Discovering patient groups in sequential electronic healthcare data using unsupervised representation learning.

Introduction: Unsupervised feature learning methods inspired by natural language processing (NLP) models are capable of constructing patient-specific features from longitudinal Electronic Health Records (EHR).

Design: We applied document embedding algorithms to real-world paediatric intensive care (PICU) EHR data to extract patient-specific features from 1853 patients' PICU journeys using 647 unique lab tests and medication events. We evaluated the clinical utility of the patient features via a K-means clustering analysis.

Antiretroviral therapy in people with HIV and end-stage kidney disease.

Objective: To summarize antiretroviral therapy (ART) use in the setting of end-stage kidney disease (ESKD).

Design: Cross-sectional analysis.

Methods: Descriptive analysis of ART regimens and dose of nucleoside/nucleotide reverse-transcriptase inhibitors (NRTI) in people with HIV and ESKD (dialysis, kidney transplantation, or estimated glomerular filtration rate (eGFR) <15 mL/min/1.

Outcomes of surgically treated posterior pelvic fractures in an Australian population: A multicenter study.

Background: Unstable posterior pelvic-ring fractures are rare and difficult to manage. There are many injury patterns, they are associated with high morbidity and mortality, and optimal surgical management remains contentions. This study aims to compare outcomes and complications for different surgical management of these injuries.

A multiscale functional map of somatic mutations in cancer integrating protein structure and network topology.

A major goal of cancer biology is to understand the mechanisms driven by somatically acquired mutations. Two distinct methodologies-one analyzing mutation clustering within protein sequences and 3D structures, the other leveraging protein-protein interaction network topology-offer complementary strengths. We present NetFlow3D, a unified, end-to-end 3D structurally-informed protein interaction network propagation framework that maps the multiscale mechanistic effects of mutations.

Co-designing a film showcasing the dental experiences of community returners (ex-offenders).

Background: The oral health of over 90,000 individuals in UK prisons is four times worse than the general population. A recent scoping review on the oral health of prisoners inside the justice system highlighted the lack of research about what happens when they transition out of prison to become community returners.

Objectives: To co-design a film to showcase the dental experiences of community returners before and after they transition out of prison, change perceptions and inform oral health research priorities.