The role of continuous monitoring in acute-care settings for predicting all-cause 30-day hospital readmission: A pilot study
Background: Accurate prediction and prevention of hospital readmission remains a clinical challenge. The influence of different data sources, including remotely monitored continuous vital signs and activity, on machine learning (ML) models’ performances is examined for predicting all-cause unplanned...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844025003743 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832573110375677952 |
|---|---|
| author | Michael Joseph Pettinati Kyriakos Vattis Henry Mitchell Nicole Alexis Rosario David Michael Levine Nandakumar Selvaraj |
| author_facet | Michael Joseph Pettinati Kyriakos Vattis Henry Mitchell Nicole Alexis Rosario David Michael Levine Nandakumar Selvaraj |
| author_sort | Michael Joseph Pettinati |
| collection | DOAJ |
| description | Background: Accurate prediction and prevention of hospital readmission remains a clinical challenge. The influence of different data sources, including remotely monitored continuous vital signs and activity, on machine learning (ML) models’ performances is examined for predicting all-cause unplanned 30-day readmission. Methods: Patients (n = 354) recruited in the emergency department and admitted to acute care at either hospital or home hospital settings are analyzed. Data sources included continuous vital signs and activity, electronic health record (EHR) data – episodic physiological monitoring of laboratory and vital signs, demographics, hospital utilization history, and quality of life survey measures. Five (5) machine learning classifiers were systematically trained by varying input data sources for readmission. Performances of ML models as well as the standard-of-care HOSPITAL score for readmissions were assessed with area under the receiver operating characteristic curve (AUROC) and area under precision-recall curve (AUPRC) statistics. Results: There were 29 patients readmitted out of the 354 total included patients (an 8.2 % readmission rate). The average five-fold cross-validation AUROC and AUPRC scores of the five readmission models ranged from 0.76 to 0.84 (P > .05) and 0.23–0.49 (P < .05), respectively. The model input with episodic physiological monitoring (vitals and labs) had an AUPRC of 0.23 ± 0.07, while the model input with continuous vitals and activity data and episodic vitals and laboratory measurements had an AUPRC of as 0.49 ± 0.10 (P < .005). The HOSPITAL score had an AUROC of 0.62 and AUPRC of 0.16 in this pilot study. Conclusions: The systematic ML modeling and analysis showcased diversity in predictive power and performances of patient data sources for predicting readmission. This pilot study suggests continuous vital signs and activity data, when added to episodic physiological monitoring, boosts performance. The HOSPITAL score shows low predictive power for readmission in this population. Predictive modeling of unplanned 30-day readmission improves with continuous vital signs and activity monitoring. |
| format | Article |
| id | doaj-art-d73206caafa14bb193081a78aaa155a8 |
| institution | Kabale University |
| issn | 2405-8440 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj-art-d73206caafa14bb193081a78aaa155a82025-02-02T05:28:44ZengElsevierHeliyon2405-84402025-01-01112e41994The role of continuous monitoring in acute-care settings for predicting all-cause 30-day hospital readmission: A pilot studyMichael Joseph Pettinati0Kyriakos Vattis1Henry Mitchell2Nicole Alexis Rosario3David Michael Levine4Nandakumar Selvaraj5Biofourmis Inc, Needham, MA, USABiofourmis Inc, Needham, MA, USADivision of General Internal Medicine and Primary Care, Brigham and Women's Hospital, Boston, MA, USADivision of General Internal Medicine and Primary Care, Brigham and Women's Hospital, Boston, MA, USADivision of General Internal Medicine and Primary Care, Brigham and Women's Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USABiofourmis Inc, Needham, MA, USA; Corresponding author. Data Science, Biofourmis Inc c/o Workbar, 117 Kendrick Street Unit 300, Needham, MA 02494, USA.Background: Accurate prediction and prevention of hospital readmission remains a clinical challenge. The influence of different data sources, including remotely monitored continuous vital signs and activity, on machine learning (ML) models’ performances is examined for predicting all-cause unplanned 30-day readmission. Methods: Patients (n = 354) recruited in the emergency department and admitted to acute care at either hospital or home hospital settings are analyzed. Data sources included continuous vital signs and activity, electronic health