@article{antaki_evaluating_2023,
	title = {Evaluating the {Performance} of {ChatGPT} in {Ophthalmology}: {An} {Analysis} of its {Successes} and {Shortcomings}},
	url = {https://www.proquest.com/working-papers/evaluating-performance-chatgpt-ophthalmology/docview/2768841875/se-2},
	doi = {10.1101/2023.01.22.23284882},
	abstract = {We tested the accuracy of ChatGPT, a large language model (LLM), in the ophthalmology question-answering space using two popular multiple choice question banks used for the high-stakes Ophthalmic Knowledge Assessment Program (OKAP) exam. The testing sets were of easy-to-moderate difficulty and were diversified, including recall, interpretation, practical and clinical decision-making problems. ChatGPT achieved 55.8\% and 42.7\% accuracy in the two 260-question simulated exams. Its performance varied across subspecialties, with the best results in general medicine and the worst in neuro-ophthalmology and ophthalmic pathology and intraocular tumors. These results are encouraging but suggest that specialising LLMs through domain-specific pre-training may be necessary to improve their performance in ophthalmic subspecialties.},
	language = {English},
	journal = {MedRxiv},
	author = {Antaki, Fares and Touma, Samir and Milad, Daniel and El-Khoury, Jonathan and Duval, Renaud},
	month = jan,
	year = {2023},
	note = {Place: Cold Spring Harbor
Publisher: Cold Spring Harbor Laboratory Press},
	keywords = {Medical Sciences, Decision making},
	annote = {Copyright - © 2023. This article is published under http://creativecommons.org/licenses/by-nd/4.0/ (“the License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.},
	annote = {Última actualización - 2023-01-27},
}

{"_id":"9WqL92KnCY9kDk4hf","bibbaseid":"antaki-touma-milad-elkhoury-duval-evaluatingtheperformanceofchatgptinophthalmologyananalysisofitssuccessesandshortcomings-2023","author_short":["Antaki, F.","Touma, S.","Milad, D.","El-Khoury, J.","Duval, R."],"bibdata":{"bibtype":"article","type":"article","title":"Evaluating the Performance of ChatGPT in Ophthalmology: An Analysis of its Successes and Shortcomings","url":"https://www.proquest.com/working-papers/evaluating-performance-chatgpt-ophthalmology/docview/2768841875/se-2","doi":"10.1101/2023.01.22.23284882","abstract":"We tested the accuracy of ChatGPT, a large language model (LLM), in the ophthalmology question-answering space using two popular multiple choice question banks used for the high-stakes Ophthalmic Knowledge Assessment Program (OKAP) exam. The testing sets were of easy-to-moderate difficulty and were diversified, including recall, interpretation, practical and clinical decision-making problems. ChatGPT achieved 55.8% and 42.7% accuracy in the two 260-question simulated exams. Its performance varied across subspecialties, with the best results in general medicine and the worst in neuro-ophthalmology and ophthalmic pathology and intraocular tumors. These results are encouraging but suggest that specialising LLMs through domain-specific pre-training may be necessary to improve their performance in ophthalmic subspecialties.","language":"English","journal":"MedRxiv","author":[{"propositions":[],"lastnames":["Antaki"],"firstnames":["Fares"],"suffixes":[]},{"propositions":[],"lastnames":["Touma"],"firstnames":["Samir"],"suffixes":[]},{"propositions":[],"lastnames":["Milad"],"firstnames":["Daniel"],"suffixes":[]},{"propositions":[],"lastnames":["El-Khoury"],"firstnames":["Jonathan"],"suffixes":[]},{"propositions":[],"lastnames":["Duval"],"firstnames":["Renaud"],"suffixes":[]}],"month":"January","year":"2023","note":"Place: Cold Spring Harbor Publisher: Cold Spring Harbor Laboratory Press","keywords":"Medical Sciences, Decision making","annote":"Última actualización - 2023-01-27","bibtex":"@article{antaki_evaluating_2023,\n\ttitle = {Evaluating the {Performance} of {ChatGPT} in {Ophthalmology}: {An} {Analysis} of its {Successes} and {Shortcomings}},\n\turl = {https://www.proquest.com/working-papers/evaluating-performance-chatgpt-ophthalmology/docview/2768841875/se-2},\n\tdoi = {10.1101/2023.01.22.23284882},\n\tabstract = {We tested the accuracy of ChatGPT, a large language model (LLM), in the ophthalmology question-answering space using two popular multiple choice question banks used for the high-stakes Ophthalmic Knowledge Assessment Program (OKAP) exam. The testing sets were of easy-to-moderate difficulty and were diversified, including recall, interpretation, practical and clinical decision-making problems. ChatGPT achieved 55.8\\% and 42.7\\% accuracy in the two 260-question simulated exams. Its performance varied across subspecialties, with the best results in general medicine and the worst in neuro-ophthalmology and ophthalmic pathology and intraocular tumors. These results are encouraging but suggest that specialising LLMs through domain-specific pre-training may be necessary to improve their performance in ophthalmic subspecialties.},\n\tlanguage = {English},\n\tjournal = {MedRxiv},\n\tauthor = {Antaki, Fares and Touma, Samir and Milad, Daniel and El-Khoury, Jonathan and Duval, Renaud},\n\tmonth = jan,\n\tyear = {2023},\n\tnote = {Place: Cold Spring Harbor\nPublisher: Cold Spring Harbor Laboratory Press},\n\tkeywords = {Medical Sciences, Decision making},\n\tannote = {Copyright - © 2023. This article is published under http://creativecommons.org/licenses/by-nd/4.0/ (“the License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.},\n\tannote = {Última actualización - 2023-01-27},\n}\n\n","author_short":["Antaki, F.","Touma, S.","Milad, D.","El-Khoury, J.","Duval, R."],"key":"antaki_evaluating_2023","id":"antaki_evaluating_2023","bibbaseid":"antaki-touma-milad-elkhoury-duval-evaluatingtheperformanceofchatgptinophthalmologyananalysisofitssuccessesandshortcomings-2023","role":"author","urls":{"Paper":"https://www.proquest.com/working-papers/evaluating-performance-chatgpt-ophthalmology/docview/2768841875/se-2"},"keyword":["Medical Sciences","Decision making"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/network/files/22WYpzbBvi3hDHX7Y","dataSources":["cYu6uhMkeFHgRrEty","hLMh7bwHyFsPNWAEL","LKW3iRvnztCpLNTW7","TLD9JxqHfSQQ4r268","X9BvByJrC3kGJexn8","iovNvcnNYDGJcuMq2","NjZJ5ZmWhTtMZBfje"],"keywords":["medical sciences","decision making"],"search_terms":["evaluating","performance","chatgpt","ophthalmology","analysis","successes","shortcomings","antaki","touma","milad","el-khoury","duval"],"title":"Evaluating the Performance of ChatGPT in Ophthalmology: An Analysis of its Successes and Shortcomings","year":2023}