Fathizadeh, Sam

ABSTRACTObjectivesTo achieve consensus among expert laser surgeons on standards for the prevention and management of adverse events from fully ablative laser resurfacing of the face.Materials and MethodsDelphi study with two rounds of ratings and revisions until consensus was achieved. The draft set of statements was developed by a steering committee based on expert clinical experience. This was followed by two rounds of rating and revisions completed by an expert panel, then a virtual consensus meeting. In both rounds, respondents rated the draft statements on a 9‐point Likert scale (1 = strongly disagree; 9 = strongly agree) and optionally provided comments. The consensus meeting was supplemented by the results of a systematic review of the literature (from 2000 to 2023).ResultsTwo rounds of Delphi survey were completed by 34 participants across four countries. Represented specialties were dermatology, facial plastic surgery, plastic surgery, and oculoplastic surgery. The initial 105 statements from round 1 expanded to 112 in round 2, with 96 statements achieving consensus. These included possible adverse events (11 statements); absolute and relative contraindications to treatment (5 statements); preoperative care and antimicrobial prophylaxis precautions (16 statements); intraoperative precautions (17 statements); postoperative care (21 statements); monitoring for and management of infection (16 statements); management of pigmentation changes (6 statements); and management of scarring and incipient scarring (4 statements).ConclusionAn international consensus statement was developed for the prevention and management of complications associated with fully ablative laser resurfacing of the face. While expert practices vary, key factors for optimizing outcomes include careful patient selection, counseling, and meticulous pre‐ and postoperative care. Further research will improve our understanding of this treatment technique.

Education-level or socioeconomic background of patients may dictate their ability to understand medical jargon. Inability to understand primary findings from a radiology report may lead to unnecessary anxiety among patients or missed follow up. We aim to meet this challenge by developing a patient-sensitive summarization model for radiology reports. We selected computed tomography (CT) exams of chest as a use-case and collected 7,000 studies from Mayo Clinic. Summarization model was built on top of the T5 large language model (LLM) as our experiments indicated that its text-to-text transfer architecture was suited for abstractive text summarization, resulting in a model with 0.77B trainable parameters. Noisy ground truth for model training was collected by prompting LLaMA-13B model. We recruited experts (board-certified radiologists) and laymen to manually evaluate model-generated summaries generated by model. Our model rarely missed information as marked by majority opinion of radiologists. Laymen indicated 63% improvement in their understanding by reading model-generated layman summaries. Comparison with zero-shot performance of ChatGPT indicated that the proposed model reduced the rate of hallucination by half and rate of missing important information by fivefold. The proposed model can generate reliable summaries for radiology reports understandable by patients with vastly different levels of medical knowledge.