1
|
Poly TN, Islam MM, Muhtar MS, Yang HC, Nguyen PAA, Li YCJ. Machine Learning Approach to Reduce Alert Fatigue Using a Disease Medication-Related Clinical Decision Support System: Model Development and Validation. JMIR Med Inform 2020; 8:e19489. [PMID: 33211018 PMCID: PMC7714650 DOI: 10.2196/19489] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2020] [Revised: 09/12/2020] [Accepted: 09/19/2020] [Indexed: 12/28/2022] Open
Abstract
Background Computerized physician order entry (CPOE) systems are incorporated into clinical decision support systems (CDSSs) to reduce medication errors and improve patient safety. Automatic alerts generated from CDSSs can directly assist physicians in making useful clinical decisions and can help shape prescribing behavior. Multiple studies reported that approximately 90%-96% of alerts are overridden by physicians, which raises questions about the effectiveness of CDSSs. There is intense interest in developing sophisticated methods to combat alert fatigue, but there is no consensus on the optimal approaches so far. Objective Our objective was to develop machine learning prediction models to predict physicians’ responses in order to reduce alert fatigue from disease medication–related CDSSs. Methods We collected data from a disease medication–related CDSS from a university teaching hospital in Taiwan. We considered prescriptions that triggered alerts in the CDSS between August 2018 and May 2019. Machine learning models, such as artificial neural network (ANN), random forest (RF), naïve Bayes (NB), gradient boosting (GB), and support vector machine (SVM), were used to develop prediction models. The data were randomly split into training (80%) and testing (20%) datasets. Results A total of 6453 prescriptions were used in our model. The ANN machine learning prediction model demonstrated excellent discrimination (area under the receiver operating characteristic curve [AUROC] 0.94; accuracy 0.85), whereas the RF, NB, GB, and SVM models had AUROCs of 0.93, 0.91, 0.91, and 0.80, respectively. The sensitivity and specificity of the ANN model were 0.87 and 0.83, respectively. Conclusions In this study, ANN showed substantially better performance in predicting individual physician responses to an alert from a disease medication–related CDSS, as compared to the other models. To our knowledge, this is the first study to use machine learning models to predict physician responses to alerts; furthermore, it can help to develop sophisticated CDSSs in real-world clinical settings.
Collapse
Affiliation(s)
- Tahmina Nasrin Poly
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan.,International Center for Health Information Technology, Taipei Medical University, Taipei, Taiwan.,Research Center of Big Data and Meta-analysis, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan
| | - Md Mohaimenul Islam
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan.,International Center for Health Information Technology, Taipei Medical University, Taipei, Taiwan.,Research Center of Big Data and Meta-analysis, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan
| | | | - Hsuan-Chia Yang
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan.,International Center for Health Information Technology, Taipei Medical University, Taipei, Taiwan.,Research Center of Big Data and Meta-analysis, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan
| | - Phung Anh Alex Nguyen
- International Center for Health Information Technology, Taipei Medical University, Taipei, Taiwan.,Department of Healthcare Information & Management, Ming Chuan University, Taoyuan City, Taiwan
| | - Yu-Chuan Jack Li
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan.,International Center for Health Information Technology, Taipei Medical University, Taipei, Taiwan.,Research Center of Big Data and Meta-analysis, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan.,Department of Dermatology, Wan Fang Hospital, Taipei, Taiwan.,TMU Research Center of Cancer Translational Medicine, Taipei Medical University, Taipei, Taiwan
| |
Collapse
|
2
|
Feng C, Le D, McCoy AB. Using Electronic Health Records to Identify Adverse Drug Events in Ambulatory Care: A Systematic Review. Appl Clin Inform 2019; 10:123-128. [PMID: 30786301 PMCID: PMC6382497 DOI: 10.1055/s-0039-1677738] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/02/2022] Open
Abstract
OBJECTIVE We identified the methods used and determined the roles of electronic health records (EHRs) in detecting and assessing adverse drug events (ADEs) in the ambulatory setting. METHODS We performed a systematic literature review by searching PubMed and Google Scholar for studies on ADEs detected in the ambulatory setting involving any EHR use published before June 2017. We extracted study characteristics from included studies related to ADE detection methods for analysis. RESULTS We identified 30 studies that evaluated ADEs in an ambulatory setting with an EHR. In 27 studies, EHRs were used only as the data source for ADE identification. In two studies, the EHR was used as both a data source and to deliver decision support to providers during order entry. In one study, the EHR was a source of data and generated patient safety reports that researchers used in the process of identifying ADEs. Methods of identification included manual chart review by trained nurses, pharmacists, and/or physicians; prescription review; computer monitors; electronic triggers; International Classification of Diseases codes; natural language processing of clinical notes; and patient phone calls and surveys. Seven studies provided examples of search phrases, laboratory values, and rules used to identify ADEs. CONCLUSION The majority of studies examined used EHRs as sources of data for ADE detection. This retrospective approach is appropriate to measure incidence rates of ADEs but not adequate to detect preventable ADEs before patient harm occurs. New methods involving computer monitors and electronic triggers will enable researchers to catch preventable ADEs and take corrective action.
