Sabrina Adelaine
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Sabrina Adelaine has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Brian W. Patterson
BerbeeWalsh Department of Emergency Medicine, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
6 shared publications - Frank Liao
University of Wisconsin Hospitals and Clinics, Madison, WI, USA
6 shared publications - Fernando Acosta-Perez
Department of Industrial and Systems Engineering, University of Wisconsin-Madison, Madison, WI, United States
4 shared publications - Gabriel Zayas-Cabán
University of Wisconsin–Madison
4 shared publications - Justin J. Boutilier
Telfer School of Management, University of Ottawa, Ottawa, Ontario K1N 9B9, Canada
4 shared publications - Benjamin Schnapp
Benjamin H. Schnapp, MD, MEd, is an Associate Professor, BerbeeWalsh Department of Emergency Medicine, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA
2 shared publications
Latest Publications
- Open Access
- 23 September 2025
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 27 (1) , e83802
Correction: Toward Real-Time Discharge Volume Predictions in Multisite Health Care Systems: Longitudinal Observational Study
[This corrects the article DOI: 10.2196/63765.].
- 23 September 2025
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 27 (1) , e83802
Open AccessCorrection: Toward Real-Time Discharge Volume Predictions in Multisite Health Care Systems: Longitudinal Observational Study
[This corrects the article DOI: 10.2196/63765.].
- Open Access
- 8 September 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Correction: Toward Real-Time Discharge Volume Predictions in Multisite Health Care Systems: Longitudinal Observational Study (Preprint)
UNSTRUCTURED Correction: Towards Real Time Discharge Volume Predictions in Multisite Healthcare Systems: Longitudinal Observational Study The authors would like to correct several in-text citation issues that occurred during the editing process. In the Introduction, paragraph 4, the third citation should be [20,21] (was [15,16]). In paragraph 5, the first citation should be [11–15] (was [7–11]), the second [16,17] (was [12,13]), and the fifth and sixth [11–13] (were [7–9]). Additionally, we are adding a missing reference: Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B, 58(1), 267–288, now listed as reference [22]. As a result, all subsequent references have been renumbered. In the Models and Model Evaluation section, the first citation is now updated to Tibshirani [22], and the second refers only to the Random Forest paper [23] (previously [22]). The correction will appear in the online version of the paper on the JMIR Publications website, together with the publication of this correction notice. Because this was made after submission to PubMed, PubMed Central, and other full-text repositories, the corrected article has also been resubmitted to those repositories.
- 8 September 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessCorrection: Toward Real-Time Discharge Volume Predictions in Multisite Health Care Systems: Longitudinal Observational Study (Preprint)
UNSTRUCTURED Correction: Towards Real Time Discharge Volume Predictions in Multisite Healthcare Systems: Longitudinal Observational Study The authors would like to correct several in-text citation issues that occurred during the editing process. In the Introduction, paragraph 4, the third citation should be [20,21] (was [15,16]). In paragraph 5, the first citation should be [11–15] (was [7–11]), the second [16,17] (was [12,13]), and the fifth and sixth [11–13] (were [7–9]). Additionally, we are adding a missing reference: Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B, 58(1), 267–288, now listed as reference [22]. As a result, all subsequent references have been renumbered. In the Models and Model Evaluation section, the first citation is now updated to Tibshirani [22], and the second refers only to the Random Forest paper [23] (previously [22]). The correction will appear in the online version of the paper on the JMIR Publications website, together with the publication of this correction notice. Because this was made after submission to PubMed, PubMed Central, and other full-text repositories, the corrected article has also been resubmitted to those repositories.
