Annals Academy of Medicine Singapore最新文献

Introduction: Detection of neurological conditions is of high importance in the current context of increasingly ageing populations. Imaging of the retina and the optic nerve head represents a unique opportunity to detect brain diseases, but requires specific human expertise. We review the current outcomes of artificial intelligence (AI) methods applied to retinal imaging for the detection of neurological and neuro-ophthalmic conditions.

Method: Current and emerging concepts related to the detection of neurological conditions, using AI-based investigations of the retina in patients with brain disease were examined and summarised.

Results: Papilloedema due to intracranial hypertension can be accurately identified with deep learning on standard retinal imaging at a human expert level. Emerging studies suggest that patients with Alzheimer's disease can be discriminated from cognitively normal individuals, using AI applied to retinal images.

Conclusion: Recent AI-based systems dedicated to scalable retinal imaging have opened new perspectives for the detection of brain conditions directly or indirectly affecting retinal structures. However, further validation and implementation studies are required to better understand their potential value in clinical practice.

Introduction: To compare epidemiological features and clinical presentations of deep infiltrating endometriosis with endometrioma and adenomyosis, as well as to identify risk factors for the respective histologically confirmed conditions.

Method: Patients undergoing index surgery at the National University Hospital, Singapore for endometriosis or adenomyosis over a 7-year period-from 2015 to 2021-were identified from hospital databases using the Table of Surgical Procedures coding. Social and epidemiological features of cases with histologically confirmed diagnoses of endometrioma only, adenomyosis only, and deep infiltrating endometriosis were compared. Significant variables from univariate analysis were entered into 3 binary multivariate logistic regression models to obtain independent risk factors for: deep infiltrating endometriosis versus endometrioma only, deep infiltrating endometriosis versus adenomyosis only, and adenomyosis only versus endometrioma only.

Results: A total of 258 patients were included with 59 ovarian endometrioma only, 47 adenomyosis only, and 152 deep infiltrating endometrioses. Compared to endometrioma only, deep infiltrating endometriosis was associated with higher rates of severe dysmenorrhoea (odds ratio [OR] 2.80, 95% confidence interval [CI] 1.02-7.70) and out-of-pocket private surgical care (OR 4.72, 95% CI 1.85-12.04). Compared to adenomyosis only, deep infiltrating endometriosis was associated with a higher fertility desire (OR 13.47, 95% CI 1.01-180.59) and a lower body mass index (OR 0.89, 95% CI 0.79-0.99). In contrast, heavy menstrual bleeding was the hallmark of adenomyosis, being less common in patients with endometriosis.

Conclusion: Deep infiltrating endometriosis is associated with severe dysmenorrhoea, pain related to urinary and gastrointestinal tracts, higher fertility desire and infertility rate. Patients with pain symptomatology and subfertility should be referred early to a tertiary centre with the capability to diagnose and manage deep infiltrating endometriosis.

Bradyarrhythmias are commonly encountered in clinical practice. While there are several electrocardiographic criteria and algorithms for tachyarrhythmias, there is no algorithm for bradyarrhythmias to the best of our knowledge. In this article, we propose a diagnostic algorithm that uses simple concepts: (1) the presence or absence of P waves, (2) the relationship between the number of P waves and QRS complexes, and (3) the regularity of time intervals (PP, PR and RR intervals). We believe this straightforward, stepwise method provides a structured and thorough approach to the wide differential diagnosis of bradyarrhythmias, and in doing so, reduces misdiagnosis and mismanagement.