Background

Community acquired pneumonia (CAP) is a leading cause of hospital admission, and in older adults has high rates of mortality and complications. CAP is associated with increased long-term mortality and loss of independence for older adults. CAP typically affects older adults with co-morbidities. Complications such as sepsis, and empyema (infected fluid around the lung) prolong hospital admission, result in additional interventions in hospital and have higher mortality than CAP alone. The causative agents for CAP are often poorly identified in real world clinical practice.

The treatment of patients with CAP is complex. Key decisions relate to the antibiotics used, the way antibiotics are given (in a tablet or by a drip) and the place of care (home, hospital and in hospital, a normal ward or intensive care). These data will allow analyses on differing antimicrobial treatments and outcomes, as well as differing pathways of care. This data has been constructed to support machine learning including algorithm generation and testing models.

PIONEER geography The West Midlands (WM) has a population of 5.9 million and includes a diverse ethnic and socio-economic mix.

EHR. UHB is one of the largest NHS Trusts in England, providing direct acute services and specialist care across four hospital sites, with 2.2 million patient episodes per year, 2750 beds and an expanded 250 ITU bed capacity during COVID. UHB runs a fully electronic healthcare record (EHR) (PICS; Birmingham Systems), a shared primary and secondary care record (Your Care Connected) and a patient portal “My Health”.

Scope: All patients admitted to hospital from 2000 because of Community Acquired Pneumonia. Longitudinal and individually linked, so that the preceding and subsequent health journey can be mapped and healthcare utilisation prior to and after admission understood. The dataset includes highly granular patient demographics, co-morbidities taken from ICD-10 and SNOMED-CT codes. Serial, structured data pertaining to process of care (timings and admissions), presenting complaints, therapy, ventilation route, assessments components (AMT10, falls, MMS, thrombosis and waterlow), physiology readings (temperature, blood pressure, respiratory rate, NEWS2 score, oxygen saturations, AVPU scale and others), Sample analysis results (bilirubin, urea, albumin, platelets, white blood cells and others) drug administered and all outcomes. Linked images available (radiographs, CT scans, MRI).

Available supplementary data: CAP admission data from 2000 onwards. Matched controls; ambulance, OMOP data, synthetic data.

Available supplementary support: Analytics, Model build, validation and refinement; A.I.; Data partner support for ETL (extract, transform and load) process, Clinical expertise, Patient and end-user access, Purchaser access, Regulatory requirements, Data-driven trials, “fast screen” services.