When predictions are used to allocate scarce health care resources: three considerations for models in the era of Covid-19
Abstract Background The need for life-saving interventions such as mechanical ventilation may threaten to outstrip resources during the Covid-19 pandemic. Allocation of these resources to those most likely to benefit can be supported by clinical prediction models. The ethical and practical considera...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2020-05-01
|
| Series: | Diagnostic and Prognostic Research |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s41512-020-00079-y |
| _version_ | 1818107757767688192 |
|---|---|
| author | David M. Kent Jessica K. Paulus Richard R. Sharp Negin Hajizadeh |
| author_facet | David M. Kent Jessica K. Paulus Richard R. Sharp Negin Hajizadeh |
| author_sort | David M. Kent |
| collection | DOAJ |
| description | Abstract Background The need for life-saving interventions such as mechanical ventilation may threaten to outstrip resources during the Covid-19 pandemic. Allocation of these resources to those most likely to benefit can be supported by clinical prediction models. The ethical and practical considerations relevant to predictions supporting decisions about microallocation are distinct from those that inform shared decision-making in ways important for model design. Main body We review three issues of importance for microallocation: (1) Prediction of benefit (or of medical futility) may be technically very challenging; (2) When resources are scarce, calibration is less important for microallocation than is ranking to prioritize patients, since capacity determines thresholds for resource utilization; (3) The concept of group fairness, which is not germane in shared decision-making, is of central importance in microallocation. Therefore, model transparency is important. Conclusion Prediction supporting allocation of life-saving interventions should be explicit, data-driven, frequently updated and open to public scrutiny. This implies a preference for simple, easily understood and easily applied prognostic models. |
| first_indexed | 2024-12-11T02:04:33Z |
| format | Article |
| id | doaj.art-ab71c8b1c52a497aa64d434ea2d3072e |
| institution | Directory Open Access Journal |
| issn | 2397-7523 |
| language | English |
| last_indexed | 2024-12-11T02:04:33Z |
| publishDate | 2020-05-01 |
| publisher | BMC |
| record_format | Article |
| series | Diagnostic and Prognostic Research |
| spelling | doaj.art-ab71c8b1c52a497aa64d434ea2d3072e2022-12-22T01:24:26ZengBMCDiagnostic and Prognostic Research2397-75232020-05-01411310.1186/s41512-020-00079-yWhen predictions are used to allocate scarce health care resources: three considerations for models in the era of Covid-19David M. Kent0Jessica K. Paulus1Richard R. Sharp2Negin Hajizadeh3Predictive Analytics and Comparative Effectiveness (PACE) Center, Tufts Medical CenterPredictive Analytics and Comparative Effectiveness (PACE) Center, Tufts Medical CenterBiomedical Ethics Program, Mayo ClinicFeinstein Institutes for Medical Research, Northwell HealthAbstract Background The need for life-saving interventions such as mechanical ventilation may threaten to outstrip resources during the Covid-19 pandemic. Allocation of these resources to those most likely to benefit can be supported by clinical prediction models. The ethical and practical considerations relevant to predictions supporting decisions about microallocation are distinct from those that inform shared decision-making in ways important for model design. Main body We review three issues of importance for microallocation: (1) Prediction of benefit (or of medical futility) may be technically very challenging; (2) When resources are scarce, calibration is less important for microallocation than is ranking to prioritize patients, since capacity determines thresholds for resource utilization; (3) The concept of group fairness, which is not germane in shared decision-making, is of central importance in microallocation. Therefore, model transparency is important. Conclusion Prediction supporting allocation of life-saving interventions should be explicit, data-driven, frequently updated and open to public scrutiny. This implies a preference for simple, easily understood and easily applied prognostic models.http://link.springer.com/article/10.1186/s41512-020-00079-yClinical prediction modelsCovid-19Healthcare rationingAlgorithmic fairness |
| spellingShingle | David M. Kent Jessica K. Paulus Richard R. Sharp Negin Hajizadeh When predictions are used to allocate scarce health care resources: three considerations for models in the era of Covid-19 Diagnostic and Prognostic Research Clinical prediction models Covid-19 Healthcare rationing Algorithmic fairness |
| title | When predictions are used to allocate scarce health care resources: three considerations for models in the era of Covid-19 |
| title_full | When predictions are used to allocate scarce health care resources: three considerations for models in the era of Covid-19 |
| title_fullStr | When predictions are used to allocate scarce health care resources: three considerations for models in the era of Covid-19 |
| title_full_unstemmed | When predictions are used to allocate scarce health care resources: three considerations for models in the era of Covid-19 |
| title_short | When predictions are used to allocate scarce health care resources: three considerations for models in the era of Covid-19 |
| title_sort | when predictions are used to allocate scarce health care resources three considerations for models in the era of covid 19 |
| topic | Clinical prediction models Covid-19 Healthcare rationing Algorithmic fairness |
| url | http://link.springer.com/article/10.1186/s41512-020-00079-y |
| work_keys_str_mv | AT davidmkent whenpredictionsareusedtoallocatescarcehealthcareresourcesthreeconsiderationsformodelsintheeraofcovid19 AT jessicakpaulus whenpredictionsareusedtoallocatescarcehealthcareresourcesthreeconsiderationsformodelsintheeraofcovid19 AT richardrsharp whenpredictionsareusedtoallocatescarcehealthcareresourcesthreeconsiderationsformodelsintheeraofcovid19 AT neginhajizadeh whenpredictionsareusedtoallocatescarcehealthcareresourcesthreeconsiderationsformodelsintheeraofcovid19 |