About & Tutorial<- Back to Main page
The InAdvance ProjectThe project Patient-centred pathways of early palliative care, supportive ecosystems and appraisal standard (InAdvance) http://www.inadvanceproject.eu/ proposes a model of palliative care (PC) based on early integration and personalized pathways addressed specifically to older people with complex chronic conditions. Thus, the overall aim of InAdvance is to improve the benefit of PC through the design of effective, replicable and cost-effective early PC interventions centred-on and oriented-by the patients. In order to achieve this main goal, InAdvance will produce the following evidence-based outputs to assist care professionals, service managers and policy and decision-makers in their scalability and replicability: a) stratification tools to identify potential beneficiaries of early PC actions; b) optimized interventions co-designed by needs and preferences from patients and their relatives; c) eHealth tools addressed to empower palliative patients ecosystem; d) policy recommendations and clinical guidelines addressed to service providers and policy and decision makers; e) an appraisal standard and dashboard facilitating a critical and comprehensive comparison between actions and interventions derived from the project.
The work done hereThis website represents a part of the work done in the work package 2 (WP2), where three predictive models have been developed: one-year mortality, mortality regression and a frailty model as proxies for a much more complicated problem which is the palliative care need. The models are intended to provide a data-driven insight to the eligibility for palliative care on a more data-driven approach than other clinical standards such as the Surprise Question. The technology has been developed (work still in progress) by the Biomedical Data Science Lab (BDSLab) from Universitat Politècnica de València in collaboration with Hospital Universitari i Politècnic La Fe, both from Valencia (Spain).
How to use the webIn the main page, there are available three models (each model is a row) with two modes each (columns). The models, as mentioned before, are:
- one-year mortality model, which predicts if the patient will die in the next 12 months after the hospital admission (the moment when data is gathered);
- the mortality regression model that is very similar to the previous one, but trying to predict the number of days until exitus;
- the frailty model that is defined as attempting to predict the frailty index defined by Hospital La Fe – which is in the range 0-29, being 29 the most fragile –, within the next six months since the data gathering.
Since the launch of the website two essential features have been included, the possibility of having several models of the same type using versioning and the sandbox mode. The page will show a drop-down menu with the different versions when possible, including the type of model and the date it was added to the website. Sandbox mode allows you to run several models simultaneously for both single and multiple predictions.
In sandbox mode, as several models are available, the 'label' column has been replaced by '1ym' for the one-year mortality classifier, 'regression' for the mortality regression model and 'frailty' for the 6-month frailty model. To increase compatibility, this nomenclature can also be used in single model modes.