Background Fluid assessment is challenging, and fluid overload poses a significant problem among dialysis patients, with pulmonary oedema being the most serious consequence. Our study aims to develop a simple objective fluid assessment strategy using lung ultrasound (LUS) and artificial intelligence (AI) to assess the fluid status of dialysis patients. Methods This was a single-centre study of 76 hemodialysis and peritoneal dialysis patients carried out between July 2020 to May 2022. The fluid status of dialysis patients was assessed via a simplified 8-point LUS method using a portable handheld ultrasound device (HHUSD), clinical examination and bioimpedance analysis (BIA). The primary outcome was the performance of 8-point LUS using a portable HHUSD in diagnosing fluid overload compared to physical examination and BIA. The secondary outcome was to develop and validate a novel AI software program to quantify B-line count and assess the fluid status of dialysis patients. Results Our study showed a moderate correlation between LUS B-line count and fluid overload assessed by clinical examination (r = 0.475, p < 0.001) and BIA (r = 0.356. p < 0.001). The use of AI to detect B-lines on LUS in our study for dialysis patients was shown to have good agreement with LUS B lines observed by physicians; (r = 0.825, p < 0.001) for the training dataset and (r = 0.844, p < 0.001) for the validation dataset. Conclusion Our study confirms that 8-point LUS using HHUSD, with AI-based detection of B lines, can provide clinically useful information on the assessment of hydration status and diagnosis of fluid overload for dialysis patients in a user-friendly and time-efficient way.

Background Burkholderia pseudomallei is endemic in the tropics and associated with high mortality. We performed a retrospective study analyzing the clinical and microbiologic features of melioidosis, and predictors of mortality.MethodsPatients with culture-positive melioidosis from 2006 to 2016 were identified from microbiologic records. Clinical data including demographics, treatment, and outcomes were extracted from medical records. Categorical variables were compared using χ2 test or Fisher exact test while continuous variables were compared using Student’s t-test or Mann–Whitney U test.ResultsForty-three cases of melioidosis were identified. Presentations included fever (41.9%), respiratory symptoms (20.9%), and joint swelling (9.3%). 76.7% were bacteremic and 69.7% were culture-positive from a nonblood source. Mean time from presentation to positive microbiological data was 5.1 ± 6.4 days. Infection sites included pulmonary (62.8%), spleen (27.9%), skin/soft tissue (25.6%), and bone/joint (25.3%). Antibiotic susceptibility were as follows: ceftazidime (97.5%), imipenem (100.0%), trimethoprim–sulfamethoxazole (92.1%), amoxicillin–clavulanate (94.7%), and doxycycline (94.7%). Mean time from presentation to melioid-active coverage was 6.8 ± 9.1 days. Thirty-day all-cause mortality occurred in nine patients (from first positive culture); one patient died within 5 months. Univariable analysis associations with 30-day all-cause mortality were: intensive care unit (ICU) admission (OR 26.3, 95% CI 4.0–173.1, P < 0.01), mechanical ventilation (OR 15.0, 95% CI 2.6–85.0, P < 0.01), higher median Pitt Bacteremia Score (PBS) (4.0 vs. 2.0; P < 0.01), receipt of ceftazidime (vs. a carbapenem) as primary induction antibiotic therapy (OR 0.2, 95% CI 0.03–0.91, P = 0.047) and not receiving melioidosis-active induction intravenous antibiotics (P = 0.04). Multivariable analysis found mechanical ventilation to be an independent predictor for 30-day mortality (P = 0.003, OR 18.8, 95% CI 2.7–130.9).ConclusionICU admission, a high PBS, and in particular, receipt of mechanical ventilation may help identify patients with high mortality risk. Delays in melioid-active therapy were not uncommon. Prompt recognition of melioidosis and early institution of active therapy, especially in the critically ill, may reduce mortality.Disclosures All authors: No reported disclosures.

Introduction: Cannulation of complex arteriovenous fistula (AVF) or graft (AVG) frequently poses challenges to renal nursing practice. Ultrasound (US) guidance on visualizing central and peripheral venous access has been widely adopted in nephrology, reducing vascular intervention complications. Renal nurses could acquire this point-of-care technique to increase the successful cannulation rate while facilitating confidence build-up during practice. We aim to evaluate the use of handheld US on difficult AVF/AVG cannulation in a hospital-based dialysis unit. Methods:We conducted a single-center randomized controlled trial from January 2021 to January 2022. Ten renal nurses were trained by an interventional nephrologist before patient recruitment and had completed a pre-and posttraining questionnaire on their confidence level. Fifty hemodialysis patients with complex AVF were randomized to US-guided or conventional cannulation. The total time spent on cannulation and patients' pain scores were also collected.Findings: Renal nurses increased their confidence level after training (pretraining score 26.6 AE 6.9 vs. posttraining score 36.4 AE 3.0; p = 0.014). There was a higher success rate (only one cannulation attempt required) for US-guided (96%) versus conventional (72.0%) cannulation (p = 0.049). US-guided cannulation had a lower pain score than the conventional method (1.48 AE 0.73 vs. 2.13 AE 0.95, p = 0.012). The pre-cannulation assessment time and time spent on cannulation were comparable between the two groups. Discussion: Our study showed that US-guided cannulation increased renal nurses' confidence level in difficult cannulation and improved success rate. Larger scale studies are required to further assess the applications of handheld US in AVF cannulation, particularly in different clinical settings (e.g., chronic dialysis centers).