Challenges with reinforcement learning model transportability for sepsis treatment in emergency care
Abstract Pivotal moments in sepsis care occur in the emergency department (ED), however, and it is unclear whether ED data is adequate to inform reinforcement learning (RL) models. We evaluated the early opportunity for the AI Clinician, a validated ICU-based RL-model, as a use case. Amongst emergen...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-025-01485-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861604659232768 |
|---|---|
| author | Peter C. Nauka Jason N. Kennedy Emily B. Brant Matthieu Komorowski Romain Pirracchio Derek C. Angus Christopher W. Seymour |
| author_facet | Peter C. Nauka Jason N. Kennedy Emily B. Brant Matthieu Komorowski Romain Pirracchio Derek C. Angus Christopher W. Seymour |
| author_sort | Peter C. Nauka |
| collection | DOAJ |
| description | Abstract Pivotal moments in sepsis care occur in the emergency department (ED), however, and it is unclear whether ED data is adequate to inform reinforcement learning (RL) models. We evaluated the early opportunity for the AI Clinician, a validated ICU-based RL-model, as a use case. Amongst emergency sepsis patients, model parameters were often missing and invariably measured. Current iterations of RL-models trained on ICU data face challenges in emergency sepsis care. |
| format | Article |
| id | doaj-art-ec96bcccfbd2467881e724f9aa7e193b |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-ec96bcccfbd2467881e724f9aa7e193b2025-02-09T12:55:45ZengNature Portfolionpj Digital Medicine2398-63522025-02-01811510.1038/s41746-025-01485-6Challenges with reinforcement learning model transportability for sepsis treatment in emergency carePeter C. Nauka0Jason N. Kennedy1Emily B. Brant2Matthieu Komorowski3Romain Pirracchio4Derek C. Angus5Christopher W. Seymour6Division of Pulmonary, Allergy, Critical Care, and Sleep Medicine, Department of Medicine, University of Pittsburgh Medical CenterDepartment of Critical Care Medicine, University of Pittsburgh School of MedicineDepartment of Critical Care Medicine, University of Pittsburgh School of MedicineDepartment of Surgery and Cancer, Imperial College LondonDepartment of Anesthesia and Perioperative Medicine, Zuckerberg San Francisco General Hospital and Trauma Center, University of California San FranciscoDepartment of Critical Care Medicine, University of Pittsburgh School of MedicineDepartment of Critical Care Medicine, University of Pittsburgh School of MedicineAbstract Pivotal moments in sepsis care occur in the emergency department (ED), however, and it is unclear whether ED data is adequate to inform reinforcement learning (RL) models. We evaluated the early opportunity for the AI Clinician, a validated ICU-based RL-model, as a use case. Amongst emergency sepsis patients, model parameters were often missing and invariably measured. Current iterations of RL-models trained on ICU data face challenges in emergency sepsis care.https://doi.org/10.1038/s41746-025-01485-6 |
| spellingShingle | Peter C. Nauka Jason N. Kennedy Emily B. Brant Matthieu Komorowski Romain Pirracchio Derek C. Angus Christopher W. Seymour Challenges with reinforcement learning model transportability for sepsis treatment in emergency care npj Digital Medicine |
| title | Challenges with reinforcement learning model transportability for sepsis treatment in emergency care |
| title_full | Challenges with reinforcement learning model transportability for sepsis treatment in emergency care |
| title_fullStr | Challenges with reinforcement learning model transportability for sepsis treatment in emergency care |
| title_full_unstemmed | Challenges with reinforcement learning model transportability for sepsis treatment in emergency care |
| title_short | Challenges with reinforcement learning model transportability for sepsis treatment in emergency care |
| title_sort | challenges with reinforcement learning model transportability for sepsis treatment in emergency care |
| url | https://doi.org/10.1038/s41746-025-01485-6 |
| work_keys_str_mv | AT petercnauka challengeswithreinforcementlearningmodeltransportabilityforsepsistreatmentinemergencycare AT jasonnkennedy challengeswithreinforcementlearningmodeltransportabilityforsepsistreatmentinemergencycare AT emilybbrant challengeswithreinforcementlearningmodeltransportabilityforsepsistreatmentinemergencycare AT matthieukomorowski challengeswithreinforcementlearningmodeltransportabilityforsepsistreatmentinemergencycare AT romainpirracchio challengeswithreinforcementlearningmodeltransportabilityforsepsistreatmentinemergencycare AT derekcangus challengeswithreinforcementlearningmodeltransportabilityforsepsistreatmentinemergencycare AT christopherwseymour challengeswithreinforcementlearningmodeltransportabilityforsepsistreatmentinemergencycare |