- Open Access
- 30 April 2025
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 27 (1) , e63765
Toward Real-Time Discharge Volume Predictions in Multisite Health Care Systems: Longitudinal Observational Study
Background: Emergency department (ED) admissions are one of the most critical decisions made in health care, with 40% of ED visits resulting in inpatient hospitalization for Medicare patients. A main challenge with the ED admissions process is the inability to move patients from the ED to an inpatient unit quickly. Identifying hospital discharge volume in advance may be valuable in helping hospitals determine capacity management mechanisms to reduce ED boarding, such as transferring low-complexity patients to neighboring hospitals. Although previous research has studied the prediction of discharges in the context of inpatient care, most of the work is on long-term predictions (ie, discharges within the next 24 to 48 hours) in single-site health care systems. In this study, we approach the problem of inpatient discharge prediction from a system-wide lens and evaluate the potential interactions between the two facilities in our partner multisite system to predict short-term discharge volume. Objective: The objective of this paper was to predict discharges from the general care units within a large tertiary teaching hospital network in the Midwest and evaluate the impact of external information from other hospitals on model performance. Methods: We conducted 2 experiments with 174,799 discharge records from 2 hospitals. In Experiment 1, we predicted the number of discharges across 2 time points (within the hour and the next 4 hours) using random forest (RF) and linear regression (LR) models. Models with access to internal hospital data (ie, system-agnostic) were compared with models with access to additional data from the other hospitals in the network (ie, system-aware). In Experiment 2, we evaluated the performance of an RF model to predict afternoon discharges (ie, 12 PM to 4 PM) 1 to 4 hours in advance. Results: In Experiment 1 and Hospital 1, RF and LR models performed equivalently, with R2 scores varying from 0.76 (hourly) to 0.89 (4 hours). In Hospital 2, the RF model performed best, with scores varying from 0.68 (hourly) to 0.84 (4 hours), while scores for LR models ranged from 0.63 to 0.80. There was no significant difference in performance between a system-aware approach and a system-agnostic one. In experiment 2, the mean absolute percentage error increased from 11% to 16% when predicting 4 hours in advance relative to zero hours in Hospital 1 and from 24% to 35% in Hospital 2. Conclusions: Short-term discharges in multisite hospital systems can be locally predicted with high accuracy, even when predicting hours in advance.
- 30 April 2025
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 27 (1) , e63765
Open AccessToward Real-Time Discharge Volume Predictions in Multisite Health Care Systems: Longitudinal Observational Study
Background: Emergency department (ED) admissions are one of the most critical decisions made in health care, with 40% of ED visits resulting in inpatient hospitalization for Medicare patients. A main challenge with the ED admissions process is the inability to move patients from the ED to an inpatient unit quickly. Identifying hospital discharge volume in advance may be valuable in helping hospitals determine capacity management mechanisms to reduce ED boarding, such as transferring low-complexity patients to neighboring hospitals. Although previous research has studied the prediction of discharges in the context of inpatient care, most of the work is on long-term predictions (ie, discharges within the next 24 to 48 hours) in single-site health care systems. In this study, we approach the problem of inpatient discharge prediction from a system-wide lens and evaluate the potential interactions between the two facilities in our partner multisite system to predict short-term discharge volume. Objective: The objective of this paper was to predict discharges from the general care units within a large tertiary teaching hospital network in the Midwest and evaluate the impact of external information from other hospitals on model performance. Methods: We conducted 2 experiments with 174,799 discharge records from 2 hospitals. In Experiment 1, we predicted the number of discharges across 2 time points (within the hour and the next 4 hours) using random forest (RF) and linear regression (LR) models. Models with access to internal hospital data (ie, system-agnostic) were compared with models with access to additional data from the other hospitals in the network (ie, system-aware). In Experiment 2, we evaluated the performance of an RF model to predict afternoon discharges (ie, 12 PM to 4 PM) 1 to 4 hours in advance. Results: In Experiment 1 and Hospital 1, RF and LR models performed equivalently, with R2 scores varying from 0.76 (hourly) to 0.89 (4 hours). In Hospital 2, the RF model performed best, with scores varying from 0.68 (hourly) to 0.84 (4 hours), while scores for LR models ranged from 0.63 to 0.80. There was no significant difference in performance between a system-aware approach and a system-agnostic one. In experiment 2, the mean absolute percentage error increased from 11% to 16% when predicting 4 hours in advance relative to zero hours in Hospital 1 and from 24% to 35% in Hospital 2. Conclusions: Short-term discharges in multisite hospital systems can be locally predicted with high accuracy, even when predicting hours in advance.
