Dacre R.T. Knight , Christopher A. Aakre , Christopher V. Anstine , Bala Munipalli , Parisa Biazar , Ghada Mitri , Jose Raul Valery , Tara Brigham , Shehzad K. Niazi , Adam I. Perlman , John D. Halamka , Abd Moain Abu Dabrh
{"title":"Artificial intelligence for patient scheduling in the real-world health care setting: A metanarrative review","authors":"Dacre R.T. Knight , Christopher A. Aakre , Christopher V. Anstine , Bala Munipalli , Parisa Biazar , Ghada Mitri , Jose Raul Valery , Tara Brigham , Shehzad K. Niazi , Adam I. Perlman , John D. Halamka , Abd Moain Abu Dabrh","doi":"10.1016/j.hlpt.2023.100824","DOIUrl":null,"url":null,"abstract":"<div><h3>Objectives</h3><p>The application of artificial intelligence (AI) and machine learning (ML) to scheduling in medical practices has considerable implications for most specialties. However, the landscape of AI and ML use in scheduling optimization is unclear. We aimed to systematically summarize up-to-date evidence about application of AI and ML models for scheduling optimization in clinical settings.</p></div><div><h3>Methods</h3><p><span>We systematically searched multiple databases from inception through August 2020 to identify studies that described real-world application of AI and ML in health care scheduling and reported outcomes. Eligible studies included those conducted in any health care setting using ML or </span>predictive modeling through AI to optimize patient scheduling processes in real-time, real-world settings. Outcomes of interest included assessing impact on stakeholders (i.e., providers, patients, health systems), including impact on workload, burden, burnout, cost, utilization, patient and provider satisfaction, waste reduction, and quality. Data were extracted and reviewed in duplicates, independently and blindly by two reviewers. The results were synthesized and summarized using a metanarrative approach.</p></div><div><h3>Results</h3><p>The initial search strategy yielded 3,415 citations, of which 11 eligible studies were included. Outcome measures for studies on missed appointments covered patient double-booking volume, missed appointments, service use, and missed appointment risk. Resource allocation outcomes assessed wait time, disease-type matching performance, schedule efficiency revenue, and new patient volume wait time. Other outcomes included visit requests, examination length prediction, and surgical case time.</p></div><div><h3>Conclusions</h3><p>Available evidence shows heterogeneity in the stages of AI and ML development as they apply to patient scheduling. AI and ML applications can be used to decrease the burden on provider time, increase patient satisfaction, and ultimately provide more patient-directed health care and efficiency for medical practices. These findings help identify additional opportunities in which AI platforms can be developed to optimize patient scheduling.</p></div><div><h3>Public Interest Summary</h3><p><span>Artificial Intelligence (AI) and machine learning (ML) can help many aspects of health care. Patient scheduling has significant implications for the cost benefits of improved technology. The longstanding use of technology in medicine serves as a strong foundation for future AI applications. Here, we present an up-to-date review of the current use of AI and ML for schedule optimization in the health care clinic setting. Current evidence shows a wide variety of stages in the development, function, and application of AI and ML </span>in patient scheduling. Given the current gaps of knowledge, future studies should address feasibility, effectiveness, generalizability, and risk of AI bias in patient scheduling.</p></div>","PeriodicalId":48672,"journal":{"name":"Health Policy and Technology","volume":"12 4","pages":"Article 100824"},"PeriodicalIF":3.4000,"publicationDate":"2023-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Health Policy and Technology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2211883723001004","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"HEALTH POLICY & SERVICES","Score":null,"Total":0}
引用次数: 0
Abstract
Objectives
The application of artificial intelligence (AI) and machine learning (ML) to scheduling in medical practices has considerable implications for most specialties. However, the landscape of AI and ML use in scheduling optimization is unclear. We aimed to systematically summarize up-to-date evidence about application of AI and ML models for scheduling optimization in clinical settings.
Methods
We systematically searched multiple databases from inception through August 2020 to identify studies that described real-world application of AI and ML in health care scheduling and reported outcomes. Eligible studies included those conducted in any health care setting using ML or predictive modeling through AI to optimize patient scheduling processes in real-time, real-world settings. Outcomes of interest included assessing impact on stakeholders (i.e., providers, patients, health systems), including impact on workload, burden, burnout, cost, utilization, patient and provider satisfaction, waste reduction, and quality. Data were extracted and reviewed in duplicates, independently and blindly by two reviewers. The results were synthesized and summarized using a metanarrative approach.
Results
The initial search strategy yielded 3,415 citations, of which 11 eligible studies were included. Outcome measures for studies on missed appointments covered patient double-booking volume, missed appointments, service use, and missed appointment risk. Resource allocation outcomes assessed wait time, disease-type matching performance, schedule efficiency revenue, and new patient volume wait time. Other outcomes included visit requests, examination length prediction, and surgical case time.
Conclusions
Available evidence shows heterogeneity in the stages of AI and ML development as they apply to patient scheduling. AI and ML applications can be used to decrease the burden on provider time, increase patient satisfaction, and ultimately provide more patient-directed health care and efficiency for medical practices. These findings help identify additional opportunities in which AI platforms can be developed to optimize patient scheduling.
Public Interest Summary
Artificial Intelligence (AI) and machine learning (ML) can help many aspects of health care. Patient scheduling has significant implications for the cost benefits of improved technology. The longstanding use of technology in medicine serves as a strong foundation for future AI applications. Here, we present an up-to-date review of the current use of AI and ML for schedule optimization in the health care clinic setting. Current evidence shows a wide variety of stages in the development, function, and application of AI and ML in patient scheduling. Given the current gaps of knowledge, future studies should address feasibility, effectiveness, generalizability, and risk of AI bias in patient scheduling.
期刊介绍:
Health Policy and Technology (HPT), is the official journal of the Fellowship of Postgraduate Medicine (FPM), a cross-disciplinary journal, which focuses on past, present and future health policy and the role of technology in clinical and non-clinical national and international health environments.
HPT provides a further excellent way for the FPM to continue to make important national and international contributions to development of policy and practice within medicine and related disciplines. The aim of HPT is to publish relevant, timely and accessible articles and commentaries to support policy-makers, health professionals, health technology providers, patient groups and academia interested in health policy and technology.
Topics covered by HPT will include:
- Health technology, including drug discovery, diagnostics, medicines, devices, therapeutic delivery and eHealth systems
- Cross-national comparisons on health policy using evidence-based approaches
- National studies on health policy to determine the outcomes of technology-driven initiatives
- Cross-border eHealth including health tourism
- The digital divide in mobility, access and affordability of healthcare
- Health technology assessment (HTA) methods and tools for evaluating the effectiveness of clinical and non-clinical health technologies
- Health and eHealth indicators and benchmarks (measure/metrics) for understanding the adoption and diffusion of health technologies
- Health and eHealth models and frameworks to support policy-makers and other stakeholders in decision-making
- Stakeholder engagement with health technologies (clinical and patient/citizen buy-in)
- Regulation and health economics