Collapse
Affiliation(s)
- Chenchen Feng
- Tulane University School of Medicine, Tulane University, New Orleans, Louisiana, United States
| | - David Le
- Tulane University School of Medicine, Tulane University, New Orleans, Louisiana, United States
| | - Allison B McCoy
- Department of Global Biostatistics and Data Science, Tulane University School of Public Health and Tropical Medicine, Tulane University, New Orleans, Louisiana, United States
| |
Collapse
|
3
|
Kim JW, Torous J, Chan S, Gipson SYMT. Developing a Digitally Informed Curriculum in Psychiatry Education and Clinical Practice. ACADEMIC PSYCHIATRY : THE JOURNAL OF THE AMERICAN ASSOCIATION OF DIRECTORS OF PSYCHIATRIC RESIDENCY TRAINING AND THE ASSOCIATION FOR ACADEMIC PSYCHIATRY 2018; 42:782-790. [PMID: 29473134 DOI: 10.1007/s40596-018-0895-5] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/22/2018] [Accepted: 02/09/2018] [Indexed: 06/08/2023]
Affiliation(s)
- Jung Won Kim
- University of Alabama at Birmingham, Birmingham, AL, USA.
| | | | - Steven Chan
- University of California at San Francisco, San Francisco, CA, USA
| | | |
Collapse
|
4
|
Meyer-Massetti C, Hofstetter V, Hedinger-Grogg B, Meier CR, Guglielmo BJ. Medication-related problems during transfer from hospital to home care: baseline data from Switzerland. Int J Clin Pharm 2018; 40:1614-1620. [PMID: 30291577 DOI: 10.1007/s11096-018-0728-3] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2017] [Accepted: 09/25/2018] [Indexed: 11/26/2022]
Abstract
Background The shift from inpatient to ambulatory care has resulted in an increase in home care patients. Little is known regarding medication safety associated with patient transfer from hospital to home care. Objective To evaluate medication-related problems in patients transferring from hospital to home care in Switzerland. Setting A non-for-profit home care organization in the city of Lucerne/Switzerland. Methods We conducted a prospective observational study, including patients aged ≥ 64 years and receiving ≥ 4 medications at hospital discharge. Two structured questionnaires assessing the transfer process were completed by home care nurses. Prescription quality was assessed using a PCNE Type 2b Medication Review. Main outcome measures The quality of the transfer process was measured comparing agreed-upon with reported parameters. Prescription quality was analyzed assessing the unambiguity of the prescription. Potentially inappropriate medications (Priscus® list), contraindications, duplications and interactions, and clinical pharmacist-identified potential medication-related problems were collected. Results Study patients (n = 100) received 8.6 ± 3.5 regularly administered medications. Only 5/100 patients had a complete set of written discharge information. At the time of the first visit, 13/100 patients had no written medication information available. Discharge medication prescriptions were clear to nurses in 62% of patients. In 20 patients, the required medications were unavailable, resulting in 19 medication errors. Assessment by a clinical pharmacist revealed only 33/100 patients had a clear discharge prescription. Of a total of 984 prescribed drugs, 16% were considered to be ambiguous, 22 (2.2%) were potentially inappropriate. 7/984 drugs were contraindicated, 8 were duplicates. Conclusion In addition to the known risk factors in patients transferring from hospital to home care (age, polymedication, multiple providers), 3 major problems impacted upon medication safety: fragmented communication, unreliable medication availability and a poor prescription quality. Clinical pharmacists are an important option to improve medication safety ass.
Collapse
Affiliation(s)
- Carla Meyer-Massetti
- Clincal Pharmacy & Epidemiology, Department of Pharmaceutical Sciences, University of Basel, Basel, Switzerland.
- Hospital Pharmacy, University Hospital of Basel, Spitalstrasse 26, 4031, Basel, Switzerland.
| | - Vera Hofstetter
- Clincal Pharmacy & Epidemiology, Department of Pharmaceutical Sciences, University of Basel, Basel, Switzerland
| | | | - Christoph R Meier
- Clincal Pharmacy & Epidemiology, Department of Pharmaceutical Sciences, University of Basel, Basel, Switzerland
- Hospital Pharmacy, University Hospital of Basel, Spitalstrasse 26, 4031, Basel, Switzerland
| | - B Joseph Guglielmo
- School of Pharmacy, University of California San Francisco, San Francisco, USA
| |
Collapse
|