Kidney and liver transplantation are two sub-specialized medical disciplines, with transplant professionals spending decades in training. While artificial intelligence-based (AI-based) tools could potentially assist in everyday clinical practice, comparative assessment of their effectiveness in clinical decision-making remains limited.

To compare the use of ChatGPT and GPT-4 as potential tools in AI-assisted clinical practice in these challenging disciplines.

In total, 400 different questions tested ChatGPT’s/GPT-4 knowledge and decision-making capacity in various renal and liver transplantation concepts. Specifically, 294 multiple-choice questions were derived from open-access sources, 63 questions were derived from published open-access case reports, and 43 from unpublished cases of patients treated at our department. The evaluation covered a plethora of topics, including clinical predictors, treatment options, and diagnostic criteria, among others.

ChatGPT correctly answered 50.3% of the 294 multiple-choice questions, while GPT-4 demonstrated a higher performance, answering 70.7% of questions (P < 0.001). Regarding the 63 questions from published cases, ChatGPT achieved an agreement rate of 50.79% and partial agreement of 17.46%, while GPT-4 demonstrated an agreement rate of 80.95% and partial agreement of 9.52% (P = 0.01). Regarding the 43 questions from unpublished cases, ChatGPT demonstrated an agreement rate of 53.49% and partial agreement of 23.26%, while GPT-4 demonstrated an agreement rate of 72.09% and partial agreement of 6.98% (P = 0.004). When factoring by the nature of the task for all cases, notably, GPT-4 demonstrated outstanding performance, providing a differential diagnosis that included the final diagnosis in 90% of the cases (P = 0.008), and successfully predicting the prognosis of the patient in 100% of related questions (P < 0.001).

GPT-4 consistently provided more accurate and reliable clinical recommendations with higher percentages of full agreements both in renal and liver transplantation compared with ChatGPT. Our findings support the potential utility of AI models like ChatGPT and GPT-4 in AI-assisted clinical practice as sources of accurate, individualized medical information and facilitating decision-making. The progression and refinement of such AI-based tools could reshape the future of clinical practice, making their early adoption and adaptation by physicians a necessity.

• Artificial intelligence
• ChatGPT
• GPT-4
• Transplantation
• Kidney
• Liver
• Clinical decision support
• Generative artificial intelligence

• Allograft kidneys
• clear cell renal cell carcinoma
• end-stage renal disease
• kidney transplantation
• renal cell carcinoma
• renal transplant recipients

Patient: Female, 30-year-old

Final Diagnosis: Chromophobe renal cell carcinoma

Symptoms: Pain

Medication: —

Clinical Procedure: —

Specialty: Transplantology

There are few reported cases of allograft nephrectomy due to malignancy followed by successful renal re-transplantation two years later. In this paper, we report a patient who underwent kidney re-transplantation after living donor graft nephrectomy due to de novo chromophobe renal cell carcinoma (ChRCC) involving the allograft kidney.

A 34-year-old man underwent living kidney transplantation at the age of 22 years for end-stage renal disease. Maintenance immunosuppression consisted of tacrolimus, mycophenolate mofetil (MMF), and prednisone. Six years post-transplantation, at another hospital, ultrasonography revealed a small mass involving the upper pole of the graft. The patient declined further examination and treatment at this point. Seven years and three months post-transplantation, the patient experienced decreasing appetite, weight loss, gross hematuria, fatigue, and oliguria. Laboratory tests showed anemia (hemoglobin level was 53 g/L). Contrast-enhanced computed tomography revealed a large heterogeneous cystic-solid mass involving the upper pole of the renal allograft. Graft nephrectomy was performed and immunosuppressants were withdrawn. Histological and immunohistochemical features of the tumor were consistent with ChRCC. One year after allograft nephrectomy, low doses of tacrolimus and MMF were administered for preventing allosensitization. Two years after allograft nephrectomy, the patient underwent kidney re-transplantation. Graft function remained stable with no ChRCC recurrence in more than 2-years of follow-up.

De novo ChRCC in kidney graft generally has a good prognosis after graft nephrectomy and withdrawal of immunosuppression. Kidney re-transplantation could be a viable treatment. A 2-year malignancy-free period may be sufficient time before re-transplantation.

• Chromophobe
• Renal cell carcinoma
• Kidney
• Nephrectomy
• Transplantation
• Case report