For how we live.
A network meta-analysis of 53 studies and more than 7 million admissions finds machine learning out-discriminates traditional sepsis scores — and would raise roughly two false alarms for every real one.
Across 26 states, expansion raised the Medicaid-paid share of deliveries by 5.2% and changed the severe maternal morbidity rate by 0.02% — an interval that includes zero in both directions.
The tool reads vital signs, lab results, and history the way clinicians already do — just faster and continuously. Its accuracy tops out around 90%, which means it's also still wrong a meaningful share of the time.
A Lancet Digital Health scoping review found the field's fairness metrics fragmented and rarely clinically validated. A second review found that most studies don't measure fairness at all.
A Lancet study across 547,000 adults and 925 infectious diseases finds obesity raises the risk of severe infection across almost every pathogen type. The global estimate rests on modelling, not on the cohorts themselves.
Nearly a million conscripts followed for three decades: obesity carried a 3.1-fold hazard for sepsis, and high cardiorespiratory fitness was associated with a 42% lower risk of dying from bacterial infection.
A new GBD analysis puts sepsis-related deaths at 21.4 million, roughly double the 11.0 million estimated for 2017 — a change driven partly by COVID-19 and partly by a different method.