Impact of providing patient information leaflets prior to hospital discharge to patients with acute kidney injury: a quality improvement project

Evaluating ChatGPT's Accuracy in Responding to Patient Education Questions on Acute Kidney Injury and Continuous Renal Replacement Therapy

INTRODUCTION

Acute kidney injury (AKI) and continuous renal replacement therapy (CRRT) are critical areas in nephrology. The effectiveness of ChatGPT in simpler, patient education-oriented questions has not been thoroughly assessed. This study evaluates the proficiency of ChatGPT 4.0 in responding to such questions, subjected to various linguistic alterations.

METHODS

Eighty-nine questions were sourced from the Mayo Clinic Handbook for educating patients on AKI and CRRT. These questions were categorized as original, paraphrased with different interrogative adverbs, paraphrased resulting in incomplete sentences, and paraphrased containing misspelled words. Two nephrologists verified the questions for medical accuracy. A χ2 test was conducted to ascertain notable discrepancies in ChatGPT 4.0's performance across these formats.

RESULTS

ChatGPT provided notable accuracy in handling a variety of question formats for patient education in AKI and CRRT. Across all question types, ChatGPT demonstrated an accuracy of 97% for both original and adverb-altered questions and 98% for questions with incomplete sentences or misspellings. Specifically for AKI-related questions, the accuracy was consistently maintained at 97% for all versions. In the subset of CRRT-related questions, the tool achieved a 96% accuracy for original and adverb-altered questions, and this increased to 98% for questions with incomplete sentences or misspellings. The statistical analysis revealed no significant difference in performance across these varied question types (p value: 1.00 for AKI and 1.00 for CRRT), and there was no notable disparity between the artificial intelligence (AI)'s responses to AKI and CRRT questions (p value: 0.71).

CONCLUSION

ChatGPT 4.0 demonstrates consistent and high accuracy in interpreting and responding to queries related to AKI and CRRT, irrespective of linguistic modifications. These findings suggest that ChatGPT 4.0 has the potential to be a reliable support tool in the delivery of patient education, by accurately providing information across a range of question formats. Further research is needed to explore the direct impact of AI-generated responses on patient understanding and education outcomes.

Nurses' assessment of health literacy requirements for adult inpatients: An integrative review

ISSUE ADDRESSED

This paper reviews current research which examines nurses' assessment of patient's health literacy in the acute hospital setting. Research highlights, that patients with low health literacy have more frequent hospitalisations and are more likely to be re-admitted. Within the healthcare team, nurses are primarily responsible for teaching patients and deciphering health communication, to enhance understanding. Within the acute care setting, there remains a disparity in patient understanding of information, despite nurse-led education. The health literacy assessment and tailoring of information by nurses, is becoming more important with shorter stays, plus limited family visits and the wearing of masks with COVID-19 related changes.

METHODS

An integrative review across four nursing databases, from 2010 and June 2022 was conducted. The integrative framework included problem identification, literature search, data evaluation, data analysis with thematic analysis, and results presentation.

RESULTS

Nine studies were included. Common themes were nurses' overestimation of patients' health literacy, the use of universal precautions, and adapting communication techniques to improve education moments.

CONCLUSION

The findings of this review indicate a tendency among nurses to overestimate their patients' health literacy levels, which can result in ineffective health education and inadequate discharge planning.

SO WHAT

Nurses decipher health communication for their patients. Designing tailored patient communication and education could potentially be a cost saving measure for hospitals by reducing length of stay and reducing readmissions. Health literacy training should be incorporated into nursing practice.

Improving Plastic Dressing Clinic Burden by Reducing Punch Biopsy Referrals Using a Patient Information Leaflet: A Quality Improvement Project

Background

Although being a safe intervention with low complication rates, a significant proportion of patients undergoing punch biopsies were referred to the local plastic dressing clinic (PDC) despite providing minimal utility and adding to an already heavily burdened clinic. The aim of this quality improvement (QI) project was to reduce the number of patients who had undergone a punch biopsy who were referred to PDC. The steering group included a plastic surgeon consultant, a senior outpatient department (OPD) and a PDC nurse, and a junior trainee. Process mapping and driver diagrams were used to identify a patient information leaflet as the intervention.

Methods

A patient information leaflet was created by the clinical lead, which included advice for postoperative wound care and when to seek medical attention. This leaflet was provided to every patient who underwent a minor operation for a skin lesion from September 2021. Operative notes of patients who underwent a punch biopsy were reviewed from October to November 2021 and from August to September 2022 to identify the number of patients who were referred to PDC. Concurrently informal feedback from patients and the process manager guided any necessary changes.

Results

There was a small improvement in the number of PDC referrals during October-November 2021 (46%) compared to the baseline measurements (54%). This corresponded with an absolute risk reduction (ARR) of 7%, risk ratio (RR) of 0.86, and relative risk reduction (RRR) of 14%. No changes were made at this stage. There was a much greater improvement in August-September 2022 (20%) compared to the baseline measurements with 34% ARR, 0.37 RR, and 63% RRR. Informal feedback from the process manager confirmed that every patient received a leaflet and that the patients found the leaflet very helpful.

Conclusions

The implementation of the patient information leaflet has led to a reduction in referrals of patients with punch biopsies to PDC. While this is a small and narrow project, it demonstrates the values of QI methodology to select a successful intervention. Furthermore, it corroborates with other studies that have shown that patient information leaflets empower patients and can help reduce the National Health Service (NHS) outpatient burden. Considering its simplicity, trialing a similar approach in other specialties is strongly encouraged.