Browsing by Author "Kaya, Gulsum Kubra"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    A comparison of machine learning algorithms in predicting COVID-19 prognostics
    (Springer, 2022-09-18) Ustebay, Serpil; Sarmis, Abdurrahman; Kaya, Gulsum Kubra; Sujan, Mark
    ML algorithms are used to develop prognostic and diagnostic models and so to support clinical decision-making. This study uses eight supervised ML algorithms to predict the need for intensive care, intubation, and mortality risk for COVID-19 patients. The study uses two datasets: (1) patient demographics and clinical data (n = 11,712), and (2) patient demographics, clinical data, and blood test results (n = 602) for developing the prediction models, understanding the most significant features, and comparing the performances of eight different ML algorithms. Experimental findings showed that all prognostic prediction models reported an AUROC value of over 0.92, in which extra tree and CatBoost classifiers were often outperformed (AUROC over 0.94). The findings revealed that the features of C-reactive protein, the ratio of lymphocytes, lactic acid, and serum calcium have a substantial impact on COVID-19 prognostic predictions. This study provides evidence of the value of tree-based supervised ML algorithms for predicting prognosis in health care.
  • Thumbnail Image
    ItemOpen Access
    Exploring the impact of safety culture on incident reporting: lessons learned from machine learning analysis of NHS England staff survey and incident data
    (Elsevier, 2023-07-13) Kaya, Gulsum Kubra; Ustebay, S.; Nixon, James; Pilbeam, Colin
    Safety culture is one of the key factors contributing to safety, even though limited evidence supports its impact on safety outcomes. This study uses supervised machine learning algorithms to explore the association between safety culture and incident reporting. The study used National Health Service (NHS) England annual staff survey data as a proxy of safety culture to predict eighteen incident reporting variables. The study did not achieve high accuracy rates in the prediction models. The highest association was found between safety culture and the number of incidents reported in class low, medium and high. LightGBM was the best-performed algorithm. SHAP plots were used to explain the model. Findings suggest that compassionate culture, violence and harassment and work pressure are critical in predicting the number of incidents reported. More specifically, the violence and harassment had a more significant impact on predicting the number of incidents reported in class high than in class medium and low. The involvement had more effect on predicting class low. The results demonstrated different behaviours in predicting different incident reporting classes. The findings facilitate lessons learned from staff surveys and incident reporting data in NHS England. Consequently, the findings can contribute to improving the safety culture in hospitals.
  • Thumbnail Image
    ItemOpen Access
    What kinds of insights do Safety-I and Safety-II approaches provide? a critical reflection on the use of SHERPA and FRAM in healthcare
    (Elsevier, 2024-02-02) Sujan, Mark; Lounsbury, O.; Pickup, L.; Kaya, Gulsum Kubra; Earl, L.; McCulloch, P.
    Over the past decade, the field of healthcare has seen a significant shift in its approach to patient safety. Traditionally, safety efforts focused on understanding past harm and preventing errors, primarily through the use of standardisation and the introduction of barriers and safeguards, such as standardised communication protocols (e.g., SBAR (Haig et al., 2006)), checklists (e.g., WHO surgical safety checklist (Haynes et al., 2009)) and technology with safety features (e.g., smart infusion pumps (Taxis and Franklin, 2011)). This type of thinking about patient safety in terms of past harm and errors is also referred to as Safety-I (Hollnagel, 2014), even though this terminology has been criticised as it does not reflect adequately the diversity in safety science thinking (Leveson, 2020). However, the evidence for whether interventions based on this (Safety-I) thinking lead to improvements in patient safety is mixed at best (Kellogg et al., 2017, Wears and Sutcliffe, 2019), and critics have argued that the additional “safety clutter” produced as a result of such interventions might be counterproductive (Rae et al., 2018, Halligan et al., 2023).