- Open Access
- 1 July 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Toward Real-Time Discharge Volume Predictions in Multisite Health Care Systems: Longitudinal Observational Study (Preprint)
BACKGROUND Emergency department (ED) admissions are one of the most critical decisions made in health care, with 40% of ED visits resulting in inpatient hospitalization for Medicare patients. A main challenge with the ED admissions process is the inability to move patients from the ED to an inpatient unit quickly. Identifying hospital discharge volume in advance may be valuable in helping hospitals determine capacity management mechanisms to reduce ED boarding, such as transferring low-complexity patients to neighboring hospitals. Although previous research has studied the prediction of discharges in the context of inpatient care, most of the work is on long-term predictions (ie, discharges within the next 24 to 48 hours) in single-site health care systems. In this study, we approach the problem of inpatient discharge prediction from a system-wide lens and evaluate the potential interactions between the two facilities in our partner multisite system to predict short-term discharge volume. OBJECTIVE The objective of this paper was to predict discharges from the general care units within a large tertiary teaching hospital network in the Midwest and evaluate the impact of external information from other hospitals on model performance. METHODS We conducted 2 experiments with 174,799 discharge records from 2 hospitals. In Experiment 1, we predicted the number of discharges across 2 time points (within the hour and the next 4 hours) using random forest (RF) and linear regression (LR) models. Models with access to internal hospital data (ie, system-agnostic) were compared with models with access to additional data from the other hospitals in the network (ie, system-aware). In Experiment 2, we evaluated the performance of an RF model to predict afternoon discharges (ie, 12 PM to 4 PM) 1 to 4 hours in advance. RESULTS In Experiment 1 and Hospital 1, RF and LR models performed equivalently, with R2 scores varying from 0.76 (hourly) to 0.89 (4 hours). In Hospital 2, the RF model performed best, with scores varying from 0.68 (hourly) to 0.84 (4 hours), while scores for LR models ranged from 0.63 to 0.80. There was no significant difference in performance between a system-aware approach and a system-agnostic one. In experiment 2, the mean absolute percentage error increased from 11% to 16% when predicting 4 hours in advance relative to zero hours in Hospital 1 and from 24% to 35% in Hospital 2. CONCLUSIONS Short-term discharges in multisite hospital systems can be locally predicted with high accuracy, even when predicting hours in advance.
- 1 July 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessToward Real-Time Discharge Volume Predictions in Multisite Health Care Systems: Longitudinal Observational Study (Preprint)
BACKGROUND Emergency department (ED) admissions are one of the most critical decisions made in health care, with 40% of ED visits resulting in inpatient hospitalization for Medicare patients. A main challenge with the ED admissions process is the inability to move patients from the ED to an inpatient unit quickly. Identifying hospital discharge volume in advance may be valuable in helping hospitals determine capacity management mechanisms to reduce ED boarding, such as transferring low-complexity patients to neighboring hospitals. Although previous research has studied the prediction of discharges in the context of inpatient care, most of the work is on long-term predictions (ie, discharges within the next 24 to 48 hours) in single-site health care systems. In this study, we approach the problem of inpatient discharge prediction from a system-wide lens and evaluate the potential interactions between the two facilities in our partner multisite system to predict short-term discharge volume. OBJECTIVE The objective of this paper was to predict discharges from the general care units within a large tertiary teaching hospital network in the Midwest and evaluate the impact of external information from other hospitals on model performance. METHODS We conducted 2 experiments with 174,799 discharge records from 2 hospitals. In Experiment 1, we predicted the number of discharges across 2 time points (within the hour and the next 4 hours) using random forest (RF) and linear regression (LR) models. Models with access to internal hospital data (ie, system-agnostic) were compared with models with access to additional data from the other hospitals in the network (ie, system-aware). In Experiment 2, we evaluated the performance of an RF model to predict afternoon discharges (ie, 12 PM to 4 PM) 1 to 4 hours in advance. RESULTS In Experiment 1 and Hospital 1, RF and LR models performed equivalently, with R2 scores varying from 0.76 (hourly) to 0.89 (4 hours). In Hospital 2, the RF model performed best, with scores varying from 0.68 (hourly) to 0.84 (4 hours), while scores for LR models ranged from 0.63 to 0.80. There was no significant difference in performance between a system-aware approach and a system-agnostic one. In experiment 2, the mean absolute percentage error increased from 11% to 16% when predicting 4 hours in advance relative to zero hours in Hospital 1 and from 24% to 35% in Hospital 2. CONCLUSIONS Short-term discharges in multisite hospital systems can be locally predicted with high accuracy, even when predicting hours in advance.
