<span style="font-variant: small-caps">DataToCare</span>: Predicting Treatments for Intensive Care Unit Patients Based on Similarity of Abnormalities
Clinical decision-making lies at the heart of health care. Medical data collection has made it possible for clinical decision-making to be data-driven. However, data-driven systems for decision-making have so far worked only for a limited set of clinical conditions. It is still unclear whether a pur...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/18/6/311 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839655107431497728 |
|---|---|
| author | Shan Randhawa Abbas Shojaee Elisa Sorrentino Yifan Li Azza Abouzied Dennis Shasha |
| author_facet | Shan Randhawa Abbas Shojaee Elisa Sorrentino Yifan Li Azza Abouzied Dennis Shasha |
| author_sort | Shan Randhawa |
| collection | DOAJ |
| description | Clinical decision-making lies at the heart of health care. Medical data collection has made it possible for clinical decision-making to be data-driven. However, data-driven systems for decision-making have so far worked only for a limited set of clinical conditions. It is still unclear whether a pure data-driven clinical decision-making system can work for a wide set of clinical conditions in real-time environments such as Intensive Care Units. Our <span style="font-variant: small-caps;">DataToCare</span> system receives demographic information, initial diagnoses and measurements from the first hours of a patient’s arrival in an Intensive Care Unit. From that information, <span style="font-variant: small-caps;">DataToCare</span> suggests treatments to offer the patient, based on the treatments given to similar patients. Patients are considered similar if they have abnormal measurements in common. This paper describes the analytics pipeline and the results of its evaluation. <span style="font-variant: small-caps;">DataToCare</span> has the potential to increase patient safety and transfer expertise across medical teams. Though we apply these ideas in the context of Intensive Care Units, the approach could potentially be applied more broadly within medicine. |
| format | Article |
| id | doaj-art-f09d36cd4e064768baf0429aef8e7da7 |
| institution | Matheson Library |
| issn | 1999-4893 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj-art-f09d36cd4e064768baf0429aef8e7da72025-06-25T13:21:17ZengMDPI AGAlgorithms1999-48932025-05-0118631110.3390/a18060311<span style="font-variant: small-caps">DataToCare</span>: Predicting Treatments for Intensive Care Unit Patients Based on Similarity of AbnormalitiesShan Randhawa0Abbas Shojaee1Elisa Sorrentino2Yifan Li3Azza Abouzied4Dennis Shasha5School of Information, University of Michigan, Ann Arbor, MI 48109, USABiology Department, New York University, New York, NY 10012, USAFujifilm Healthcare Italia, 20090 Milano, ItalyVirginia Tech Carilion School of Medicine, Roanoke, VA 24016, USADepartment of Computer Science, New York University, Abu Dhabi P.O. Box 129188, United Arab EmiratesDepartment of Computer Science, New York University, New York, NY 10012, USAClinical decision-making lies at the heart of health care. Medical data collection has made it possible for clinical decision-making to be data-driven. However, data-driven systems for decision-making have so far worked only for a limited set of clinical conditions. It is still unclear whether a pure data-driven clinical decision-making system can work for a wide set of clinical conditions in real-time environments such as Intensive Care Units. Our <span style="font-variant: small-caps;">DataToCare</span> system receives demographic information, initial diagnoses and measurements from the first hours of a patient’s arrival in an Intensive Care Unit. From that information, <span style="font-variant: small-caps;">DataToCare</span> suggests treatments to offer the patient, based on the treatments given to similar patients. Patients are considered similar if they have abnormal measurements in common. This paper describes the analytics pipeline and the results of its evaluation. <span style="font-variant: small-caps;">DataToCare</span> has the potential to increase patient safety and transfer expertise across medical teams. Though we apply these ideas in the context of Intensive Care Units, the approach could potentially be applied more broadly within medicine.https://www.mdpi.com/1999-4893/18/6/311recommender systemtreatments prediction pipelineIntensive Care Unithealth informatics |
| spellingShingle | Shan Randhawa Abbas Shojaee Elisa Sorrentino Yifan Li Azza Abouzied Dennis Shasha <span style="font-variant: small-caps">DataToCare</span>: Predicting Treatments for Intensive Care Unit Patients Based on Similarity of Abnormalities Algorithms recommender system treatments prediction pipeline Intensive Care Unit health informatics |
| title | <span style="font-variant: small-caps">DataToCare</span>: Predicting Treatments for Intensive Care Unit Patients Based on Similarity of Abnormalities |
| title_full | <span style="font-variant: small-caps">DataToCare</span>: Predicting Treatments for Intensive Care Unit Patients Based on Similarity of Abnormalities |
| title_fullStr | <span style="font-variant: small-caps">DataToCare</span>: Predicting Treatments for Intensive Care Unit Patients Based on Similarity of Abnormalities |
| title_full_unstemmed | <span style="font-variant: small-caps">DataToCare</span>: Predicting Treatments for Intensive Care Unit Patients Based on Similarity of Abnormalities |
| title_short | <span style="font-variant: small-caps">DataToCare</span>: Predicting Treatments for Intensive Care Unit Patients Based on Similarity of Abnormalities |
| title_sort | span style font variant small caps datatocare span predicting treatments for intensive care unit patients based on similarity of abnormalities |
| topic | recommender system treatments prediction pipeline Intensive Care Unit health informatics |
| url | https://www.mdpi.com/1999-4893/18/6/311 |
| work_keys_str_mv | AT shanrandhawa spanstylefontvariantsmallcapsdatatocarespanpredictingtreatmentsforintensivecareunitpatientsbasedonsimilarityofabnormalities AT abbasshojaee spanstylefontvariantsmallcapsdatatocarespanpredictingtreatmentsforintensivecareunitpatientsbasedonsimilarityofabnormalities AT elisasorrentino spanstylefontvariantsmallcapsdatatocarespanpredictingtreatmentsforintensivecareunitpatientsbasedonsimilarityofabnormalities AT yifanli spanstylefontvariantsmallcapsdatatocarespanpredictingtreatmentsforintensivecareunitpatientsbasedonsimilarityofabnormalities AT azzaabouzied spanstylefontvariantsmallcapsdatatocarespanpredictingtreatmentsforintensivecareunitpatientsbasedonsimilarityofabnormalities AT dennisshasha spanstylefontvariantsmallcapsdatatocarespanpredictingtreatmentsforintensivecareunitpatientsbasedonsimilarityofabnormalities |