Journals / Journal of Medicine and Palliative Care / 2026 / Volume: 6 Issue: 5

Comparison of chemotherapy informed consent forms written by humans and artificial intelligence: exploring the potential of AI-assisted health communication

İnsan ve yapay zeka tarafından hazırlanan kemoterapi onam formlarının okunabilirlik açısından karşılaştırılması: yapay zeka destekli sağlık iletişiminin potansiyeli

Tuğçe Uskur(Deparment of Medical Pharmacology, Faculty of Medicine, Kırklareli University)0000-0001-6626-4859
Bahar Arıcan Tarım(UNIVERSITY OF HEALTH SCIENCES, İSTANBUL KARTAL DR. LÜTFİ KIRDAR HEALTH RESEARCH CENTER)0000-0002-6017-3259
Pages
—
Publication Date
2025-10-24
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

These findings suggest that AI may serve as a supportive tool in simplifying medical texts and enhancing patient communication-particularly in information-dense fields such as pharmacology.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Aims: Informed consent is a legal requirement prior to chemotherapy treatment, and its readability is critical to ensuring that patients are adequately informed before undergoing a therapy associated with significant side effects and complications.
📊
Key Findings & Data:This study aimed to compare the readability levels of informed consent documents for chemotherapy, authored by a human and generated by artificial intelligence (AI), in both their original Turkish versions and English translations.
💡
Conclusion & Impact:These findings suggest that AI may serve as a supportive tool in simplifying medical texts and enhancing patient communication-particularly in information-dense fields such as pharmacology.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Chemotherapy · informed consent · readability

Abstract

Aims: Informed consent is a legal requirement prior to chemotherapy treatment, and its readability is critical to ensuring that patients are adequately informed before undergoing a therapy associated with significant side effects and complications. This study aimed to compare the readability levels of informed consent documents for chemotherapy, authored by a human and generated by artificial intelligence (AI), in both their original Turkish versions and English translations. Methods: This in silico study evaluated two chemotherapy informed consent forms: one written by a healthcare professional currently used at Kartal Dr. Lütfi Kırdar City Hospital, and the other generated using the GPT-4 language model. Both forms were assessed in their original Turkish versions and in their English translations. Readability of the Turkish texts was measured using the Ateşman index, while the English versions were evaluated using the Flesch-Kincaid grade level (FKGL) formula. Results: The human-written Turkish form had an Ateşman score of 62.2, corresponding to the 9th–10th grade reading level, while the AI-generated Turkish form had a slightly higher score of 65.7, also indicating a 9th–10th grade readability level. In the English versions, the human-authored form scored 16.56 on the FKGL scale, representing a "college graduate" reading level and classified as “extremely difficult”. In contrast, the AI-generated form scored 14.07, corresponding to a “college junior” level and classified as “professional” in terms of reading difficulty. Conclusion: Although both forms require advanced reading skills, the AI-generated documents were found to be shorter, more concise, and had higher readability scores. These findings suggest that AI may serve as a supportive tool in simplifying medical texts and enhancing patient communication-particularly in information-dense fields such as pharmacology.

Özet

Amaç: Bilgilendirilmiş onam, kemoterapi tedavisi öncesi yasal bir gereklilik olup, hastaların bu yüksek yan etki ve komplikasyona sahip tedavi öncesi bilinçli olması bakımından okunabilirliği önemlidir. Bu çalışmada insan ve yapay zeka tarafından oluşuturulmuş kemoterapi için bilgilendirilmiş onam belgelerinin Türkçe ve İngilizce çevirilerinin okuabilirlik düzeyleri karşılaştırılmıştır. Yöntemler: Çalışma in-silico gerçekleştirilmiş olup, Kartal Dr. Lütfi Kırdar Şehir Hastanesinde kullanılan insan tarafından yazılmış bir kemoterapi onam formu ile GPT-4 modeli aracılığıyla yapay zeka tarafından oluşturulmuş benzer yapıda bir onam formunun hem Türkçe hem de İngilizceye çevrilmiş versiyonları değerlendirilmiştir. Türkçe metinlerin okunabilirliği Ateşman İndeksi, İngilizce metinlerin okunabilirliği ise Flesch-Kincaid Grade Level (FKGL) formülü ile ölçülmüştür. Bulgular: İnsan tarafından yazılmış Türkçe formun Ateşman skoru 62,2 (9–10. sınıf düzeyi), GPT-4 tarafından oluşturulan Türkçe formun ise 65,7 (9–10. sınıf düzeyi) olarak bulunmuştur. İngilizce versiyonlarda ise insan yazımı form 16,56 FKGL puanıyla “üniversite mezunu” seviyesinde ve “son derece zor” okunabilirlik düzeyindeyken; GPT-4 formu 14,07 FKGL puanıyla “üniversite 3. sınıf” seviyesinde ve “profesyonel” düzeyde sınıflandırılmıştır. Sonuç: Her iki form da yüksek okuma becerisi gerektirse de, GPT-4 tarafından oluşturulan formlar daha kısa, daha sade ve daha yüksek okunabilirlik puanlarına sahip bulunmuştur. Bu sonuçlar, tıbbi metinlerin sadeleştirilmesi ve hasta iletişiminin güçlendirilmesinde yapay zekanın, farmakoloji gibi yüksek bilgi yoğunluğu gerektiren alanlarda destekleyici bir araç olarak kullanılabileceğini göstermektedir.

