Exploiting the similarity of dissimilarities for biomedical applications and enhanced machine learning.

The "similarity of dissimilarities" is an emerging paradigm in biomedical science with significant implications for protein function prediction, machine learning (ML), and personalized medicine. In protein function prediction, recognizing dissimilarities alongside similarities provides a more detailed understanding of evolutionary processes, allowing for a deeper exploration of regions that influence biological functionality. For ML models, incorporating dissimilarity measures helps avoid misleading results caused by highly correlated or similar data, addressing confounding issues like the Doppelgänger Effect.

Burnout among medical residents: key drivers and practical mitigating strategies.

Burnout is a prevalent phenomenon in medicine, affecting >50% of physicians and up to 60% of medical residents. This has negative consequences for both doctors' mental health and job satisfaction as well as patient care quality. While numerous studies have explored the causes, psychological effects, and workplace solutions, we aim to practicalize the issue from the perspectives of residents by discussing three key drivers of burnout and offering actionable, multipronged strategies that may be able to tackle these root causes effectively.

π-HuB: the proteomic navigator of the human body.

The human body contains trillions of cells, classified into specific cell types, with diverse morphologies and functions. In addition, cells of the same type can assume different states within an individual's body during their lifetime. Understanding the complexities of the proteome in the context of a human organism and its many potential states is a necessary requirement to understanding human biology, but these complexities can neither be predicted from the genome, nor have they been systematically measurable with available technologies.

Revisiting the conceptualisation and implications of medicine's 'hidden curriculum'.

In medical training and practice, our professional attributes, attitudes, perceptions, character traits and identities are fundamentally shaped by our lived experiences and observations in clinical and para-clinical settings instead of being inculcated through formal curriculum or classroom teaching. For instance, clinical acumen, communication skills and bedside manners are learnt through role modelling and experiential learning in the course of clinical rotations. Likewise, one's attitudes, professional behaviours and inclinations are often also influenced by direct/indirect observations of the actions of others in the medical fraternity in various clinical and non-clinical settings.

A generalisability theory approach to quantifying changes in psychopathology among ultra-high-risk individuals for psychosis.

Distinguishing stable and fluctuating psychopathological features in young individuals at Ultra High Risk (UHR) for psychosis is challenging, but critical for building robust, accurate, early clinical detection and prevention capabilities. Over a 24-month period, 159 UHR individuals were assessed using the Positive and Negative Symptom Scale (PANSS). Generalisability Theory was used to validate the PANSS with this population and to investigate stable and fluctuating features, by estimating the reliability and generalisability of three factor (Positive, Negative, and General) and five factor (Positive, Negative, Cognitive, Depression, and Hostility) symptom models.

Ten quick tips for ensuring machine learning model validity.

Artificial Intelligence (AI) and Machine Learning (ML) models are increasingly deployed on biomedical and health data to shed insights on biological mechanism, predict disease outcomes, and support clinical decision-making. However, ensuring model validity is challenging. The 10 quick tips described here discuss useful practices on how to check AI/ML models from 2 perspectives-the user and the developer.

Kikuchi-Fujimoto lymphadenitis in a patient with human immunodeficiency virus infection: The importance of precision pathology.

Background: Kikuchi-Fujimoto lymphadenitis (or histiocytic necrotising lymphadenitis) is a rare disease that is usually benign and self-limiting. A higher prevalence is reported amongst East Asian populations. No clear etiology has been identified although it has been associated with some viruses, rarely the Human Immunodeficiency Virus (HIV) and autoimmune pathologies.

Adding Hyponatremia to the "Rule-of-6" Prediction Tool Improves Performance in Identifying Hospitalised Patients with COVID-19 at Risk of Adverse Clinical Outcomes.

The 'rule-of-6' prediction tool was shown to be able to identify COVID-19 patients at risk of adverse outcomes. During the pandemic, we frequently observed hyponatremia at presentation. We sought to evaluate if adding hyponatremia at presentation could improve the 'rule-of-6' prediction tool.

Referring wisely: knowing when and how to make subspecialty consultations in hospital medicine.

Subspecialty consultations are becoming highly prevalent in hospital medicine, due to an ageing population with multimorbid conditions and increasingly complex care needs, as well as medicolegal fears that lead to widespread defensive medical practices. Although timely subspecialty consultations in the appropriate clinical context have been found to improve clinical outcomes, there remains a significant proportion of specialty referrals in hospital medicine which are inappropriate, excessive, or do not add value to patient care. In this article, we sought to provide an overview of the common problems pertaining to excessive quantity and suboptimal quality of inpatient subspecialty consultations made in real-world practice and highlight their implications for healthcare financing and patient care.

Trends in electrocardiographic and cardiovascular manifestations of patients hospitalised with COVID-19.

Introduction: Early in the coronavirus disease 2019 (COVID-19) pandemic, a low incidence of cardiovascular complications was reported in Singapore. Little was known about the trend of cardiovascular complications as the pandemic progressed. In this study, we examined the evolving trends in electrocardiographic and cardiovascular manifestations in patients hospitalised with COVID-19.

Clinical reasoning in real-world practice: a primer for medical trainees and practitioners.

Clinical reasoning is a crucial skill and defining characteristic of the medical profession, which relates to intricate cognitive and decision-making processes that are needed to solve real-world clinical problems. However, much of our current competency-based medical education systems have focused on imparting swathes of content knowledge and skills to our medical trainees, without an adequate emphasis on strengthening the cognitive schema and psychological processes that govern actual decision-making in clinical environments. Nonetheless, flawed clinical reasoning has serious repercussions on patient care, as it is associated with diagnostic errors, inappropriate investigations, and incongruent or suboptimal management plans that can result in significant morbidity and even mortality.

OLB-AC: toward optimizing ligand bioactivities through deep graph learning and activity cliffs.

Motivation: Deep graph learning (DGL) has been widely employed in the realm of ligand-based virtual screening. Within this field, a key hurdle is the existence of activity cliffs (ACs), where minor chemical alterations can lead to significant changes in bioactivity. In response, several DGL models have been developed to enhance ligand bioactivity prediction in the presence of ACs.

Optimizing differential expression analysis for proteomics data via high-performing rules and ensemble inference.

Identification of differentially expressed proteins in a proteomics workflow typically encompasses five key steps: raw data quantification, expression matrix construction, matrix normalization, missing value imputation (MVI), and differential expression analysis. The plethora of options in each step makes it challenging to identify optimal workflows that maximize the identification of differentially expressed proteins. To identify optimal workflows and their common properties, we conduct an extensive study involving 34,576 combinatoric experiments on 24 gold standard spike-in datasets.