Importance: The time to accurately diagnose rare pediatric diseases often spans years. Assessing the diagnostic accuracy of an LLM-based tool on real pediatric cases can help reduce this time, providing quicker diagnoses for patients and their families. Objective: To evaluate the clinical utility of DxGPT as a support tool for differential diagnosis of both common and rare diseases. Design: Unicentric descriptive cross-sectional exploratory study. Anonymized data from 50 pediatric patients’ medical histories, covering common and rare pathologies, were used to generate clinical case notes. Each clinical case included essential data, with some expanded by complementary tests. Setting: This study was conducted at a reference pediatric hospital, Sant Joan de Déu Barcelona Children’s Hospital. Participants: A total of 50 clinical cases were diagnosed by 78 volunteer doctors (medical diagnostic team) with varying experience, each reviewing 3 clinical cases. Interventions: Each clinician listed up to five diagnoses per clinical case note. The same was done on the DxGPT web platform, obtaining the Top-5 diagnostic proposals. To evaluate DxGPT’s variability, each note was queried three times. Main Outcome(s) and Measure(s): The study mainly focused on comparing diagnostic accuracy, defined as the percentage of cases with the correct diagnosis, between the medical diagnostic team and DxGPT. Other evaluation criteria included qualitative assessments. The medical diagnostic team also completed a survey on their user experience with DxGPT. Results: Top-5 diagnostic accuracy was 65% for clinicians and 60% for DxGPT, with no significant differences. Accuracies for common diseases were higher (Clinicians: 79%, DxGPT: 71%) than for rare diseases (Clinicians: 50%, DxGPT: 49%). Accuracy increased similarly in both groups with expanded information, but this increase was only stastitically significant in clinicians (simple 52% vs. expanded 69%; p =0.03). DxGPT’s response variability affected less than 5% of clinical case notes. A survey of 48 clinicians rated the DxGPT platform 3.9/5 overall, 4.1/5 for usefulness, and 4.5/5 for usability. Conclusions and Relevance: DxGPT showed diagnostic accuracies similar to medical staff from a pediatric hospital, indicating its potential for supporting differential diagnosis in other settings. Clinicians praised its usability and simplicity. These tools could provide new insights for challenging diagnostic cases. Key Points: Question: Is DxGPT, a large language model-based (LLM-based) tool, effective for differential diagnosis support, specifically in the context of a clinical pediatric setting? Findings: In this unicentric cross-sectional study, diagnostic accuracy, measured as the proportion of clinical cases where any of the five diagnostic options included the correct diagnosis, showed comparable results between clinicians and DxGPT. Top-5 accuracy was 65% for clinicians and 60% for DxGPT. Meaning: These findings highlight the potential of LLM-based tools like DxGPT to support clinicians in making accurate and timely diagnoses, ultimately improving patient care.

Background: Hospital-at-home (HAH) programs deliver hospital-level care in patients’ homes, improving satisfaction and optimizing resource use. While widely adopted in adults, pediatric HAH remains limited. At Sant Joan de Déu Hospital (Barcelona, Spain), the pediatric HAH program for acutely ill children has expanded to include more clinically complex cases. Family involvement is essential, as caregivers are trained to administer treatments, monitor clinical status, and support telematic follow-ups, supporting the healthcare team’s workload. Objective: To identify patient characteristics influencing healthcare workload and develop a predictive model to enhance resource allocation. Methods: This single-center, prospective cohort study included all patients admitted to the pediatric HAH program for one year. Primary variables were caregiver training time, home visiting time, patient age, type of care provided, and clinical complexity. Secondary variables included referral specialty and team composition. Data were collected using digital time-tracking, manual records, and clinical databases. Analyses included Kruskal–Wallis and Dunn’s multiple comparison tests. Results: All variables showed significant differences in training and visiting times. Training time ranged from 19 to 157 min; visiting time from 6.2 to 157 min. A predictive model using five key variables estimated visiting time, and another model based on care type estimated training time were created. Conclusions: Patient characteristics and caregiver involvement significantly affect direct care workload. These findings can inform strategies to optimize staffing and scale pediatric HAH programs effectively.