Use of ChatGPT in Pediatric Urology and its Relevance in Clinical Practice: Is it useful?
Notice bibliographique
Résumé
Abstract Introduction Artificial intelligence (AI) can be described as the combination of computer sciences and linguistics, objective building machines capable of performing various tasks that otherwise would need Human Intelligence. One of the many AI based tools that has gained popularity is the Chat-Generative Pre-Trained Transformer (ChatGPT). Due to the popularity and its massive media coverage, incorrect and misleading information provided by ChatGPT will have a profound impact on patient misinformation. Furthermore, it may cause mistreatment and misdiagnosis as ChatGPT can mislead physicians on the decision-making pathway. Objective Eevaluate and assess the accuracy and reproducibility of ChatGPT answers regarding common pediatric urological diagnoses. Methods ChatGPT 3.5 version was used. The questions asked for the program involved Primary Megaureter (pMU), Enuresis and Vesicoureteral Reflux (VUR). There were three queries for each topic, adding up to 9 in total. The queries were inserted into ChatGPT twice, and both responses were recorded to examine the reproducibility of ChatGPT’s answers. After that analysis, both questions were combined, forming a single answer. Afterwards, those responses were evaluated qualitatively by a board of three specialists with a deep expertise in the field. A descriptive analysis was performed. Results ChatGPT demonstrated general knowledge on the researched topics, including the definition, diagnosis, and treatment of Enuresis, VUR and pMU. Regarding Enuresis, the provided definition was partially correct, as the generic response allowed for misinterpretation. As for the definition of VUR, the response was considered appropriate. And for pMU it was partially correct, lacking essential aspects of its definition such as the diameter of the dilatation of the ureter. Unnecessary exams were suggested, for both Enuresis and pMU. Regarding the treatment of the conditions mentioned, it specified treatments to Enuresis that are known to be ineffective, such as bladder training. Discussion AI has a wide potential to bring several benefits to medical knowledge, improving decision-making and patient education. However, following the reports on the literature, we found a lack of genuine clinical experience and judgment from ChatGPT, performing well in less complex questions, yet with a steep decrease on its performance as the complexity of the queries increase. Therefore, providing wrong answers to crucial topics. Conclusion ChatGPT responses present a combination of accurate and relevant information, but also incomplete, ambiguous and, occasionally, misleading details, especially regarding the treatment of the investigated diseases. Because of that, it is not recommended to make clinical decisions based exclusively on ChatGPT.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,030 | 0,180 |
| Méta-épidémiologie (sens strict) | 0,000 | 0,000 |
| Méta-épidémiologie (sens large) | 0,001 | 0,001 |
| Bibliométrie | 0,003 | 0,003 |
| Études des sciences et des technologies | 0,001 | 0,001 |
| Communication savante | 0,002 | 0,002 |
| Science ouverte | 0,001 | 0,002 |
| Intégrité de la recherche | 0,001 | 0,001 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,004 | 0,001 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».