Khon Kaen Hospital

In addition to the Human Leukocyte Antigen B*58:01(HLA-B*58:01), several non-genetic factors have been associated with allopurinol hypersensitivity syndrome, particularly severe cutaneous adverse drug reactions (SCAR), which are clinically serious. However, the magnitude of the impact of these non-genetic factors on the development of SCAR remains unclear. This study aimed to develop a non-genetic risk prediction model for predicting allopurinol-induced SCAR. This retrospective observational study was performed during the same time period. SCAR cases were collected from tertiary care hospital centers, while the non-SCAR cases were collected from primary and tertiary care hospital centers. Non-genetic factors including sex, age, renal function, concomitant use of diuretics, starting dose of allopurinol, and serum urate (SU) were used for the development of the prediction models. Of the 23,294 cases, 209 were SCAR and 23,085 were non-SCAR cases. Three risk stratification models were developed. Models 1A and 1B were applied for patients who did not have and had SU level at the time of starting allopurinol, respectively. Model 2 was applied for patients who had all non-genetic risk factors, started allopurinol within 60 days, but had not yet developed SCAR. The area under the receiver operating characteristic curve for Models 1A, 1B, and 2 was 0.73 (95

Dengue virus (DENV) infection is a major global health problem. While DENV infection rarely results in serious complications, the more severe illness dengue hemorrhagic fever (DHF) has a significant mortality rate due to the associated plasma leakage that may lead to hypovolemic shock. Proper care thus requires identifying patients with DHF among those with suspected dengue so that they can be provided with adequate and prompt fluid replacement. In this study we used seventeen years of pediatric patient data from a prospective cohort study in two hospitals in Thailand to develop models to predict DHF among patients with suspected dengue infection. We produced models for a general hospital setting and for a primary care unit setting lacking lab facilities. The best model using combined data from both hospitals achieved an AUC of 0.90 for the general hospital setting and 0.79 for the primary care unit setting. We then investigated the generalizability of the models by training models with data from one hospital and testing them with data from the other. For some models, we found a significant reduction in performance. Possible sources of this are differences in how attributes are defined or measured and differences in the hematological parameters of the two patient populations. We conclude that while high accuracy prediction of DHF is possible, care must be taken when applying DHF predictive models from one clinical setting to another.

Gestational diabetes mellitus affects approximately 14% of pregnancies worldwide. Especially in Thailand, the prevalence reaches 29.2%, among the highest in Southeast Asia, because access to personalized nutritional counseling remains limited, particularly in Thai-language healthcare settings. This study developed and validated a Thai-language multi-agent conversational platform comprising a Passive Agent for trimester-aware dietary and health information retrieval and an Active Agent for proactive dietary monitoring and glucose management through multi-turn interactions. The system is aimed to support patient education and self-management. We validated our system through task-specific assessments. The Passive Agent was assessed by ten healthcare professionals across nutrition, gestational diabetes mellitus, and antenatal care domains using accuracy, source attribution, Global Quality Score, trimester-specific appropriateness, response repeatability, and inter-rater reliability. The Active Agent was validated on 125 nutritionist-curated food items for carbohydrate estimation accuracy and consistency against nutritionist-established ground truth. Passive Agent achieved the highest accuracy in gestational diabetes mellitus (88–96%), followed by nutrition (88%) and general antenatal care (68–72%), with question-level accuracy of 84%. Global Quality Score and trimester-specific appropriateness were highest in nutrition, and response repeatability exceeded the threshold (mean cosine similarity 0.855). Active Agent achieved 92.8% carbohydrate estimation accuracy within 0.5 exchanges, a mean absolute error of 0.107 ± 0.234 exchanges, and a coefficient of variation below 10% for 98.4% of items, with no significant difference from nutritionist ground truth. These findings demonstrate the feasibility and expert-rated quality of a RAG-based agentic conversational prototype, supporting future testing with real patients in full RCT experiments before consideration as a national maternal healthcare tool.

Background:Despite the clinical importance of brain sparing in fetal growth restriction (FGR), current data on the specific patterns of brain growth trajectory in early-onset FGR (EO-FGR) remain sparse. Methods:A multicenter prospective longitudinal study was conducted between November 2024 and February 2026. Three-dimensional tomographic ultrasound imaging was used to measure brain parameters in 36 pregnant women with EO-FGR and 36 with appropriate-for-gestational-age (AGA) fetuses at three time points: 26-28, 30-32, and 34-36 weeks of gestation. Results:The EO-FGR group initially showed delayed growth in normalized cavum septi pellucidi length (CSPL') at GA 30-32 weeks compared with the AGA group, with values of 0.03 ± 0.001 and 0.03 ± 0.01, respectively (P-value = 0.007). Further significant reductions were observed in the EO-FGR group at a GA of 34-36 weeks in the CSPL' (0.03 ± 0.01 vs 0.04 ± 0.01, P-value < 0.001), normalized CSP width (0.03 ± 0.01 vs 0.03 ± 0.01, P-value < 0.001), and normalized occipitofrontal diameter (0.32 ± 0.09 vs 0.35 ± 0.01, P-value = 0.031). Conclusion:The cavum septi pellucidi and occipitofrontal diameter may serve as early structural indicators of brain growth trajectory in EO-FGR. However, larger cohort studies are needed to validate these findings and correlate them with post-natal imaging and long-term outcomes.