User login
With the goal of reducing 28-day or 30-day readmissions, some health care teams are turning to predictive models to identify patients at high risk for readmission and to efficiently focus resource-intensive prevention strategies. Recently, there’s been a rapid multiplying of these models.
Many of these models do accurately predict readmission risk, according to a recent BMJ editorial. “Among the 14 published models that target all unplanned readmissions (rather than readmissions for specific patient groups), the ‘C statistic’ ranges from 0.55 to 0.80, meaning that, when presented with two patients, these models correctly identify the higher risk individual between 55% and 80% of the time,” the authors wrote.
But, the authors suggested, the real value is not in simply making predictions but in using predictive models in ways that improve outcomes for patients.
“This will require linking predictive models to actionable opportunities for improving care,” they wrote. “Such linkages will most likely be identified through close collaboration between analytical teams, health care practitioners, and patients.” Being at high risk of readmission is not the only consideration; the patient must also be able to benefit from interventions being considered – they must be “impactible.”
“The distinction between predictive risk and impactibility might explain why practitioners tend to identify quite different patients for intervention than predictive risk models,” the authors wrote.
But together, predictive models and clinicians might produce more effective decisions than either does alone. “One of the strengths of predictive models is that they produce objective and consistent judgments regarding readmission risk, whereas clinical judgment can be affected by personal attitudes or attentiveness. Predictive risk models can also be operationalised across whole populations, and might therefore identify needs that would otherwise be missed by clinical teams (e.g., among more socioeconomically deprived neighbourhoods or groups with inadequate primary care). On the other hand, clinicians have access to a much wider range of information regarding patients than predictive risk models, which is essential to judge impactibility.”
The authors conclude, “The predictive modelling enterprise would benefit enormously from such collaboration because the real goal of this activity lies not in predicting the risk of readmission but in identifying patients at risk for preventable readmissions and ‘impactible’ by available interventions.”
Reference
Steventon A et al. Preventing hospital readmissions: The importance of considering ‘impactibility,’ not just predicted risk. BMJ Qual Saf. 2017 Oct;26(10):782-5. Accessed Oct. 9, 2017.
With the goal of reducing 28-day or 30-day readmissions, some health care teams are turning to predictive models to identify patients at high risk for readmission and to efficiently focus resource-intensive prevention strategies. Recently, there’s been a rapid multiplying of these models.
Many of these models do accurately predict readmission risk, according to a recent BMJ editorial. “Among the 14 published models that target all unplanned readmissions (rather than readmissions for specific patient groups), the ‘C statistic’ ranges from 0.55 to 0.80, meaning that, when presented with two patients, these models correctly identify the higher risk individual between 55% and 80% of the time,” the authors wrote.
But, the authors suggested, the real value is not in simply making predictions but in using predictive models in ways that improve outcomes for patients.
“This will require linking predictive models to actionable opportunities for improving care,” they wrote. “Such linkages will most likely be identified through close collaboration between analytical teams, health care practitioners, and patients.” Being at high risk of readmission is not the only consideration; the patient must also be able to benefit from interventions being considered – they must be “impactible.”
“The distinction between predictive risk and impactibility might explain why practitioners tend to identify quite different patients for intervention than predictive risk models,” the authors wrote.
But together, predictive models and clinicians might produce more effective decisions than either does alone. “One of the strengths of predictive models is that they produce objective and consistent judgments regarding readmission risk, whereas clinical judgment can be affected by personal attitudes or attentiveness. Predictive risk models can also be operationalised across whole populations, and might therefore identify needs that would otherwise be missed by clinical teams (e.g., among more socioeconomically deprived neighbourhoods or groups with inadequate primary care). On the other hand, clinicians have access to a much wider range of information regarding patients than predictive risk models, which is essential to judge impactibility.”
The authors conclude, “The predictive modelling enterprise would benefit enormously from such collaboration because the real goal of this activity lies not in predicting the risk of readmission but in identifying patients at risk for preventable readmissions and ‘impactible’ by available interventions.”
Reference
Steventon A et al. Preventing hospital readmissions: The importance of considering ‘impactibility,’ not just predicted risk. BMJ Qual Saf. 2017 Oct;26(10):782-5. Accessed Oct. 9, 2017.
With the goal of reducing 28-day or 30-day readmissions, some health care teams are turning to predictive models to identify patients at high risk for readmission and to efficiently focus resource-intensive prevention strategies. Recently, there’s been a rapid multiplying of these models.
Many of these models do accurately predict readmission risk, according to a recent BMJ editorial. “Among the 14 published models that target all unplanned readmissions (rather than readmissions for specific patient groups), the ‘C statistic’ ranges from 0.55 to 0.80, meaning that, when presented with two patients, these models correctly identify the higher risk individual between 55% and 80% of the time,” the authors wrote.
But, the authors suggested, the real value is not in simply making predictions but in using predictive models in ways that improve outcomes for patients.
“This will require linking predictive models to actionable opportunities for improving care,” they wrote. “Such linkages will most likely be identified through close collaboration between analytical teams, health care practitioners, and patients.” Being at high risk of readmission is not the only consideration; the patient must also be able to benefit from interventions being considered – they must be “impactible.”
“The distinction between predictive risk and impactibility might explain why practitioners tend to identify quite different patients for intervention than predictive risk models,” the authors wrote.
But together, predictive models and clinicians might produce more effective decisions than either does alone. “One of the strengths of predictive models is that they produce objective and consistent judgments regarding readmission risk, whereas clinical judgment can be affected by personal attitudes or attentiveness. Predictive risk models can also be operationalised across whole populations, and might therefore identify needs that would otherwise be missed by clinical teams (e.g., among more socioeconomically deprived neighbourhoods or groups with inadequate primary care). On the other hand, clinicians have access to a much wider range of information regarding patients than predictive risk models, which is essential to judge impactibility.”
The authors conclude, “The predictive modelling enterprise would benefit enormously from such collaboration because the real goal of this activity lies not in predicting the risk of readmission but in identifying patients at risk for preventable readmissions and ‘impactible’ by available interventions.”
Reference
Steventon A et al. Preventing hospital readmissions: The importance of considering ‘impactibility,’ not just predicted risk. BMJ Qual Saf. 2017 Oct;26(10):782-5. Accessed Oct. 9, 2017.