Frank Liao

Frank Liao

Auto-generated profile, based on publicly available information

Frank Liao

University of Wisconsin Hospitals and Clinics, Madison, WI, USA

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 November 2025 in NEJM AI
Verified
Journal Article
Closed access
MAMajid Afshar
Majid Afshar
MBMary Ryan Baumann
Mary Ryan Baumann
FRFelice Resnik
Felice Resnik
JHJosie Hintzke
Josie Hintzke
ASAnne Gravel Sullivan
Anne Gravel Sullivan
JGJoel Gordon
Joel Gordon
Electronic health record (EHR) documentation is a major contributor to work-related practitioner exhaustion and the interpersonal disengagement known as burnout. Generative artificial intelligence (AI) scribes that passively capture clinical conversations and draft visit notes may alleviate this burden, but evidence remains limited. A 24-week, stepped-wedge, individually randomized pragmatic trial was conducted across ambulatory clinics in two states. Sixty-six health care practitioners were randomly assigned to three 6-week sequences of ambient AI. The coprimary outcomes were professional fulfillment and work exhaustion/interpersonal disengagement from the Stanford Professional Fulfillment Index. Secondary measures included time spent on notes, work outside work (WoW), documentation quality with the Provider Documentation Summarization Quality Instrument 9 (PDSQI-9), and billing diagnostic codes reviewed by professional staff coders. Linear mixed models were used for intention-to-treat (ITT) analyses. A total of 71,487 notes were authored, of which 27,092 (38%) were generated using ambient AI. Ambient AI use had a significant reduction in work exhaustion/interpersonal disengagement (−0.44 points; 95% confidence interval [CI], −0.62 to −0.25; P<0.001), and a nonsignificant increase in professional fulfillment (+0.14 points; 95% CI, 0.004 to 0.28; P=0.04) on a five-point Likert scale. Among secondary measures, time spent on notes decreased (−0.36 hours per day; 95% CI, −0.55 to −0.17). The reduction in WoW (−0.50 hours per day; 95% CI, −0.90 to −0.09) was sensitive to exclusion of extreme values and was no longer significant after removing the top 3% of daily observations. Diagnostic billing codes improved with ambient AI use (P<0.001). Documentation quality, assessed with the PDSQI-9, demonstrated mean scores ranging from 3.97 to 4.99 across domains on a five-point scale. No drift in software performance was detected. In a real-world randomized implementation, ambient AI reduced health care practitioners’ work exhaustion/interpersonal disengagement but did not significantly increase professional fulfillment. Documentation time decreased without compromising diagnosis, billing compliance, or note quality. (Funded by the University of Wisconsin Hospital and Clinics and the National Institutes of Health Clinical and Translational Science Award; ClinicalTrials.gov number, NCT06517082.)

20 April 2023 in JMIR Medical Informatics
Verified
Journal Article
Open access
MAMajid Afshar
Majid Afshar
SASabrina Adelaine
Sabrina Adelaine
FRFelice Resnik
Felice Resnik
MMMarlon Mundt
Marlon Mundt
JLJohn Long
John Long
FLFrank Liao
Frank Liao
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

