Advantages and pitfalls in utilizing artificial intelligence for crafting medical examinations: a medical education pilot study with GPT-4.


Journal

BMC medical education
ISSN: 1472-6920
Titre abrégé: BMC Med Educ
Pays: England
ID NLM: 101088679

Informations de publication

Date de publication:
17 Oct 2023
Historique:
received: 06 07 2023
accepted: 07 10 2023
medline: 23 10 2023
pubmed: 18 10 2023
entrez: 17 10 2023
Statut: epublish

Résumé

The task of writing multiple choice question examinations for medical students is complex, timely and requires significant efforts from clinical staff and faculty. Applying artificial intelligence algorithms in this field of medical education may be advisable. During March to April 2023, we utilized GPT-4, an OpenAI application, to write a 210 multi choice questions-MCQs examination based on an existing exam template and thoroughly investigated the output by specialist physicians who were blinded to the source of the questions. Algorithm mistakes and inaccuracies, as identified by specialists were classified as stemming from age, gender or geographical insensitivities. After inputting a detailed prompt, GPT-4 produced the test rapidly and effectively. Only 1 question (0.5%) was defined as false; 15% of questions necessitated revisions. Errors in the AI-generated questions included: the use of outdated or inaccurate terminology, age-sensitive inaccuracies, gender-sensitive inaccuracies, and geographically sensitive inaccuracies. Questions that were disqualified due to flawed methodology basis included elimination-based questions and questions that did not include elements of integrating knowledge with clinical reasoning. GPT-4 can be used as an adjunctive tool in creating multi-choice question medical examinations yet rigorous inspection by specialist physicians remains pivotal.

Sections du résumé

BACKGROUND BACKGROUND
The task of writing multiple choice question examinations for medical students is complex, timely and requires significant efforts from clinical staff and faculty. Applying artificial intelligence algorithms in this field of medical education may be advisable.
METHODS METHODS
During March to April 2023, we utilized GPT-4, an OpenAI application, to write a 210 multi choice questions-MCQs examination based on an existing exam template and thoroughly investigated the output by specialist physicians who were blinded to the source of the questions. Algorithm mistakes and inaccuracies, as identified by specialists were classified as stemming from age, gender or geographical insensitivities.
RESULTS RESULTS
After inputting a detailed prompt, GPT-4 produced the test rapidly and effectively. Only 1 question (0.5%) was defined as false; 15% of questions necessitated revisions. Errors in the AI-generated questions included: the use of outdated or inaccurate terminology, age-sensitive inaccuracies, gender-sensitive inaccuracies, and geographically sensitive inaccuracies. Questions that were disqualified due to flawed methodology basis included elimination-based questions and questions that did not include elements of integrating knowledge with clinical reasoning.
CONCLUSION CONCLUSIONS
GPT-4 can be used as an adjunctive tool in creating multi-choice question medical examinations yet rigorous inspection by specialist physicians remains pivotal.

Identifiants

pubmed: 37848913
doi: 10.1186/s12909-023-04752-w
pii: 10.1186/s12909-023-04752-w
pmc: PMC10580534
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

772

Informations de copyright

© 2023. BioMed Central Ltd., part of Springer Nature.

Références

Nature. 2023 Jan;613(7944):423
pubmed: 36635510
Science. 2023 Jan 27;379(6630):313
pubmed: 36701446
Acad Med. 2022 Mar 1;97(3S):S90-S97
pubmed: 34817404
JMIR Med Educ. 2023 Feb 8;9:e45312
pubmed: 36753318
CMAJ. 2010 Mar 23;182(5):524
pubmed: 20231338
Pak J Med Sci. 2023 Mar-Apr;39(2):605-607
pubmed: 36950398
PLOS Digit Health. 2023 Feb 9;2(2):e0000198
pubmed: 36812645

Auteurs

Klang E (K)

The Sami Sagol AI Hub, ARC Innovation Center, Chaim Sheba Medical Center. Affiliated to the Faculty of Medicine, Tel-Aviv University, Ramat Aviv, Israel.

Portugez S (P)

Silesia Medical University, Katowice, Poland.

Gross R (G)

Division of Psychiatry, the Chaim Sheba Medical Center, Tel-Hashomer, Ramat Gan, Israel. Affiliated to the Faculty of Medicine, Tel-Aviv University, Ramat Aviv, Israel.

Kassif Lerner R (KL)

Department of Pediatric Intensive Care, The Edmond and Lily Safra Children's' Hospital, Chaim Sheba Medical Center. Affiliated to the Faculty of Medicine, Tel-Aviv University, Ramat Aviv, Israel.

Brenner A (B)

Obstetrics and Gynecology Division, Chaim Sheba Medical Center. Affiliated to the Faculty of Medicine, Tel-Aviv University, Ramat Aviv, Israel.

Gilboa M (G)

Infection Prevention and Control Unit, Chaim Sheba Medical Center. Affiliated to the Faculty of Medicine, Tel-Aviv University, Ramat Aviv, Israel.

Ortal T (O)

Education Authority, Chaim Sheba Medical Center. Affiliated to the Faculty of Medicine, Tel-Aviv University, Ramat Aviv, Israel.

Ron S (R)

Education Authority, Chaim Sheba Medical Center. Affiliated to the Faculty of Medicine, Tel-Aviv University, Ramat Aviv, Israel.

Robinzon V (R)

Education Authority, Chaim Sheba Medical Center. Affiliated to the Faculty of Medicine, Tel-Aviv University, Ramat Aviv, Israel.

Meiri H (M)

Department of Surgery and Transplantation B, Chaim Sheba Medical Center. Affiliated to the Faculty of Medicine, Tel-Aviv University, Ramat Aviv, Israel.

Segal G (S)

Infection Prevention and Control Unit, Chaim Sheba Medical Center. Affiliated to the Faculty of Medicine, Tel-Aviv University, Ramat Aviv, Israel. Gad.segal@sheba.health.gov.il.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH