COMPARATIVE EVALUATION OF ARTIFICIAL INTELLIGENCE AND DRUG INTERACTION TOOLS: A PERSPECTIVE WITH THE EXAMPLE OF CLOPIDOGREL

Zinnet Şevval Aksoyalp; Betül Rabia Erdoğan

Makale detayları

COMPARATIVE EVALUATION OF ARTIFICIAL INTELLIGENCE AND DRUG INTERACTION TOOLS: A PERSPECTIVE WITH THE EXAMPLE OF CLOPIDOGREL

Yazarlar:

Zinnet Şevval Aksoyalp | Betül Rabia Erdoğan

Yayıncı:

Ankara University

Ana Başlıklar:

Klinik Farmakoloji ve Terapötikler

Dergi:

Ankara Üniversitesi Eczacılık Fakültesi Dergisi Vol.48 Issue 3, pp.1011-1020

Belge Tipi:

Makale

Yayın Tarihi:

10/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001319073

pISSN:

1015-3918

Anahtar kelimeler:

Özet:

 Objective: The study aims to compare the ability of free artificial intelligence AI chatbots to detect drug interactions with freely available drug interaction tools, using clopidogrel as an example. Material and Method: The Lexicomp database was used as a reference to determine drug interactions with clopidogrel. ChatGPT-3.5 AI and Bing AI were selected as the free AI chatbots. Medscape Drug Interaction Checker, DrugBank Drug Interaction Checker and Epocrates Interaction Check were selected as free drug interaction tools. Accuracy score and comprehensiveness score were calculated for each drug interaction tool and AI chatbots. The kappa coefficient was calculated to assess inter-source agreement for interaction severity. Result and Discussion: The results most similar to those of Lexicomp were obtained from the DrugBank and the ChatGPT-3.5 AI chatbot. The ChatGPT-3.5 AI chatbot performed best, with 69 correct results and an accuracy score of 307. ChatGPT-3.5 AI has the highest overall score of 387 points for accuracy and comprehensiveness. In addition, the highest kappa coefficient with Lexicomp was found for ChatGPT-3.5 AI chatbot 0.201, fair agreement. However, some of the results obtained by ChatGPT-3.5 AI need to be improved as they are incorrectinadequate. Therefore, information obtained using AI tools should not be used as a reference for clinical applications by healthcare professionals and patients should not change their treatment without consulting doctor.

 Objective: The study aims to compare the ability of free artificial intelligence AI chatbots to detect drug interactions with freely available drug interaction tools, using clopidogrel as an example. Material and Method: The Lexicomp database was used as a reference to determine drug interactions with clopidogrel. ChatGPT-3.5 AI and Bing AI were selected as the free AI chatbots. Medscape Drug Interaction Checker, DrugBank Drug Interaction Checker and Epocrates Interaction Check were selected as free drug interaction tools. Accuracy score and comprehensiveness score were calculated for each drug interaction tool and AI chatbots. The kappa coefficient was calculated to assess inter-source agreement for interaction severity. Result and Discussion: The results most similar to those of Lexicomp were obtained from the DrugBank and the ChatGPT-3.5 AI chatbot. The ChatGPT-3.5 AI chatbot performed best, with 69 correct results and an accuracy score of 307. ChatGPT-3.5 AI has the highest overall score of 387 points for accuracy and comprehensiveness. In addition, the highest kappa coefficient with Lexicomp was found for ChatGPT-3.5 AI chatbot 0.201, fair agreement. However, some of the results obtained by ChatGPT-3.5 AI need to be improved as they are incorrectinadequate. Therefore, information obtained using AI tools should not be used as a reference for clinical applications by healthcare professionals and patients should not change their treatment without consulting doctor.

 Objective: The study aims to compare the ability of free artificial intelligence AI chatbots to detect drug interactions with freely available drug interaction tools, using clopidogrel as an example. Material and Method: The Lexicomp database was used as a reference to determine drug interactions with clopidogrel. ChatGPT-3.5 AI and Bing AI were selected as the free AI chatbots. Medscape Drug Interaction Checker, DrugBank Drug Interaction Checker and Epocrates Interaction Check were selected as free drug interaction tools. Accuracy score and comprehensiveness score were calculated for each drug interaction tool and AI chatbots. The kappa coefficient was calculated to assess inter-source agreement for interaction severity. Result and Discussion: The results most similar to those of Lexicomp were obtained from the DrugBank and the ChatGPT-3.5 AI chatbot. The ChatGPT-3.5 AI chatbot performed best, with 69 correct results and an accuracy score of 307. ChatGPT-3.5 AI has the highest overall score of 387 points for accuracy and comprehensiveness. In addition, the highest kappa coefficient with Lexicomp was found for ChatGPT-3.5 AI chatbot 0.201, fair agreement. However, some of the results obtained by ChatGPT-3.5 AI need to be improved as they are incorrectinadequate. Therefore, information obtained using AI tools should not be used as a reference for clinical applications by healthcare professionals and patients should not change their treatment without consulting doctor.

