Paul J. Lukac

Paul J. Lukac

Auto-generated profile, based on publicly available information

Paul J. Lukac

Department of Pediatrics, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-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
PLPaul J. Lukac
Paul J. Lukac
WTWilliam Turner
William Turner
SVSitaram Vangala
Sitaram Vangala
ACAaron T. Chin
Aaron T. Chin
JKJoshua Khalili
Joshua Khalili
JMJohn N. Mafi
John N. Mafi
Ambient artificial intelligence (AI) scribes record patient encounters and rapidly generate visit notes, representing a promising solution to documentation burden and physician burnout. However, the scribes’ impacts have not been examined in randomized clinical trials. In this parallel three-group pragmatic randomized clinical trial, 238 outpatient physicians, representing 14 specialties, were assigned 1:1:1 via covariate-constrained randomization (balancing on time-in-note, baseline burnout score, and clinic days per week) to either one of two AI scribe applications — Microsoft Dragon Ambient eXperience (DAX) Copilot or Nabla — or a usual-care control group from November 4, 2024, to January 3, 2025. The primary outcome was the change from baseline log writing time-in-note. Secondary end points measured by surveys included the Mini-Z 2.0, a four-item physician task load (PTL), and Professional Fulfillment Index — Work Exhaustion (PFI-WE) scores to evaluate aspects of burnout; work environment; stress; and targeted questions addressing safety, accuracy, and usability. DAX was used in 33.5% of 24,696 visits; Nabla was used in 29.5% of 23,653 visits. Nabla users experienced a 9.5% (95% confidence interval [CI], −17.2% to −1.8%; P=0.02) decrease in time-in-note versus the control group, whereas DAX users exhibited no significant change versus the control group (−1.7%; 95% CI, −9.4% to +5.9%; P=0.66). Increases in total Mini-Z (scale 10–50; DAX 2.83 [95% CI, +1.28 to +4.37]; Nabla +2.69 [95% CI, +1.14 to +4.23]) and reductions in PTL (scale 0–400; DAX −39.9 [95% CI, −71.9 to −7.9]; Nabla −31.7 [95% CI, −63.8 to +0.4]), and PFI-WE (scale 0–4; DAX 0.32 [95% CI,−0.55 to −0.08]; Nabla −0.23 [95% CI, −0.46 to +0.01]) scores suggest improvement for users of either scribe versus the control. One grade 1 (mild) adverse event was reported, while clinically significant inaccuracies were noted “occasionally” on five-point Likert questions (DAX 2.7 [95% CI, 2.4 to 3.0]; Nabla 2.8 [95% CI, 2.6 to 3.0]). Nabla reduced time-in-note versus the control. Both DAX and Nabla resulted in potential improvements in burnout, task load, and work exhaustion, but these secondary end point findings need confirmation in larger, multicenter trials. Clinicians reported that performance was similar across the two distinct platforms, and occasional inaccuracies observed in either scribe require ongoing vigilance. (Funded by the University of California, Los Angeles, Department of Medicine and others; ClinicalTrials.gov number, NCT06792890.)

