Radiology Reporting in the Era of Patient-Centered Care: How Can We Improve Readability?

Understanding Health-Related Social Risks

Because of the established contribution of social factors to health outcomes, approaches that address upstream determinants of health have increasingly been recognized as cost-effective means to improve population health. Understanding and usage of precise terminology is important to facilitate collaboration across disciplines. Social determinants of health affect everyone, not just the socially and economically disadvantaged, whereas health-related social risks (HRSR) are specific adverse conditions at the individual or family level that are associated with poor health and related to the immediate challenges individuals face. Health-related social needs account for patient preference in addressing identified social risks. The use of validated screening tools is important to capture risk factors in a standardized fashion to support research and quality improvement. There is a paucity of studies that address HRSR in the context of radiology. This review provides an understanding of HRSR and outlines various ways in which radiologists can work to mitigate them.

Generating colloquial radiology reports with large language models

OBJECTIVES

Patients are increasingly being given direct access to their medical records. However, radiology reports are written for clinicians and typically contain medical jargon, which can be confusing. One solution is for radiologists to provide a "colloquial" version that is accessible to the layperson. Because manually generating these colloquial translations would represent a significant burden for radiologists, a way to automatically produce accurate, accessible patient-facing reports is desired. We propose a novel method to produce colloquial translations of radiology reports by providing specialized prompts to a large language model (LLM).

MATERIALS AND METHODS

Our method automatically extracts and defines medical terms and includes their definitions in the LLM prompt. Using our method and a naive strategy, translations were generated at 4 different reading levels for 100 de-identified neuroradiology reports from an academic medical center. Translations were evaluated by a panel of radiologists for accuracy, likability, harm potential, and readability.

RESULTS

Our approach translated the Findings and Impression sections at the 8th-grade level with accuracies of 88% and 93%, respectively. Across all grade levels, our approach was 20% more accurate than the baseline method. Overall, translations were more readable than the original reports, as evaluated using standard readability indices.

CONCLUSION

We find that our translations at the eighth-grade level strike an optimal balance between accuracy and readability. Notably, this corresponds to nationally recognized recommendations for patient-facing health communication. We believe that using this approach to draft patient-accessible reports will benefit patients without significantly increasing the burden on radiologists.

Simplifying radiologic reports with natural language processing: a novel approach using ChatGPT in enhancing patient understanding of MRI results

PURPOSE

The aim of this prospective cohort study was to assess the factual accuracy, completeness of medical information, and potential harmfulness of incorrect conclusions by medical professionals in automatically generated texts of varying complexity (1) using ChatGPT, Furthermore, patients without a medical background were asked to evaluate comprehensibility, information density, and conclusion possibilities (2).

METHODS

In the study, five different simplified versions of MRI findings of the knee of different complexity (A: simple, B: moderate, C: complex) were each created using ChatGPT. Subsequently, a group of four medical professionals (two orthopedic surgeons and two radiologists) and a group of 20 consecutive patients evaluated the created reports. For this purpose, all participants received a group of simplified reports (simple, moderate, and severe) at intervals of 1 week each for their respective evaluation using a specific questionnaire. Each questionnaire consisted of the original report, the simplified report, and a series of statements to assess the quality of the simplified reports. Participants were asked to rate their level of agreement with a five-point Likert scale.

RESULTS

The evaluation of the medical specialists showed that the findings produced were consistent in quality depending on their complexity. Factual correctness, reproduction of relevant information and comprehensibility for patients were rated on average as "Agree". The question about possible harm resulted in an average of "Disagree". The evaluation of patients also revealed consistent quality of reports, depending on complexity. Simplicity of word choice and sentence structure was rated "Agree" on average, with significant differences between simple and complex findings (p = 0.0039) as well as between moderate and complex findings (p = 0.0222). Participants reported being significantly better at knowing what the text was about (p = 0.001) and drawing the correct conclusions the more simplified the report of findings was (p = 0.013829). The question of whether the text informed them as well as a healthcare professional was answered as "Neutral" across all findings.

CONCLUSION

By using ChatGPT, MRI reports can be simplified automatically with consistent quality so that the relevant information is understandable to patients. However, a report generated in this way does not replace a thorough discussion between specialist and patient.

Remotely shared CT-derived presurgical understanding of lung cancer: A randomized trial

Shared decision‐making is imperative for patient‐and family‐centered care. However, gathering individuals in a single place was challenged by modern life and pandemic restrictions. This study conducted a 1:1 randomized trial to examine the feasibility of a CT‐derived 3D virtual explanation module for lung cancer to improve the understanding of patients and third parties in physically separate locations. We prospectively enrolled adults in whom elective surgical resection for lung cancer was planned at a single tertiary hospital in 2020. From presurgical CT scans, deep neural networks automatically segmented lung cancer, airway, pulmonary lobes, skin, and bony thorax. The segmented structures were subsequently transformed into an anonymized interactive 3D module which comprised a standardized scenario with explanatory texts. The intervention group received a link to the module on their smartphone before admission and could repeatedly access the link or transfer it to patients' third parties. A total of 33 and 29 patients were enrolled in the intervention and control arms. The understanding score did not statistically differ between the arms (mean difference, 0.7 [95% CI: −0.2, 1.5]; p = 0.13). However, 76% of patients in the intervention arm accessed the link, and patient median access count was 14. The link recipients of third parties had comparable understanding scores to the patients (mean difference, −0.2 [95% CI: −1.9, 1.5]; p = 1.00), indicating that the understanding could be shared remotely with patients and patients’ third parties. In conclusion, it was feasible that people physically separated from patients obtained a comparable understanding of lung cancer surgery using the patient's CT‐derived 3D virtual explanation module.