Page 55 - Read Online

Boyd et al. Art Int Surg 2024;4:316-23 https://dx.doi.org/10.20517/ais.2024.53 Page 318

Table 1. Listing of inputs into the NLP interfaces
Question General inquiry Specific inquiry
number
1 Breast augmentation bruising I had a breast augmentation yesterday and now I have bruising. What should I do?
2 Breast augmentation bleeding I had a breast augmentation yesterday and now I have bleeding. What should I do?
3 Breast augmentation size I had a breast augmentation yesterday and am concerned about the size of my
breasts. What should I do?
4 Breast augmentation swelling I had a breast augmentation yesterday and now I have swelling. What should I do?
5 Breast augmentation soreness I had a breast augmentation yesterday and now I have soreness. What should I do?
6 Breast augmentation exercise I had a breast augmentation yesterday. When can I exercise?
7 Breast augmentation driving I had a breast augmentation yesterday. When can I drive?
8 Breast augmentation restarting I had a breast augmentation yesterday. When can I restart my normal medications?
medications
9 Breast augmentation pain I had a breast augmentation yesterday and now I have pain. What should I do?
10 Breast augmentation showering I had a breast augmentation yesterday. When can I shower?
11 Breast augmentation dressings I had a breast augmentation yesterday. What do I do with the dressings?
12 Breast augmentation pain medication I had a breast augmentation yesterday. What should I take for pain medication?
13 Breast augmentation drainage I had a breast augmentation yesterday and now I have drainage. What should I do?
14 Breast augmentation diet I had a breast augmentation yesterday. What can I eat?
15 Breast augmentation sleeping I had a breast augmentation yesterday. How can I sleep?
16 Breast augmentation recovery I had a breast augmentation yesterday. How long is the recovery?
17 Breast augmentation bra I had a breast augmentation yesterday. When can I wear a bra?
18 Breast augmentation antibiotics I had a breast augmentation yesterday. Do I need antibiotics?
19 Breast augmentation breast and nipple I had a breast augmentation yesterday. Will I still have breast and nipple sensation?
sensation
20 Breast augmentation follow-up I had a breast augmentation yesterday. When is my follow-up appointment?
appointment

A total of 20 topic areas were assessed. A general and specific query for each topic was placed into both Doximity GPT and ChatGPT. NLP:
Natural language processing.

asking a specific clinical question (“I had a breast augmentation yesterday. When can I drive?”). A list of all
input terms is listed in Table 1. A separate session was created for each inquiry to prohibit any influence
from prior inputs and to limit the effect of learning by part of the NLP. Objective assessment of the NLP
outputs included the length (word length, number of characters, number of sentences) and sentence
structure (words per sentence) of the outputs. The readability of the outputs was also determined by four
validated scoring tools, including the Flesh Kincaid Reading Ease, Flesch Kincaid Grade Level, Coleman-
Liau Index, and the Automated Readability Index. Each of these instruments has been commonly utilized to
assess the readability of plastic surgery educational materials for patients [12,15,16] . The Flesch Kincaid Reading
Ease score is reported on a scale from 1 to 100, where higher scores denote a more readable passage. The
Flesch-Kincaid grade level is another standardized metric employed in similar scenarios but focuses on
determining the grade level of schooling necessary for comprehending the output. A Flesch-Kincaid grade
level reported as 5 denotes that the completion of fifth grade is required for an adequate understanding of a
given passage. While the prior two indices primarily utilize syllables per word as the driving metric to
determine readability, the Coleman-Liau Index and Automated Readability Index base their scoring on
character-level metrics with subtle nuances in weighting. Similar to the Flesch-Kincaid grade level, the
Coleman-Liau Index and Automated Readability Index both report the level of schooling required to
understand a given text. Each output was individually analyzed by four distinct reviewers (L.P.R. - senior
medical student, T.J.S. - junior plastic surgery resident, C.J.B. - senior plastic surgery resident, and K.H. -
senior plastic surgery resident) to determine the medical accuracy of the recommendations for each AI-
generated response and cross-referenced based on readily available resources. Given difficulties in