Volume 52, Number 3
March 2024

A systematic review identified 26 distinct automated machine learning (autoML) platforms that have been trialled and/or applied in a clinical context.

The performance of autoML compares well to bespoke computational and clinical benchmarks across clinical tasks ranging from diagnosis to prognostication, with exemplar use cases including identifying pathology on common imaging modalities.

Illustration by Ngiam Li Yi

Singapore tuberculosis (TB) clinical management guidelines 2024: A modified Delphi adaptation of international guidelines for drug-susceptible TB infection and pulmonary disease

Tuberculosis (TB) is an infectious disease caused by the Mycobacterium tuberculosis complex. For decades, it was the leading cause of death worldwide from a single infectious disease before being displaced by COVID-19 during the pandemic years.1 TB is endemic in Singapore, with over 2000 cases of TB disease (formerly active TB)...

Asian media reporting on suicide: Concerning trends

Asharani et al. present an enlightening study of media influences on suicidality and suicides from multinational data, all within Asia.1 This is important, as knowledge based on media and suicide has been dominated by Western cultures and English and other European languages. Pulling together various independent studies, as Asharani...

Bridging expertise with machine learning and automated machine learning in clinical medicine

In this issue of the Annals, Thirunavukarasu et al.'s systematic review on the clinical performance of automated machine learning (autoML) highlights its extensive applicability across 22 clinical specialties, showcasing its potential to redefine healthcare by making artificial intelligence (AI) technologies accessible to those without advanced computational skills.1 This enables...

Mitigating adverse social determinants of health in the vulnerable population: Insights from a home visitation programme

Strong evidence consistently links low income to Adverse Childhood Experiences (ACEs) and children’s long-term health, developmental, educational and social outcomes.1,2 Poverty increases parenting stress, and this is especially important in early childhood when the home environment and parent-child bond are the main contributing factors in shaping children’s biological and psychosocial...

Health practices, behaviours and quality of life of low-income preschoolers: A community-based cross-sectional comparison study in Singapore

Poverty is a serious concern that has been found to bring about various adverse psychological, social and developmental outcomes.1 Living in poverty as a child can affect an individual’s life well into adulthood2 due to risks including poor nutrition, poorly controlled chronic ailments and unstable environments.3,4 Overall, these children...

MOST VIEWED ARTICLES

Board of Reviewers 2024

Organ donation in the paediatric intensive care unit: Time for change?