The Electronic Inbox—Benefits, Questions, and Solutions for the Road Ahead

Rotenstein, Lisa S.; Landman, Adam; Bates, David W.

doi:10.1001/jama.2023.19195

Cited by 5 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been estimated that physicians now spend more than 50% of their time updating electronic health records. Since the advent of COVID-19, they have also been spending an increasing amount of time in their out-of-office hours taking care of the exorbitant volume of electronic communication with patients [22,90,91]. This comes at the expense of efficacious communication, empathy, and clinicians' psychological wellbeing [22], which all affect patients' empowerment, satisfaction with treatment, adherence to treatment, symptom perception, and ability to remain integrated in society despite suffering from a chronic condition [92][93][94].…”

Section: Role In Reducing the Burden Linked To Administrative Workmentioning

confidence: 99%

Artificial Intelligence in the Management of Women with Endometriosis and Adenomyosis: Can Machines Ever Be Worse Than Humans?

Cetera,

Tozzi,

Chiappa

et al. 2024

JCM

View full text Add to dashboard Cite

Artificial intelligence (AI) is experiencing advances and integration in all medical specializations, and this creates excitement but also concerns. This narrative review aims to critically assess the state of the art of AI in the field of endometriosis and adenomyosis. By enabling automation, AI may speed up some routine tasks, decreasing gynecologists’ risk of burnout, as well as enabling them to spend more time interacting with their patients, increasing their efficiency and patients’ perception of being taken care of. Surgery may also benefit from AI, especially through its integration with robotic surgery systems. This may improve the detection of anatomical structures and enhance surgical outcomes by combining intra-operative findings with pre-operative imaging. Not only that, but AI promises to improve the quality of care by facilitating clinical research. Through the introduction of decision-support tools, it can enhance diagnostic assessment; it can also predict treatment effectiveness and side effects, as well as reproductive prognosis and cancer risk. However, concerns exist regarding the fact that good quality data used in tool development and compliance with data sharing guidelines are crucial. Also, professionals are worried AI may render certain specialists obsolete. This said, AI is more likely to become a well-liked team member rather than a usurper.

show abstract

Section: Role In Reducing the Burden Linked To Administrative Workmentioning

confidence: 99%

Artificial Intelligence in the Management of Women with Endometriosis and Adenomyosis: Can Machines Ever Be Worse Than Humans?

Cetera,

Tozzi,

Chiappa

et al. 2024

JCM

View full text Add to dashboard Cite

show abstract

“…Large language models, like generative pretrained transformer 4 (GPT-4; OpenAI), have shown the ability to draft empathetic responses to online patient questions and to assist with medical knowledge tasks . A novel Health Insurance Portability and Accountability Act–compliant, electronic health record (EHR)–integrated version of this tool was created to generate draft replies to patient portal messages for clinicians but has not been assessed in clinical practice . Therefore, this study evaluated the implementation of this novel technology using an evaluation guided by the Reach, Efficacy, Adoption, Implementation, Maintenance/Practical, Robust Implementation, and Sustainability Model (RE-AIM/PRISM) .…”

Section: Introductionmentioning

confidence: 99%

“… 10 A novel Health Insurance Portability and Accountability Act–compliant, electronic health record (EHR)–integrated version of this tool was created to generate draft replies to patient portal messages for clinicians but has not been assessed in clinical practice. 11 Therefore, this study evaluated the implementation of this novel technology using an evaluation guided by the Reach, Efficacy, Adoption, Implementation, Maintenance/Practical, Robust Implementation, and Sustainability Model (RE-AIM/PRISM). 12 , 13 , 14 The developmental assessment of readiness for adoption and clinician experience included a primary outcome of utilization, with secondary outcomes evaluating time, usability, utility, and impact on clinician well-being.…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence–Generated Draft Replies to Patient Inbox Messages

