Predictive modeling of U.S. health care spending in late life
2017 © The Authors. That one-quarter of Medicare spending in the United States occurs in the last year of life is commonly interpreted as waste. But this interpretation presumes knowledge of who will die and when. Here we analyze how spending is distributed by predicted mortality, based on a machine...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Association for the Advancement of Science (AAAS)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/135852 |
| _version_ | 1826200685722468352 |
|---|---|
| author | Einav, Liran Finkelstein, Amy Mullainathan, Sendhil Obermeyer, Ziad |
| author_facet | Einav, Liran Finkelstein, Amy Mullainathan, Sendhil Obermeyer, Ziad |
| author_sort | Einav, Liran |
| collection | MIT |
| description | 2017 © The Authors. That one-quarter of Medicare spending in the United States occurs in the last year of life is commonly interpreted as waste. But this interpretation presumes knowledge of who will die and when. Here we analyze how spending is distributed by predicted mortality, based on a machine-learning model of annual mortality risk built using Medicare claims. Death is highly unpredictable. Less than 5% of spending is accounted for by individuals with predicted mortality above 50%. The simple fact that we spend more on the sick—both on those who recover and those who die—accounts for 30 to 50% of the concentration of spending on the dead. Our results suggest that spending on the ex post dead does not necessarily mean that we spend on the ex ante “hopeless.” |
| first_indexed | 2024-09-23T11:40:16Z |
| format | Article |
| id | mit-1721.1/135852 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:40:16Z |
| publishDate | 2021 |
| publisher | American Association for the Advancement of Science (AAAS) |
| record_format | dspace |
| spelling | mit-1721.1/1358522021-10-28T04:13:06Z Predictive modeling of U.S. health care spending in late life Einav, Liran Finkelstein, Amy Mullainathan, Sendhil Obermeyer, Ziad 2017 © The Authors. That one-quarter of Medicare spending in the United States occurs in the last year of life is commonly interpreted as waste. But this interpretation presumes knowledge of who will die and when. Here we analyze how spending is distributed by predicted mortality, based on a machine-learning model of annual mortality risk built using Medicare claims. Death is highly unpredictable. Less than 5% of spending is accounted for by individuals with predicted mortality above 50%. The simple fact that we spend more on the sick—both on those who recover and those who die—accounts for 30 to 50% of the concentration of spending on the dead. Our results suggest that spending on the ex post dead does not necessarily mean that we spend on the ex ante “hopeless.” 2021-10-27T20:29:38Z 2021-10-27T20:29:38Z 2018 2019-10-22T17:32:52Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/135852 en 10.1126/SCIENCE.AAR5045 Science Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf American Association for the Advancement of Science (AAAS) PMC |
| spellingShingle | Einav, Liran Finkelstein, Amy Mullainathan, Sendhil Obermeyer, Ziad Predictive modeling of U.S. health care spending in late life |
| title | Predictive modeling of U.S. health care spending in late life |
| title_full | Predictive modeling of U.S. health care spending in late life |
| title_fullStr | Predictive modeling of U.S. health care spending in late life |
| title_full_unstemmed | Predictive modeling of U.S. health care spending in late life |
| title_short | Predictive modeling of U.S. health care spending in late life |
| title_sort | predictive modeling of u s health care spending in late life |
| url | https://hdl.handle.net/1721.1/135852 |
| work_keys_str_mv | AT einavliran predictivemodelingofushealthcarespendinginlatelife AT finkelsteinamy predictivemodelingofushealthcarespendinginlatelife AT mullainathansendhil predictivemodelingofushealthcarespendinginlatelife AT obermeyerziad predictivemodelingofushealthcarespendinginlatelife |