 Amaç: Çalışmanın amacı, klopidogrel örneğini kullanarak ücretsiz yapay zekâ AI sohbet robotlarının ilaç etkileşimlerini saptama yeteneklerini ücretsiz olarak erişilebilen ilaç etkileşim araçları ile karşılaştırmaktır. Gereç ve Yöntem: Klopidogrel ile ilaç etkileşimlerini belirlemek için referans veri tabanı olarak Lexicomp kullanılmıştır. Ücretsiz yapay zekâ sohbet robotları olarak ChatGPT-3.5 AI ve Bing AI, ücretsiz ilaç etkileşim araçları olarak ise Medscape Drug Interaction Checker, DrugBank Drug Interaction Checker ve Epocrates Interaction Check seçilmiştir. Her bir ilaç etkileşim aracı ve yapay zekâ sohbet robotu için doğruluk puanı ve kapsamlılık puanı hesaplanmıştır. Etkileşim şiddeti açısından kaynaklar arası uyumu değerlendirmek için kappa katsayısı hesaplanmıştır. Sonuç ve Tartışma: Lexicomp veri tabanına en benzer sonuçlar Drugbank ve ChatGPT-3.5 AI sohbet robotundan elde edilmiştir. ChatGPT-3.5 AI sohbet robotunun 69 doğru sonuç ve 307 doğruluk puanı ile en yüksek sonuçlara sahip olduğu bulunmuştur. Doğruluk ve kapsamlılık açısından 387 puanla en yüksek toplam puan ChatGPT-3.5 AI sohbet robotu sonuçları ile elde edilmiştir. Ayrıca Lexicomp ile en yüksek kappa skoru 0.201, orta düzey uyum ChatGPT-3.5 AI chatbot için bulunmuştur. Ancak ChatGPT-3.5 AI ile elde edilen sonuçlardan bazılarının yanlışyetersiz bulunması nedeniyle iyileştirilmesine ihtiyaç vardır. Sonuç olarak yapay zekâ araçlarından yararlanılarak elde edilen bilgiler sağlık profesyonelleri tarafından klinik uygulamalar için referans olarak kullanılmamalı ve hastalar doktora danışmadan tedavilerini değiştirmemelidir.

Makale detayları

COMPARATIVE EVALUATION OF ARTIFICIAL INTELLIGENCE AND DRUG INTERACTION TOOLS: A PERSPECTIVE WITH THE EXAMPLE OF CLOPIDOGREL

Yazarlar:

Zinnet Şevval Aksoyalp | Betül Rabia Erdoğan

Yayıncı:

Ankara University

Ana Başlıklar:

Klinik Farmakoloji ve Terapötikler

Dergi:

Ankara Üniversitesi Eczacılık Fakültesi Dergisi Vol.48 Issue 3, pp.1011-1020

Belge Tipi:

Makale

Yayın Tarihi:

10/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001319073

pISSN:

1015-3918

Artificial intelligence

clopidogrel

drug interactions

patient safety

pharmaceutical databasesHasta güvenliği

ilaç etkileşimleri

ilaç veri tabanları

klopidogrel

yapay zekâ

Sayı

Makale detayları

Yazarlar: Zinnet Şevval Aksoyalp | Betül Rabia Erdoğan

Yayıncı: Ankara University

Ana Başlıklar: Klinik Farmakoloji ve Terapötikler

Dergi: Ankara Üniversitesi Eczacılık Fakültesi Dergisi Vol.48 Issue 3, pp.1011-1020

Belge Tipi: Makale

Yayın Tarihi: 10/2024

Belge Dili: İngilizce

Document ID (Org No.): 2001319073

pISSN: 1015-3918

Sayı

Yazarlar:

Zinnet Şevval Aksoyalp | Betül Rabia Erdoğan

Yayıncı:

Ankara University

Ana Başlıklar:

Klinik Farmakoloji ve Terapötikler

Dergi:

Ankara Üniversitesi Eczacılık Fakültesi Dergisi Vol.48 Issue 3, pp.1011-1020

Belge Tipi:

Makale

Yayın Tarihi:

10/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001319073

pISSN:

1015-3918