Faculty Bibliography

With the advent of Large Language Models (LLMs) like ChatGPT, the integration of Generative Artificial Intelligence (GAI) into clinical medicine is becoming increasingly feasible. This study aimed to evaluate the ability of the freely available ChatGPT-3.5 to generate complex differential diagnoses, comparing its output to case records of the Massachusetts General Hospital published in the New England Journal of Medicine (NEJM). Forty case records were presented to ChatGPT-3.5, prompting it to provide a differential diagnosis and then narrow it down to the most likely diagnosis. The results indicated that the final diagnosis was included in ChatGPT-3.5's original differential list in 42.5% of the cases. After narrowing, ChatGPT correctly determined the final diagnosis in 27.5% of the cases, demonstrating a decrease in accuracy compared to previous studies using common chief complaints. These findings emphasize the necessity for further investigation into the capabilities and limitations of LLMs in clinical scenarios while highlighting the potential role of GAI as an augmented clinical opinion. Anticipating the growth and enhancement of GAI tools like ChatGPT, physicians and other healthcare workers will likely find increasing support in generating differential diagnoses. However, continued exploration and regulation are essential to ensure the safe and effective integration of GAI into healthcare practice. Future studies may seek to compare newer versions of ChatGPT or investigate patient outcomes with physicians integrating this GAI technology. Understanding and expanding GAI's capabilities, particularly in differential diagnosis, may foster innovation and provide additional resources, especially in underserved areas in the medical field.

Point of care ultrasound (POCUS) is rapidly expanding throughout the United States. Due to its ability to quickly and accurately diagnose and guide therapy for critical conditions, POCUS is becoming routine in many specialties, with established guidelines in fields such as emergency medicine and critical care 1, 2, 3. For example, a study entitled "Ultrasound Integration in Undergraduate Medical Education: Comparison of Ultrasound Proficiency Between Trained and Untrained Medical Students" initiated an Emergency Medicine POCUS curriculum for first-year medical students that showed an increase in ultrasound capability 4. In short, as POCUS becomes more common practice, medical schools are beginning to implement POCUS training into their undergraduate medical education; studies from these institutions demonstrate that implementing a formal ultrasound curriculum into preclinical medical education significantly increases medical students' POCUS capabilities4, 5 and assisted in their understanding and learning of anatomy 6, 7.

A 26 year old nulligravida presented at 24 weeks gestation for the second opinion of abnormal fetal profile and mid-face views on ultrasound at another institution. A detailed fetal anatomic ultrasound at our facility revealed the absence of fetal lens and globes bilaterally consistent with bilateral anophthalmia (HP: 0000528) without other anomalies. Karyotype and chromosomal microarray analysis were completed from amniocentesis sample. After these results, duo exome testing with paternal sequencing was completed from proband amniotic fluid sample and parental blood samples. A pathogenic variant in SOX2 (NM_003106.3: c.513C>G p.(Tyr171*Ter)) with heterozygous autosomal dominant inheritance resulted. On duo exome testing with paternal segregation analysis, the variant was found to be consistent with likely sporadic de novo inheritance. The SOX2 variant reported is consistent with the fetal phenotype in this case. While germline mosaicism could exist, this identified variant provided the family with a likely explanation for this proband's finding. This ultrasound and genetic testing allowed the family to make decisions related to planning in current and future pregnancies.

This commentary examines how ChatGPT can assist healthcare teams in the prenatal diagnosis of rare and complex cases by creating a differential diagnoses based on deidentified clinical findings, while also acknowledging its limitations.