Deploying artificial intelligence in the detection of adult appendicular and pelvic fractures in the Singapore emergency department after hours: efficacy, cost savings and non-monetary benefits.

INTRODUCTION: Radiology plays an integral role in fracture detection in the emergency department (ED). After hours, when there are fewer reporting radiologists, most radiographs are interpreted by ED physicians. A minority of these interpretations may miss diagnoses, which later require the callback of patients for further management. Artificial intelligence (AI) has been viewed as a potential solution to augment the shortage of radiologists after hours. We explored the efficacy of an AI solution in the detection of appendicular and pelvic fractures for adult radiographs performed after hours at a general hospital ED in Singapore, and estimated the potential monetary and non-monetary benefits. METHODS: One hundred and fifty anonymised abnormal radiographs were retrospectively collected and fed through an AI fracture detection solution. The radiographs were re-read by two radiologist reviewers and their consensus was established as the reference standard. Cases were stratified based on the concordance between the AI solution and the reviewers' findings. Discordant cases were further analysed based on the nature of the discrepancy into overcall and undercall subgroups. Statistical analysis was performed to evaluate the accuracy, sensitivity and inter-rater reliability of the AI solution. RESULTS: Ninety-two examinations were included in the final study radiograph set. The AI solution had a sensitivity of 98.9%, an accuracy of 85.9% and an almost perfect agreement with the reference standard. CONCLUSION: An AI fracture detection solution has similar sensitivity to human radiologists in the detection of fractures on ED appendicular and pelvic radiographs. Its implementation offers significant potential measurable cost, manpower and time savings.

Improved outcomes for index cholecystectomy for acute cholecystitis following a dedicated emergency surgery and trauma service (ESAT).

INTRODUCTION: Early laparoscopic cholecystectomy (ELC) has shown to reduce length of stay and improve patients' satisfaction as compared to delayed laparoscopic cholecystectomy (DLC). However, logistics and manpower limitations often preclude ELC. METHODS: A retrospective study was conducted in a single institute to compare outcomes of AC before (August 2013-2014) and after (August 2017-2018) establishment of emergency surgery and trauma (ESAT). RESULTS: There were 82 patients in pre-ESAT period and 172 patients in ESAT period. Mean age was 52.3 ± 11.6 and 55.7 ± 13.8 years, respectively, p = 0.369. There were more patients with moderate-severe grading of cholecystitis based on Tokyo Guidelines (TG 18) in ESAT 143/172 (83.1%) as compared to pre-ESAT 65/82 (79.3%), p = 0.042. Index cholecystectomy was performed in 145/172 (84.3%) of patients in the ESAT vs 34/82 (41.5%) of patients in the pre-ESAT period (p = 0.001). Time interval between booking to surgery was 180 ± 56 min in ESAT vs 197 ± 98 min in pre-ESAT, p = 0.014. Operative duration was shorter in ESAT 121 ± 38.5 min vs 139 ± 53.4, in pre-ESAT period, p = 0.030. Conversion rates were lower in ESAT (4/172, 2.3%) vs (9/72, 11%) in pre-ESAT, p = 0.003. Length of stay was shorter in ESAT (DLC 1.89 ± 1.6 and ELC ± 2.9 days) as compared to pre-ESAT (DLC 4.55 ± 2.2 and ELC 5.03 ± 2.6 days), p = 0.001. 30-day readmissions were lower in ESAT (3/172, 1.7%) vs pre-ESAT (8/72, 9.8%). CONCLUSION: The ESAT model provided more early laparoscopic cholecystectomies with improved efficiency and clinical outcomes.