5 May 2025 in Journal of the American Medical Informatics Association
Verified
Journal Article
Closed access
ECEmma Croxford
Emma Croxford
YGYanjun Gao
Yanjun Gao
NPNicholas Pellegrino
Nicholas Pellegrino
KWKaren Wong
Karen Wong
GWGraham Wills
Graham Wills
MAMajid Afshar
Majid Afshar
Objectives: As large language models (LLMs) are integrated into electronic health record (EHR) workflows, validated instruments are essential to evaluate their performance before implementation and as models and documentation practices evolve. Existing instruments for provider documentation quality are often unsuitable for the complexities of LLM-generated text and lack validation on real-world data. The Provider Documentation Summarization Quality Instrument (PDSQI-9) was developed to evaluate LLM-generated clinical summaries. This study aimed to validate the PDSQI-9 across key aspects of construct validity. Materials and Methods: Multi-document summaries were generated from real-world EHR data across multiple specialties using several LLMs (GPT-4o, Mixtral 8x7b, and Llama 3-8b). Validation included Pearson correlation analyses for substantive validity, factor analysis and Cronbach’s α for structural validity, inter-rater reliability (ICC and Krippendorff’s α) for generalizability, a semi-Delphi process for content validity, and comparisons of high- versus low-quality summaries for discriminant validity. Raters underwent standardized training to ensure consistent application of the instrument. Results: Seven physician raters evaluated 779 summaries and answered 8329 questions, achieving over 80% power for inter-rater reliability. The PDSQI-9 demonstrated strong internal consistency (Cronbach’s α = 0.879; 95% CI, 0.867-0.891) and high inter-rater reliability (ICC = 0.867; 95% CI, 0.867-0.868), supporting structural validity and generalizability. Factor analysis identified a 4-factor model explaining 58% of the variance, representing organization, clarity, accuracy, and utility. Substantive validity was supported by correlations between note length and scores for Succinct (ρ = −0.200, P = .029) and Organized (ρ = −0.190, P = .037). The semi-Delphi process ensured clinically relevant attributes, and discriminant validity distinguished high- from low-quality summaries (P<.001). Discussion: The PDSQI-9 showed high inter-rater reliability, internal consistency, and a meaningful factor structure that reliably captured key dimensions of documentation quality. It distinguished between high- and low-quality summaries, supporting its practical utility for health systems needing an evaluation instrument for LLMs. Conclusions: The PDSQI-9 demonstrates robust construct validity, supporting its use in clinical practice to evaluate LLM-generated summaries and facilitate safer, more effective integration of LLMs into healthcare workflows.

28 August 2025 in NEJM AI
Verified
Journal Article
Closed access
MAMajid Afshar
Majid Afshar
FRFelice Resnik
Felice Resnik
MBMary Ryan Baumann
Mary Ryan Baumann
JHJosie Hintzke
Josie Hintzke
KLKayla Lemmon
Kayla Lemmon
JGJoel E. Gordon
Joel E. Gordon
Ambient artificial intelligence (AI) offers the potential to reduce documentation burden and improve efficiency through clinical note generation. Widespread adoption, however, remains limited due to challenges in electronic health record (EHR) integration, coding compliance, and real-world evaluation. This study introduces a framework and protocols to design, monitor, and deploy ambient AI within routine care. We launched an implementation phase to build technical workflows, establish governance, and inform a pragmatic randomized trial. A bidirectional governance model linked operations and research through multidisciplinary workgroups that incorporated the Systems Engineering Initiative for Patient Safety (SEIPS) framework. Integration into the EHR used Fast Healthcare Interoperability Resources (FHIR), and a real-time dashboard tracked utilization and documentation accuracy. To monitor drift, a difference-in-differences analysis was applied to three process metrics: time in notes, work outside work, and utilization. Audits of International Statistical Classification of Diseases and Related Health Problems, Tenth Revision (ICD-10) compliance were performed using an internally developed large language model (LLM), the validity of which was assessed through correlation with certified professional coders. Ambient AI utilization, measured as the proportion of eligible clinical notes completed using the system, had a weighted median of 65.4% (interquartile range, 50.6 to 84.0%). Iterative improvement cycles targeted task-specific adoption. A brief workflow issue related to a note template change initially reduced ICD-10 documentation accuracy from 79% (95% confidence interval [CI], 72 to 86%) to 35% (95% CI, 28 to 42%); accuracy returned to baseline after note template redesign and user training. The internally developed LLM coder achieved a strong correlation with professional coders (Pearson’s r=0.97). The trial enrolled 66 providers across eight specialties, powered at 90% for the primary outcome of provider well-being. We provide a publicly available framework and protocols to help safely implement ambient AI in health care. Innovations include an embedded pragmatic trial design, human factors engineering, compliance-driven feedback loops, and real-time monitoring to support deployment, ensuring fidelity before initiation of the clinical trial. (Funded by the University of Wisconsin Hospital and Clinics and the National Institutes of Health Clinical and Translational Science Award; NIH/ NCATS UL1TR002737; ClinicalTrials.gov number, NCT06517082.)


3 April 2025 in Nature Medicine
Verified
Journal Article
Closed access
PDF file
MAMajid Afshar
Majid Afshar
FRFelice Resnik
Felice Resnik
CJCara Joyce
Cara Joyce
MOMadeline Oguss
Madeline Oguss
DDDmitriy Dligach
Dmitriy Dligach
MMMarlon Mundt
Marlon Mundt