.png){kind=logo}
Improve adherence rates by 20%-30%, optimize healthcare resources, reduce associated costs and improve patient outcomes.
Non-adherence to treatment is a critical issue in managing chronic and acute diseases.
It is estimated that between 30% and 50% of patients fail to follow their therapeutic regimens, leading to 10% of hospitalizations and up to 125,000 deaths annually in the U.S. alone.
Additionally, it generates additional costs of up to $100 billion annually for healthcare systems [1].
In Spain, non-adherence can reduce treatment effectiveness by 40%, negatively impacting patients' quality of life.
Insufficient adherence disproportionately affects patients with chronic diseases such as diabetes, hypertension, and COPD, with non-compliance rates reaching up to 60% in some groups. This represents avoidable healthcare costs that, in European countries, amount to 1.5%-2% of total health budgets [2].
The predictive model identifies patterns of non-adherence risk using individual and clinical data, such as age, medical history, socioeconomic factors, and treatment complexity.
These predictions enable the design of personalized interventions, including automated reminders, health education, and emotional support, improving the patient experience and enhancing treatment efficacy [1].
Variables such as chronic disease count, medication count, level of participation, and frequency of interaction are used to predict adherence. The synthetic data set for this model is based on empirical findings from scientific research, including studies by Unni, Chaudri, Jimmy and Jose , and Brown and Bussell. These references inform the selection of variables and their ranges, ensuring that model predictions align with real-world behavior within clinically relevant paraeters.
Non-adherence to treatment is a critical issue in managing chronic and acute diseases.
It is estimated that between 30% and 50% of patients fail to follow their therapeutic regimens, leading to 10% of hospitalizations and up to 125,000 deaths annually in the U.S. alone.
Additionally, it generates additional costs of up to $100 billion annually for healthcare systems [1].
In Spain, non-adherence can reduce treatment effectiveness by 40%, negatively impacting patients' quality of life.
Insufficient adherence disproportionately affects patients with chronic diseases such as diabetes, hypertension, and COPD, with non-compliance rates reaching up to 60% in some groups. This represents avoidable healthcare costs that, in European countries, amount to 1.5%-2% of total health budgets [2].
The predictive model identifies patterns of non-adherence risk using individual and clinical data, such as age, medical history, socioeconomic factors, and treatment complexity.
These predictions enable the design of personalized interventions, including automated reminders, health education, and emotional support, improving the patient experience and enhancing treatment efficacy [1].
Failure to implement these technologies perpetuates high non-adherence rates, resulting in significant avoidable costs.
In Spain, expenses due to complications related to non-adherence amount to €11.25 billion annually, of which up to 40% could be avoided with effective intervention strategies [2].
Furthermore, non-adherence erodes trust in PSPs, negatively impacting their reputation and stakeholder outcomes.
Using a predictive model could improve adherence rates by 20%-30%, reducing hospitalizations and avoidable complications. This would optimize healthcare resources, lower associated costs, and improve patients' quality of life, generating a positive clinical and economic impact [2,3].
Variables such as chronic disease count, medication count, level of participation, and frequency of interaction are used to predict adherence. The synthetic data set for this model is based on empirical findings from scientific research, including studies by Unni, Chaudri, Jimmy and Jose , and Brown and Bussell. These references inform the selection of variables and their ranges, ensuring that model predictions align with real-world behavior within clinically relevant paraeters.
