Background Healthcare data frequently lack the specificity level needed to achieve clinical and operational objectives such as optimising bed management. Pneumonia is a disease of importance as it accounts for more bed days than any other lung disease and has a varied aetiology. The condition has a range of SNOMED CT concepts with different levels of specificity. Objective This study aimed to quantify the importance of the specificity of an SNOMED CT concept, against well-established predictors, for forecasting length of stay for pneumonia patients. Method A retrospective data analysis was conducted of pneumonia admissions to a tertiary hospital between 2011 and 2021. For inclusion, the primary diagnosis was a subtype of bacterial or viral pneumonia, as identified by SNOMED CT concepts. Three linear mixed models were constructed. Model One included known predictors of length of stay. Model Two included the predictors in Model One and SNOMED CT concepts of lower specificity. Model Three included the Model Two predictors and the concepts with higher specificity. Model performances were compared. Results Sex, ethnicity, deprivation rank and Charlson Comorbidity Index scores (age-adjusted) were meaningful predictors of length of stay in all models. Inclusion of lower specificity SNOMED CT concepts did not significantly improve performance (ΔR2 = 0.41%, p = .058). SNOMED CT concepts with higher specificity explained more variance than each of the individual predictors (ΔR2 = 4.31%, p < .001). Conclusion SNOMED CT concepts with higher specificity explained more variance in length of stay than a range of well-studied predictors. Implications Accurate and specific clinical documentation using SNOMED CT can improve predictive modelling and the generation of actionable insights. Resources should be dedicated to optimising and assuring clinical documentation quality at the point of recording.

Background: Pain is a leading cause of disability worldwide. Pain assessments are an essential part of evidence-based care and management. Among comparable care providers, there is variation in how nurses document assessments as well as the content in them, and there is a notable associated administrative burden. Aims: This study evaluated the impact and significance of a new, structured, digitised pain assessment form from quality, safety and efficiency standpoints. Methods: Samples of pain assessments were examined at three consecutive stages: first, the pre-existing form was used, then the new structured form was introduced and, finally, the structured form was taken away and nurses went back to completing the original form. Assessments were scored by two clinical analysts against 18 clinically defined pain-related characteristics and factors. The time taken to extract and interpret the assessments was also recorded. Statistically significant changes were assessed using Welch's t-tests and Fisher's exact tests. Findings: There was a significant improvement in data quality using the new structured form compared with the pre-existing template, including an increase in the capture of five safety-related variables. Less time was needed to extract and interpret data with the new form. Conclusion: Intelligent structured forms are highly effective for documenting pain assessments, and offer notable benefits in quality, safety, and efficiency.

Machine learning has the potential to transform how healthcare is delivered. It can support clinical decision making, determine the risk, presence and prognosis of disease and help optimise patient pathways. Widespread use and access to digital health records mean implementing machine learning models is quicker and easier than ever before. It is imperative for clinical and operational leads to understand the principles behind machine learning, so they can evaluate how it may be helpful to them and their teams. This article provides an overview of machine learning and how it can be used to help solve common healthcare-related problems.

In this article, Roberts et al discuss the importance of SNOMED CT in improving electronic health records, and the benefits this can bring healthcare organisations, professionals and patients.