Garcia,

Ma,

Shah

et al. 2024

JAMA Netw Open

View full text Add to dashboard Cite

ImportanceThe emergence and promise of generative artificial intelligence (AI) represent a turning point for health care. Rigorous evaluation of generative AI deployment in clinical practice is needed to inform strategic decision-making.ObjectiveTo evaluate the implementation of a large language model used to draft responses to patient messages in the electronic inbox.Design, Setting, and ParticipantsA 5-week, prospective, single-group quality improvement study was conducted from July 10 through August 13, 2023, at a single academic medical center (Stanford Health Care). All attending physicians, advanced practice practitioners, clinic nurses, and clinical pharmacists from the Divisions of Primary Care and Gastroenterology and Hepatology were enrolled in the pilot.InterventionDraft replies to patient portal messages generated by a Health Insurance Portability and Accountability Act–compliant electronic health record–integrated large language model.Main Outcomes and MeasuresThe primary outcome was AI-generated draft reply utilization as a percentage of total patient message replies. Secondary outcomes included changes in time measures and clinician experience as assessed by survey.ResultsA total of 197 clinicians were enrolled in the pilot; 35 clinicians who were prepilot beta users, out of office, or not tied to a specific ambulatory clinic were excluded, leaving 162 clinicians included in the analysis. The survey analysis cohort consisted of 73 participants (45.1%) who completed both the presurvey and postsurvey. In gastroenterology and hepatology, there were 58 physicians and APPs and 10 nurses. In primary care, there were 83 physicians and APPs, 4 nurses, and 8 clinical pharmacists. The mean AI-generated draft response utilization rate across clinicians was 20%. There was no change in reply action time, write time, or read time between the prepilot and pilot periods. There were statistically significant reductions in the 4-item physician task load score derivative (mean [SD], 61.31 [17.23] presurvey vs 47.26 [17.11] postsurvey; paired difference, −13.87; 95% CI, −17.38 to −9.50; P &lt; .001) and work exhaustion scores (mean [SD], 1.95 [0.79] presurvey vs 1.62 [0.68] postsurvey; paired difference, −0.33; 95% CI, −0.50 to −0.17; P &lt; .001).Conclusions and RelevanceIn this quality improvement study of an early implementation of generative AI, there was notable adoption, usability, and improvement in assessments of burden and burnout. There was no improvement in time. Further code-to-bedside testing is needed to guide future development and organizational strategy.

show abstract

Are Artificial Intelligence–Generated Replies the Answer to the Electronic Health Record Inbox Problem?

Rotenstein,

Wachter

2024

JAMA Netw Open

View full text Add to dashboard Cite

Engagement with electronic health record (EHR)-based patient portals has multiple benefits for patients: enabling them to see their test results, update or correct their health information, access educational materials, and correspond with their care teams. However, this engagement has also had unexpected consequences for health care systems and clinicians. As the prevalence and frequency of patient portal use have increased, so too has the number of messages (EHR inbox messages) sent by patients to their care teams. Over the past few years, health care systems have realized that they have essentially enabled around-the-clock patient access to these teams without adequately preparing for the workflow, workforce, and financial implications of this access. The work associated with EHR inbox messages has disproportionately impacted primary care clinicians, who receive 5 times as many messages as their surgical clinician counterparts. 2 Unsurprisingly, patient portal use and messaging accelerated during the COVID-19 pandemic. 3 Health care systems have implemented various solutions to manage the growing volume of EHR inbox messages, 4 including hiring nonphysician clinicians, developing triage strategies, and even charging for clinician answers to messages deemed complex. More recently, the use of artificial intelligence (AI)-generated responses to patient messages have been of particular interest.Responses drafted by large language model (LLM) technology can potentially reduce the messaging burden for care teams while maintaining patient engagement. However, little evidence has been available to assess the quality of such responses and the specifics of their implementation in complex health care practices.The quality improvement study by English et al, 5 which characterizes the use of and perceptions regarding LLM-drafted replies to EHR-inbox messages across 9 clinic sites and multiple clinical role types, advances our understanding of this new AI application. Notably, the study 5 also provides insight into the iterative process used by a large academic health system to refine the AI-generated replies after rollout. The study's principal findings were that overall, a small proportion (12%) of AI-generated message drafts were used and that the perceptions of the value of the draft messages varied substantially by role type, with nurses holding more favorable views. 5 The study 5 raises several points to reflect on. First, it underscores the importance of careful adoption of LLM-based tools, accompanied by careful analysis of end-users' experiences. For example, the authors 5 describe how providing the assessment and plan from the last clinic note to the LLM improved the draft replies. Given the constant updating of LLMs and the frequency of unanticipated consequences, it will be crucial for health care systems to undertake this type of iteration, considering the possibility-perhaps the likelihood-that one size of LLM responses will not fit all situations and specialties or the needs of all clinical role types.Notably...

show abstract

The Electronic Inbox—Benefits, Questions, and Solutions for the Road Ahead

Abstract: This Viewpoint looks at digital communication between patients and physicians, including approaches to provide adequate support for these efforts that balance patient needs with appropriate time investments from clinicians.

Cited by 5 publications

References 9 publications

Artificial Intelligence in the Management of Women with Endometriosis and Adenomyosis: Can Machines Ever Be Worse Than Humans?

Artificial Intelligence in the Management of Women with Endometriosis and Adenomyosis: Can Machines Ever Be Worse Than Humans?

Artificial Intelligence–Generated Draft Replies to Patient Inbox Messages

Are Artificial Intelligence–Generated Replies the Answer to the Electronic Health Record Inbox Problem?

Contact Info

Product

Resources

About