🔖

Cite This Article

Uskur, T., Tarım, B. A. (2025). Comparison of chemotherapy informed consent forms written by humans and artificial intelligence: exploring the potential of AI-assisted health communication. Journal of Medicine and Palliative Care, Volume: 6 Issue: 5. https://doi.org/10.47582/jompac.1757913

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (20)

  1. Kara İ, Kökoğlu K, Şan F. Orhan İ. Türkiye’de KBB hastalıkları alanında sık kullanılan onam formlarının okunabilirliklerinin değerlendirilmesi. KBBForum. 2020;19(2):153-160.
  2. Borello A, Ferrarese A, Passera R, et al. Use of a simplified consent form to facilitate patient understanding of informed consent for laparoscopic cholecystectomy. Open Med. 2016;11(1):564-573. doi:10.1515/med-2016-0092
  3. Ören E, Eren CS, Yeşildere FB, Erdoğan N. Kontrast maddelere ait aydınlatılmış onam formlarının anlaşılabilirlik düzeyi ve hasta anksiyetesi üzerine etkisi. Tepecik Eğitim Hastan Derg. 2010;20(3):122-130. doi:10.5222/terh.2010.43760
  4. Reuter SR. An overview of informed consent for radiologists. AJR Am J Roentgenol. 1987;148(1):219-227. doi:10.2214/ajr.148.1.219
  5. Güzeldemir ME. Hasta bilgilendirmenin önemi. Sendrom. 2005;17(5): 36-53.
  6. Michels D, Cahill M. Informed consent and chemotherapy. J Oncol Pract. 2005;1(3):99. doi:10.1200/JOP.2005.1.3.99
  7. National Cancer Institute (NCI). Cancer treatment and its side effects. https://www.cancer.gov/about-cancer/treatment/side-effects
  8. Nurgali K, Jagoe RT, Abalo R. Editorial: adverse effects of cancer chemotherapy: anything new to improve tolerance and reduce sequelae? Front Pharmacol. 201822;9:245. doi:10.3389/fphar.2018.00245
  9. Boztas N, Ozbilgin S, Ocmen E, et al. Evaluating the readibility of informed consent forms available before anaesthesia: a comparative study. Turkish J Anesth Reanim. 2014;42(3):140-144. doi:10.5152/TJAR. 2014.94547
  10. Klare GR. Measures of the readability of written communication: an evaluation. J Educ Psychol. 1952;43(7):385-399. doi:10.1037/h0058972
  11. Kozahan B, Tutar MS. Readability of patient education texts presented on the internet in the field of anesthesiology. Turkiye Klin J Anesthesiol Reanim. 2017;15(2):63-70.
  12. Kattih M, Bressler M, Smith LR, Schinelli A, Mhaskar R, Hanna K. Artificial intelligence-prompted explanations of common primary care diagnoses. PRiMER. 2024;8:51. doi:10.22454/PRiMER.2024.916089
  13. Ateşman, E. Türkçe’de okunabilirliğin ölçülmesi. Dil Dergisi. 1997;58: 71-74.
  14. Hardy M, Harvey H. Artificial intelligence in diagnostic imaging: impact on the radiography profession. Br J Radiol. 2020;93(1108):20190840. doi: 10.1259/bjr.20190840
  15. Restrepo E, Ko N, Warner ET. An evaluation of readability and understandability of online education materials for breast cancer survivors. J Cancer Surviv. 2024;18(2):457-465. doi:10.1007/s11764-022- 01240-w
  16. Coolbrandt A, Van den Heede K, Clemens K, et al. The Leuven questionnaire for patient self-care during chemotherapy (L-PaSC): instrument development and psychometric evaluation. Eur J Oncol Nurs. 2013;17(3):275-283. doi:10.1016/j.ejon.2012.07.008
  17. Prutipinyo C, Maikeow K, Sirichotiratana N. Selfcare behaviours of chemotherapy patients. J Med Assoc Thai. 2012;95(Suppl 6):30-37.
  18. García-Álvarez JM, García-Sánchez A. Readability of informed consent forms for medical and surgical clinical procedures: a systematic review. Clin Pract. 2025;15(2):26. doi:10.3390/clinpract15020026
  19. Türker Kader İ, Arıcan B. Comparing the readability of human- and AI-written informed consent forms for provisional dental restorations. J Health Sci Med. 2025;8(4):697-702. doi:10.32322/jhsm.1700777
  20. Vaira LA, Lechien JR, Maniaci A, et al. Evaluating AI-generated informed consent documents in oral surgery: a comparative study of ChatGPT-4, Bard gemini advanced, and human-written consents. J Craniomaxillofac Surg. 2025;53(1):18-23. doi:10.1016/j.jcms.2024.10.002