- Open Access
- 20 April 2023
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 11 (1) , e44977
Deployment of Real-time Natural Language Processing and Deep Learning Clinical Decision Support in the Electronic Health Record: Pipeline Implementation for an Opioid Misuse Screener in Hospitalized Adults
Background: The clinical narrative in electronic health records (EHRs) carries valuable information for predictive analytics; however, its free-text form is difficult to mine and analyze for clinical decision support (CDS). Large-scale clinical natural language processing (NLP) pipelines have focused on data warehouse applications for retrospective research efforts. There remains a paucity of evidence for implementing NLP pipelines at the bedside for health care delivery. Objective: We aimed to detail a hospital-wide, operational pipeline to implement a real-time NLP-driven CDS tool and describe a protocol for an implementation framework with a user-centered design of the CDS tool. Methods: The pipeline integrated a previously trained open-source convolutional neural network model for screening opioid misuse that leveraged EHR notes mapped to standardized medical vocabularies in the Unified Medical Language System. A sample of 100 adult encounters were reviewed by a physician informaticist for silent testing of the deep learning algorithm before deployment. An end user interview survey was developed to examine the user acceptability of a best practice alert (BPA) to provide the screening results with recommendations. The planned implementation also included a human-centered design with user feedback on the BPA, an implementation framework with cost-effectiveness, and a noninferiority patient outcome analysis plan. Results: The pipeline was a reproducible workflow with a shared pseudocode for a cloud service to ingest, process, and store clinical notes as Health Level 7 messages from a major EHR vendor in an elastic cloud computing environment. Feature engineering of the notes used an open-source NLP engine, and the features were fed into the deep learning algorithm, with the results returned as a BPA in the EHR. On-site silent testing of the deep learning algorithm demonstrated a sensitivity of 93% (95% CI 66%-99%) and specificity of 92% (95% CI 84%-96%), similar to published validation studies. Before deployment, approvals were received across hospital committees for inpatient operations. Five interviews were conducted; they informed the development of an educational flyer and further modified the BPA to exclude certain patients and allow the refusal of recommendations. The longest delay in pipeline development was because of cybersecurity approvals, especially because of the exchange of protected health information between the Microsoft (Microsoft Corp) and Epic (Epic Systems Corp) cloud vendors. In silent testing, the resultant pipeline provided a BPA to the bedside within minutes of a provider entering a note in the EHR. Conclusions: The components of the real-time NLP pipeline were detailed with open-source tools and pseudocode for other health systems to benchmark. The deployment of medical artificial intelligence systems in routine clinical care presents an important yet unfulfilled opportunity, and our protocol aimed to close the gap in the implementation of artificial intelligence–driven CDS. Trial Registration: ClinicalTrials.gov NCT05745480; https://www.clinicaltrials.gov/ct2/show/NCT05745480
- 20 April 2023
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 11 (1) , e44977
Open AccessDeployment of Real-time Natural Language Processing and Deep Learning Clinical Decision Support in the Electronic Health Record: Pipeline Implementation for an Opioid Misuse Screener in Hospitalized Adults
Background: The clinical narrative in electronic health records (EHRs) carries valuable information for predictive analytics; however, its free-text form is difficult to mine and analyze for clinical decision support (CDS). Large-scale clinical natural language processing (NLP) pipelines have focused on data warehouse applications for retrospective research efforts. There remains a paucity of evidence for implementing NLP pipelines at the bedside for health care delivery. Objective: We aimed to detail a hospital-wide, operational pipeline to implement a real-time NLP-driven CDS tool and describe a protocol for an implementation framework with a user-centered design of the CDS tool. Methods: The pipeline integrated a previously trained open-source convolutional neural network model for screening opioid misuse that leveraged