Personality Changes and Staring Spells in a 12-Year-Old Child: A Case Report Incorporating ChatGPT, a Natural Language Processing Tool Driven by Artificial Intelligence (AI)

Abstract

Low grade gliomas (LGGs) are the most common type of brain tumors diagnosed in children. The presentation of intracranial tumors in pediatric patients is varied and diverse. The early identification and treatment of LGGs are important to achieve favorable outcomes. Although personality changes can be a symptom of intracranial tumors, they are rarely the only main presenting feature. In addition to central nervous system (CNS) tumors, personality changes can be associated with psychological and endocrine conditions, contributing to a broad differential diagnosis. Because symptoms such as personality changes have the potential to be missed, communication between family members and clinicians is imperative to identify these symptoms early. We report the case of a 12-year-old child who presented with personality changes as her main symptom and was found to have an intracranial neoplasm. This case report integrates original author writing with output from ChatGPT, a natural language processing tool driven by artificial intelligence (AI). In addition to the case itself, this report will explore the benefits and drawbacks of using natural language AI in this context.

Popular large language model chatbots’ accuracy, comprehensiveness, and self-awareness in answering ocular symptom queries

“… 1 , 2 The user-friendly interfaces of LLMs have propelled their popularity and facilitated their extensive adoption across diverse healthcare settings. 3 Their versatility extends to various clinical applications, 4 including supporting clinical decision-making, 5 , 6 , 7 generating medical documentation, 8 , 9 , 10 and assisting in diagnosis. 11 , 12 , 13 , 14 , 15 , 16 …”

Assessing the research landscape and clinical utility of large language models: a scoping review

“…But who should be involved in these discussions in the first place? Multiple of our extracted articles highlighted the importance of consulting various stakeholders for the successful implementation of LLMs in healthcare [ 16 , 20 ]. Key stakeholders include clinical informaticians, developers, healthcare providers, policymakers, industry representatives, and civil society as a whole [ 75 ].…”

A Systematic Review of ChatGPT and Other Conversational Large Language Models in Healthcare

“…ChatGPT has been shown to be effective in summarizing medical documents for a diverse set of applications [13,14], including tasks such as adapting clinical guidelines for diagnosis, treatment, and disease management [15], summarizing medical notes [16][17][18], assisting in writing medical case reports [19][20][21][22][23][24], and generating and translating radiological reports [18,25]. Notably, efforts have been made to integrate ChatGPT-4 1 with "Link Reader" for automating medical text synthesis [26], which boosted model performance in providing answers according to clinical guidelines [26].…”

“…Second, ChatGPT struggled to interpret all the coherent laboratory tests [60], generating superficial and incorrect responses. Indeed, ChatGPT could generate overly general answers without citing original references [20,40,42].…”