11 July 2025 in medRxiv
Verified
Preprint
Open access
PDF file
PLPaul J. Lukac
Paul J. Lukac
WTWilliam Turner
William Turner
SVSitaram Vangala
Sitaram Vangala
ACAaron T. Chin
Aaron T. Chin
JKJoshua Khalili
Joshua Khalili
JMJohn N. Mafi
John N. Mafi
Importance Ambient artificial intelligence (AI) scribes record patient encounters and generate visit notes almost instantaneously, representing a promising solution to documentation burden and associated physician burnout. Despite swift and widespread adoption of AI scribes, their impacts have not been examined in randomized-clinical trials. Objective To test the effectiveness of two AI scribes in reducing time spent writing notes and associated burnout in a randomized-clinical trial. Design Parallel three-arm pragmatic randomized-clinical trial where physicians were assigned 1:1:1 via covariate-constrained randomization (balancing on time-in-note, baseline burnout score, and clinic days /week) to either one of two AI scribe applications—Microsoft DAX or Nabla—or a usual-care control group from 11/4/2024-1/3/2025. Setting A large academic health system in California. Participants 313 outpatient physicians were recruited based on leadership referrals and department-wide emails. 238 participants representing 14 specialties qualified. Intervention Intervention-arm physicians gained access to an AI scribe for two months. Main Outcomes and Measures The primary outcome was change from baseline log writing time-in-note. Secondary outcomes measured by surveys included Mini-Z 2.0, 4-item physician task load (TL), and Professional Fulfillment Index-Work Exhaustion (PFI-WE) scores to evaluate aspects of burnout, work environment, and stress, as well as targeted questions addressing safety and accuracy. Results DAX was used in 33.5% of 24,696 visits; Nabla was used in 29.5% of 23,653 visits. Nabla users experienced a 9.5% [95% CI:-17.2%,-1.8%] (p=.02) decrease in time-in-note versus the control group and a 7.8% [-15.5%,-0.1%] (p=.05) decrease versus DAX users, while DAX users exhibited no significant change versus control (-1.7% [-9.4%,+5.9%]; p=.66). Total Mini-Z, scaled 10-50 with higher scores indicating improvement, increased with users of any scribe (+2.76 [+1.41,+4.10]; p<.001). Reductions in TL (scale 0-400, TL=-35.8 [-63.7,-7.9]; p=.01) and work exhaustion (scale 0-4, PFI-WE=-0.27 [-0.48,-0.07]; p=.01) were seen with users of any scribe. One Grade 1 (mild) adverse event was reported, while clinically-significant inaccuracies were noted “occasionally” on 5-point Likert questions (DAX 2.7 [2.4-3.0] vs. Nabla 2.8 [2.6-3.0]; p=.68). Conclusion and Relevance Use of Nabla reduced time-in-note, while use of any scribe led to modest improvements in physician burnout, work exhaustion, and task load. Performance was remarkably similar across two distinct vendor platforms, and occasional inaccuracies observed in either scribe require ongoing physician vigilance. Trial Registration ClinicalTrials.gov Identifier: NCT06792890

26 September 2025 in Journal of the American Medical Informatics Association
Verified
Journal Article
Closed access
LJLaleh Jalilian
Laleh Jalilian
PLPaul Lukac
Paul Lukac
MLMeghan Lane-Fall
Meghan Lane-Fall
Objective: This perspective explores how ambient artificial intelligence (AI) scribes could support documentation and quality improvement (QI) of structured, team-based provider-to-provider communication in acute care settings. Background: In acute care settings, team-based discussions such as multidisciplinary rounds and handoffs are essential to the delivery of safe care. These discussions rely on standardized frameworks (eg, IPASS, checklists) to ensure consistent information transfer and shared understanding. Despite their importance, these verbal discussions are often incompletely documented or left undocumented in the electronic health record, leading to gaps in clinical narrative, difficulty in QI evaluation, and lost opportunities for organizational learning. Approach: We outline how ambient AI scribes could enhance documentation of team-based communication in daily rounding and handoff discussions. We examine key sociotechnical challenges, including workflow integration, multiprovider consent, surveillance concerns, and vendor collaboration. We describe our experience with proof-of-concept demonstrations as an early feasibility signal. Results: Ambient AI scribes are a promising tool for capturing structured team communication. Their use should be explored for its potential to improve documentation, support clinician well-being, and enable data-driven approaches to QI and communication fidelity assessments. Effective implementation requires workflow adaptations incorporating scribe output verification, transparent governance, and trust-building efforts to ensure clinician acceptance. Discussion: Ambient AI scribes represent a novel frontier in documentation of structured team discussions in acute care settings, with the potential to strengthen communication reliability and systems learning of these vital conversations. Future research should evaluate their impact on patient safety, workforce well-being, and patient outcomes in acute care settings.

12 January 2023 in Applied Clinical Informatics
Verified
Journal Article
Closed access
PDF file
PLPaul J. Lukac
Paul J. Lukac
DBDouglas Bell
Douglas Bell
PSPriya Sreedharan
Priya Sreedharan
JGJeffrey A. Gornbein
Jeffrey A. Gornbein
CLCarlos Lerner
Carlos Lerner
Background Fluoride is vital in the prevention of dental caries in children. In 2014, the U.S. Preventive Services Task Force deemed fluoride varnish a recommended preventive service (grade B). Electronic health record-based clinical decision support (CDS) tools have shown variable ability to alter physicians' ordering behaviors. Objectives This study aimed to increase the application of fluoride varnish in children while analyzing the effect of two passive CDS tools—an order set and a note template. Methods Data on outpatient pediatric visits over an 18-month period before and after CDS implementation (October 15, 2020–April 15, 2022) were queried, while trends in application rate of fluoride were examined. We constructed a multiple logistic regression model with a primary outcome of whether a patient received fluoride at his/her visit. The primary predictor was a “phase” variable representing the CDS implemented. Physician interaction with CDS as well as the financial effects of the resulting service use were also examined. Results There were 3,049 well-child visits of children aged 12 months to 5 years. The addition of a fluoride order to a “Well Child Check” order set led to a 10.6% increase in ordering over physician education alone (25.4 vs. 14.8%, p = 0.001), while the insertion of fluoride-specific text to drop-down lists in clinical notes led to a 6.2% increase (31.5 vs. 25.4%, p = 0.005). Whether a patient received topical fluoride was positively associated with order set implementation (odds ratio [OR] = 5.87, 95% confidence interval [CI]: 4.20–8.21) and fluoride-specific drop-down lists (OR = 7.81, 95% CI: 5.41–11.28). Female providers were more likely to use order sets when ordering fluoride (56.2 vs. 40.9% for males, p ≤ 0.0001). Added revenue totaled $15,084. Conclusion The targeted use of order sets and note templates was positively associated with the ordering of topical fluoride by physicians.