record (EHR) data – episodic physiological monitoring of laboratory and vital signs, demographics, hospital utilization history, and quality of life survey measures. Five (5) machine learning classifiers were systematically trained by varying input data sources for readmission. Performances of ML models as well as the standard-of-care HOSPITAL score for readmissions were assessed with area under the receiver operating characteristic curve (AUROC) and area under precision-recall curve (AUPRC) statistics. Results: There were 29 patients readmitted out of the 354 total included patients (an 8.2 % readmission rate). The average five-fold cross-validation AUROC and AUPRC scores of the five readmission models ranged from 0.76 to 0.84 (P > .05) and 0.23–0.49 (P < .05), respectively. The model input with episodic physiological monitoring (vitals and labs) had an AUPRC of 0.23 ± 0.07, while the model input with continuous vitals and activity data and episodic vitals and laboratory measurements had an AUPRC of as 0.49 ± 0.10 (P < .005). The HOSPITAL score had an AUROC of 0.62 and AUPRC of 0.16 in this pilot study. Conclusions: The systematic ML modeling and analysis showcased diversity in predictive power and performances of patient data sources for predicting readmission. This pilot study suggests continuous vital signs and activity data, when added to episodic physiological monitoring, boosts performance. The HOSPITAL score shows low predictive power for readmission in this population. Predictive modeling of unplanned 30-day readmission improves with continuous vital signs and activity monitoring.http://www.sciencedirect.com/science/article/pii/S2405844025003743MonitoringPhysiologicPatient readmissionRemote sensing technologyHome environmentHome hospital |
| spellingShingle | Michael Joseph Pettinati Kyriakos Vattis Henry Mitchell Nicole Alexis Rosario David Michael Levine Nandakumar Selvaraj The role of continuous monitoring in acute-care settings for predicting all-cause 30-day hospital readmission: A pilot study Heliyon Monitoring Physiologic Patient readmission Remote sensing technology Home environment Home hospital |
| title | The role of continuous monitoring in acute-care settings for predicting all-cause 30-day hospital readmission: A pilot study |
| title_full | The role of continuous monitoring in acute-care settings for predicting all-cause 30-day hospital readmission: A pilot study |
| title_fullStr | The role of continuous monitoring in acute-care settings for predicting all-cause 30-day hospital readmission: A pilot study |
| title_full_unstemmed | The role of continuous monitoring in acute-care settings for predicting all-cause 30-day hospital readmission: A pilot study |
| title_short | The role of continuous monitoring in acute-care settings for predicting all-cause 30-day hospital readmission: A pilot study |
| title_sort | role of continuous monitoring in acute care settings for predicting all cause 30 day hospital readmission a pilot study |
| topic | Monitoring Physiologic Patient readmission Remote sensing technology Home environment Home hospital |
| url | http://www.sciencedirect.com/science/article/pii/S2405844025003743 |
| work_keys_str_mv | AT michaeljosephpettinati theroleofcontinuousmonitoringinacutecaresettingsforpredictingallcause30dayhospitalreadmissionapilotstudy AT kyriakosvattis theroleofcontinuousmonitoringinacutecaresettingsforpredictingallcause30dayhospitalreadmissionapilotstudy AT henrymitchell theroleofcontinuousmonitoringinacutecaresettingsforpredictingallcause30dayhospitalreadmissionapilotstudy AT nicolealexisrosario theroleofcontinuousmonitoringinacutecaresettingsforpredictingallcause30dayhospitalreadmissionapilotstudy AT davidmichaellevine theroleofcontinuousmonitoringinacutecaresettingsforpredictingallcause30dayhospitalreadmissionapilotstudy AT nandakumarselvaraj theroleofcontinuousmonitoringinacutecaresettingsforpredictingallcause30dayhospitalreadmissionapilotstudy AT michaeljosephpettinati roleofcontinuousmonitoringinacutecaresettingsforpredictingallcause30dayhospitalreadmissionapilotstudy AT kyriakosvattis roleofcontinuousmonitoringinacutecaresettingsforpredictingallcause30dayhospitalreadmissionapilotstudy AT henrymitchell roleofcontinuousmonitoringinacutecaresettingsforpredictingallcause30dayhospitalreadmissionapilotstudy AT nicolealexisrosario roleofcontinuousmonitoringinacutecaresettingsforpredictingallcause30dayhospitalreadmissionapilotstudy AT davidmichaellevine roleofcontinuousmonitoringinacutecaresettingsforpredictingallcause30dayhospitalreadmissionapilotstudy AT nandakumarselvaraj roleofcontinuousmonitoringinacutecaresettingsforpredictingallcause30dayhospitalreadmissionapilotstudy |