Page 11 - Read Online

Page 27 Landau et al. Art Int Surg. 2025;5:24-35 https://dx.doi.org/10.20517/ais.2024.78

size to substantiate study conclusions, appropriate methodology for chosen study design, and adherence to
reporting guidelines specific to study type. The role of AI/ML/NLP technologies was evaluated for accuracy
and efficiency in CPT code application, advantages and disadvantages in clinical and administrative
workflow, and indirect facets implicated in a plastic and reconstructive surgeon’s ability to provide patient
care. Sources were cross-compared to understand innovations and perceptions in terms of chronological
trends regarding the implementation of AI, ML, or NLP. Any studies that did not contain all variables
outlined for data extraction were manually removed from the final pool of included literature.

Data were grouped such that study identifiers (publication year, procedure/subspecialty, AI/ML/NLP
methods, CPT codes), corresponding quantitative characteristics (sample sizes) and results (accuracy
measurements) could be synthesized into tables using Microsoft Excel. Figures were generated from
qualitative results to visually represent the key findings in a collective manner: Graphically (Microsoft
Excel) and diagrammatically (Biorender.com). These methods for representation were selected to best
preserve extracted data in the format in which they originated.

RESULTS
Of 123 unique database search results, 11 articles met the eligibility criteria, as shown in Figure 1. The
publication year of included articles ranged from 2015 to 2024, with 5/11 (45.5%) having been published
within 1 year of database searches [Table 1].

Studies were characterized by study design, for which a retrospective approach to investigation was
observed in all studies. AI/ML/NLP methods employed exhibited heterogeneity between studies, with most
investigator groups opting to cross-compare multiple technologies for accuracy in CPT code generation
[Table 1]. A variety of subspecialties were found in the procedures examined, all possessing similarity to
plastic and reconstructive surgery due to direct overlap in the domain of surgical practice or similarity in
techniques such that analogous performance of AI/ML/NLP methods would be expected [Table 1].

All measures of accuracy and efficiency were analyzed in the context of their unique grouping of
computational techniques [Table 2]. The risk of bias evaluated through quality assessment was minimized
via data interpretation and presentation in the originating format following data extraction. Simpler models
(coinciding with earlier studies), reliant on a less elaborate collection of methods, tended to perform better
in terms of achieved accuracy, and specificity was almost always reported to be greater than sensitivity,
independent of model choice [Table 2].

Overall trends in public perception concerning the role of generative AI and integrative technologies
discussed in literature sources are illustrated in Figure 2.

Surgeon workflow, involving the cyclic relationship between billing and administrative tasks, AI, and
patient care, is illustrated in Figure 3.

DISCUSSION
[22]
The epidemic of physician burnout reportedly ranges from 29% to 55% among physicians , frequently
resulting in poor work-life balance, decreased career satisfaction, increased medical errors, and diminished
[23]
quality of patient care . Tasks such as procedural coding and other administrative obligations are often
cited as reasons for dissatisfaction and stress among surgeons, contributing to burnout [22,24] . A 2020 study of
surgeon self-reported activity, recorded in a smartphone app, found that US physicians across six specialties
in 16 US states spent 7.7% of their time on administrative tasks, 20.7% of their time on electronic health