4 July 2023 in JAMIA Open
Verified
Journal Article
Open access
PDF file
TLTimothy Lee
Timothy Lee
PLPaul J Lukac
Paul J Lukac
SVSitaram Vangala
Sitaram Vangala
KKKamran Kowsari
Kamran Kowsari
VVVu Vu
Vu Vu
DBDouglas S Bell
Douglas S Bell
Objectives: Tertiary and quaternary (TQ) care refers to complex cases requiring highly specialized health services. Our study aimed to compare the ability of a natural language processing (NLP) model to an existing human workflow in predictively identifying TQ cases for transfer requests to an academic health center. Materials and methods: Data on interhospital transfers were queried from the electronic health record for the 6-month period from July 1, 2020 to December 31, 2020. The NLP model was allowed to generate predictions on the same cases as the human predictive workflow during the study period. These predictions were then retrospectively compared to the true TQ outcomes. Results: There were 1895 transfer cases labeled by both the human predictive workflow and the NLP model, all of which had retrospective confirmation of the true TQ label. The NLP model receiver operating characteristic curve had an area under the curve of 0.91. Using a model probability threshold of ≥0.3 to be considered TQ positive, accuracy was 81.5% for the NLP model versus 80.3% for the human predictions (P = .198) while sensitivity was 83.6% versus 67.7% (P<.001). Discussion: The NLP model was as accurate as the human workflow but significantly more sensitive. This translated to 15.9% more TQ cases identified by the NLP model. Conclusion: Integrating an NLP model into existing workflows as automated decision support could translate to more TQ cases identified at the onset of the transfer process.

19 November 2024 in Applied Clinical Informatics
Verified
Journal Article
Closed access
PDF file
TMTaylor B. Martin
Taylor B. Martin
DBDouglas S. Bell
Douglas S. Bell
JGJeffrey A. Gornbein
Jeffrey A. Gornbein
PLPaul J. Lukac
Paul J. Lukac
Objective This study aimed to assist residents in selecting the correct Current Procedural Terminology (CPT) code for evaluation and management (E/M) services through the addition of disappearing help text into a standardized note template. Methods We created a disappearing text block that summarizes E/M requirements and embedded it into the note template used by residents at a pediatric urgent care clinic. An intervention cohort composed of postgraduate year 1 (PGY 1) residents was instructed to use this note template, while senior residents (PGY 2–3) were instructed to use an identical template that lacked the help text. We evaluated the incidence of CPT change by the attending physician for each visit as a proxy for improvement in resident billing practices. Logistic regression with a primary outcome of whether the encounter CPT code was changed was completed. Results There were 2,869 encounters during the 255-day study period; the help text was used in 1,112 (38.8%) encounters. There was some crossover in note use; that is, PGY 1s used the note without help text and PGY 2s used the note with help text. Nevertheless, all residents who used the help text had a lower unadjusted rate of CPT change (22.1 vs. 30.6%, odds ratio [OR] = 0.64, p < 0.0001). This pattern persisted when stratified by trainee level—PGY 1 (22.6 vs. 45.3%, OR = 0.35, p < 0.0001) and PGY 2–3 (12.2 vs. 27.8%, p = 0.018). Adjusting for multiple factors, the use of help text was associated with a lower incidence of CPT change (OR = 0.28, 95% confidence interval [CI]: 0.19–0.44). Conclusion Residents' use of the disappearing help text was associated with a large decrease in CPT code adjustment by attending physicians, which demonstrates its promise for improved E/M coding and other applications.