rheumatol. 2025 Nov;44(11):4703-4710. https://doi.org/10.1007/s10067-025-07640-4.
39. Ah-Yan C, Boissonnault È, Boudier-Revéret M, Mares C. Impact of artificial intelligence in managing musculoskeletal pathologies in physiatry: a qualitative observational study evaluating the potential use of ChatGPT versus Copilot for patient information and clinical advice on low back pain. J Yeungnam Med Sci. 2025;42:11. https://doi.org/10.12701/jyms.2024.01151.
40. Özduran E. “Bel Ağrısı” ile İlgili Türkçe İnternet Kaynaklı Hasta Eğitim Materyallerinin Okunabilirliklerinin Değerlendirilmesi. DEU Tıp Derg. 01 Ağustos 2022;36(2):135-50. https://doi.org/10.18614/deutip.1174522
41. Gonzalez Fiol A, Mootz AA, He Z, Delgado C, Ortiz V, Reale SC. Accuracy of Spanish and English-generated ChatGPT responses to commonly asked patient questions about labor epidurals: a survey-based study among bilingual obstetric anesthesia experts. Int J Obstet Anesth. 2025;61:104290. https://doi.org/10.1016/j.ijoa.2024.104290. Epub 2024 Nov 6.
42. Wang S, Chi X, Hao Q, Wang H, Tao H, Xiao J, et al. Large language models in Chinese anesthesiology residency examinations: a comparative analysis of performance, reliability and clinical reasoning. BMC Med Educ. 2026 Jan 31;26(1):348. https://doi.org/10.1186/s12909-026-08704-y.
43. Madwi FHM. Integrating artificial intelligence in Arabic language education: challenges and opportunities. Dzil Majaz J Arab Lit. 2025;3(1):45-55.
44. Bagcier F, Yurdakul OV, Ozduran E. Top 100 cited articles on ankylosing spondylitis. Reumatismo. 2021;72(4):218-227. https://doi.org/10.4081/reumatismo.2020.1325