EHR notes mapped to standardized medical vocabularies in the Unified Medical Language System. A sample of 100 adult encounters were reviewed by a physician informaticist for silent testing of the deep learning algorithm before deployment. An end user interview survey was developed to examine the user acceptability of a best practice alert (BPA) to provide the screening results with recommendations. The planned implementation also included a human-centered design with user feedback on the BPA, an implementation framework with cost-effectiveness, and a noninferiority patient outcome analysis plan. Results: The pipeline was a reproducible workflow with a shared pseudocode for a cloud service to ingest, process, and store clinical notes as Health Level 7 messages from a major EHR vendor in an elastic cloud computing environment. Feature engineering of the notes used an open-source NLP engine, and the features were fed into the deep learning algorithm, with the results returned as a BPA in the EHR. On-site silent testing of the deep learning algorithm demonstrated a sensitivity of 93% (95% CI 66%-99%) and specificity of 92% (95% CI 84%-96%), similar to published validation studies. Before deployment, approvals were received across hospital committees for inpatient operations. Five interviews were conducted; they informed the development of an educational flyer and further modified the BPA to exclude certain patients and allow the refusal of recommendations. The longest delay in pipeline development was because of cybersecurity approvals, especially because of the exchange of protected health information between the Microsoft (Microsoft Corp) and Epic (Epic Systems Corp) cloud vendors. In silent testing, the resultant pipeline provided a BPA to the bedside within minutes of a provider entering a note in the EHR. Conclusions: The components of the real-time NLP pipeline were detailed with open-source tools and pseudocode for other health systems to benchmark. The deployment of medical artificial intelligence systems in routine clinical care presents an important yet unfulfilled opportunity, and our protocol aimed to close the gap in the implementation of artificial intelligence–driven CDS. Trial Registration: ClinicalTrials.gov NCT05745480; https://www.clinicaltrials.gov/ct2/show/NCT05745480
- Open Access
- 11 December 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Deployment of Real-time Natural Language Processing and Deep Learning Clinical Decision Support in the Electronic Health Record: Pipeline Implementation for an Opioid Misuse Screener in Hospitalized Adults (Preprint)
BACKGROUND The clinical narrative in electronic health records (EHRs) carries valuable information for predictive analytics; however, its free-text form is difficult to mine and analyze for clinical decision support (CDS). Large-scale clinical natural language processing (NLP) pipelines have focused on data warehouse applications for retrospective research efforts. There remains a paucity of evidence for implementing NLP pipelines at the bedside for health care delivery. OBJECTIVE We aimed to detail a hospital-wide, operational pipeline to implement a real-time NLP-driven CDS tool and describe a protocol for an implementation framework with a user-centered design of the CDS tool. METHODS The pipeline integrated a previously trained open-source convolutional neural network model for screening opioid misuse that leveraged EHR notes mapped to standardized medical vocabularies in the Unified Medical Language System. A sample of 100 adult encounters were reviewed by a physician informaticist for silent testing of the deep learning algorithm before deployment. An end user interview survey was developed to examine the user acceptability of a best practice alert (BPA) to provide the screening results with recommendations. The planned implementation also included a human-centered design with user feedback on the BPA, an implementation framework with cost-effectiveness, and a noninferiority patient outcome analysis plan. RESULTS The pipeline was a reproducible workflow with a shared pseudocode for a cloud service to ingest, process, and store clinical notes as Health Level 7 messages from a major EHR vendor in an elastic cloud computing environment. Feature engineering of the notes used an open-source NLP engine, and the features were fed into the deep learning algorithm, with the results returned as a BPA in the EHR. On-site silent testing of the deep learning algorithm demonstrated a sensitivity of 93% (95% CI 66%-99%) and specificity of 92% (95% CI 