Implementation of machine learning in the clinic: challenges and lessons in prospective deployment from the System for High Intensity EvaLuation During Radiation Therapy (SHIELD-RT) randomized controlled study

Identifying Facilitators and Barriers to Implementation of AI-Assisted Clinical Decision Support in an Electronic Health Record System

Recent advancements in computing have led to the development of artificial intelligence (AI) enabled healthcare technologies. AI-assisted clinical decision support (CDS) integrated into electronic health records (EHR) was demonstrated to have a significant potential to improve clinical care. With the rapid proliferation of AI-assisted CDS, came the realization that a lack of careful consideration of socio-technical issues surrounding the implementation and maintenance of these tools can result in unanticipated consequences, missed opportunities, and suboptimal uptake of these potentially useful technologies. The 48-h Discharge Prediction Tool (48DPT) is a new AI-assisted EHR CDS to facilitate discharge planning. This study aimed to methodologically assess the implementation of 48DPT and identify the barriers and facilitators of adoption and maintenance using the validated implementation science frameworks. The major dimensions of RE-AIM (Reach, Effectiveness, Adoption, Implementation, Maintenance) and the constructs of the Consolidated Framework for Implementation Research (CFIR) frameworks have been used to analyze interviews of 24 key stakeholders using 48DPT. The systematic assessment of the 48DPT implementation allowed us to describe facilitators and barriers to implementation such as lack of awareness, lack of accuracy and trust, limited accessibility, and transparency. Based on our evaluation, the factors that are crucial for the successful implementation of AI-assisted EHR CDS were identified. Future implementation efforts of AI-assisted EHR CDS should engage the key clinical stakeholders in the AI tool development from the very inception of the project, support transparency and explainability of the AI models, provide ongoing education and onboarding of the clinical users, and obtain continuous input from clinical staff on the CDS performance.

Health Care Cost Reductions with Machine Learning-Directed Evaluations during Radiation Therapy - An Economic Analysis of a Randomized Controlled Study

BACKGROUND

Machine learning (ML) may cost-effectively direct health care by identifying patients most likely to benefit from preventative interventions to avoid negative and expensive outcomes. System for High-Intensity Evaluation During Radiation Therapy (SHIELD-RT; NCT04277650) was a single-institution, randomized controlled study in which electronic health record-based ML accurately identified patients at high risk for acute care (emergency visit or hospitalization) during radiotherapy (RT) and targeted them for supplemental clinical evaluations. This ML-directed intervention resulted in decreased acute care utilization. Given the limited prospective data showing the ability of ML to direct interventions cost-efficiently, an economic analysis was performed.

METHODS

A post hoc economic analysis was conducted of SHIELD-RT that included RT courses from January 7, 2019, to June 30, 2019. ML-identified high-risk courses (≥10% risk of acute care during RT) were randomized to receive standard of care weekly clinical evaluations with ad hoc supplemental evaluations per clinician discretion versus mandatory twice-weekly evaluations. The primary outcome was difference in mean total medical costs during and 15 days after RT. Acute care costs were obtained via institutional cost accounting. Physician and intervention costs were estimated via Medicare and Medicaid data. Negative binomial regression was used to estimate cost outcomes after adjustment for patient and disease factors.

RESULTS

A total of 311 high-risk RT courses among 305 patients were randomized to the standard (n=157) or the intervention (n=154) group. Unadjusted mean intervention group supplemental visit costs were $155 per course (95% confidence interval, $142 to $168). The intervention group had fewer acute care visits per course (standard, 0.47; intervention, 0.31; P=0.04). Total mean adjusted costs were $3110 per course for the standard group and $1494 for the intervention group (difference in means, $1616 [95% confidence interval, $1450 to $1783]; P=0.03).

CONCLUSIONS

In this economic analysis of a randomized controlled, health care ML study, mandatory supplemental evaluations for ML-identified high-risk patients were associated with both reduced total medical costs and improved clinical outcomes. Further study is needed to determine whether economic results are generalizable. (Funded in part by The Duke Endowment, The Conquer Cancer Foundation, the Duke Department of Radiation Oncology, and the National Cancer Institute of the National Institutes of Health [R01CA277782]; ClinicalTrials.gov number, NCT04277650.).

Automation in Contemporary Clinical Information Systems: a Survey of AI in Healthcare Settings

AIMS AND OBJECTIVES

To examine the nature and use of automation in contemporary clinical information systems by reviewing studies reporting the implementation and evaluation of artificial intelligence (AI) technologies in healthcare settings.

METHOD

PubMed/MEDLINE, Web of Science, EMBASE, the tables of contents of major informatics journals, and the bibliographies of articles were searched for studies reporting evaluation of AI in clinical settings from January 2021 to December 2022. We documented the clinical application areas and tasks supported, and the level of system autonomy. Reported effects on user experience, decision-making, care delivery and outcomes were summarised.

RESULTS

AI technologies are being applied in a wide variety of clinical areas. Most contemporary systems utilise deep learning, use routinely collected data, support diagnosis and triage, are assistive (requiring users to confirm or approve AI provided information or decisions), and are used by doctors in acute care settings in high-income nations. AI systems are integrated and used within existing clinical information systems including electronic medical records. There is limited support for One Health goals. Evaluation is largely based on quantitative methods measuring effects on decision-making.

CONCLUSION

AI systems are being implemented and evaluated in many clinical areas. There remain many opportunities to understand patterns of routine use and evaluate effects on decision-making, care delivery and patient outcomes using mixed-methods. Support for One Health including integrating data about environmental factors and social determinants needs further exploration.

Healthcare provider evaluation of machine learning-directed care: reactions to deployment on a randomised controlled study

OBJECTIVES

Clinical artificial intelligence and machine learning (ML) face barriers related to implementation and trust. There have been few prospective opportunities to evaluate these concerns. System for High Intensity EvaLuation During Radiotherapy (NCT03775265) was a randomised controlled study demonstrating that ML accurately directed clinical evaluations to reduce acute care during cancer radiotherapy. We characterised subsequent perceptions and barriers to implementation.

METHODS

An anonymous 7-question Likert-type scale survey with optional free text was administered to multidisciplinary staff focused on workflow, agreement with ML and patient experience.

RESULTS

59/71 (83%) responded. 81% disagreed/strongly disagreed their workflow was disrupted. 67% agreed/strongly agreed patients undergoing intervention were high risk. 75% agreed/strongly agreed they would implement the ML approach routinely if the study was positive. Free-text feedback focused on patient education and ML predictions.

CONCLUSIONS

Randomised data and firsthand experience support positive reception of clinical ML. Providers highlighted future priorities, including patient counselling and workflow optimisation.