In questa sezione potrete consultare i risultati del progetto DARE in open access: risorse software su GitHub, pubblicazioni su Zenodo, e dataset pubblici.
DATASET:
SOFTWARE:
LETTERATURA GRIGIA:
Deliverable: D1.1 - List of process and outcome indicators
WP Number: WP1
Dissemination Level: Public, fully open
Publishable Summary:
The DARE project aims to provide the Italian Ministry of Health and NHS with innovative
technologies that are effective, efficient, and ready to be used, enabling the country to
accelerate and revolutionize the health paradigm encompassing prevention through to
treatment.
Indicators are defined as specific, observable, and measurable changes showing progress
toward achieving a specific output or outcome in a logic model or work plan. The purpose
of this deliverable is to provide all DARE consortium partners with a list of possible
indicators that will be used to assess the utility and implementability of innovative
technologies during the development of a pilot.
The DARE project consortium involves many entities and promotes the implementation of a
wide variety of studies that focus on prevention, and the maturity level of the proposed pilots
could be very different. Two frameworks have been selected for the identification of
indicators: the GRADE (Grading of Recommendations Assessment, Development, and
Evaluation) Evidence to Decision (EtD) framework, to be used by any partner that will
implement a clinical study, and the Predictive Clinical Model framework, to be followed by
any proponent that will focus on creating a predictive clinical model using artificial
intelligence, machine learning, and deep learning.
The GRADE EtD framework is a tool used to inform and guide health system and public
health decision-making. It presents a set of criteria and indicators that can be used to evaluate
and assess the potential benefits, harms, feasibility, acceptability, and impact of an
intervention or option. Each domain of the GRADE EtD is filled with a list of possible
indicators that should be gathered in the course of the development of the pilots.
The list of indicators includes the seriousness of the problem, priority of the problem, clinical
utility of the intervention, impact of the intervention, benefits and harms of the intervention,
balance between the desirable and undesirable effects, equity and human rights, financial
and economic considerations, values and preferences, acceptability, and feasibility.
PNC 0000002 DARE S1.D1.1 Page 6 of 45
The Predictive Clinical Model is a framework for developing and evaluating predictive
models in clinical research. An indicator for predictive models is a metric or set of metrics
used to evaluate the performance of a model in predicting specific outcomes. Such indicators
are essential for ensuring that the model is effective in achieving the defined tasks and
objectives. Indeed, without indicators, it is difficult to determine whether the model is
working properly or whether improvements are needed.
The selection of appropriate indicators will depend on the type of predictive model and the
application domain, and they should provide meaningful insights into the model’s
performance.
The list includes the seriousness of the problem, the priority of the problem, impact analysis,
discrimination of the model, calibration of the model, equity and human rights, values and
preferences, and feasibility.
Item content. Click the edit button to change this text.
Item content. Click the edit button to change this text.
Item content. Click the edit button to change this text.
Item content. Click the edit button to change this text.