84%-96%), similar to published validation studies. Before deployment, approvals were received across hospital committees for inpatient operations. Five interviews were conducted; they informed the development of an educational flyer and further modified the BPA to exclude certain patients and allow the refusal of recommendations. The longest delay in pipeline development was because of cybersecurity approvals, especially because of the exchange of protected health information between the Microsoft (Microsoft Corp) and Epic (Epic Systems Corp) cloud vendors. In silent testing, the resultant pipeline provided a BPA to the bedside within minutes of a provider entering a note in the EHR. CONCLUSIONS The components of the real-time NLP pipeline were detailed with open-source tools and pseudocode for other health systems to benchmark. The deployment of medical artificial intelligence systems in routine clinical care presents an important yet unfulfilled opportunity, and our protocol aimed to close the gap in the implementation of artificial intelligence–driven CDS. CLINICALTRIAL ClinicalTrials.gov NCT05745480; https://www.clinicaltrials.gov/ct2/show/NCT05745480
- 11 December 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessDeployment of Real-time Natural Language Processing and Deep Learning Clinical Decision Support in the Electronic Health Record: Pipeline Implementation for an Opioid Misuse Screener in Hospitalized Adults (Preprint)
BACKGROUND The clinical narrative in electronic health records (EHRs) carries valuable information for predictive analytics; however, its free-text form is difficult to mine and analyze for clinical decision support (CDS). Large-scale clinical natural language processing (NLP) pipelines have focused on data warehouse applications for retrospective research efforts. There remains a paucity of evidence for implementing NLP pipelines at the bedside for health care delivery. OBJECTIVE We aimed to detail a hospital-wide, operational pipeline to implement a real-time NLP-driven CDS tool and describe a protocol for an implementation framework with a user-centered design of the CDS tool. METHODS The pipeline integrated a previously trained open-source convolutional neural network model for screening opioid misuse that leveraged EHR notes mapped to standardized medical vocabularies in the Unified Medical Language System. A sample of 100 adult encounters were reviewed by a physician informaticist for silent testing of the deep learning algorithm before deployment. An end user interview survey was developed to examine the user acceptability of a best practice alert (BPA) to provide the screening results with recommendations. The planned implementation also included a human-centered design with user feedback on the BPA, an implementation framework with cost-effectiveness, and a noninferiority patient outcome analysis plan. RESULTS The pipeline was a reproducible workflow with a shared pseudocode for a cloud service to ingest, process, and store clinical notes as Health Level 7 messages from a major EHR vendor in an elastic cloud computing environment. Feature engineering of the notes used an open-source NLP engine, and the features were fed into the deep learning algorithm, with the results returned as a BPA in the EHR. On-site silent testing of the deep learning algorithm demonstrated a sensitivity of 93% (95% CI 66%-99%) and specificity of 92% (95% CI 84%-96%), similar to published validation studies. Before deployment, approvals were received across hospital committees for inpatient operations. Five interviews were conducted; they informed the development of an educational flyer and further modified the BPA to exclude certain patients and allow the refusal of recommendations. The longest delay in pipeline development was because of cybersecurity approvals, especially because of the exchange of protected health information between the Microsoft (Microsoft Corp) and Epic (Epic Systems Corp) cloud vendors. In silent testing, the resultant pipeline provided a BPA to the bedside within minutes of a provider entering a note in the EHR. CONCLUSIONS The components of the real-time NLP pipeline were detailed with open-source tools and pseudocode for other health systems to benchmark. The deployment of medical artificial intelligence systems in routine clinical care presents an important yet unfulfilled opportunity, and our protocol aimed to close the gap in the implementation of artificial intelligence–driven CDS. CLINICALTRIAL ClinicalTrials.gov NCT05745480; https://www.clinicaltrials.gov/ct2/show/NCT05745480