Artificial intelligence for detection of intracranial haemorrhage on head computed tomography scans: diagnostic accuracy in Hong Kong.

INTRODUCTION: The use of artificial intelligence (AI) to identify acute intracranial haemorrhage (ICH) on computed tomography (CT) scans may facilitate initial imaging interpretation in the accident and emergency department. However, AI model construction requires a large amount of annotated data for training, and validation with real-world data has been limited. We developed an algorithm using an open-access dataset of CT slices, then assessed its utility in clinical practice by validating its performance on CT scans from our institution. METHODS: Using a publicly available international dataset of >750 000 expert-labelled CT slices, we developed an AI model which determines ICH probability for each CT scan and nominates five potential ICH-positive CT slices for review. We validated the model using retrospective data from 1372 non-contrast head CT scans (84 [6.1%] with ICH) collected at our institution. RESULTS: The model achieved an area under the curve of 0.842 (95% confidence interval=0.791-0.894; P<0.001) for scan-based detection of ICH. A pre-specified probability threshold of ≥50% for the presence of ICH yielded 78.6% accuracy, 73% sensitivity, 79% specificity, 18.6% positive predictive value, and 97.8% negative predictive value. There were 62 true-positive scans and 22 false-negative scans, which could be reduced to six false-negative scans by manual review of model-nominated CT slices. CONCLUSION: Our model exhibited good accuracy in the CT scan-based detection of ICH, considering the low prevalence of ICH in Hong Kong. Model refinement to allow direct localisation of ICH will facilitate the use of AI solutions in clinical practice.

Estrogen receptor alpha CA dinucleotide repeat polymorphism is associated with rate of bone loss in perimenopausal women and bone mineral density and risk of osteoporotic fractures in postmenopausal women.

UNLABELLED: The association between a newly identified CA repeat polymorphism of the estrogen receptor alpha gene (ESR1) with osteoporosis was investigated. Postmenopausal women with <18 CA repeats had low BMD, increased rate of bone loss and increased fracture risk. INTRODUCTION: Studies have shown that intronic dinucleotide repeat polymorphisms in some genes are associated with disease risk by modulating mRNA splicing efficiency. D6S440 is a newly identified intronic CA repeat polymorphism located downstream of the 5'-splicing site of exon 5 of ESR1. METHODS: The associations of D6S440 with bone mineral density (BMD), rate of bone loss and fracture risk were evaluated in 452 pre-, 110 peri- and 622 postmenopausal southern Chinese women using regression models. RESULTS: Post- but not premenopausal women with less CA repeats had lower spine and hip BMD. The number of CA repeats was linearly related to hip BMD in postmenopausal women (beta=0.008; p=0.004). Postmenopausal women with CA repeats <18 had higher risks of having osteoporosis (BMD T-score< -2.5 at the spine: OR 2.46, 95% CI 1.30-4.65; at the hip: OR 3.79(1.64-8.74)) and low trauma fractures (OR 2.31(1.29-4.14)) than those with >or= 18 repeats. Perimenopausal women with <18 CA repeats had significantly greater bone loss in 18 months at the hip than those with >or= 18 repeats (-1.96% vs. -1.61%, p = 0.029). CONCLUSIONS: ESR1 CA repeat polymorphism is associated with BMD variation, rate of bone loss and fracture risk, and this may be a useful genetic marker for fracture risk assessment.